Introduction

Ee are interested in comparing DEGs between the following comparison groups:

  • Latently- vs productively-infected cells (groups 3 vs 4).

  • Latently-infected vs bystander cells (2 vs 3).

  • Productively-infected vs mock (4 vs 1)

  • Mock vs bystander (1 vs 2).

As discussed, I think we will do these comparisons separately for both MDM and AlvMDM samples initially. Then, it would be of interest to compare DEGs for MDM vs AlvMDM for each of the four infection groups.

suppressPackageStartupMessages({
  library("kableExtra")
  library("ggplot2")
  library("plyr")
  library("Seurat")
  library("hdf5r")
  library("SingleCellExperiment")
  library("parallel")
  library("stringi")
  library("beeswarm")
  library("muscat")
  library("DESeq2")
  library("mitch")
  library("harmony")
  library("celldex")
  library("SingleR")
  library("limma")
  library("gplots")
})

Load data

Sample Patient Group
mock0 MDMP236 mock
mock1 MDMV236 mock
mock2 MDMO236 mock
mock3 MDMP239 mock
mock4 AlvP239 mock
mock5 AlvM239 mock
mock6 AlvN239 mock
active0 MDMP236 active
active1 MDMV236 active
active2 MDMO236 active
active3 MDMP239 active
active4 AlvP239 active
active5 AlvM239 active
active6 AlvN239 active
latent0 MDMP236 latent
latent1 MDMV236 latent
latent2 MDMO236 latent
latent3 MDMP239 latent
latent4 AlvP239 latent
latent5 AlvM239 latent
latent6 AlvN239 latent
bystander0 MDMP236 bystander
bystander1 MDMV236 bystander
bystander2 MDMO236 bystander
bystander3 MDMP239 bystander
bystander4 AlvP239 bystander
bystander5 AlvM239 bystander
bystander6 AlvN239 bystander
react6 AlvN239 reactivated

exclude react6

ss <- read.table("samplesheet.tsv",header=TRUE,row.names=1)

ss %>% kbl(caption="sample sheet") %>% kable_paper("hover", full_width = F)
sample sheet
Patient Group
mock0 MDMP236 mock
mock1 MDMV236 mock
mock2 MDMO236 mock
mock3 MDMP239 mock
mock4 AlvP239 mock
mock5 AlvM239 mock
mock6 AlvN239 mock
active0 MDMP236 active
active1 MDMV236 active
active2 MDMO236 active
active3 MDMP239 active
active4 AlvP239 active
active5 AlvM239 active
active6 AlvN239 active
latent0 MDMP236 latent
latent1 MDMV236 latent
latent2 MDMO236 latent
latent3 MDMP239 latent
latent4 AlvP239 latent
latent5 AlvM239 latent
latent6 AlvN239 latent
bystander0 MDMP236 bystander
bystander1 MDMV236 bystander
bystander2 MDMO236 bystander
bystander3 MDMP239 bystander
bystander4 AlvP239 bystander
bystander5 AlvM239 bystander
bystander6 AlvN239 bystander
react6 AlvN239 reactivated 
mylist <- readRDS("macrophage_counts.rds")

Make single cell experiment object

comb <- do.call(cbind,mylist)
sce <- SingleCellExperiment(list(counts=comb))
sce
## class: SingleCellExperiment 
## dim: 36622 24311 
## metadata(0):
## assays(1): counts
## rownames(36622): HIV_LTRR HIV_LTRU5 ... AC007325.4 AC007325.2
## rowData names(0):
## colnames(24311): mdm_mock1|AAACGAATCACATACG mdm_mock1|AAACGCTCATCAGCGC
##   ... react6|TTTGTTGTCTGAACGT react6|TTTGTTGTCTTGGCTC
## colData names(0):
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## reducedDimNames(0):
## mainExpName: NULL
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## altExpNames(0):

Normalise data

cellmetadata <- data.frame(colnames(comb) ,sapply(strsplit(colnames(comb),"\\|"),"[[",1))
colnames(cellmetadata) <- c("cell","sample")
comb <- CreateSeuratObject(comb, project = "mac", assay = "RNA", meta.data = cellmetadata)
## Warning: Feature names cannot have underscores ('_'), replacing with dashes
## ('-')
comb <- NormalizeData(comb)
## Normalizing layer: counts
comb <- FindVariableFeatures(comb, selection.method = "vst", nfeatures = 2000)
## Finding variable features for layer counts
comb <- ScaleData(comb)
## Centering and scaling data matrix

PCA and Cluster

comb <- RunPCA(comb, features = VariableFeatures(object = comb))
## PC_ 1 
## Positive:  GAPDH, FABP3, TXN, IFI30, S100A10, PRDX6, TUBA1B, BLVRB, OTOA, S100A9 
##     FAH, C15orf48, CYSTM1, GCHFR, CARD16, GSTP1, HAMP, PSMA7, CSTA, FABP4 
##     ACTG1, CTSB, H2AFZ, LDHB, LINC01827, CFD, TUBA1A, MMP9, LINC02244, SELENOW 
## Negative:  ARL15, DOCK3, FTX, NEAT1, EXOC4, MALAT1, DPYD, LRMDA, RASAL2, JMJD1C 
##     TMEM117, PLXDC2, VPS13B, FHIT, ATG7, TRIO, TPRG1, ZNF438, ZFAND3, MAML2 
##     MITF, COP1, ZEB2, ELMO1, DENND4C, MED13L, TCF12, ERC1, JARID2, FMNL2 
## PC_ 2 
## Positive:  HLA-DRB1, CD74, HLA-DRA, HLA-DPA1, GCLC, HLA-DPB1, LYZ, RCBTB2, KCNMA1, MRC1 
##     SPRED1, C1QA, FGL2, AC020656.1, SLCO2B1, CYP1B1, AIF1, HLA-DRB5, PTGDS, S100A4 
##     VAMP5, LINC02345, CA2, CRIP1, CAMK1, ALOX5AP, RTN1, HLA-DQB1, MX1, TGFBI 
## Negative:  CYSTM1, CD164, PSAT1, FAH, FDX1, GDF15, ATP6V1D, BCAT1, SAT1, CCPG1 
##     PHGDH, PSMA7, HEBP2, SLAMF9, RETREG1, GARS, HES2, TXN, TCEA1, RHOQ 
##     RILPL2, B4GALT5, CLGN, NUPR1, CSTA, SPTBN1, HSD17B12, SNHG5, STMN1, PTER 
## PC_ 3 
## Positive:  NCAPH, CRABP2, RGCC, CHI3L1, TM4SF19, DUSP2, GAL, CCL22, AC015660.2, ACAT2 
##     LINC01010, TMEM114, MGST1, RGS20, TRIM54, LINC02244, MREG, NUMB, TCTEX1D2, GPC4 
##     CCND1, POLE4, SYNGR1, SLC20A1, SERTAD2, IL1RN, GCLC, CLU, PLEK, AC092353.2 
## Negative:  MARCKS, CD14, BTG1, MS4A6A, TGFBI, CTSC, FPR3, HLA-DQA1, AIF1, MPEG1 
##     MEF2C, CD163, IFI30, TIMP1, HLA-DPB1, ALDH2, SELENOP, NUPR1, NAMPT, HLA-DQB1 
##     HIF1A, C1QC, MS4A7, FUCA1, EPB41L3, HLA-DQA2, RNASE1, ARL4C, ZNF331, TCF4 
## PC_ 4 
## Positive:  ACTG1, TPM4, CTSB, CCL3, TUBA1B, CSF1, DHCR24, CYTOR, LGMN, INSIG1 
##     GAPDH, TUBB, CD36, HAMP, C1QA, CCL7, AIF1, MGLL, LIMA1, TYMS 
##     C1QC, HSP90B1, CCL2, C1QB, TNFSF13, PCLAF, C15orf48, CLSPN, CAMK1, TK1 
## Negative:  PTGDS, LINC02244, CLU, CSTA, CCPG1, MGST1, SYNGR1, EPHB1, LINC01010, ALDH2 
##     LY86-AS1, AC015660.2, GAS5, NCF1, BX664727.3, S100P, AP000331.1, TMEM91, SNHG5, CLEC12A 
##     APOD, PDE4D, C1QTNF4, VAMP5, DIXDC1, LYZ, AC073359.2, ARHGAP15, RCBTB2, CFD 
## PC_ 5 
## Positive:  TYMS, PCLAF, TK1, MKI67, MYBL2, RRM2, CENPM, BIRC5, CEP55, CLSPN 
##     CDK1, DIAPH3, SHCBP1, NUSAP1, CENPF, CENPK, PRC1, TOP2A, NCAPG, ESCO2 
##     KIF11, ANLN, CCNA2, TPX2, ASPM, FAM111B, MAD2L1, RAD51AP1, GTSE1, HMMR 
## Negative:  HIV-BaLEnv, HIV-LTRU5, HIV-Polprot, HIV-Gagp17, HIV-Nef, HIV-TatEx1, HIV-Polp15p31, HIV-LTRR, HIV-Vif, HIV-Gagp1Pol 
##     HIV-TatEx2Rev, HIV-Gagp2p7, HIV-EnvStart, HIV-Vpu, HIV-Vpr, HIV-EGFP, CTSB, MMP19, IL6R-AS1, CSF1 
##     IL1RN, CCL3, MGLL, INSIG1, AL157912.1, SDS, TCTEX1D2, TNFRSF9, LGMN, PHLDA1
comb <- RunHarmony(comb,"sample")
## Transposing data matrix
## Initializing state using k-means centroids initialization
## Harmony 1/10
## Harmony 2/10
## Harmony 3/10
## Harmony 4/10
## Harmony converged after 4 iterations
## Warning: The `slot` argument of `GetAssayData()` is deprecated as of SeuratObject 5.0.0.
## ℹ Please use the `layer` argument instead.
## ℹ The deprecated feature was likely used in the Seurat package.
##   Please report the issue at <https://github.com/satijalab/seurat/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.
DimHeatmap(comb, dims = 1:6, cells = 500, balanced = TRUE)
## Warning: The `slot` argument of `FetchData()` is deprecated as of SeuratObject 5.0.0.
## ℹ Please use the `layer` argument instead.
## ℹ The deprecated feature was likely used in the Seurat package.
##   Please report the issue at <https://github.com/satijalab/seurat/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.

ElbowPlot(comb)

comb <- JackStraw(comb, num.replicate = 100)
comb <- FindNeighbors(comb, dims = 1:10)
## Computing nearest neighbor graph
## Computing SNN
comb <- FindClusters(comb, resolution = 0.5)
## Modularity Optimizer version 1.3.0 by Ludo Waltman and Nees Jan van Eck
## 
## Number of nodes: 24311
## Number of edges: 745637
## 
## Running Louvain algorithm...
## Maximum modularity in 10 random starts: 0.8948
## Number of communities: 14
## Elapsed time: 3 seconds

UMAP

comb <- RunUMAP(comb, dims = 1:10)
## Warning: The default method for RunUMAP has changed from calling Python UMAP via reticulate to the R-native UWOT using the cosine metric
## To use Python UMAP via reticulate, set umap.method to 'umap-learn' and metric to 'correlation'
## This message will be shown once per session
## 12:40:00 UMAP embedding parameters a = 0.9922 b = 1.112
## 12:40:00 Read 24311 rows and found 10 numeric columns
## 12:40:00 Using Annoy for neighbor search, n_neighbors = 30
## 12:40:00 Building Annoy index with metric = cosine, n_trees = 50
## 0%   10   20   30   40   50   60   70   80   90   100%
## [----|----|----|----|----|----|----|----|----|----|
## **************************************************|
## 12:40:02 Writing NN index file to temp file /tmp/RtmpRdHgON/file11d0d41e0bebac
## 12:40:02 Searching Annoy index using 1 thread, search_k = 3000
## 12:40:08 Annoy recall = 100%
## 12:40:09 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30
## 12:40:11 Initializing from normalized Laplacian + noise (using RSpectra)
## 12:40:11 Commencing optimization for 200 epochs, with 972676 positive edges
## 12:40:11 Using rng type: pcg
## 12:40:18 Optimization finished
DimPlot(comb, reduction = "umap")

Assign names to clusters

ADGRE1, CCR2, CD169, CX3CR1, CD206, CD163, LYVE1, CD9, TREM2

HLA-DP, HLA-DM, HLA-DOA, HLA-DOB, HLA-DQ, and HLA-DR.

message("macrophage markers")
## macrophage markers
FeaturePlot(comb, features = c("ADGRE1", "CCR2", "SIGLEC1", "CX3CR1", "MRC1", "CD163", "LYVE1", "CD9", "TREM2"))

DimPlot(comb, reduction = "umap", label = TRUE, pt.size = 0.5) + NoLegend()

That’s pretty useless. Let’s use celldex pkg to annotate cells and get the macs.

ref <- celldex::MonacoImmuneData()

DefaultAssay(comb) <- "RNA"
comb2 <- as.SingleCellExperiment(comb)
## Warning: `PackageCheck()` was deprecated in SeuratObject 5.0.0.
## ℹ Please use `rlang::check_installed()` instead.
## ℹ The deprecated feature was likely used in the Seurat package.
##   Please report the issue at <https://github.com/satijalab/seurat/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
lc <- logcounts(comb2)

pred_imm_broad <- SingleR(test=comb2, ref=ref,
                          labels=ref$label.main)

head(pred_imm_broad)
## DataFrame with 6 rows and 4 columns
##                                                    scores      labels
##                                                  <matrix> <character>
## mdm_mock1|AAACGAATCACATACG 0.306472:0.325537:0.166567:...   Monocytes
## mdm_mock1|AAACGCTCATCAGCGC 0.311527:0.281167:0.189514:...   Monocytes
## mdm_mock1|AAACGCTGTCGAGTGA 0.316271:0.276472:0.170736:...   Monocytes
## mdm_mock1|AAAGGTAAGCCATATC 0.290547:0.291036:0.154976:...   Monocytes
## mdm_mock1|AAAGGTAGTTTCCAAG 0.290907:0.279384:0.181857:...   Monocytes
## mdm_mock1|AAATGGAAGATCGCCC 0.242404:0.241021:0.117564:...   Monocytes
##                            delta.next pruned.labels
##                             <numeric>   <character>
## mdm_mock1|AAACGAATCACATACG  0.1823977     Monocytes
## mdm_mock1|AAACGCTCATCAGCGC  0.0338547     Monocytes
## mdm_mock1|AAACGCTGTCGAGTGA  0.1301308     Monocytes
## mdm_mock1|AAAGGTAAGCCATATC  0.1794308     Monocytes
## mdm_mock1|AAAGGTAGTTTCCAAG  0.0952702     Monocytes
## mdm_mock1|AAATGGAAGATCGCCC  0.1508974     Monocytes
table(pred_imm_broad$pruned.labels)
## 
##       Basophils Dendritic cells       Monocytes 
##               1              86           23423
cellmetadata$label <- pred_imm_broad$pruned.labels

pred_imm_fine <- SingleR(test=comb2, ref=ref,
                          labels=ref$label.fine)
head(pred_imm_fine)
## DataFrame with 6 rows and 4 columns
##                                                    scores              labels
##                                                  <matrix>         <character>
## mdm_mock1|AAACGAATCACATACG 0.180057:0.485292:0.202974:... Classical monocytes
## mdm_mock1|AAACGCTCATCAGCGC 0.195973:0.430960:0.226764:... Classical monocytes
## mdm_mock1|AAACGCTGTCGAGTGA 0.170594:0.441313:0.186890:... Classical monocytes
## mdm_mock1|AAAGGTAAGCCATATC 0.156243:0.415082:0.167816:... Classical monocytes
## mdm_mock1|AAAGGTAGTTTCCAAG 0.185006:0.431679:0.205883:... Classical monocytes
## mdm_mock1|AAATGGAAGATCGCCC 0.125917:0.383407:0.146835:... Classical monocytes
##                            delta.next       pruned.labels
##                             <numeric>         <character>
## mdm_mock1|AAACGAATCACATACG  0.0675290 Classical monocytes
## mdm_mock1|AAACGCTCATCAGCGC  0.1150706 Classical monocytes
## mdm_mock1|AAACGCTGTCGAGTGA  0.0651352 Classical monocytes
## mdm_mock1|AAAGGTAAGCCATATC  0.1076301 Classical monocytes
## mdm_mock1|AAAGGTAGTTTCCAAG  0.1521533 Classical monocytes
## mdm_mock1|AAATGGAAGATCGCCC  0.1282183 Classical monocytes
table(pred_imm_fine$pruned.labels)
## 
##          Classical monocytes       Intermediate monocytes 
##                        20826                         2648 
##      Low-density neutrophils      Myeloid dendritic cells 
##                            1                           90 
##      Non classical monocytes Plasmacytoid dendritic cells 
##                           11                            6
cellmetadata$finelabel <- pred_imm_fine$pruned.labels

col_pal <- c('#e31a1c', '#ff7f00', "#999900", '#cc00ff', '#1f78b4', '#fdbf6f',
             '#33a02c', '#fb9a99', "#a6cee3", "#cc6699", "#b2df8a", "#99004d", "#66ff99",
             "#669999", "#006600", "#9966ff", "#cc9900", "#e6ccff", "#3399ff", "#ff66cc",
             "#ffcc66", "#003399")

annot_df <- data.frame(
  barcodes = rownames(pred_imm_broad),
  monaco_broad_annotation = pred_imm_broad$labels,
  monaco_broad_pruned_labels = pred_imm_broad$pruned.labels,
  monaco_fine_annotation = pred_imm_fine$labels,
  monaco_fine_pruned_labels = pred_imm_fine$pruned.labels
)

meta_inf <- comb@meta.data
meta_inf$cell_barcode <- colnames(comb)

meta_inf <- meta_inf %>% dplyr::left_join(y = annot_df,
                                          by = c("cell_barcode" = "barcodes"))
rownames(meta_inf) <- colnames(lc)

comb@meta.data <- meta_inf

DimPlot(comb, label=TRUE, group.by = "monaco_broad_annotation", reduction = "umap",
  cols = col_pal, pt.size = 0.5) + ggtitle("Annotation With the Monaco Reference Database")

DimPlot(comb, label=TRUE, group.by = "monaco_fine_annotation", reduction = "umap",
  cols = col_pal, pt.size = 0.5) + ggtitle("Annotation With the Monaco Reference Database")

Make MDM object

mdmlist <- mylist[grep("mdm",names(mylist))]
comb1 <- do.call(cbind,mdmlist)
sce1 <- SingleCellExperiment(list(counts=comb1))
sce1
## class: SingleCellExperiment 
## dim: 36622 10269 
## metadata(0):
## assays(1): counts
## rownames(36622): HIV_LTRR HIV_LTRU5 ... AC007325.4 AC007325.2
## rowData names(0):
## colnames(10269): mdm_mock1|AAACGAATCACATACG mdm_mock1|AAACGCTCATCAGCGC
##   ... mdm_bystander4|TTTGTTGAGAACGCGT mdm_bystander4|TTTGTTGCAAATGCGG
## colData names(0):
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## reducedDimNames(0):
## mainExpName: NULL
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## altExpNames(0):
cellmetadata1 <- data.frame(colnames(comb1) ,sapply(strsplit(colnames(comb1),"\\|"),"[[",1))
colnames(cellmetadata1) <- c("cell","sample")
comb1 <- CreateSeuratObject(comb1, project = "mac", assay = "RNA", meta.data = cellmetadata1)
## Warning: Feature names cannot have underscores ('_'), replacing with dashes
## ('-')
comb1 <- NormalizeData(comb1)
## Normalizing layer: counts
comb1 <- FindVariableFeatures(comb1, selection.method = "vst", nfeatures = 2000)
## Finding variable features for layer counts
comb1 <- ScaleData(comb1)
## Centering and scaling data matrix
comb1 <- RunPCA(comb1, features = VariableFeatures(object = comb1))
## PC_ 1 
## Positive:  S100A10, TXN, COX5B, PRDX6, FABP3, C15orf48, BCL2A1, CALM3, PSME2, TUBA1B 
##     CYSTM1, SPP1, CHI3L1, TUBA1A, CRABP2, ACTB, ACTG1, MGST1, ACAT2, FBP1 
##     IFI30, FABP4, GAL, HAMP, RGCC, MMP9, AKR7A2, LILRA1, CTSL, LDHA 
## Negative:  ARL15, FTX, EXOC4, NEAT1, DPYD, FHIT, JMJD1C, RAD51B, VPS13B, ZFAND3 
##     MALAT1, PLXDC2, TRIO, LRMDA, ZEB2, DOCK3, COP1, MBD5, TCF12, ATXN1 
##     RASAL2, MAML2, ATG7, ZSWIM6, FNDC3B, DOCK4, ELMO1, ZNF438, SPIDR, ARHGAP15 
## PC_ 2 
## Positive:  TM4SF19, ANO5, GPC4, CYSTM1, FNIP2, TXNRD1, BCL2A1, SPP1, SNX10, PSD3 
##     RETREG1, RGS20, TXN, TCTEX1D2, SLC28A3, MGST1, EPB41L1, FABP3, RGCC, CALM3 
##     NIBAN1, TGM2, ATP6V0D2, ACAT2, CCL22, CCDC26, LINC01010, CHI3L1, MREG, CRABP2 
## Negative:  HLA-DPB1, HLA-DRA, CD74, HLA-DPA1, TGFBI, MS4A6A, AIF1, HLA-DQB1, C1QA, HLA-DQA1 
##     HLA-DRB1, CEBPD, FPR3, C1QC, MS4A7, CD163, CD14, MPEG1, LYZ, TIMP1 
##     ST8SIA4, LILRB2, FOS, EPB41L3, TCF4, MAFB, HLA-DRB5, RNASE1, SELENOP, FCN1 
## PC_ 3 
## Positive:  CCPG1, NUPR1, HES2, PSAT1, S100P, CLGN, CARD16, TCEA1, PHGDH, SUPV3L1 
##     BTG1, NIBAN1, G0S2, BEX2, NMB, PDE4D, PLEKHA5, RAB6B, STMN1, XIST 
##     ME1, CLEC4A, CLEC4E, RETREG1, IFI6, CYSTM1, GDF15, CXCR4, DUSP1, SEL1L3 
## Negative:  ACTB, CALR, SLC35F1, TIMP3, TUBA1B, FBP1, ACTG1, LINC01091, HSP90B1, GSN 
##     MGLL, IL1RN, GLIPR1, INSIG1, LPL, GCLC, PLEK, PDIA4, MADD, RGCC 
##     LDHA, MANF, ALCAM, HLA-DRB1, IGSF6, TMEM176B, DHCR24, CSF1, TUBA1A, CYP1B1 
## PC_ 4 
## Positive:  PTGDS, NCAPH, CLU, BX664727.3, LINC02244, SYNGR1, COX5B, RCBTB2, CRABP2, AL136317.2 
##     MT-ATP6, SSBP3, RARRES1, ADRA2B, LINC01010, AC015660.2, S100A4, CRIP1, MT-ND2, LY86-AS1 
##     RNASE6, HLA-C, S100A8, VAMP5, MT-CO3, MT-CYB, CCL22, CPE, CSRP2, TMEM176B 
## Negative:  HIV-Gagp17, HIV-BaLEnv, HIV-Polprot, HIV-Polp15p31, HIV-LTRU5, HIV-Vif, HIV-Nef, HIV-TatEx1, HIV-LTRR, HIV-Gagp1Pol 
##     HIV-Gagp2p7, HIV-TatEx2Rev, MARCKS, CCL3, HIV-Vpu, HIV-EGFP, TPM4, UGCG, SNCA, HIV-EnvStart 
##     HIV-Vpr, CD36, LGMN, G0S2, HES4, B4GALT5, CLEC4A, BCAT1, TNFRSF9, SDS 
## PC_ 5 
## Positive:  TYMS, PCLAF, BIRC5, MKI67, CEP55, CENPF, CENPM, TK1, CDKN3, PRC1 
##     CDK1, DIAPH3, MYBL2, SHCBP1, NUSAP1, DLGAP5, RRM2, CENPK, HMMR, TPX2 
##     ASPM, NCAPG, CCNA2, MAD2L1, PTTG1, TOP2A, CLSPN, KIF4A, CIT, KIF11 
## Negative:  GCLC, TIMP3, TMEM117, TMEM176B, AC067751.1, CRABP2, NUMB, LINC01091, CHI3L1, LY86-AS1 
##     LINC00278, TNFSF14, RGCC, KCNJ1, IGSF6, SH3RF3, AC015660.2, IL1RN, DUSP2, MADD 
##     KCNA2, DOCK3, FLT1, RPS4Y1, TTTY14, TNS3, GADD45G, NCAPH, AL157886.1, TM4SF19-AS1
comb1 <- RunHarmony(comb1,"sample")
## Transposing data matrix
## Initializing state using k-means centroids initialization
## Harmony 1/10
## Harmony 2/10
## Harmony 3/10
## Harmony 4/10
## Harmony 5/10
## Harmony converged after 5 iterations
DimHeatmap(comb1, dims = 1:6, cells = 500, balanced = TRUE)

ElbowPlot(comb1)

comb1 <- JackStraw(comb1, num.replicate = 100)
comb1 <- FindNeighbors(comb1, dims = 1:10)
## Computing nearest neighbor graph
## Computing SNN
comb1 <- FindClusters(comb1, resolution = 0.5)
## Modularity Optimizer version 1.3.0 by Ludo Waltman and Nees Jan van Eck
## 
## Number of nodes: 10269
## Number of edges: 322519
## 
## Running Louvain algorithm...
## Maximum modularity in 10 random starts: 0.8766
## Number of communities: 12
## Elapsed time: 0 seconds
comb1 <- RunUMAP(comb1, dims = 1:10)
## 12:43:56 UMAP embedding parameters a = 0.9922 b = 1.112
## 12:43:56 Read 10269 rows and found 10 numeric columns
## 12:43:56 Using Annoy for neighbor search, n_neighbors = 30
## 12:43:56 Building Annoy index with metric = cosine, n_trees = 50
## 0%   10   20   30   40   50   60   70   80   90   100%
## [----|----|----|----|----|----|----|----|----|----|
## **************************************************|
## 12:43:57 Writing NN index file to temp file /tmp/RtmpRdHgON/file11d0d444252c19
## 12:43:57 Searching Annoy index using 1 thread, search_k = 3000
## 12:44:00 Annoy recall = 100%
## 12:44:01 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30
## 12:44:02 Initializing from normalized Laplacian + noise (using RSpectra)
## 12:44:02 Commencing optimization for 200 epochs, with 405542 positive edges
## 12:44:02 Using rng type: pcg
## 12:44:06 Optimization finished
DimPlot(comb1, reduction = "umap")

message("macrophage markers")
## macrophage markers
FeaturePlot(comb1, features = c("ADGRE1", "CCR2", "SIGLEC1", "CX3CR1", "MRC1", "CD163", "LYVE1", "CD9", "TREM2"))

DimPlot(comb1, reduction = "umap", label = TRUE, pt.size = 0.5) + NoLegend()

ref <- celldex::MonacoImmuneData()
DefaultAssay(comb1) <- "RNA"
comb21 <- as.SingleCellExperiment(comb1)
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
lc1 <- logcounts(comb21)
pred_imm_broad1 <- SingleR(test=comb21, ref=ref,labels=ref$label.main)
head(pred_imm_broad1)
## DataFrame with 6 rows and 4 columns
##                                                    scores      labels
##                                                  <matrix> <character>
## mdm_mock1|AAACGAATCACATACG 0.306472:0.325537:0.166567:...   Monocytes
## mdm_mock1|AAACGCTCATCAGCGC 0.311527:0.281167:0.189514:...   Monocytes
## mdm_mock1|AAACGCTGTCGAGTGA 0.316271:0.276472:0.170736:...   Monocytes
## mdm_mock1|AAAGGTAAGCCATATC 0.290547:0.291036:0.154976:...   Monocytes
## mdm_mock1|AAAGGTAGTTTCCAAG 0.290907:0.279384:0.181857:...   Monocytes
## mdm_mock1|AAATGGAAGATCGCCC 0.242404:0.241021:0.117564:...   Monocytes
##                            delta.next pruned.labels
##                             <numeric>   <character>
## mdm_mock1|AAACGAATCACATACG  0.1823977     Monocytes
## mdm_mock1|AAACGCTCATCAGCGC  0.0338547     Monocytes
## mdm_mock1|AAACGCTGTCGAGTGA  0.1301308     Monocytes
## mdm_mock1|AAAGGTAAGCCATATC  0.1794308     Monocytes
## mdm_mock1|AAAGGTAGTTTCCAAG  0.0952702     Monocytes
## mdm_mock1|AAATGGAAGATCGCCC  0.1508974     Monocytes
table(pred_imm_broad1$pruned.labels)
## 
##       Basophils Dendritic cells       Monocytes 
##               1              71            9629
cellmetadata1$label <- pred_imm_broad1$pruned.labels
pred_imm_fine1 <- SingleR(test=comb21, ref=ref, labels=ref$label.fine)
head(pred_imm_fine1)
## DataFrame with 6 rows and 4 columns
##                                                    scores              labels
##                                                  <matrix>         <character>
## mdm_mock1|AAACGAATCACATACG 0.180057:0.485292:0.202974:... Classical monocytes
## mdm_mock1|AAACGCTCATCAGCGC 0.195973:0.430960:0.226764:... Classical monocytes
## mdm_mock1|AAACGCTGTCGAGTGA 0.170594:0.441313:0.186890:... Classical monocytes
## mdm_mock1|AAAGGTAAGCCATATC 0.156243:0.415082:0.167816:... Classical monocytes
## mdm_mock1|AAAGGTAGTTTCCAAG 0.185006:0.431679:0.205883:... Classical monocytes
## mdm_mock1|AAATGGAAGATCGCCC 0.125917:0.383407:0.146835:... Classical monocytes
##                            delta.next       pruned.labels
##                             <numeric>         <character>
## mdm_mock1|AAACGAATCACATACG  0.0675290 Classical monocytes
## mdm_mock1|AAACGCTCATCAGCGC  0.1150706 Classical monocytes
## mdm_mock1|AAACGCTGTCGAGTGA  0.0651352 Classical monocytes
## mdm_mock1|AAAGGTAAGCCATATC  0.1076301 Classical monocytes
## mdm_mock1|AAAGGTAGTTTCCAAG  0.1521533 Classical monocytes
## mdm_mock1|AAATGGAAGATCGCCC  0.1282183 Classical monocytes
table(pred_imm_fine1$pruned.labels)
## 
##          Classical monocytes       Intermediate monocytes 
##                         8841                          823 
##      Low-density neutrophils      Myeloid dendritic cells 
##                            1                           51 
##      Non classical monocytes Plasmacytoid dendritic cells 
##                            8                            6
cellmetadata1$finelabel <- pred_imm_fine1$pruned.labels
col_pal <- c('#e31a1c', '#ff7f00', "#999900", '#cc00ff', '#1f78b4', '#fdbf6f',
             '#33a02c', '#fb9a99', "#a6cee3", "#cc6699", "#b2df8a", "#99004d", "#66ff99",
             "#669999", "#006600", "#9966ff", "#cc9900", "#e6ccff", "#3399ff", "#ff66cc",
             "#ffcc66", "#003399")
annot_df1 <- data.frame(
  barcodes = rownames(pred_imm_broad1),
  monaco_broad_annotation = pred_imm_broad1$labels,
  monaco_broad_pruned_labels = pred_imm_broad1$pruned.labels,
  monaco_fine_annotation = pred_imm_fine1$labels,
  monaco_fine_pruned_labels = pred_imm_fine1$pruned.labels)

meta_inf1 <- comb1@meta.data
meta_inf1$cell_barcode <- colnames(comb1)
meta_inf1 <- meta_inf1 %>% dplyr::left_join(y = annot_df1, by = c("cell_barcode" = "barcodes"))
rownames(meta_inf1) <- colnames(lc1)
comb1@meta.data <- meta_inf1
DimPlot(comb1, label=TRUE, group.by = "monaco_broad_annotation", reduction = "umap",
  cols = col_pal, pt.size = 0.5) + ggtitle("Annotation With the Monaco Reference Database")

DimPlot(comb1, label=TRUE, group.by = "monaco_fine_annotation", reduction = "umap",
  cols = col_pal, pt.size = 0.5) + ggtitle("Annotation With the Monaco Reference Database")

message("extract mono")
## extract mono
mono <- comb1[,which(meta_inf1$monaco_broad_annotation == "Monocytes")]
mono_metainf1 <- meta_inf1[which(meta_inf1$monaco_broad_annotation == "Monocytes"),]
mono_metainf1 <- mono_metainf1[grep("monocytes",mono_metainf1$monaco_fine_pruned_labels),]
mono <- mono[,which(colnames(mono) %in% rownames(mono_metainf1))]
mono <- FindVariableFeatures(mono, selection.method = "vst", nfeatures = 2000)
## Finding variable features for layer counts
mono <- RunPCA(mono, features = VariableFeatures(object = mono))
## Warning in PrepDR5(object = object, features = features, layer = layer, : The
## following features were not available: AL358779.1, CSTA, RALA, PLAUR, ACP5,
## ALDH1A1, NABP1, PTPRJ, S100A9, ZCCHC7, LCP1, GATAD2B, FDX1, RPS20, EML1, RAB10,
## AL669970.1, RPS6KA2, RASGEF1B, FAM13B, SLC11A1, AC002429.2.
## PC_ 1 
## Positive:  S100A10, TXN, COX5B, PRDX6, C15orf48, FABP3, BCL2A1, PSME2, TUBA1B, CALM3 
##     ACTB, CYSTM1, CHI3L1, ACTG1, TUBA1A, CRABP2, ACAT2, MGST1, IFI30, SPP1 
##     FBP1, RGCC, LDHA, MMP9, CTSL, HAMP, AKR7A2, ANXA1, LILRA1, HLA-C 
## Negative:  ARL15, FTX, EXOC4, NEAT1, DPYD, FHIT, RAD51B, MALAT1, VPS13B, JMJD1C 
##     ZFAND3, MBD5, LRMDA, TRIO, ZEB2, TCF12, DOCK4, COP1, DOCK3, ZSWIM6 
##     SPIDR, ARHGAP15, ELMO1, PLXDC2, MAML2, RERE, SBF2, ATP9B, MED13L, ATG7 
## PC_ 2 
## Positive:  TM4SF19, ANO5, GPC4, CYSTM1, FNIP2, TXNRD1, BCL2A1, SPP1, PSD3, SNX10 
##     RETREG1, RGS20, TCTEX1D2, SLC28A3, TXN, EPB41L1, NIBAN1, MGST1, CALM3, FABP3 
##     RGCC, TGM2, CCL22, ATP6V0D2, CCDC26, LINC01010, AC092353.2, ACAT2, LINC01135, HES2 
## Negative:  HLA-DPB1, HLA-DRA, CD74, HLA-DPA1, TGFBI, AIF1, HLA-DQB1, MS4A6A, C1QA, HLA-DQA1 
##     HLA-DRB1, CEBPD, C1QC, FPR3, MS4A7, CD163, CD14, MPEG1, TIMP1, LYZ 
##     ST8SIA4, FOS, EPB41L3, MAFB, TCF4, HLA-DRB5, SELENOP, FCN1, RNASE1, ARL4C 
## PC_ 3 
## Positive:  CCPG1, NUPR1, HES2, PSAT1, CARD16, CLGN, S100P, TCEA1, BTG1, SUPV3L1 
##     PHGDH, NIBAN1, G0S2, BEX2, NMB, STMN1, IFI6, CLEC4A, CLEC4E, PLEKHA5 
##     RAB6B, DUSP1, GDF15, CYSTM1, ME1, PDE4D, CXCR4, RETREG1, QPCT, XIST 
## Negative:  ACTB, CALR, SLC35F1, TIMP3, LINC01091, TUBA1B, FBP1, ACTG1, IL1RN, HSP90B1 
##     GSN, INSIG1, MGLL, LPL, GLIPR1, GCLC, MADD, PDIA4, ALCAM, PLEK 
##     MANF, RGCC, CSF1, DHCR24, LDHA, GADD45G, TMEM176B, HLA-DRB1, DUSP2, TNS3 
## PC_ 4 
## Positive:  HIV-Gagp17, HIV-BaLEnv, HIV-Polprot, HIV-Polp15p31, HIV-LTRU5, HIV-Vif, HIV-Nef, HIV-TatEx1, HIV-LTRR, HIV-Gagp1Pol 
##     HIV-Gagp2p7, HIV-TatEx2Rev, HIV-Vpu, HIV-EGFP, MARCKS, CCL3, HIV-EnvStart, TPM4, SNCA, UGCG 
##     HIV-Vpr, G0S2, CD36, LGMN, HES4, B4GALT5, TNFRSF9, CLEC4A, BCAT1, SDS 
## Negative:  PTGDS, CLU, NCAPH, BX664727.3, LINC02244, SYNGR1, COX5B, RCBTB2, MT-ATP6, CRABP2 
##     AL136317.2, RARRES1, SSBP3, LINC01010, ADRA2B, AC015660.2, MT-ND2, S100A4, CRIP1, MT-CYB 
##     LY86-AS1, RNASE6, MT-CO3, S100A8, HLA-C, VAMP5, CCL22, CPE, CSRP2, TMEM176B 
## PC_ 5 
## Positive:  TYMS, BIRC5, MKI67, PCLAF, CEP55, CENPF, CENPM, TK1, PRC1, CDKN3 
##     DIAPH3, CDK1, MYBL2, SHCBP1, NUSAP1, DLGAP5, RRM2, CENPK, HMMR, ASPM 
##     TPX2, NCAPG, CCNA2, MAD2L1, TOP2A, CIT, KIF4A, CLSPN, KIF11, PTTG1 
## Negative:  RGCC, TMEM176B, CRABP2, IGSF6, GCLC, TIMP3, IFI30, AC005280.2, GSN, CCND1 
##     NUMB, TNFSF14, PLEK, BCL2A1, NCAPH, KCNJ1, GPAT3, MGLL, AC015660.2, MREG 
##     PTGDS, RPS4Y1, RASSF4, TMEM117, CFD, CHI3L1, HLA-DRB1, DUSP2, ACTB, AC067751.1
DimHeatmap(mono, dims = 1:2, cells = 500, balanced = TRUE)

DimHeatmap(mono, dims = 3:4, cells = 500, balanced = TRUE)

ElbowPlot(mono)

mono <- FindNeighbors(mono, dims = 1:4)
## Computing nearest neighbor graph
## Computing SNN
mono <- FindClusters(mono, algorithm = 3, resolution = 0.3, verbose = FALSE)
mono <- RunUMAP(mono, dims = 1:4)
## 12:44:41 UMAP embedding parameters a = 0.9922 b = 1.112
## 12:44:41 Read 9669 rows and found 4 numeric columns
## 12:44:41 Using Annoy for neighbor search, n_neighbors = 30
## 12:44:41 Building Annoy index with metric = cosine, n_trees = 50
## 0%   10   20   30   40   50   60   70   80   90   100%
## [----|----|----|----|----|----|----|----|----|----|
## **************************************************|
## 12:44:41 Writing NN index file to temp file /tmp/RtmpRdHgON/file11d0d479ab57a3
## 12:44:41 Searching Annoy index using 1 thread, search_k = 3000
## 12:44:44 Annoy recall = 100%
## 12:44:45 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30
## 12:44:46 Initializing from normalized Laplacian + noise (using RSpectra)
## 12:44:47 Commencing optimization for 500 epochs, with 332446 positive edges
## 12:44:47 Using rng type: pcg
## 12:44:53 Optimization finished
DimPlot(mono, reduction = "umap", label=TRUE)

DimPlot(mono, group.by="monaco_fine_annotation" , reduction = "umap", label=TRUE)

DimPlot(mono, group.by="sample" , reduction = "umap", label=TRUE)

Make Alv object

alvlist <- mylist[grep("alv",names(mylist))]

comb1 <- do.call(cbind,alvlist)
sce1 <- SingleCellExperiment(list(counts=comb1))
sce1
## class: SingleCellExperiment 
## dim: 36622 11212 
## metadata(0):
## assays(1): counts
## rownames(36622): HIV_LTRR HIV_LTRU5 ... AC007325.4 AC007325.2
## rowData names(0):
## colnames(11212): alv_mock1|AAACCCAGTGCTGCAC alv_mock1|AAAGGATAGCATGAAT
##   ... alv_bystander3|TTTGGTTCAGGTTCCG alv_bystander3|TTTGTTGTCGCGTTTC
## colData names(0):
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## reducedDimNames(0):
## mainExpName: NULL
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## altExpNames(0):
cellmetadata1 <- data.frame(colnames(comb1) ,sapply(strsplit(colnames(comb1),"\\|"),"[[",1))
colnames(cellmetadata1) <- c("cell","sample")
comb1 <- CreateSeuratObject(comb1, project = "mac", assay = "RNA", meta.data = cellmetadata1)
## Warning: Feature names cannot have underscores ('_'), replacing with dashes
## ('-')
comb1 <- NormalizeData(comb1)
## Normalizing layer: counts
comb1 <- FindVariableFeatures(comb1, selection.method = "vst", nfeatures = 2000)
## Finding variable features for layer counts
comb1 <- ScaleData(comb1)
## Centering and scaling data matrix
comb1 <- RunPCA(comb1, features = VariableFeatures(object = comb1))
## PC_ 1 
## Positive:  S100A6, GAPDH, LGALS1, DBI, MIF, LGALS3, PRDX6, PSME2, CSTB, GSTO1 
##     LINC02244, PTGDS, CALM3, CYSTM1, ELOC, TXN, TMEM176B, GSTP1, CLU, MGST1 
##     CRIP1, MMP9, CHI3L1, SYNGR1, FAH, H2AFZ, ACTB, TMEM176A, TUBA1A, LDHA 
## Negative:  DOCK3, ARL15, MALAT1, RASAL2, LRMDA, TMEM117, DPYD, PLXDC2, EXOC4, ASAP1 
##     FTX, ATG7, NEAT1, MITF, TPRG1, JMJD1C, VPS13B, FHIT, ELMO1, UBE2E2 
##     MAML2, ZNF438, ZFAND3, FMNL2, FRMD4B, LPP, COP1, TRIO, ZEB2, DENND4C 
## PC_ 2 
## Positive:  HLA-DPA1, HLA-DRA, CD74, HLA-DPB1, LYZ, AIF1, MRC1, HLA-DRB1, TGFBI, CTSC 
##     C1QA, VAMP5, RCBTB2, SAMSN1, HMOX1, FOS, CLEC7A, SLCO2B1, FCGR2A, C1QC 
##     FGL2, SPRED1, SLC8A1, RBPJ, SELENOP, PDGFC, CLEC4A, ME1, FCGR3A, CD14 
## Negative:  TM4SF19, GAL, CCL22, CYSTM1, ATP6V1D, GM2A, CD164, FDX1, SCD, ACAT2 
##     CSTB, TGM2, CIR1, IARS, TCTEX1D2, RHOF, BCAT1, CYTOR, NCAPH, EPB41L1 
##     DCSTAMP, SLC20A1, GOLGA7B, LGALS1, CSF1, SNHG32, ADCY3, DUSP13, NRIP3, MREG 
## PC_ 3 
## Positive:  PTGDS, TMEM176B, LINC02244, CLU, LINC01800, RGS20, LGALS3, TMEM176A, MGST1, KCNMA1 
##     SERTAD2, NCAPH, CRIP1, AC067751.1, SYNGR1, GPC4, GCLC, C2orf92, NOS1AP, TRIM54 
##     S100A6, LINC01010, FCMR, SLC35F1, LY86-AS1, NCF1, FGL2, ST5, NRCAM, CT69 
## Negative:  CTSZ, SLC11A1, MS4A7, AIF1, MRC1, FCER1G, CTSB, LGMN, ID3, MSR1 
##     FCGR3A, TPM4, CLEC7A, FPR3, C1QA, CTSC, CAMK1, CTSL, HLA-DRB5, CCL3 
##     S100A9, C1QC, HAMP, CSTB, HLA-DQA1, HLA-DQB1, MARCO, MARCKS, SLA, PLAU 
## PC_ 4 
## Positive:  TYMS, PCLAF, CLSPN, TK1, DIAPH3, MYBL2, RRM2, ESCO2, CENPM, MKI67 
##     FAM111B, TCF19, SHCBP1, CDK1, HELLS, CEP55, CENPK, BIRC5, CENPU, ATAD2 
##     DTL, KIF11, NCAPG, NUSAP1, MCM10, TOP2A, PRC1, GINS2, ANLN, TPX2 
## Negative:  GCHFR, XIST, HLA-DRB5, GPX3, SAT1, SLC11A1, MS4A7, MSR1, QPCT, AC020656.1 
##     GPRIN3, MARCO, NMB, PAX8-AS1, FRMD4A, ST6GAL1, AL035446.2, FDX1, SERINC2, CTSZ 
##     S100A9, STX4, FUCA1, RARRES1, SASH1, AC008591.1, LINC01500, CCDC26, GM2A, C22orf34 
## PC_ 5 
## Positive:  AC020656.1, NIPAL2, LINC02244, GCHFR, RARRES1, TDRD3, BX664727.3, FDX1, XIST, AL136317.2 
##     LINC01010, TDRD9, OSBP2, QPCT, GJB2, CFD, LYZ, S100A9, GAPLINC, TMTC1 
##     PKD1L1, PRSS21, SLC6A16, CCDC26, GM2A, HES2, CTSK, PLEKHA5, HLA-DRB5, ANO5 
## Negative:  HIV-Gagp17, HIV-BaLEnv, HIV-LTRU5, HIV-TatEx1, HIV-Polprot, MIF, HIV-Nef, HIV-LTRR, HIV-Polp15p31, HIV-Vif 
##     HIV-Gagp1Pol, IL1RN, PLEK, HIV-EnvStart, HIV-TatEx2Rev, HIV-Vpu, HIV-Gagp2p7, SLC35F1, ACTB, HIV-Vpr 
##     TMEM176A, CYTOR, ACTG1, HIV-EGFP, PSME2, TUBA1A, CTSB, MARCKS, MYL9, PHLDA1
comb1 <- RunHarmony(comb1,"sample")
## Transposing data matrix
## Initializing state using k-means centroids initialization
## Harmony 1/10
## Harmony 2/10
## Harmony 3/10
## Harmony 4/10
## Harmony converged after 4 iterations
DimHeatmap(comb1, dims = 1:6, cells = 500, balanced = TRUE)

ElbowPlot(comb1)

comb1 <- JackStraw(comb1, num.replicate = 100)
comb1 <- FindNeighbors(comb1, dims = 1:10)
## Computing nearest neighbor graph
## Computing SNN
comb1 <- FindClusters(comb1, resolution = 0.5)
## Modularity Optimizer version 1.3.0 by Ludo Waltman and Nees Jan van Eck
## 
## Number of nodes: 11212
## Number of edges: 344775
## 
## Running Louvain algorithm...
## Maximum modularity in 10 random starts: 0.8624
## Number of communities: 10
## Elapsed time: 0 seconds
comb1 <- RunUMAP(comb1, dims = 1:10)
## 12:48:16 UMAP embedding parameters a = 0.9922 b = 1.112
## 12:48:16 Read 11212 rows and found 10 numeric columns
## 12:48:16 Using Annoy for neighbor search, n_neighbors = 30
## 12:48:16 Building Annoy index with metric = cosine, n_trees = 50
## 0%   10   20   30   40   50   60   70   80   90   100%
## [----|----|----|----|----|----|----|----|----|----|
## **************************************************|
## 12:48:17 Writing NN index file to temp file /tmp/RtmpRdHgON/file11d0d49e2e086
## 12:48:17 Searching Annoy index using 1 thread, search_k = 3000
## 12:48:20 Annoy recall = 100%
## 12:48:21 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30
## 12:48:22 Initializing from normalized Laplacian + noise (using RSpectra)
## 12:48:22 Commencing optimization for 200 epochs, with 450140 positive edges
## 12:48:22 Using rng type: pcg
## 12:48:26 Optimization finished
DimPlot(comb1, reduction = "umap")

message("macrophage markers")
## macrophage markers
FeaturePlot(comb1, features = c("ADGRE1", "CCR2", "SIGLEC1", "CX3CR1", "MRC1", "CD163", "LYVE1", "CD9", "TREM2"))

DimPlot(comb1, reduction = "umap", label = TRUE, pt.size = 0.5) + NoLegend()

ref <- celldex::MonacoImmuneData()
DefaultAssay(comb1) <- "RNA"
comb21 <- as.SingleCellExperiment(comb1)
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
lc1 <- logcounts(comb21)
pred_imm_broad1 <- SingleR(test=comb21, ref=ref,labels=ref$label.main)
head(pred_imm_broad1)
## DataFrame with 6 rows and 4 columns
##                                                    scores      labels
##                                                  <matrix> <character>
## alv_mock1|AAACCCAGTGCTGCAC 0.273560:0.272344:0.161242:...   Monocytes
## alv_mock1|AAAGGATAGCATGAAT 0.318711:0.307377:0.191663:...   Monocytes
## alv_mock1|AAAGGATAGTCAGGGT 0.294485:0.275673:0.182914:...   Monocytes
## alv_mock1|AAAGGATAGTTCCGGC 0.294678:0.294725:0.183945:...   Monocytes
## alv_mock1|AAAGGATTCACCATCC 0.278966:0.268607:0.190627:...   Monocytes
## alv_mock1|AAAGGGCCATGACGTT 0.284776:0.293739:0.171230:...   Monocytes
##                            delta.next pruned.labels
##                             <numeric>   <character>
## alv_mock1|AAACCCAGTGCTGCAC   0.134488     Monocytes
## alv_mock1|AAAGGATAGCATGAAT   0.104645     Monocytes
## alv_mock1|AAAGGATAGTCAGGGT   0.140018     Monocytes
## alv_mock1|AAAGGATAGTTCCGGC   0.128407     Monocytes
## alv_mock1|AAAGGATTCACCATCC   0.147810     Monocytes
## alv_mock1|AAAGGGCCATGACGTT   0.166792     Monocytes
table(pred_imm_broad1$pruned.labels)
## 
## Dendritic cells       Monocytes 
##              12           11014
cellmetadata1$label <- pred_imm_broad1$pruned.labels
pred_imm_fine1 <- SingleR(test=comb21, ref=ref, labels=ref$label.fine)
head(pred_imm_fine1)
## DataFrame with 6 rows and 4 columns
##                                                    scores              labels
##                                                  <matrix>         <character>
## alv_mock1|AAACCCAGTGCTGCAC 0.163017:0.398232:0.176698:... Classical monocytes
## alv_mock1|AAAGGATAGCATGAAT 0.180234:0.435146:0.208731:... Classical monocytes
## alv_mock1|AAAGGATAGTCAGGGT 0.169967:0.389207:0.187751:... Classical monocytes
## alv_mock1|AAAGGATAGTTCCGGC 0.166462:0.422480:0.189466:... Classical monocytes
## alv_mock1|AAAGGATTCACCATCC 0.184520:0.383707:0.203877:... Classical monocytes
## alv_mock1|AAAGGGCCATGACGTT 0.173873:0.439659:0.198357:... Classical monocytes
##                            delta.next       pruned.labels
##                             <numeric>         <character>
## alv_mock1|AAACCCAGTGCTGCAC  0.1433756 Classical monocytes
## alv_mock1|AAAGGATAGCATGAAT  0.1213924 Classical monocytes
## alv_mock1|AAAGGATAGTCAGGGT  0.0502055 Classical monocytes
## alv_mock1|AAAGGATAGTTCCGGC  0.0994518 Classical monocytes
## alv_mock1|AAAGGATTCACCATCC  0.0283404 Classical monocytes
## alv_mock1|AAAGGGCCATGACGTT  0.0687853 Classical monocytes
table(pred_imm_fine1$pruned.labels)
## 
##     Classical monocytes  Intermediate monocytes Myeloid dendritic cells 
##                    9702                    1332                      25 
## Non classical monocytes 
##                       3
cellmetadata1$finelabel <- pred_imm_fine1$pruned.labels
col_pal <- c('#e31a1c', '#ff7f00', "#999900", '#cc00ff', '#1f78b4', '#fdbf6f',
             '#33a02c', '#fb9a99', "#a6cee3", "#cc6699", "#b2df8a", "#99004d", "#66ff99",
             "#669999", "#006600", "#9966ff", "#cc9900", "#e6ccff", "#3399ff", "#ff66cc",
             "#ffcc66", "#003399")
annot_df1 <- data.frame(
  barcodes = rownames(pred_imm_broad1),
  monaco_broad_annotation = pred_imm_broad1$labels,
  monaco_broad_pruned_labels = pred_imm_broad1$pruned.labels,
  monaco_fine_annotation = pred_imm_fine1$labels,
  monaco_fine_pruned_labels = pred_imm_fine1$pruned.labels)

meta_inf1 <- comb1@meta.data
meta_inf1$cell_barcode <- colnames(comb1)
meta_inf1 <- meta_inf1 %>% dplyr::left_join(y = annot_df1, by = c("cell_barcode" = "barcodes"))
rownames(meta_inf1) <- colnames(lc1)
comb1@meta.data <- meta_inf1
DimPlot(comb1, label=TRUE, group.by = "monaco_broad_annotation", reduction = "umap",
  cols = col_pal, pt.size = 0.5) + ggtitle("Annotation With the Monaco Reference Database")

DimPlot(comb1, label=TRUE, group.by = "monaco_fine_annotation", reduction = "umap",
  cols = col_pal, pt.size = 0.5) + ggtitle("Annotation With the Monaco Reference Database")

message("extract mono")
## extract mono
mono <- comb1[,which(meta_inf1$monaco_broad_annotation == "Monocytes")]
mono_metainf1 <- meta_inf1[which(meta_inf1$monaco_broad_annotation == "Monocytes"),]
mono_metainf1 <- mono_metainf1[grep("monocytes",mono_metainf1$monaco_fine_pruned_labels),]
mono <- mono[,which(colnames(mono) %in% rownames(mono_metainf1))]
mono <- FindVariableFeatures(mono, selection.method = "vst", nfeatures = 2000)
## Finding variable features for layer counts
mono <- RunPCA(mono, features = VariableFeatures(object = mono))
## Warning in PrepDR5(object = object, features = features, layer = layer, : The
## following features were not available: AC074099.1, MBOAT4, CYP1B1, AC022035.1,
## MS4A4A, IFI30, PSMA7, ZCCHC7, CPEB2-DT, ZNF609, CEP85L, AC023194.3, GLUL,
## LINC01951, LINC02643, DIAPH3-AS1, F2RL1, AC108860.2, DNAI1, HULC, AL135818.3,
## KIF16B, TESK2, HCAR3, LIMCH1, PGBD5, DOP1B, YJEFN3, LINC02732.
## PC_ 1 
## Positive:  S100A6, GAPDH, LGALS1, DBI, MIF, LGALS3, PSME2, PRDX6, CSTB, GSTO1 
##     LINC02244, PTGDS, CYSTM1, ELOC, CALM3, TXN, GSTP1, TMEM176B, MMP9, CRIP1 
##     MGST1, CLU, CHI3L1, H2AFZ, FAH, TUBA1A, LDHA, TMEM176A, SYNGR1, S100A4 
## Negative:  DOCK3, ARL15, MALAT1, RASAL2, LRMDA, TMEM117, DPYD, PLXDC2, FTX, EXOC4 
##     ASAP1, TPRG1, ATG7, MITF, NEAT1, JMJD1C, VPS13B, FHIT, ELMO1, MAML2 
##     UBE2E2, ZNF438, COP1, FMNL2, LPP, ZFAND3, TRIO, FRMD4B, ZEB2, MED13L 
## PC_ 2 
## Positive:  TM4SF19, CCL22, GAL, CYSTM1, ATP6V1D, GM2A, CD164, FDX1, SCD, ACAT2 
##     CSTB, TGM2, IARS, CIR1, TCTEX1D2, RHOF, BCAT1, CYTOR, NCAPH, EPB41L1 
##     DCSTAMP, SLC20A1, GOLGA7B, CSF1, LGALS1, ADCY3, SNHG32, DUSP13, NRIP3, MREG 
## Negative:  HLA-DPA1, HLA-DRA, CD74, HLA-DPB1, AIF1, LYZ, HLA-DRB1, MRC1, CTSC, TGFBI 
##     VAMP5, C1QA, RCBTB2, SAMSN1, HMOX1, FOS, CLEC7A, SLCO2B1, FCGR2A, C1QC 
##     FGL2, SPRED1, SLC8A1, SELENOP, RBPJ, PDGFC, CLEC4A, ME1, FCGR3A, CD14 
## PC_ 3 
## Positive:  PTGDS, TMEM176B, LINC02244, CLU, LINC01800, LGALS3, TMEM176A, RGS20, MGST1, KCNMA1 
##     CRIP1, NCAPH, SERTAD2, SYNGR1, AC067751.1, GPC4, GCLC, TRIM54, C2orf92, NOS1AP 
##     S100A6, FCMR, SLC35F1, LINC01010, NCF1, LY86-AS1, FGL2, ST5, PLEK, MX1 
## Negative:  CTSZ, SLC11A1, MS4A7, AIF1, MRC1, FCER1G, LGMN, CTSB, MSR1, FCGR3A 
##     ID3, TPM4, CLEC7A, FPR3, CAMK1, C1QA, CTSC, HLA-DRB5, CTSL, CCL3 
##     S100A9, HAMP, C1QC, CSTB, HLA-DQA1, MARCO, HLA-DQB1, FMN1, SLA, MARCKS 
## PC_ 4 
## Positive:  GCHFR, XIST, SAT1, GPX3, HLA-DRB5, QPCT, MS4A7, SLC11A1, AC020656.1, MSR1 
##     GPRIN3, NMB, MARCO, PAX8-AS1, FRMD4A, ST6GAL1, FDX1, AL035446.2, SERINC2, CTSZ 
##     FUCA1, S100A9, STX4, RARRES1, SASH1, AC008591.1, LINC01500, CCDC26, GM2A, CFD 
## Negative:  TYMS, PCLAF, CLSPN, TK1, MYBL2, DIAPH3, RRM2, ESCO2, CENPM, FAM111B 
##     MKI67, TCF19, SHCBP1, HELLS, CDK1, CENPU, CEP55, CENPK, DTL, BIRC5 
##     ATAD2, NCAPG, KIF11, MCM10, GINS2, NUSAP1, TOP2A, PRC1, TPX2, ANLN 
## PC_ 5 
## Positive:  AC020656.1, NIPAL2, LINC02244, GCHFR, RARRES1, TDRD3, BX664727.3, XIST, FDX1, AL136317.2 
##     LINC01010, GJB2, CFD, QPCT, OSBP2, TDRD9, LYZ, S100A9, GAPLINC, TMTC1 
##     PRSS21, CTSK, SLC6A16, PKD1L1, GM2A, HES2, CCDC26, PLEKHA5, HLA-DRB5, ANO5 
## Negative:  HIV-Gagp17, HIV-LTRU5, HIV-BaLEnv, HIV-TatEx1, HIV-Polprot, MIF, HIV-Nef, HIV-LTRR, HIV-Polp15p31, HIV-Vif 
##     HIV-Gagp1Pol, IL1RN, PLEK, HIV-EnvStart, HIV-Vpu, HIV-TatEx2Rev, HIV-Gagp2p7, ACTB, SLC35F1, HIV-Vpr 
##     CYTOR, ACTG1, TMEM176A, HIV-EGFP, PSME2, CTSB, MARCKS, TUBA1A, MYL9, PHLDA1
DimHeatmap(mono, dims = 1:2, cells = 500, balanced = TRUE)

DimHeatmap(mono, dims = 3:4, cells = 500, balanced = TRUE)

ElbowPlot(mono)

mono <- FindNeighbors(mono, dims = 1:4)
## Computing nearest neighbor graph
## Computing SNN
mono <- FindClusters(mono, algorithm = 3, resolution = 0.3, verbose = FALSE)
mono <- RunUMAP(mono, dims = 1:4)
## 12:49:04 UMAP embedding parameters a = 0.9922 b = 1.112
## 12:49:04 Read 11036 rows and found 4 numeric columns
## 12:49:04 Using Annoy for neighbor search, n_neighbors = 30
## 12:49:04 Building Annoy index with metric = cosine, n_trees = 50
## 0%   10   20   30   40   50   60   70   80   90   100%
## [----|----|----|----|----|----|----|----|----|----|
## **************************************************|
## 12:49:05 Writing NN index file to temp file /tmp/RtmpRdHgON/file11d0d43a052a0d
## 12:49:05 Searching Annoy index using 1 thread, search_k = 3000
## 12:49:08 Annoy recall = 100%
## 12:49:09 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30
## 12:49:11 Initializing from normalized Laplacian + noise (using RSpectra)
## 12:49:11 Commencing optimization for 200 epochs, with 374004 positive edges
## 12:49:11 Using rng type: pcg
## 12:49:14 Optimization finished
DimPlot(mono, reduction = "umap", label=TRUE)

DimPlot(mono, group.by="monaco_fine_annotation" , reduction = "umap", label=TRUE)

DimPlot(mono, group.by="sample" , reduction = "umap", label=TRUE)

Extract monocytes MDM only

mono <- comb[,which(meta_inf$monaco_broad_annotation == "Monocytes")]
mono_metainf <- meta_inf[which(meta_inf$monaco_broad_annotation == "Monocytes"),]
mono_metainf1 <- mono_metainf[grep("monocytes",mono_metainf$monaco_fine_pruned_labels),]
mono <- mono[,which(colnames(mono) %in% rownames(mono_metainf))]
mono <- FindVariableFeatures(mono, selection.method = "vst", nfeatures = 2000)
## Finding variable features for layer counts
mono <- RunPCA(mono, features = VariableFeatures(object = mono))
## Warning in PrepDR5(object = object, features = features, layer = layer, : The
## following features were not available: ADGRF1, AP000812.1, ACTB, AC005740.5,
## AC138123.1, HIF1A-AS3, PRH1, AL592494.2.
## PC_ 1 
## Positive:  GAPDH, FABP3, TXN, IFI30, S100A10, PRDX6, TUBA1B, BLVRB, OTOA, S100A9 
##     FAH, C15orf48, GCHFR, CYSTM1, CARD16, GSTP1, HAMP, PSMA7, CTSB, CSTA 
##     ACTG1, FABP4, H2AFZ, LDHB, LINC01827, CFD, TUBA1A, MMP9, SELENOW, LINC02244 
## Negative:  ARL15, DOCK3, FTX, NEAT1, EXOC4, MALAT1, DPYD, LRMDA, RASAL2, JMJD1C 
##     TMEM117, PLXDC2, VPS13B, FHIT, TPRG1, TRIO, ATG7, ZNF438, MAML2, ZFAND3 
##     MITF, COP1, ZEB2, ELMO1, MED13L, DENND4C, TCF12, ERC1, JARID2, FMNL2 
## PC_ 2 
## Positive:  HLA-DRB1, CD74, HLA-DRA, HLA-DPA1, GCLC, HLA-DPB1, LYZ, RCBTB2, MRC1, KCNMA1 
##     SPRED1, C1QA, FGL2, AC020656.1, SLCO2B1, CYP1B1, AIF1, HLA-DRB5, PTGDS, S100A4 
##     VAMP5, LINC02345, CA2, CRIP1, CAMK1, ALOX5AP, RTN1, HLA-DQB1, MX1, TGFBI 
## Negative:  CYSTM1, CD164, PSAT1, FAH, FDX1, GDF15, ATP6V1D, BCAT1, SAT1, CCPG1 
##     PHGDH, PSMA7, HEBP2, SLAMF9, RETREG1, GARS, HES2, TCEA1, TXN, RHOQ 
##     RILPL2, B4GALT5, CLGN, NUPR1, CSTA, SPTBN1, HSD17B12, STMN1, SNHG5, PTER 
## PC_ 3 
## Positive:  MARCKS, CD14, BTG1, MS4A6A, TGFBI, CTSC, FPR3, HLA-DQA1, AIF1, MPEG1 
##     MEF2C, CD163, IFI30, TIMP1, HLA-DPB1, ALDH2, SELENOP, NUPR1, NAMPT, HLA-DQB1 
##     HIF1A, C1QC, MS4A7, FUCA1, EPB41L3, HLA-DQA2, RNASE1, ARL4C, ZNF331, TCF4 
## Negative:  NCAPH, CRABP2, RGCC, CHI3L1, TM4SF19, DUSP2, GAL, AC015660.2, CCL22, ACAT2 
##     LINC01010, TMEM114, MGST1, RGS20, TRIM54, LINC02244, MREG, NUMB, TCTEX1D2, GPC4 
##     CCND1, POLE4, SYNGR1, SLC20A1, SERTAD2, IL1RN, GCLC, CLU, PLEK, AC092353.2 
## PC_ 4 
## Positive:  ACTG1, TPM4, CCL3, CTSB, TUBA1B, CSF1, DHCR24, CYTOR, LGMN, INSIG1 
##     GAPDH, TUBB, CD36, HAMP, CCL7, C1QA, AIF1, MGLL, TYMS, LIMA1 
##     C1QC, PCLAF, CCL2, HSP90B1, CLSPN, C1QB, TNFSF13, TK1, C15orf48, CAMK1 
## Negative:  PTGDS, LINC02244, CLU, CSTA, CCPG1, MGST1, SYNGR1, LINC01010, EPHB1, ALDH2 
##     AC015660.2, LY86-AS1, GAS5, NCF1, BX664727.3, S100P, TMEM91, SNHG5, CLEC12A, AP000331.1 
##     APOD, PDE4D, C1QTNF4, VAMP5, LYZ, CFD, RCBTB2, DIXDC1, AC073359.2, ARHGAP15 
## PC_ 5 
## Positive:  TYMS, PCLAF, TK1, MKI67, MYBL2, RRM2, CENPM, BIRC5, CEP55, CLSPN 
##     CDK1, DIAPH3, SHCBP1, NUSAP1, CENPF, CENPK, PRC1, TOP2A, NCAPG, ESCO2 
##     KIF11, ANLN, CCNA2, TPX2, ASPM, FAM111B, MAD2L1, RAD51AP1, GTSE1, HMMR 
## Negative:  HIV-BaLEnv, HIV-LTRU5, HIV-Polprot, HIV-Gagp17, HIV-Nef, HIV-TatEx1, HIV-Polp15p31, HIV-LTRR, HIV-Vif, HIV-Gagp1Pol 
##     HIV-TatEx2Rev, HIV-Gagp2p7, HIV-EnvStart, HIV-Vpu, HIV-Vpr, HIV-EGFP, CTSB, MMP19, IL6R-AS1, CSF1 
##     CCL3, MGLL, IL1RN, INSIG1, AL157912.1, SDS, LGMN, TCTEX1D2, TNFRSF9, PHLDA1
DimHeatmap(mono, dims = 1:2, cells = 500, balanced = TRUE)

DimHeatmap(mono, dims = 3:4, cells = 500, balanced = TRUE)

ElbowPlot(mono)

mono <- FindNeighbors(mono, dims = 1:4)
## Computing nearest neighbor graph
## Computing SNN
mono <- FindClusters(mono, algorithm = 3, resolution = 0.3, verbose = FALSE)
mono <- RunUMAP(mono, dims = 1:4)
## 12:50:00 UMAP embedding parameters a = 0.9922 b = 1.112
## 12:50:00 Read 24224 rows and found 4 numeric columns
## 12:50:00 Using Annoy for neighbor search, n_neighbors = 30
## 12:50:00 Building Annoy index with metric = cosine, n_trees = 50
## 0%   10   20   30   40   50   60   70   80   90   100%
## [----|----|----|----|----|----|----|----|----|----|
## **************************************************|
## 12:50:02 Writing NN index file to temp file /tmp/RtmpRdHgON/file11d0d466b58b08
## 12:50:02 Searching Annoy index using 1 thread, search_k = 3000
## 12:50:10 Annoy recall = 100%
## 12:50:11 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30
## 12:50:13 Initializing from normalized Laplacian + noise (using RSpectra)
## 12:50:13 Commencing optimization for 200 epochs, with 793206 positive edges
## 12:50:13 Using rng type: pcg
## 12:50:19 Optimization finished
DimPlot(mono, reduction = "umap", label=TRUE)

DimPlot(mono, group.by="monaco_fine_annotation" , reduction = "umap", label=TRUE)

DimPlot(mono, group.by="sample" , reduction = "umap", label=TRUE)

Cell counts

Most cells are classified as monocytes.

cc <- table(meta_inf[,c("sample","monaco_broad_annotation")])

cc %>% kbl(caption="cell counts") %>% kable_paper("hover", full_width = F)
cell counts
Basophils Dendritic cells Monocytes
alv_active1 0 0 774
alv_active2 0 3 543
alv_active3 0 1 540
alv_bystander1 0 1 2458
alv_bystander2 0 0 1948
alv_bystander3 0 1 1936
alv_latent1 0 1 301
alv_latent2 0 0 99
alv_latent3 0 1 137
alv_mock1 0 1 883
alv_mock2 0 0 649
alv_mock3 0 3 1031
mdm_active1 0 3 599
mdm_active2 0 0 414
mdm_active3 0 2 305
mdm_active4 0 0 401
mdm_bystander1 0 12 1845
mdm_bystander2 0 8 1957
mdm_bystander3 0 19 490
mdm_bystander4 0 1 1495
mdm_latent1 1 11 160
mdm_latent2 0 8 187
mdm_latent3 0 3 72
mdm_latent4 0 0 23
mdm_mock1 0 1 691
mdm_mock2 0 1 549
mdm_mock3 0 2 135
mdm_mock4 0 0 775
react6 0 3 2827 
tcc <- t(cc)

pctcc <- apply(tcc,2,function(x) { x/sum(x)*100} )

pctcc %>% kbl(caption="cell proportions") %>% kable_paper("hover", full_width = F)
cell proportions
alv_active1 alv_active2 alv_active3 alv_bystander1 alv_bystander2 alv_bystander3 alv_latent1 alv_latent2 alv_latent3 alv_mock1 alv_mock2 alv_mock3 mdm_active1 mdm_active2 mdm_active3 mdm_active4 mdm_bystander1 mdm_bystander2 mdm_bystander3 mdm_bystander4 mdm_latent1 mdm_latent2 mdm_latent3 mdm_latent4 mdm_mock1 mdm_mock2 mdm_mock3 mdm_mock4 react6
Basophils 0 0.0000000 0.0000000 0.0000000 0 0.0000000 0.0000000 0 0.0000000 0.0000000 0 0.0000000 0.0000000 0 0.0000000 0 0.0000000 0.0000000 0.000000 0.0000000 0.5813953 0.000000 0 0 0.0000000 0.0000000 0.000000 0 0.0000000
Dendritic cells 0 0.5494505 0.1848429 0.0406669 0 0.0516262 0.3311258 0 0.7246377 0.1131222 0 0.2901354 0.4983389 0 0.6514658 0 0.6462036 0.4071247 3.732809 0.0668449 6.3953488 4.102564 4 0 0.1445087 0.1818182 1.459854 0 0.1060071
Monocytes 100 99.4505495 99.8151571 99.9593331 100 99.9483738 99.6688742 100 99.2753623 99.8868778 100 99.7098646 99.5016611 100 99.3485342 100 99.3537964 99.5928753 96.267191 99.9331551 93.0232558 95.897436 96 100 99.8554913 99.8181818 98.540146 100 99.8939929

Focus on MOCK vs ACTIVE - exclude latent and bystander

focus <- meta_inf[grep("latent",rownames(meta_inf),invert=TRUE),]
focus <- focus[grep("bystander",rownames(focus),invert=TRUE),]
focus_mdm <- focus[grep("mdm",rownames(focus)),]
focus_alv <- focus[grep("alv",rownames(focus)),]

mono_focus_mdm <- mono[,which(colnames(mono) %in% rownames(focus_mdm))]
mono_focus_alv <- mono[,which(colnames(mono) %in% rownames(focus_alv))]

# mono_focus_mdm
mono_focus_mdm <- FindVariableFeatures(mono_focus_mdm, selection.method = "vst", nfeatures = 2000)
## Finding variable features for layer counts
mono_focus_mdm <- RunPCA(mono_focus_mdm, features = VariableFeatures(object = mono_focus_mdm))
## Warning: The following 36 features requested have zero variance; running
## reduction without them: CCL3, PDE7B, NEAT1, KCNIP1, BX664727.3, ARL4C,
## BX284613.2, HIST1H3J, ANXA1, NCALD, SLC51A, CPEB2, PRMT9, MGST1, ABCG1, EPSTI1,
## PPP2R3A, PRKCA, CU638689.5, DIAPH2-AS1, RGS20, CST7, ARMC9, AC013799.1,
## AC137770.1, GRAMD1B, RRAS2, PPP1R12B, AC124017.1, ENTPD1, GTDC1, LINC00511,
## AC024901.1, AC006001.2, PRKG2, SCLT1
## Warning in PrepDR5(object = object, features = features, layer = layer, : The
## following features were not available: HIST1H2BJ, ENG, OASL, CENPA, SSBP3,
## MT-ND5, CCND2, TVP23A, PCBP3, LINC00885, SCAI, AL009177.1, AC013287.1,
## AL355388.1, IFT80, PIWIL2, AC106793.1, AL358944.1, C16orf89, KLF12, AC108134.2,
## SETD2, C5AR2, PPP6R2, FANCM, TTK, HIF1A-AS3, TNRC6C, STXBP1, ZZEF1, HCAR2,
## GPR155, MARCH1, SLC2A14, RPS4Y1, IPCEF1, AC064805.2, PNPLA7, AL353759.1, KLRG1,
## PDIA4, TENM1, EIF2B3, LRRK2, TNFRSF4, RASIP1, ZBTB41, AGPAT5, LPL, RAP1GDS1,
## NUP93, LINC02853, CLPX, FAM118B, ESR2, MT-ATP6, SH3GL1, ATP6V0A2, CWC22, PSME2,
## PAWR, GYG2, AC034213.1, AL157911.1, AC007091.1, LINC02585, AC007364.1,
## AL357873.1, P2RY12, AC025262.1, NR2F1-AS1, ANKRD34B, PCA3, CLIC5, DUSP16, CREM,
## AL360015.1, IFT140, AURKC, CCNB2, ASTL, CHRNB4, PKIA-AS1, WWP1, SF3B3,
## TMEM220-AS1, DOK5, RAB10, LDHA, STAT5B, AC005740.5, MT-ND2, PARD3, LYPD1,
## AL355388.3, AP000462.1, AC072022.2, ZNF276, HLA-C, AC093766.1, BTBD2, FAM184A,
## IFI6, PDGFD, SRRM2-AS1, SIGLEC10, SRGN, SEMA6D, AC108879.1, MT-CO3, AC133550.2,
## MAP4K1, CPLX1, LINC01054, PACS1, OBI1-AS1, MAP3K15, ACTR3C, AL021917.1, LRRC9,
## RASSF4, TMEM212-AS1, AC105001.1, AL031658.1, CDK19, SF3B1, MT-CYB, AP000446.1,
## TTC21B-AS1, JAKMIP3, VGLL3, RGS18, CHRM3, DAPK2, AC099552.1, UBASH3B, ANK3,
## AC006427.2, AC079062.1, ACMSD, ZNF385D-AS1, CFAP52, SETBP1, MRC2, BCL2A1,
## ZFPM2-AS1, COX5B, MT-ND1, CTHRC1, AL592295.3, AC100849.2, TRIM71, CCDC7,
## AC078923.1, DPEP3, CARD11, AC240274.1, AC112236.3, ZDHHC17, IGSF6, AC089983.1,
## P2RY13, AC092490.1, MANF, GRM7, FDXACB1, NLRP4, APCDD1L, FHOD3, AC092811.1,
## MMP28, AC009315.1, AHR, KIF21A, CRISPLD2, TFG, AC007389.1, GNG4, RORA, ARC,
## SAMD11, GAS1RR, MIR155HG, DARS, CLEC4C, TRIM37, SLC44A5, AC114977.1,
## AC019117.1, CEP112, TUBB3, ADRA2B, TPTE2, STPG2, GTSF1, CORIN, CEP135,
## AL132775.1, SNAP25-AS1, AL049828.1, DNAH2, AL391807.1, PRRT2, TEX15, OR8D1,
## SOAT2, MCF2L-AS1, AC005393.1, SESN3, DHX8, VIPR1, NWD1, TNS3, GSN, OR3A2,
## HIST1H2AC, AKR7A2, ALDH1A1, TMEM45A, SRGAP3, AC084809.2, CPE, SNHG12,
## AC026333.3, AC073050.1, LINC01600, LCTL, AC019330.1, AC073569.1, ATP6V0D2,
## TACC3, GFRA2, MAPK8, LRRIQ4, LINC00649, RUFY2, CD93, ATF3, AC011365.1, GAL3ST4,
## Z99758.1, CREG2, U62317.4, SCAPER, LYPLAL1-DT, LNX1, AC096570.1, AC016074.2,
## ERO1A, AC009264.1, ENPEP, CNDP1, SIGLEC7, GLIPR1, OSBPL6, AL136418.1,
## HIST1H2BG, SULF2, MNAT1, AL589740.1, TUBB4B, PAX8-AS1, TASP1, ABCA13,
## LINC00237, AC020743.2, TSPAN8, AC015849.1, AL078602.1, CACNA2D3, LINC01917,
## LINC01855, Z94721.1, MAPK13, FKBP1B, AC021231.1, PRTG, GAK, RALGAPA2, RTKN2,
## AL445584.2, LINC02208, PODN, PDE11A, DPF1, ACTB, RPS6KA6, MCCC2, TFRC,
## AC005264.1, TMEM71, KDM6A, HIST2H2BE, EPHA6, COL8A2, LINC00958, ZBTB46,
## AC011476.3, SCFD2, GLRX, C11orf45, MLLT3, RAP2C-AS1, LGALSL, LINC01353, SOX15,
## KIAA0825, CD72, NPRL3, LINC01891, AL645929.2, MMD2, LINC02449, MAP1A, OXSR1,
## AC104459.1, SLC26A7, ZHX2, AC021086.1, SPAG7, CALR, AC090630.1, HERPUD1, ITGA4,
## AC087683.3, AC114763.1, ZFP36L1, SPEG, LINC01191, RFX3, RNF24, STAG1,
## AC117473.1, MGAT5, TUBB4A, MRVI1, CKMT1A, AC073475.1, LY96, SPTLC3, KIAA1841,
## AL031710.2, NYX, LGALS3, PTPRG-AS1, CHM, TMEM131L, MCM9, JAKMIP2-AS1, BACH1,
## AP000829.1, CFAP69, CLDN4, RHCE, PRSS3, AC010834.2, AL356379.2, MDH1, HCAR3,
## ADORA2B, MARCH3, LINC02015, CALM3, PROCR, LILRB2, IGF2R, SOCS3, NETO2,
## TMEM72-AS1, RNF180, E2F1, TNIK, P3H2, AC008115.2, SPIB, PLBD1, AF131216.1,
## AC103726.2, NALCN, AC008555.2, AC008655.2, AL672032.1, AP002793.1, AL110292.1,
## AC098588.3, UBE2T, PIP4K2C, PCLO, AC097654.1, MKX, AL121772.1, AC020637.1,
## LINC00571, LINC02112, KCNJ1, AL136298.1, TRAF2, BMPR1B, AFF1, SPIRE1, PAFAH1B1,
## CASP1, LINC02851, CNIH3, EXD2, PTPRB, SNX10, ITPR2, KIF20B, AC129803.1, NFKB1,
## BUB1, SOS1, ADAMTS10, PLXNC1, SGO1, BFSP2, AL365295.2, AHCYL2, PKN2, ZC4H2,
## HSP90AA1, FAM135A, XKR9, CDT1, PRORP, LINC01762, ITM2A, NEGR1, ANGPTL4,
## AC079584.1, LINC00987, SLC7A8, PFKFB3, LPP, STUM, FAM110B, QKI, FILIP1L, DYM,
## MYADM, ADIRF, TXNIP, ARRDC3-AS1, LINC02798, AL139246.1, AL137076.1, AL158839.1,
## AL589765.6, C4BPA, C1orf229, AC114810.1, AL133243.1, AC009229.3, AC012358.1,
## LINC01104, AC063944.3, AC092902.6, AC128709.2, AC021220.2, ADAMTS3, RBM46,
## AC116351.1, AC011374.3, LINC02533, LINC02571, Z84484.1, MRAP2, FUT9,
## AL357992.1, AL078582.1, AC002480.2, TRIM74, DEFB136, PRDM14, CALB1, AF178030.1,
## AF235103.1, CNTFR-AS1, AL353764.1, TMEM246-AS1, PPP3R2, AL356481.2, AL731559.1,
## AL121748.1, LINC02625, SYCE1, OR10A4, LINC02751, SAA4, AC013714.1, AC024940.1,
## AC012464.3, AC063943.1, C1QTNF9-AS1, SMAD9-IT1, LINC00563, AL161717.1,
## CLYBL-AS2, AL442125.2, KLHL33, CMA1, AL163953.1, AC104938.1, AC048382.1,
## AC091167.5, BAIAP3, AL133297.1, AC106820.2, NPIPB8, AC012186.2, AC092378.1,
## AC129507.2, RAI1-AS1, AC007952.6, AC004448.3, AC243773.2, KRT19, AC105094.2,
## OR7E24, ANGPTL8, LINC01858, AC022150.2, AL021396.1, LINC01747, CU634019.5,
## NUDT11, LINC00266-4P, PLA2G5, BDNF-AS, KCNA2, AC021546.1, LINC00407,
## AC246817.1, GNG7, DNAH3, GMDS, LINC02398, AL096794.1, AL390800.1, AC083836.1,
## NELL2, UFL1-AS1, PRH1, SUCLG2-AS1, ITGA9, GLUL, LINC01572, SPOCK3, POF1B, FAIM,
## SPATA5, TIMP4, CAMK2D, ELANE, PCNX2, ABCA1, TOM1L2, SLC41A2, HCRTR2, ST3GAL3,
## MCTP2, DUSP5, MARF1, COBL, PRDM1, CD200R1, AC092134.3, CPXM2, EDA, CASC2, PKP2,
## TTLL7, GPAT3, PLAA, PRAG1, DMXL2, AL009179.1, SH3GL2, AL158068.2, AC005736.1,
## CYP4F22, LINC01098, EFL1, RERE, CRELD2, ZNF609, STAU2, EMP1, AC024084.1, RHPN2,
## MPDZ, TYW1B, LINC02457, RAB7B.
## PC_ 1 
## Positive:  PRDX6, TUBA1B, C15orf48, FABP3, S100A10, TUBA1A, TXN, S100A9, CRABP2, CHI3L1 
##     SLC35F1, RGCC, ACTG1, ACAT2, MMP9, FBP1, TUBA1C, GAL, HPGDS, LDHB 
##     BLVRB, HAMP, MYL9, SPP1, UCHL1, CCNA1, TMEM176B, LINC02244, TMEM114, TMEM176A 
## Negative:  FHIT, RAD51B, FMN1, ARL15, MALAT1, FTX, AL035446.2, MBD5, EXOC4, SLC22A15 
##     ZFAND3, SNTB1, FNDC3B, GMDS-DT, COP1, VTI1A, PDE4D, JMJD1C, DENND1A, VPS13B 
##     TRIO, DOCK4, SBF2, SMYD3, FRMD4B, DOCK3, COG5, TBC1D8, REV3L, ZBTB20 
## PC_ 2 
## Positive:  HLA-DRB1, LYZ, PTGDS, CD74, HLA-DRA, HLA-DPA1, CFD, HLA-DPB1, KCNMA1, CEBPD 
##     RCBTB2, CYP1B1, GCLC, NCAPH, RNASE6, TGFBI, SIPA1L1, S100A4, CRIP1, HLA-DRB5 
##     MNDA, ATP8B4, ATG7, CA2, HLA-DQB1, ALOX5AP, MRC1, DUSP2, VAMP5, RAPGEF1 
## Negative:  HIV-Gagp17, HIV-Polp15p31, HIV-BaLEnv, HIV-Polprot, HIV-Vif, HIV-LTRU5, HIV-Gagp2p7, GDF15, PSAT1, CYSTM1 
##     HIV-Gagp1Pol, BEX2, HIV-EGFP, TCEA1, G0S2, HIV-TatEx2Rev, SNCA, PHGDH, HIV-Vpu, B4GALT5 
##     OCIAD2, SLAMF9, HIV-TatEx1, HIV-LTRR, SUPV3L1, UGCG, RAB38, GARS, S100A10, NMRK2 
## PC_ 3 
## Positive:  BTG1, MARCKS, CD14, G0S2, TGFBI, FUCA1, MS4A6A, CLEC4E, SEMA4A, CXCR4 
##     VMO1, TIMP1, MEF2C, HIF1A, CEBPD, MS4A7, MAFB, P2RY8, RNASE1, FPR3 
##     TCF4, MPEG1, PDK4, CTSC, CD163, HLA-DQA2, HIV-Gagp17, ST8SIA4, SDS, SELENOP 
## Negative:  RGCC, NCAPH, CRABP2, CHI3L1, TM4SF19, LINC01010, MREG, LINC02244, GPC4, AC015660.2 
##     TMEM114, FNIP2, NUMB, ACAT2, PSD3, TCTEX1D2, LRCH1, SLC28A3, PLEK, ST3GAL6 
##     AC005280.2, ANO5, DOCK3, FBP1, AC092353.2, CSF1, ASAP1, GCLC, FDX1, TXNRD1 
## PC_ 4 
## Positive:  HES2, CCPG1, LINC02244, NUPR1, CARD16, RAB6B, LINC01010, S100P, PSAT1, CPD 
##     PTGDS, CLGN, CLU, BEX2, NIBAN1, SYNGR1, PHGDH, TDRD3, PLEKHA5, QPCT 
##     NMB, RETREG1, PCDH19, C5orf17, GAS5, SUPV3L1, TCEA1, PDE4D, CLEC12A, SEL1L3 
## Negative:  AC078850.1, SLC35F1, INSIG1, TUBA1B, CCL7, ACTG1, LINC01091, CD36, FABP4, C3 
##     MGLL, TPM4, TIMP3, PHLDA1, CD300LB, CSF1, TMEM176A, CADM1, TUBB, ALCAM 
##     HSP90B1, IL1RN, TNFRSF9, LIMA1, TPM2, SDS, IL18BP, PLEK, IL4I1, MACC1 
## PC_ 5 
## Positive:  PCLAF, STMN1, TYMS, CTSL, CENPF, MKI67, CEP55, CDKN3, BIRC5, KIF4A 
##     DLGAP5, PTTG1, RAD51AP1, CENPM, TK1, PRC1, PLEKHA5, CDK1, HMMR, CENPK 
##     CLSPN, CCNA2, NUSAP1, SHCBP1, TPX2, ASPM, BUB1B, TUBB, MYBL2, NCAPG 
## Negative:  HIV-Vif, HIV-Gagp2p7, HIV-Polp15p31, HIV-Polprot, HIV-Gagp17, HIV-Gagp1Pol, HIV-BaLEnv, HIV-LTRU5, HIV-TatEx1, HIV-Vpu 
##     HIV-TatEx2Rev, HIV-LTRR, HIV-EGFP, HIV-Nef, HIV-EnvStart, HIV-Vpr, CHI3L1, HES1, GCLC, PLCL1 
##     SPRED1, IL1RN, HES4, ISG15, MX1, CDKN1A, DUSP2, ST6GALNAC3, ADK, MDM2
DimHeatmap(mono_focus_mdm, dims = 1:2, cells = 500, balanced = TRUE)

DimHeatmap(mono_focus_mdm, dims = 3:4, cells = 500, balanced = TRUE)

ElbowPlot(mono_focus_mdm)

mono_focus_mdm <- FindNeighbors(mono_focus_mdm, dims = 1:4)
## Computing nearest neighbor graph
## Computing SNN
mono_focus_mdm <- FindClusters(mono_focus_mdm, algorithm = 3, resolution = 0.3, verbose = FALSE)
mono_focus_mdm <- RunUMAP(mono_focus_mdm, dims = 1:4)
## 12:50:30 UMAP embedding parameters a = 0.9922 b = 1.112
## 12:50:30 Read 3869 rows and found 4 numeric columns
## 12:50:30 Using Annoy for neighbor search, n_neighbors = 30
## 12:50:30 Building Annoy index with metric = cosine, n_trees = 50
## 0%   10   20   30   40   50   60   70   80   90   100%
## [----|----|----|----|----|----|----|----|----|----|
## **************************************************|
## 12:50:30 Writing NN index file to temp file /tmp/RtmpRdHgON/file11d0d45223eefb
## 12:50:30 Searching Annoy index using 1 thread, search_k = 3000
## 12:50:31 Annoy recall = 100%
## 12:50:32 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30
## 12:50:34 Initializing from normalized Laplacian + noise (using RSpectra)
## 12:50:34 Commencing optimization for 500 epochs, with 135842 positive edges
## 12:50:34 Using rng type: pcg
## 12:50:37 Optimization finished
DimPlot(mono_focus_mdm, reduction = "umap", label=TRUE)

DimPlot(mono_focus_mdm, group.by="monaco_fine_annotation" , reduction = "umap", label=TRUE)

DimPlot(mono_focus_mdm, group.by="sample" , reduction = "umap", label=TRUE)

# mono_focus_alv
mono_focus_alv <- FindVariableFeatures(mono_focus_alv, selection.method = "vst", nfeatures = 2000)
## Finding variable features for layer counts
mono_focus_alv <- RunPCA(mono_focus_alv, features = VariableFeatures(object = mono_focus_alv))
## Warning: The following 35 features requested have zero variance; running
## reduction without them: MT1X, HAMP, APOA1, MT2A, INHBA, ID3, ISM1, ANKRD66,
## PKD1L1, AL591135.2, LINC00607, TXN, AC087857.1, CABCOCO1, LINGO1, PPP1R17,
## LINC02073, AC093916.1, SAMSN1, AC009292.2, IGSF23, LINC00639, PRKCG, KRTAP10-4,
## SIK3, CHD9, MED13L, AC104041.1, FAM13B, PLAT, AC016152.1, AC069410.1,
## AC130650.2, LINC01276, NME5
## Warning in PrepDR5(object = object, features = features, layer = layer, : The
## following features were not available: LINC00964, NUP210L, CPNE8, IFI6,
## AC083837.1, SMS, TMIGD1, HCAR2, AC011396.2, CD28, AP002075.1, SLC6A16, TEKT5,
## EMP3, MIF, AL096794.1, PPP1R1C, ACVR2A, LYPD1, EDIL3, AC022031.2, EFCAB7,
## LINC02068, IQCA1, SPINK6, TENM4, COL25A1, HIST1H2BG, C11orf49, SRL, AC092821.3,
## EXO1, IL6, DNAH12, DNAJC9, ACTN2, SLC7A14-AS1, AC135050.3, MRPS6, NPTX2,
## LINC02269, ERAP2, KIAA1755, GNLY, AC076968.2, AC026391.1, AC013391.2, INO80,
## ADAM22, LINC00589, DSG2, MS4A5, AC207130.1, PLAAT3, AC005740.5, BTNL8,
## AC084740.1, MSRB3, ARMC8, SMCHD1, CNTNAP2, BANK1, COL27A1, TEK, GCH1, SCFD1,
## CD226, GPRC5D, AHCTF1, PMAIP1, CTSW, DCSTAMP, TRIM2, TUBB4A, NWD1, LGALS1,
## GIGYF2, MARCKSL1, CH25H, BRMS1L, RAD51C, RFX3-AS1, AL353596.1, KIF6, SHCBP1L,
## LPCAT1, RLF, LINC00350, NEURL3, MIR4300HG, AC104596.1, IGF2R, LINC02789,
## AC019131.1, ADCY3, TMEM236, AL161646.1, CR1, SVEP1, USP10, ASAP3, PTPN2, ZC3H8,
## LINC01344, TNFAIP3, STK32B, YJEFN3, CTSZ, XDH, AC010834.2, CCDC85A, RFTN2,
## DYNC1H1, AC079313.2, MECP2, AC009435.1, LINC00299, SHANK2, AC005264.1,
## AC084809.2, SPOCK1, RPH3AL, ABCB1, LINC01862, SH3TC2, CCNC, NEK4, ZPLD1,
## LINC00511, NDRG1, SPACA3, URB1, PSME2, CFAP74, XPO5, CCDC57, PPEF1, CSTB,
## AC007785.1, HSF2BP, PTX3, MFSD11, POU6F2, SLC2A5, ABRAXAS2, AC063944.1, STS,
## FBXO4, NCMAP, PAX8-AS1, MBOAT4, ANGPT1, RXFP1, FCRLB, RAB7B, SMAD1-AS2,
## AL353595.1, AC125421.1, PHACTR1, LINC02466, SOX6, LDHA, AL672032.1, LINC00842,
## TEPP, EML2-AS1, ERI2, GAPLINC, GRID2, SYT12, TIMELESS, AKAP6, ANOS1, CKAP5,
## WDR90, GOLGA7B, HNRNPM, LGALS3, WIPF3, NRG1, MID2, AC007100.1, NBAT1, C2orf72,
## FSD1, GRHL2, GLIPR1, NRIP3, TMEM37, AC092957.1, SOAT2, HCAR3, LINC01414,
## AC011346.1, INKA2-AS1, FO393415.3, UPK1A-AS1, AC073569.2, AL513166.1, GTF2IRD2,
## IPCEF1, PMPCA, DHRS9, C22orf34, AC124852.1, RFX8, ELOC, PTPRB, HRH2, HMOX1,
## GATA2, SEMA6D, CLDN18, GNRHR, LMNB1-DT, COBL, SLC23A2, AC041005.1, ZNF385D-AS1,
## NNMT, AOC1, EAF2, AC107081.2, PDE1C, CLEC7A, SERINC2, CNR2, LCP1, IL17RB, RGS7,
## SPRY4-AS1, DACH1, AL592295.3, SVOP, STPG2, AL662884.3, AC022035.1, SLC44A5,
## AC006441.4, LINC00609, HLTF-AS1, KIAA0825, MOSPD1, SLC4A8, NDRG2, FAF1, PLCH1,
## RELN, LINC01299, MTFMT, SLC6A7, HIP1, WDFY4, KIF21A, NCR3, MAS1, LINC01999,
## AC007001.1, TNC, CLSTN2, PLXDC1, AC004949.1, CD5L, TNR, AL360015.1, LINGO2,
## TMEM132C, ZNF157, NEIL3, LINC01358, ADM, SFTPD-AS1, MIR3142HG, MRC2, MIR2052HG,
## HSPA1B, ULBP2, GLUL, AC068228.3, DZIP1, AC025430.1, TPSAB1, SLC12A3,
## AC092718.1, COL4A5, AC006460.1, VIPR1, SLC9A2, TDRD9, ABLIM1, ZSCAN5A, SIK2,
## SPSB1, YLPM1, SCIN, AC116563.1, NRCAM, CRIM1, BPIFC, SLA, GALNT14, MSH4, CRIPT,
## AL354811.2, UST, NIPAL4, CTXND1, ELOVL5, LINC00378, AL049828.1, KDR, CNGB1,
## Z99758.1, AC010997.3, AC109454.3, AL354733.2, NSG2, GPAT3, SHROOM4, RASSF4,
## FOXM1, LINC00571, TNIK, OASL, RBL1, POU2F2, EML4, IKZF3, CDHR3, CLPB,
## AL645933.3, PARD3, AL136456.1, PTP4A2, CSMD2, AHCYL2, NES, AC093898.1, MARCH1,
## ARHGAP6, SLC4A1, PAWR, AC110491.2, DPYS, PARN, ABCG2, CYP4F22, ITGA2,
## SH3TC2-DT, CHODL, GM2A, GINS2, CHDH, IGSF6, BRCA1, MEP1A, SRGAP3, AC084816.1,
## TROAP, LINC01900, APOM, COL8A2, RALGAPA2, AC005753.2, AC015908.2, STXBP5L,
## DNAJC1, FBXW7, AC099489.1, TMEM45A, FCMR, FRRS1, AC002454.1, ARL9, C1orf143,
## FAXC, ATP1B2, PDLIM4, AC016831.7, EMP1, RBPJ, ANKH, AC117453.1, CHAC1, KCP,
## SNAI3, FHAD1, DENND2A, TNFRSF12A, MX2, KDM7A, AC108066.1, SLC23A1, AL109930.1,
## SH3BP5, CENPU, KCNA2, AC011893.1, AIM2, TBC1D24, ATP1B1, AP000812.1, S100A6,
## JAML, MS4A4A, TGFB3, LINC00973, ING3, SOX5, MCAM, RBM47, AC246817.1, PCLO,
## PCDH15, TNFRSF11A, SNX10, ACTB, SCFD2, LINC02109, CHD5, AC093307.1, TSGA13,
## C11orf45, RHOD, AC007529.2, AC008443.9, AMPD1, CEP126, ITSN2, KCNJ1, CD1E,
## AL359220.1, RNF212, GNAI1, AC093010.2, TEX49, SPOPL, LINC02777, PRRX2,
## SEPTIN4-AS1, LIPG, HIST1H2AC, LINC02698, SDC2, CNTNAP5, SULT6B1, STXBP6,
## PPP1R16B, CFAP57, LINC01800, SLC22A2, EXOSC10, LINC02752, AC024901.1, ASPH,
## ZNF431, BICD1, DEGS2, GALNTL6, AC079742.1, MEI4, LINC01924, AMPD3, MB21D2,
## LINC01572, PLTP, ITPR2, SAMD12, EFNA2, HTRA4, XKR9, AL713998.1, AC016587.1,
## SLC35F3, EOGT, CDC5L, LINC00519, AC113137.1, ARSF, LIN28B-AS1, RASL10A, FCER1G,
## LINC00894, SYT10, RBPJL, AC007381.1, STMND1, AC006333.1, CNGA4, GLCCI1, TCEA3,
## LINC01739, AL355981.1, MOBP, AC079298.3, AC097487.1, AC137810.1, AL357146.1,
## TMEM213, AL136119.1, AC087897.2, AL160035.1, LINC01198, AC090515.6, AC018618.1,
## MAP1A, NR1H3, DNAH2, BX004807.1, NR6A1, IARS, TMEM131L, SYNE1, AL645465.1,
## BCL2A1, SH3PXD2B, AC099560.1, LPP, AL591845.1, HPN, KLB, SKA3, CPEB2-DT,
## INPP4B, ELF5, STUM, LMO4, NANOS1, ASTN2, STX4, LINC02805, GNGT1, HIST1H1C,
## AC010343.3, TYW1B, ACSBG2, TRMT5, LDLRAD4, SSH2, SLC25A23, LPAR1, AP001496.1,
## SERPINA1, HIST2H2BE, FCHO2, CDH12, AC011476.3, PAX5, GALNT18, FA2H, SDSL,
## ABCA1, CFI, LINC01948, IAPP, WASF3-AS1, AC130456.2, ROBO4, AC087280.2, IL3RA,
## DAO, AC073091.4, FUT2, GFOD1, AC055855.2, LINC02742, ZNF609, LINC01933, CORO1A,
## CLSTN3, LIMCH1, NABP1, FBXO43, DOCK2, ASMT, TREM1, CTNNA3, GRXCR2, AP000424.1,
## CNIH3, IGF1R, AC005280.1, PPP1R14C, GLT1D1, AC068587.4, AP001636.3, ERBB4,
## MIR155HG, ERLEC1, AGPAT4, GRAMD2A, ADGRL4, AC239860.4, LHCGR, AC103563.9,
## CCDC141, NECTIN3-AS1, AC010307.4, ZBED9, AC120498.4, OPRD1, SCG2, AC145146.1,
## AC068305.2, TMEM233, HECW1, NCAM2, SLAMF7, PRAG1, AL731563.2, FRMD6-AS2, GRIK5,
## AC021851.2, CDT1, WDR54, MYO16-AS1, LMCD1-AS1, AC096531.2, MAP1B, OR10G3,
## NUDT10, CIDEC, SSPO, FAM107B, RBM11, BARD1, EGFL7, MARCH3, SLC30A10, TFRC,
## PKIB, DENND5B, SPIRE1, AC079163.2, AHRR, ZNF543, QKI.
## PC_ 1 
## Positive:  RASAL2, DOCK3, AC092353.2, TMEM117, DPYD, CPEB2, LINC01374, LRMDA, ASAP1, PLXDC2 
##     NEAT1, FMNL2, TPRG1, LRCH1, ATG7, ARL15, MALAT1, MITF, ATXN1, MAML2 
##     RAPGEF1, DENND1B, NUMB, EXOC4, ELMO1, FHIT, ST3GAL6, VWA8, ZNF438, PPARG 
## Negative:  GAPDH, H2AFZ, BLVRB, GSTP1, NUPR1, MMP9, FABP4, SAT1, CARD16, ALDH2 
##     STMN1, CFD, CYSTM1, FAH, PRDX6, MARCKS, CD74, PSAT1, IFITM3, HLA-DPA1 
##     GDF15, PTGDS, PHGDH, SELENOP, LINC02244, BTG1, TUBA1B, TMEM176B, GCHFR, TUBB 
## PC_ 2 
## Positive:  LYZ, SLC8A1, MRC1, RCBTB2, FCGR3A, CTSC, NRP1, HLA-DPA1, CFD, AL356124.1 
##     TRPS1, ME1, RARRES1, HLA-DRA, ATP8B4, PDGFC, ARHGAP15, SELENOP, XYLT1, ZEB2 
##     FCHSD2, HLA-DPB1, SLCO2B1, DOCK4, AIF1, CD74, ALDH2, KCNMA1, CAMK1D, CCDC102B 
## Negative:  HIV-Nef, HIV-TatEx1, HIV-LTRU5, HIV-BaLEnv, HIV-LTRR, HIV-Polprot, HIV-Gagp17, HIV-Polp15p31, CCL22, HIV-EnvStart 
##     HIV-Vpr, HIV-Gagp1Pol, HIV-TatEx2Rev, IL6R-AS1, AL157912.1, GAL, HIV-Vif, HIV-Vpu, HIV-Gagp2p7, SLC20A1 
##     HIV-EGFP, DUSP13, IL1RN, TRIM54, CYTOR, MIR4435-2HG, MYL9, NMRK2, GPC3, RHOF 
## PC_ 3 
## Positive:  CTSL, BCAT1, FDX1, MARCO, S100A9, DNASE2B, CCDC26, B4GALT5, TPM4, SAT1 
##     CD164, FMN1, FAH, UGCG, TXNRD1, PLEKHA5, SCD, STMN1, HES2, FABP4 
##     BCL11A, BLVRB, SNCA, SEL1L2, FRMD4A, QPCT, NUPR1, SLC11A1, SNTB1, CLMP 
## Negative:  CRIP1, MMP7, CLU, GCLC, HIV-TatEx1, RNF128, HIV-Nef, PTGDS, HIV-LTRR, CDKN2A 
##     KCNMA1, RTN1, HIV-Vpr, DUSP2, LINC02345, C1QTNF4, HIV-Gagp1Pol, IL1RN, TMEM176B, TIMP3 
##     HIV-EnvStart, CYP1B1, S100A4, ALOX5AP, VAMP5, LINC02408, RAMP1, AC067751.1, FGL2, HIV-Polprot 
## PC_ 4 
## Positive:  NCAPH, LINC02244, AC015660.2, SYNGR1, RGS20, DUSP2, PTGDS, TMEM114, C2orf92, NIPAL2 
##     LINC01010, TRIM54, TM4SF19, MGST1, PSD3, SLC28A3, AC005280.2, ACAT2, SERTAD2, MICAL3 
##     MT1E, ANO5, ZNF366, BX664727.3, RGS16, TGM2, OCSTAMP, TDRD3, AL157886.1, SPP1 
## Negative:  HIV-TatEx1, HIV-LTRR, HIV-Vpr, HIV-Nef, HIV-Polprot, HIV-Gagp1Pol, HIV-EnvStart, HIV-BaLEnv, HIV-Vif, HIV-Polp15p31 
##     HIV-Gagp17, HIV-LTRU5, HIV-Vpu, HIV-Gagp2p7, HIV-TatEx2Rev, AIF1, HIV-EGFP, FPR3, CTSB, MARCKS 
##     MRC1, C1QA, CTSC, IL7R, CCL2, LGMN, OLR1, ALOX5, TNFSF13B, COLEC12 
## PC_ 5 
## Positive:  CLSPN, SHCBP1, TYMS, DIAPH3, TK1, PCLAF, RRM2, HELLS, FAM111B, ESCO2 
##     CENPK, MYBL2, MKI67, CENPM, CIT, CDK1, ACTG1, NCAPG, CCNA2, ATAD2 
##     TOP2A, TUBB, KIF11, CEP55, HMMR, DTL, KNL1, TUBA1B, BIRC5, CENPF 
## Negative:  AC008591.1, XIST, QPCT, AC020656.1, GCHFR, GPX3, AC012668.3, LINC01340, MIR646HG, ST6GAL1 
##     LINC01708, LINC02320, AL136317.2, NMB, OSBP2, KCNMB2-AS1, LIX1-AS1, SKAP1, CFD, NIPAL2 
##     CCDC26, PDE4D, LINC00923, TMTC1, CPD, BX664727.3, GPRIN3, AP000331.1, RARRES1, GPAT2
DimHeatmap(mono_focus_alv, dims = 1:2, cells = 500, balanced = TRUE)

DimHeatmap(mono_focus_alv, dims = 3:4, cells = 500, balanced = TRUE)

ElbowPlot(mono_focus_alv)

mono_focus_alv <- FindNeighbors(mono_focus_alv, dims = 1:4)
## Computing nearest neighbor graph
## Computing SNN
mono_focus_alv <- FindClusters(mono_focus_alv, algorithm = 3, resolution = 0.3, verbose = FALSE)
mono_focus_alv <- RunUMAP(mono_focus_alv, dims = 1:4)
## 12:50:45 UMAP embedding parameters a = 0.9922 b = 1.112
## 12:50:45 Read 4420 rows and found 4 numeric columns
## 12:50:45 Using Annoy for neighbor search, n_neighbors = 30
## 12:50:45 Building Annoy index with metric = cosine, n_trees = 50
## 0%   10   20   30   40   50   60   70   80   90   100%
## [----|----|----|----|----|----|----|----|----|----|
## **************************************************|
## 12:50:45 Writing NN index file to temp file /tmp/RtmpRdHgON/file11d0d46b050f80
## 12:50:45 Searching Annoy index using 1 thread, search_k = 3000
## 12:50:46 Annoy recall = 100%
## 12:50:47 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30
## 12:50:49 Initializing from normalized Laplacian + noise (using RSpectra)
## 12:50:49 Commencing optimization for 500 epochs, with 154158 positive edges
## 12:50:49 Using rng type: pcg
## 12:50:52 Optimization finished
DimPlot(mono_focus_alv, reduction = "umap", label=TRUE)

DimPlot(mono_focus_alv, group.by="monaco_fine_annotation" , reduction = "umap", label=TRUE)

DimPlot(mono_focus_alv, group.by="sample" , reduction = "umap", label=TRUE)

Differential expression

We are going to use muscat for pseudobulk analysis. First need to convert seurat obj to singlecellexperiment object. Then summarise counts to pseudobulk level.

sce <- Seurat::as.SingleCellExperiment(comb, assay = "RNA")
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
## Found more than one class "package_version" in cache; using the first, from namespace 'SeuratObject'
## Also defined by 'alabaster.base'
head(colData(sce),2)
## DataFrame with 2 rows and 13 columns
##                            orig.ident nCount_RNA nFeature_RNA
##                              <factor>  <numeric>    <integer>
## mdm_mock1|AAACGAATCACATACG        mac      72761         7103
## mdm_mock1|AAACGCTCATCAGCGC        mac      49143         6282
##                                              cell      sample RNA_snn_res.0.5
##                                       <character> <character>        <factor>
## mdm_mock1|AAACGAATCACATACG mdm_mock1|AAACGAATCA..   mdm_mock1              5 
## mdm_mock1|AAACGCTCATCAGCGC mdm_mock1|AAACGCTCAT..   mdm_mock1              12
##                            seurat_clusters           cell_barcode
##                                   <factor>            <character>
## mdm_mock1|AAACGAATCACATACG              5  mdm_mock1|AAACGAATCA..
## mdm_mock1|AAACGCTCATCAGCGC              12 mdm_mock1|AAACGCTCAT..
##                            monaco_broad_annotation monaco_broad_pruned_labels
##                                        <character>                <character>
## mdm_mock1|AAACGAATCACATACG               Monocytes                  Monocytes
## mdm_mock1|AAACGCTCATCAGCGC               Monocytes                  Monocytes
##                            monaco_fine_annotation monaco_fine_pruned_labels
##                                       <character>               <character>
## mdm_mock1|AAACGAATCACATACG    Classical monocytes       Classical monocytes
## mdm_mock1|AAACGCTCATCAGCGC    Classical monocytes       Classical monocytes
##                               ident
##                            <factor>
## mdm_mock1|AAACGAATCACATACG       5 
## mdm_mock1|AAACGCTCATCAGCGC       12
colnames(colData(sce))
##  [1] "orig.ident"                 "nCount_RNA"                
##  [3] "nFeature_RNA"               "cell"                      
##  [5] "sample"                     "RNA_snn_res.0.5"           
##  [7] "seurat_clusters"            "cell_barcode"              
##  [9] "monaco_broad_annotation"    "monaco_broad_pruned_labels"
## [11] "monaco_fine_annotation"     "monaco_fine_pruned_labels" 
## [13] "ident"
#muscat library
pb <- aggregateData(sce,
    assay = "counts", fun = "sum",
    by = c("monaco_broad_annotation", "sample"))

# one sheet per subpopulation
assayNames(pb)
## [1] "Basophils"       "Dendritic cells" "Monocytes"
t(head(assay(pb)))
##                HIV-LTRR HIV-LTRU5 HIV-Gagp17 HIV-Gagp24 HIV-Gagp2p7
## alv_active1           0         0          0          0           0
## alv_active2           0         0          0          0           0
## alv_active3           0         0          0          0           0
## alv_bystander1        0         0          0          0           0
## alv_bystander2        0         0          0          0           0
## alv_bystander3        0         0          0          0           0
## alv_latent1           0         0          0          0           0
## alv_latent2           0         0          0          0           0
## alv_latent3           0         0          0          0           0
## alv_mock1             0         0          0          0           0
## alv_mock2             0         0          0          0           0
## alv_mock3             0         0          0          0           0
## mdm_active1           0         0          0          0           0
## mdm_active2           0         0          0          0           0
## mdm_active3           0         0          0          0           0
## mdm_active4           0         0          0          0           0
## mdm_bystander1        0         0          0          0           0
## mdm_bystander2        0         0          0          0           0
## mdm_bystander3        0         0          0          0           0
## mdm_bystander4        0         0          0          0           0
## mdm_latent1           0         0          0          0           0
## mdm_latent2           0         0          0          0           0
## mdm_latent3           0         0          0          0           0
## mdm_latent4           0         0          0          0           0
## mdm_mock1             0         0          0          0           0
## mdm_mock2             0         0          0          0           0
## mdm_mock3             0         0          0          0           0
## mdm_mock4             0         0          0          0           0
## react6                0         0          0          0           0
##                HIV-Gagp1Pol
## alv_active1               0
## alv_active2               0
## alv_active3               0
## alv_bystander1            0
## alv_bystander2            0
## alv_bystander3            0
## alv_latent1               0
## alv_latent2               0
## alv_latent3               0
## alv_mock1                 0
## alv_mock2                 0
## alv_mock3                 0
## mdm_active1               0
## mdm_active2               0
## mdm_active3               0
## mdm_active4               0
## mdm_bystander1            0
## mdm_bystander2            0
## mdm_bystander3            0
## mdm_bystander4            0
## mdm_latent1               0
## mdm_latent2               0
## mdm_latent3               0
## mdm_latent4               0
## mdm_mock1                 0
## mdm_mock2                 0
## mdm_mock3                 0
## mdm_mock4                 0
## react6                    0
plotMDS(assays(pb)[[3]], main="Monocytes" )

par(mfrow=c(2,3))

dump <- lapply(1:length(assays(pb)) , function(i) {
  cellname=names(assays(pb))[i]
  plotMDS(assays(pb)[[i]],cex=1,pch=19,main=paste(cellname),labels=colnames(assays(pb)[[1]]))
})
## Warning in plotMDS.default(assays(pb)[[i]], cex = 1, pch = 19, main =
## paste(cellname), : dimension 2 is degenerate or all zero
par(mfrow=c(1,1))

DE Prep

pbmono <- assays(pb)[["Monocytes"]]

head(pbmono)
##              alv_active1 alv_active2 alv_active3 alv_bystander1 alv_bystander2
## HIV-LTRR            4391        3316        2601            111            134
## HIV-LTRU5         162741      127498      102452           2085           2885
## HIV-Gagp17         32789       27176       17079            106            162
## HIV-Gagp24             0           0           0              0              0
## HIV-Gagp2p7         1201        1242         744             16             26
## HIV-Gagp1Pol        2100        2334        1592             26             50
##              alv_bystander3 alv_latent1 alv_latent2 alv_latent3 alv_mock1
## HIV-LTRR                138         249         261         411        31
## HIV-LTRU5              2848       10994       10224       17207       753
## HIV-Gagp17              183        2306        1784        2576       106
## HIV-Gagp24                0           0           0           0         0
## HIV-Gagp2p7              17          69         104         121         2
## HIV-Gagp1Pol             42         129         163         210         6
##              alv_mock2 alv_mock3 mdm_active1 mdm_active2 mdm_active3
## HIV-LTRR            52       200        2251        1482        1476
## HIV-LTRU5         1311      7206      100998       71868       94108
## HIV-Gagp17         178      1530       38092       23541       40568
## HIV-Gagp24           0         0           0           0           0
## HIV-Gagp2p7          7        52        1462        1021        2365
## HIV-Gagp1Pol        21        94        2021        1375        3032
##              mdm_active4 mdm_bystander1 mdm_bystander2 mdm_bystander3
## HIV-LTRR            1648            103            147             26
## HIV-LTRU5          56478           1425           1946            449
## HIV-Gagp17         15110            255            254             57
## HIV-Gagp24             0              0              0              0
## HIV-Gagp2p7          414             23             32              3
## HIV-Gagp1Pol         785             20             61             16
##              mdm_bystander4 mdm_latent1 mdm_latent2 mdm_latent3 mdm_latent4
## HIV-LTRR                 41         119         142          37          48
## HIV-LTRU5               725        5359        6710        2150        1644
## HIV-Gagp17               61        1927        2077         566         534
## HIV-Gagp24                0           0           0           0           0
## HIV-Gagp2p7               8          51         108          37          12
## HIV-Gagp1Pol             10          83         129          63          24
##              mdm_mock1 mdm_mock2 mdm_mock3 mdm_mock4 react6
## HIV-LTRR            30        37         9        39    256
## HIV-LTRU5          486       685       106      1119   7461
## HIV-Gagp17         117       253        37       159    596
## HIV-Gagp24           0         0         0         0      0
## HIV-Gagp2p7          5         8         1         5     21
## HIV-Gagp1Pol         7        14         3        13     39
dim(pbmono)
## [1] 36622    29
hiv <- pbmono[1:2,]
pbmono <- pbmono[3:nrow(pbmono),]

Gene sets

Gene ontology.

#go <- gmt_import("c5.go.v2023.2.Hs.symbols.gmt")
#names(go) <- gsub("_"," ",names(go))

#wget https://ziemann-lab.net/public/tmp/go_2024-11.gmt
go <- gmt_import("go_2024-11.gmt")

DE1 Latently- vs productively-infected cells (groups 3 vs 4).

MDM group.

pbmdm <- pbmono[,grep("mdm",colnames(pbmono))]

pb1m <- pbmdm[,c(grep("active",colnames(pbmdm)),grep("latent",colnames(pbmdm)))]

head(pb1m)
##               mdm_active1 mdm_active2 mdm_active3 mdm_active4 mdm_latent1
## HIV-Gagp17          38092       23541       40568       15110        1927
## HIV-Gagp24              0           0           0           0           0
## HIV-Gagp2p7          1462        1021        2365         414          51
## HIV-Gagp1Pol         2021        1375        3032         785          83
## HIV-Polprot         27388       18583       44857        9126        1383
## HIV-Polp15p31       75686       55267      105649       14984        3589
##               mdm_latent2 mdm_latent3 mdm_latent4
## HIV-Gagp17           2077         566         534
## HIV-Gagp24              0           0           0
## HIV-Gagp2p7           108          37          12
## HIV-Gagp1Pol          129          63          24
## HIV-Polprot          1587         877         250
## HIV-Polp15p31        5077        2425         441
pb1mf <- pb1m[which(rowMeans(pb1m)>=10),]
head(pb1mf)
##               mdm_active1 mdm_active2 mdm_active3 mdm_active4 mdm_latent1
## HIV-Gagp17          38092       23541       40568       15110        1927
## HIV-Gagp2p7          1462        1021        2365         414          51
## HIV-Gagp1Pol         2021        1375        3032         785          83
## HIV-Polprot         27388       18583       44857        9126        1383
## HIV-Polp15p31       75686       55267      105649       14984        3589
## HIV-Vif              5276        4254        7255        1109         221
##               mdm_latent2 mdm_latent3 mdm_latent4
## HIV-Gagp17           2077         566         534
## HIV-Gagp2p7           108          37          12
## HIV-Gagp1Pol          129          63          24
## HIV-Polprot          1587         877         250
## HIV-Polp15p31        5077        2425         441
## HIV-Vif               317         146          25
colSums(pb1mf)
## mdm_active1 mdm_active2 mdm_active3 mdm_active4 mdm_latent1 mdm_latent2 
##    29512873    22423101    25226765    13842115     2508756     3993617 
## mdm_latent3 mdm_latent4 
##     2428015      582852
des1m <- as.data.frame(grepl("active",colnames(pb1mf)))
colnames(des1m) <- "case"

plot(cmdscale(dist(t(pb1mf))), xlab="Coordinate 1", ylab="Coordinate 2",
  type = "p",pch=19,col="gray",cex=2)

text(cmdscale(dist(t(pb1mf))), labels=colnames(pb1mf) )

des1m$sample <- rep(1:4,2)

dds <- DESeqDataSetFromMatrix(countData = pb1mf , colData = des1m, design = ~ sample + case)
## converting counts to integer mode
##   the design formula contains one or more numeric variables with integer values,
##   specifying a model with increasing fold change for higher values.
##   did you mean for this to be a factor? if so, first convert
##   this variable to a factor using the factor() function
res <- DESeq(dds)
## estimating size factors
## estimating dispersions
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## fitting model and testing
z <- results(res)
vsd <- vst(dds, blind=FALSE)
zz <- cbind(as.data.frame(z),assay(vsd))
de <- as.data.frame(zz[order(zz$pvalue),])
de1mf <- de
write.table(de1mf,"de1mf.tsv",sep="\t")

nrow(subset(de1mf,padj<0.05 & log2FoldChange>0))
## [1] 102
nrow(subset(de1mf,padj<0.05 & log2FoldChange<0))
## [1] 246
head(subset(de1mf,padj<0.05 & log2FoldChange>0),10)[,1:6] %>%
  kbl(caption="Top upregulated genes in active MDM cells") %>%
  kable_paper("hover", full_width = F)
Top upregulated genes in active MDM cells
baseMean log2FoldChange lfcSE stat pvalue padj
HIV-EnvStart 106.40798 1.508999 0.2336803 6.457538 0.0e+00 0.0000002
HIV-TatEx2Rev 171.30897 1.228427 0.2010876 6.108913 0.0e+00 0.0000011
HIV-EGFP 179.06534 1.505331 0.2723122 5.527959 0.0e+00 0.0000230
HIV-BaLEnv 8035.68066 1.270031 0.2309893 5.498224 0.0e+00 0.0000257
HIV-Vpr 76.19161 1.396513 0.2655816 5.258322 1.0e-07 0.0000700
HPGD 609.85581 1.051743 0.2092152 5.027088 5.0e-07 0.0001900
TNFRSF9 79.53884 2.223553 0.4425434 5.024485 5.0e-07 0.0001900
HIV-Vpu 133.16300 1.275730 0.2571406 4.961216 7.0e-07 0.0002343
HIV-Vif 834.80391 1.603745 0.3339763 4.801974 1.6e-06 0.0004205
HIV-Gagp1Pol 362.34737 1.368681 0.2964683 4.616618 3.9e-06 0.0008541 
head(subset(de1mf,padj<0.05 & log2FoldChange<0),10)[,1:6] %>%
  kbl(caption="Top downregulated genes in active MDM cells") %>%
  kable_paper("hover", full_width = F)
Top downregulated genes in active MDM cells
baseMean log2FoldChange lfcSE stat pvalue padj
PDE4B 111.80062 -3.307095 0.3853403 -8.582270 0 0.0e+00
STAB1 58.70194 -5.220943 0.6780455 -7.699988 0 0.0e+00
VAMP5 158.27240 -1.835932 0.2578050 -7.121397 0 0.0e+00
FCN1 82.63210 -3.108742 0.4481621 -6.936648 0 0.0e+00
VCAN 16.54526 -4.682256 0.7056837 -6.635063 0 1.0e-07
PDE7B 32.06724 -3.887577 0.6089721 -6.383836 0 3.0e-07
SESN3 60.20373 -2.125609 0.3342092 -6.360116 0 3.0e-07
MS4A6A 293.46672 -3.015229 0.4809701 -6.269057 0 5.0e-07
FGL2 72.58902 -3.292405 0.5370701 -6.130308 0 1.1e-06
SSBP2 60.95534 -3.024786 0.4988879 -6.063057 0 1.3e-06 
m1m <- mitch_import(de,DEtype="deseq2",joinType="full")
## The input is a single dataframe; one contrast only. Converting
##         it to a list for you.
## Note: Mean no. genes in input = 13336
## Note: no. genes in output = 13336
## Note: estimated proportion of input genes in output = 1
mres1m <- mitch_calc(m1m,genesets=go,minsetsize=5,cores=4,priority="effect")
## Note: Enrichments with large effect sizes may not be
##             statistically significant.
res <- mres1m$enrichment_result
mitchtbl <- mres1m$enrichment_result
goid <- sapply(strsplit(mitchtbl$set," "),"[[",1)
mysplit <- strsplit(mitchtbl$set," ")
mysplit <- lapply(mysplit, function(x) { x[2:length(x)] } )
godescription <- unlist(lapply(mysplit, function(x) { paste(x,collapse=" ") } ))
em <- data.frame(goid,godescription,mitchtbl$pANOVA,mitchtbl$p.adjustANOVA,sign(mitchtbl$s.dist),mitchtbl$s.dist)
colnames(em) <- c("GO.ID","Description","p.Val","FDR","Phenotype","ES")
write.table(em,"de1mf_em.tsv",row.names = FALSE, quote=FALSE,sep="\t")

res <- subset(res,p.adjustANOVA<0.05)
resup <- subset(res,s.dist>0)
resdn <- subset(res,s.dist<0)
s <- c(head(resup$s.dist,10), head(resdn$s.dist,10))
names(s) <- c(head(resup$set,10),head(resdn$set,10))
s <- s[order(s)]
cols <- gsub("1","red",gsub("-1","blue",as.character(sign(s))))
par(mar=c(5,27,3,1))
barplot(abs(s),las=1,horiz=TRUE,col=cols,xlab="ES",cex.names=0.8,main="")

if (! file.exists("MDM_latent_vs_active.html") ) {
  mitch_report(mres1m,outfile="MDM_latent_vs_active.html")
}
networkplot(mres1m,FDR=0.05,n_sets=20)

network_genes(mres1m,FDR=0.05,n_sets=20)
## [[1]]
## [[1]]$`UP genesets.GO:0000221 vacuolar proton-transporting V-type ATPase, V1 domain`
## [1] "ATP6V1F"  "ATP6V1D"  "ATP6V1G1"
## 
## [[1]]$`UP genesets.GO:0005744 TIM23 mitochondrial import inner membrane translocase complex`
## [1] "TIMM44" "GRPEL1"
## 
## [[1]]$`UP genesets.GO:0005761 mitochondrial ribosome`
## [1] "MRPL18" "MRPL40" "MRPL34" "MRPL43"
## 
## [[1]]$`UP genesets.GO:0005762 mitochondrial large ribosomal subunit`
## [1] "MRPL18" "MRPL40" "MRPL15" "MRPL47" "MRPL54" "MRPL34" "MRPL43" "MRPL22"
## 
## [[1]]$`UP genesets.GO:0005763 mitochondrial small ribosomal subunit`
## [1] "MRPS16"   "CHCHD1"   "MRPS10"   "AURKAIP1" "MRPS15"   "MRPS24"  
## 
## [[1]]$`UP genesets.GO:0005839 proteasome core complex`
## [1] "PSMA7" "PSMB1" "PSMA3" "PSMA6" "PSMA4" "PSMB6" "PSMA2"
## 
## [[1]]$`UP genesets.GO:0005885 Arp2/3 protein complex`
## [1] "ARPC1B" "ARPC5L" "ARPC2"  "ACTR3"  "ARPC5"  "ARPC3"  "ARPC1A"
## 
## [[1]]$`UP genesets.GO:0008540 proteasome regulatory particle, base subcomplex`
## [1] "PSMC2" "PSMC3"
## 
## [[1]]$`UP genesets.GO:0008541 proteasome regulatory particle, lid subcomplex`
## [1] "PSMD8" "SEM1" 
## 
## [[1]]$`UP genesets.GO:0010756 positive regulation of plasminogen activation`
## [1] "ENO1"    "S100A10"
## 
## [[1]]$`UP genesets.GO:0015078 proton transmembrane transporter activity`
## [1] "ATP6V1F" "UCP2"    "SLC25A4"
## 
## [[1]]$`UP genesets.GO:0019773 proteasome core complex, alpha-subunit complex`
## [1] "PSMA7" "PSMA3" "PSMA6" "PSMA4" "PSMA2"
## 
## [[1]]$`UP genesets.GO:0022624 proteasome accessory complex`
## [1] "PSMD8" "PSMC2" "PSMC3"
## 
## [[1]]$`UP genesets.GO:0030150 protein import into mitochondrial matrix`
## [1] "TIMM44" "GRPEL1"
## 
## [[1]]$`UP genesets.GO:0030836 positive regulation of actin filament depolymerization`
## [1] "WDR1" "PLEK"
## 
## [[1]]$`UP genesets.GO:0032543 mitochondrial translation`
##  [1] "MRPS16"   "MRPL18"   "MRPL40"   "CHCHD1"   "MRPS10"   "AURKAIP1"
##  [7] "MRPS15"   "MRPL15"   "MRPL47"   "MRPL54"   "MRPL34"   "MRPL43"  
## [13] "MRPS24"   "MRPL22"  
## 
## [[1]]$`UP genesets.GO:0034709 methylosome`
## character(0)
## 
## [[1]]$`UP genesets.GO:0044305 calyx of Held`
## [1] "ACTG1" "CALM3" "CALM1"
## 
## [[1]]$`UP genesets.GO:0046961 proton-transporting ATPase activity, rotational mechanism`
## [1] "ATP6V1F"  "ATP6V0D2" "ATP6V1D"  "ATP6V1G1" "ATP5F1B" 
## 
## [[1]]$`UP genesets.GO:0097250 mitochondrial respirasome assembly`
## [1] "RAB5IF"
## 
## [[1]]$`DOWN genesets.GO:0002503 peptide antigen assembly with MHC class II protein complex`
##  [1] "HLA-DOA"  "HLA-DPA1" "HLA-DPB1" "HLA-DRA"  "HLA-DMA"  "HLA-DRB1"
##  [7] "HLA-DQA1" "HLA-DMB"  "HLA-DQB1" "HLA-DQA2" "HLA-DRB5" "B2M"     
## 
## [[1]]$`DOWN genesets.GO:0005942 phosphatidylinositol 3-kinase complex`
## [1] "PIK3R1" "PIK3R5" "PIK3CD" "PIK3R6" "PIK3CB" "PIK3CA"
## 
## [[1]]$`DOWN genesets.GO:0006198 cAMP catabolic process`
## [1] "PDE4B" "PDE7B" "PDE7A" "PDE8B" "PDE4A" "PDE4D" "PDE8A"
## 
## [[1]]$`DOWN genesets.GO:0016303 1-phosphatidylinositol-3-kinase activity`
## [1] "ATM"     "PIK3CG"  "PIK3CD"  "PIK3CB"  "PIK3CA"  "PIK3C3"  "PIK3C2B"
## [8] "PIK3C2A" "PIK3R3" 
## 
## [[1]]$`DOWN genesets.GO:0019886 antigen processing and presentation of exogenous peptide antigen via MHC class II`
##  [1] "HLA-DOA"  "HLA-DPA1" "HLA-DPB1" "HLA-DRA"  "HLA-DMA"  "CD74"    
##  [7] "HLA-DRB1" "HLA-DQA1" "HLA-DMB"  "CTSF"     "CTSS"     "PIKFYVE" 
## [13] "HLA-DQB1" "FCER1G"   "HLA-DQA2" "CTSL"     "HLA-DRB5" "FCGR2B"  
## [19] "DNM2"     "TRAF6"    "IFI30"    "CTSD"     "CTSV"     "B2M"     
## [25] "UNC93B1"  "LGMN"    
## 
## [[1]]$`DOWN genesets.GO:0030658 transport vesicle membrane`
##  [1] "HLA-DPA1"  "HLA-DPB1"  "HLA-DRA"   "CD74"      "ITPR2"     "HLA-DRB1" 
##  [7] "SORL1"     "RPH3AL"    "HLA-DQA1"  "CPE"       "HLA-DQB1"  "HLA-DQA2" 
## [13] "RAB11FIP5" "RAB1A"     "SNTB2"     "SLC17A9"   "HLA-DRB5"  "SYTL4"    
## [19] "ITPR1"     "PAM"       "TMEM30A"   "VAMP7"     "SPRED2"    "ARFGEF3"  
## 
## [[1]]$`DOWN genesets.GO:0031123 RNA 3'-end processing`
## [1] "TUT7"   "PAPOLG" "TENT2"  "CSTF3"  "TUT1"   "TUT4"   "TENT4B" "TENT4A"
## [9] "MTPAP" 
## 
## [[1]]$`DOWN genesets.GO:0032395 MHC class II receptor activity`
## [1] "HLA-DOA"  "HLA-DPA1" "HLA-DRA"  "HLA-DRB1" "HLA-DQA1" "HLA-DQB1" "HLA-DQA2"
## 
## [[1]]$`DOWN genesets.GO:0032454 histone H3K9 demethylase activity`
##  [1] "KDM3A"  "PHF2"   "KDM7A"  "JMJD1C" "PHF8"   "KDM4B"  "KDM3B"  "KDM1A" 
##  [9] "KDM4A"  "KDM4C"  "KDM4D" 
## 
## [[1]]$`DOWN genesets.GO:0038187 pattern recognition receptor activity`
##  [1] "FCN1"    "TLR8"    "TLR2"    "NLRP1"   "COLEC12" "ASGR1"   "TLR5"   
##  [8] "NOD1"    "CLEC7A"  "IFIH1"   "MARCO"   "CLEC4E"  "CLEC4A"  "CARD8"  
## [15] "PYCARD"  "TRIM5"   "DHX16"   "CLEC12A"
## 
## [[1]]$`DOWN genesets.GO:0042605 peptide antigen binding`
##  [1] "HLA-DOA"  "HLA-DPA1" "HLA-DPB1" "HLA-DRA"  "HLA-DMA"  "HLA-DRB1"
##  [7] "HLA-DQA1" "HLA-DMB"  "HFE"      "HLA-E"    "HLA-DQB1" "SLC7A8"  
## [13] "FCGRT"    "HLA-DQA2" "HLA-B"    "HLA-DRB5" "SLC7A5"   "TAPBP"   
## [19] "HLA-C"    "MAML1"    "TAP1"     "TAP2"     "HLA-A"    "HLA-F"   
## [25] "HLA-G"    "B2M"     
## 
## [[1]]$`DOWN genesets.GO:0042613 MHC class II protein complex`
##  [1] "HLA-DOA"  "HLA-DPA1" "HLA-DPB1" "HLA-DRA"  "HLA-DMA"  "CD74"    
##  [7] "HLA-DRB1" "HLA-DQA1" "HLA-DMB"  "HLA-DQB1" "HLA-DQA2" "HLA-DRB5"
## [13] "B2M"     
## 
## [[1]]$`DOWN genesets.GO:0044849 estrous cycle`
##  [1] "IGF1R"   "MDK"     "NCOA1"   "EGR1"    "OPRL1"   "CYP1B1"  "NCOR2"  
##  [8] "ADNP"    "PCNA"    "SLC26A6"
## 
## [[1]]$`DOWN genesets.GO:0046847 filopodium assembly`
##  [1] "FGD4"    "SRGAP2"  "SPATA13" "TGFBR1"  "FGD3"    "S1PR2"   "FMNL3"  
##  [8] "DNM3"    "SH3BP1"  "CD2AP"   "FGD5"    "EZR"     "CDC42"   "ITGB4"  
## [15] "SRF"     "PPP1R9B" "FGD2"    "FGD6"   
## 
## [[1]]$`DOWN genesets.GO:0046849 bone remodeling`
## [1] "MITF"   "RASSF2" "NOTCH2" "DOCK5"  "LGR4"   "LTBP3"  "LRP5"  
## 
## [[1]]$`DOWN genesets.GO:0046934 1-phosphatidylinositol-4,5-bisphosphate 3-kinase activity`
## [1] "PIK3CG"  "PIK3CD"  "PIK3R6"  "PIK3CB"  "PIK3CA"  "IPMK"    "PIK3C2A"
## 
## [[1]]$`DOWN genesets.GO:0048015 phosphatidylinositol-mediated signaling`
##  [1] "PLCL2"   "PIK3CG"  "PIK3CD"  "PIK3CB"  "PIK3CA"  "PLCG2"   "PLCB1"  
##  [8] "PIK3C3"  "RPS6KB1" "PLCG1"   "FGFR1"   "PIK3C2B" "PIK3C2A" "PI4KA"  
## [15] "PLCB2"   "PI4KB"   "PLCL1"   "PLCB3"   "INPP5F" 
## 
## [[1]]$`DOWN genesets.GO:0050778 positive regulation of immune response`
##  [1] "HLA-DOA"  "HLA-DPA1" "HLA-DPB1" "HLA-DRA"  "HLA-DMA"  "HLA-DRB1"
##  [7] "HLA-DQA1" "HLA-DMB"  "IL15"     "HLA-DQB1" "RSAD2"    "HLA-DQA2"
## [13] "HLA-DRB5" "B2M"      "C9"      
## 
## [[1]]$`DOWN genesets.GO:0051056 regulation of small GTPase mediated signal transduction`
##  [1] "SIPA1L1"   "FGD4"      "GNA13"     "VAV2"      "VAV1"      "ARHGAP45" 
##  [7] "VAV3"      "RHOD"      "GARNL3"    "STARD13"   "ITSN1"     "ARHGAP15" 
## [13] "FAM13A"    "SRGAP2"    "ARHGAP31"  "ECT2"      "ARHGAP26"  "RAP1GAP2" 
## [19] "SRGAP3"    "ARHGEF3"   "SPATA13"   "FGD3"      "RHOU"      "ARHGAP6"  
## [25] "SIPA1L3"   "ARHGEF10L" "MYO9B"     "ARHGAP19"  "RALGAPA1"  "ARHGAP30" 
## [31] "ARHGEF40"  "FAM13B"    "SH3BP1"    "DEF6"      "FGD5"      "ARHGAP8"  
## [37] "ARHGAP20"  "SYDE2"     "ARHGAP21"  "ARHGEF1"   "DOCK8"     "RACGAP1"  
## [43] "AKAP13"    "DOCK2"     "OBSCN"     "ARHGAP11A" "ARHGEF5"   "NET1"     
## [49] "KALRN"     "MYO9A"     "GMIP"      "SIPA1"     "CHN2"      "BCR"      
## [55] "ARHGAP11B" "ARHGAP4"   "CHN1"      "RALBP1"    "ARHGEF2"   "ARHGAP1"  
## [61] "ARHGAP22"  "ARHGAP5"   "TRIO"      "PREX1"     "ABR"       "ARHGAP32" 
## [67] "DLC1"      "TAGAP"     "ARHGEF28"  "ARHGEF9"   "DOCK3"     "ARHGAP27" 
## [73] "ARHGEF12"  "ARHGAP35"  "ARHGEF10"  "FGD2"      "ARHGAP9"   "DNMBP"    
## [79] "RALGAPA2"  "SIPA1L2"   "SWAP70"    "TSC2"      "ARHGAP10"  "ARHGAP18" 
## [85] "ARAP1"     "ARHGEF11"  "TIAM1"     "RALGAPB"   "TIAM2"    
## 
## [[1]]$`DOWN genesets.GO:0061470 T follicular helper cell differentiation`
## [1] "FOXP1"  "PIK3R1" "GPR183" "RC3H1"  "TBK1"   "RC3H2"  "ICOSLG"

Alv cells.

pbalv <- pbmono[,grep("alv",colnames(pbmono))]

pb1a <- pbalv[,c(grep("active",colnames(pbalv)),grep("latent",colnames(pbalv)))]
head(pb1a)
##               alv_active1 alv_active2 alv_active3 alv_latent1 alv_latent2
## HIV-Gagp17          32789       27176       17079        2306        1784
## HIV-Gagp24              0           0           0           0           0
## HIV-Gagp2p7          1201        1242         744          69         104
## HIV-Gagp1Pol         2100        2334        1592         129         163
## HIV-Polprot         23710       30544       21871        1465        2065
## HIV-Polp15p31       38437       59592       41124        2414        4070
##               alv_latent3
## HIV-Gagp17           2576
## HIV-Gagp24              0
## HIV-Gagp2p7           121
## HIV-Gagp1Pol          210
## HIV-Polprot          3280
## HIV-Polp15p31        5631
pb1af <- pb1a[which(rowMeans(pb1a)>=10),]
head(pb1af)
##               alv_active1 alv_active2 alv_active3 alv_latent1 alv_latent2
## HIV-Gagp17          32789       27176       17079        2306        1784
## HIV-Gagp2p7          1201        1242         744          69         104
## HIV-Gagp1Pol         2100        2334        1592         129         163
## HIV-Polprot         23710       30544       21871        1465        2065
## HIV-Polp15p31       38437       59592       41124        2414        4070
## HIV-Vif              3140        4489        3034         173         322
##               alv_latent3
## HIV-Gagp17           2576
## HIV-Gagp2p7           121
## HIV-Gagp1Pol          210
## HIV-Polprot          3280
## HIV-Polp15p31        5631
## HIV-Vif               423
colSums(pb1af)
## alv_active1 alv_active2 alv_active3 alv_latent1 alv_latent2 alv_latent3 
##    29715862    28360869    23446102     7231016     4200851     5268032
des1a <- as.data.frame(grepl("active",colnames(pb1af)))
colnames(des1a) <- "case"

plot(cmdscale(dist(t(pb1af))), xlab="Coordinate 1", ylab="Coordinate 2",
  type = "p",pch=19,col="gray",cex=2)

text(cmdscale(dist(t(pb1af))), labels=colnames(pb1af) )

des1a$sample <- rep(1:3,2)

dds <- DESeqDataSetFromMatrix(countData = pb1af , colData = des1a, design = ~ sample + case)
## converting counts to integer mode
##   the design formula contains one or more numeric variables with integer values,
##   specifying a model with increasing fold change for higher values.
##   did you mean for this to be a factor? if so, first convert
##   this variable to a factor using the factor() function
res <- DESeq(dds)
## estimating size factors
## estimating dispersions
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## fitting model and testing
z <- results(res)
vsd <- vst(dds, blind=FALSE)
zz <- cbind(as.data.frame(z),assay(vsd))
de <- as.data.frame(zz[order(zz$pvalue),])
de1af <- de
write.table(de1af,"de1af.tsv",sep="\t")

nrow(subset(de1af,padj<0.05 & log2FoldChange>0))
## [1] 23
nrow(subset(de1af,padj<0.05 & log2FoldChange<0))
## [1] 57
head(subset(de1af,padj<0.05 & log2FoldChange>0),10)[,1:6] %>%
  kbl(caption="Top upregulated genes in active Alv cells") %>%
  kable_paper("hover", full_width = F)
Top upregulated genes in active Alv cells
baseMean log2FoldChange lfcSE stat pvalue padj
CCL2 187.4633 1.9143141 0.3348532 5.716876 0.00e+00 0.0000161
HIV-Gagp17 8100.4242 1.1977591 0.2284677 5.242575 2.00e-07 0.0001386
HIV-BaLEnv 14478.2281 1.2308374 0.2574098 4.781625 1.70e-06 0.0010322
HIV-EnvStart 304.4463 1.3184580 0.2769949 4.759863 1.90e-06 0.0010322
AP005262.2 115.9552 1.2581355 0.2645860 4.755110 2.00e-06 0.0010322
HIV-Gagp1Pol 641.1340 1.2794395 0.2715165 4.712198 2.50e-06 0.0011387
ANK2 554.2652 0.6629198 0.1448643 4.576144 4.70e-06 0.0019343
HIV-Polprot 8352.3676 1.2390814 0.2727169 4.543470 5.50e-06 0.0021043
HIV-TatEx1 1831.0679 1.2999113 0.2864239 4.538417 5.70e-06 0.0021043
SASH1 294.2959 0.9111924 0.2136122 4.265638 1.99e-05 0.0058892 
head(subset(de1af,padj<0.05 & log2FoldChange<0),10)[,1:6] %>%
  kbl(caption="Top upregulated genes in active Alv cells") %>%
  kable_paper("hover", full_width = F)
Top upregulated genes in active Alv cells
baseMean log2FoldChange lfcSE stat pvalue padj
LGALS2 217.50384 -2.2260459 0.2893934 -7.692111 0 0.00e+00
FGL2 290.45945 -1.8890957 0.2749454 -6.870803 0 0.00e+00
IL1R2 45.87058 -2.6702007 0.4077695 -6.548309 0 2.00e-07
KCNMA1 1103.71817 -0.8853129 0.1481504 -5.975770 0 7.00e-06
TXLNB 89.27259 -2.0228132 0.3417990 -5.918137 0 8.00e-06
CHST13 187.27152 -1.4785120 0.2535128 -5.832100 0 9.80e-06
NDRG2 130.11646 -1.6267372 0.2790974 -5.828564 0 9.80e-06
GPR68 91.66040 -1.3611671 0.2387067 -5.702256 0 1.61e-05
TSPAN33 323.56673 -1.3038337 0.2295032 -5.681113 0 1.64e-05
VAMP5 453.27420 -1.3754138 0.2510658 -5.478299 0 4.78e-05 
m1a <- mitch_import(de,DEtype="deseq2",joinType="full")
## The input is a single dataframe; one contrast only. Converting
##         it to a list for you.
## Note: Mean no. genes in input = 14501
## Note: no. genes in output = 14501
## Note: estimated proportion of input genes in output = 1
mres1a <- mitch_calc(m1a,genesets=go,minsetsize=5,cores=4,priority="effect")
## Note: Enrichments with large effect sizes may not be
##             statistically significant.
res <- mres1a$enrichment_result

mitchtbl <- mres1a$enrichment_result
goid <- sapply(strsplit(mitchtbl$set," "),"[[",1)
mysplit <- strsplit(mitchtbl$set," ")
mysplit <- lapply(mysplit, function(x) { x[2:length(x)] } )
godescription <- unlist(lapply(mysplit, function(x) { paste(x,collapse=" ") } ))
em <- data.frame(goid,godescription,mitchtbl$pANOVA,mitchtbl$p.adjustANOVA,sign(mitchtbl$s.dist),mitchtbl$s.dist)
colnames(em) <- c("GO.ID","Description","p.Val","FDR","Phenotype","ES")
write.table(em,"de1af_em.tsv",row.names = FALSE, quote=FALSE,sep="\t")

res <- subset(res,p.adjustANOVA<0.05)
resup <- subset(res,s.dist>0)
resdn <- subset(res,s.dist<0)
s <- c(head(resup$s.dist,10), head(resdn$s.dist,10))
names(s) <- c(head(resup$set,10),head(resdn$set,10))
s <- s[order(s)]
cols <- gsub("1","red",gsub("-1","blue",as.character(sign(s))))
par(mar=c(5,27,3,1))
barplot(abs(s),las=1,horiz=TRUE,col=cols,xlab="ES",cex.names=0.8,main="")

if (! file.exists("Alv_latent_vs_active.html") ) {
  mitch_report(mres1a,outfile="Alv_latent_vs_active.html")
}
networkplot(mres1a,FDR=0.05,n_sets=20)

network_genes(mres1a,FDR=0.05,n_sets=20)
## [[1]]
## [[1]]$`UP genesets.GO:0000502 proteasome complex`
## [1] "PSMC4" "PSMB7" "PSMD2" "PSMD8"
## 
## [[1]]$`UP genesets.GO:0005739 mitochondrion`
##  [1] "ANK2"     "SNCA"     "SDS"      "PRDX5"    "BCKDHB"   "IFI27L2" 
##  [7] "ME3"      "MRPS33"   "SSBP1"    "MFN1"     "TRIAP1"   "MRPL35"  
## [13] "MLLT11"   "PERP"     "OCIAD2"   "GDAP1"    "PPIF"     "MRPS6"   
## [19] "NDUFA13"  "HEBP2"    "MSRB2"    "PUS10"    "FDXR"     "NDUFB8"  
## [25] "CARS2"    "BCAT1"    "SCP2"     "DDX1"     "DTD1"     "NDFIP2"  
## [31] "ARMC10"   "ARHGAP26" "BCL2"     "LYRM2"    "SQOR"     "DMAC1"   
## 
## [[1]]$`UP genesets.GO:0005743 mitochondrial inner membrane`
## [1] "MRPS33"  "MRPL35"  "PPIF"    "MRPS6"   "NDUFA13" "FDXR"    "NDUFB8" 
## [8] "SQOR"    "DMAC1"  
## 
## [[1]]$`UP genesets.GO:0005759 mitochondrial matrix`
## [1] "PRDX5"  "BCKDHB" "ME3"    "SSBP1"  "PPIF"   "FDXR"   "NDUFB8" "FDPS"  
## [9] "NRDC"  
## 
## [[1]]$`UP genesets.GO:0005762 mitochondrial large ribosomal subunit`
## [1] "MRPL35"
## 
## [[1]]$`UP genesets.GO:0005763 mitochondrial small ribosomal subunit`
## [1] "MRPS33" "MRPS6" 
## 
## [[1]]$`UP genesets.GO:0005839 proteasome core complex`
## [1] "PSMB7"
## 
## [[1]]$`UP genesets.GO:0022624 proteasome accessory complex`
## [1] "PSMC4" "PSMD2" "PSMD8"
## 
## [[1]]$`UP genesets.GO:0032543 mitochondrial translation`
## [1] "MRPS33" "MRPL35" "MRPS6" 
## 
## [[1]]$`UP genesets.GO:0060271 cilium assembly`
## [1] "BBS7"     "ATP6V1D"  "WWTR1"    "CDC14B"   "IFT80"    "KIAA0586"
## 
## [[1]]$`UP genesets.GO:0140662 ATP-dependent protein folding chaperone`
## [1] "TCP1"
## 
## [[1]]$`DOWN genesets.GO:0000381 regulation of alternative mRNA splicing, via spliceosome`
##  [1] "TRA2B"   "ARGLU1"  "RBM5"    "ZBTB7A"  "CELF1"   "FMR1"    "RNPS1"  
##  [8] "SAP18"   "SMU1"    "HNRNPA1" "YTHDC1"  "HNRNPU"  "DDX17"   "RBFOX1" 
## [15] "TIA1"    "MAGOH"   "RBFOX2"  "CELF6"   "RBM15"   "SRSF2"   "DDX5"   
## [22] "WTAP"    "SRSF6"   "THRAP3"  "RBM4"    "RBM47"   "RBPMS2"  "RBMX"   
## [29] "NSRP1"   "REST"    "RBM25"   "RBM15B"  "KHDRBS3" "PTBP1"   "PUF60"  
## [36] "RBM7"    "SRSF8"   "RBPMS"   "HNRNPL"  "CELF2"   "RBM8A"   "KHDRBS1"
## 
## [[1]]$`DOWN genesets.GO:0000976 transcription cis-regulatory region binding`
##   [1] "CEBPA"    "FOS"      "DLX3"     "EGR2"     "AR"       "ZBTB46"  
##   [7] "BASP1"    "RXRA"     "JUND"     "PER1"     "SOX6"     "ZNF217"  
##  [13] "TAF9"     "HHEX"     "ZNF174"   "TP53"     "ZFHX3"    "NFE2L2"  
##  [19] "KLF11"    "POU2F2"   "ZBED4"    "SP1"      "CEBPB"    "STAT3"   
##  [25] "SPI1"     "GABPB1"   "OVOL2"    "NR1D1"    "FLI1"     "MESP1"   
##  [31] "TCF7L2"   "ZNF746"   "TBL1X"    "RUNX1"    "CBX4"     "SUV39H1" 
##  [37] "HDAC5"    "THRA"     "ARID4B"   "GFI1"     "PER3"     "CALCOCO1"
##  [43] "IRF1"     "BRD4"     "JUN"      "CARM1"    "ZBTB14"   "ZNF513"  
##  [49] "ARID5B"   "PAX8"     "ATF7"     "CREB3L2"  "ATF6"     "ATF5"    
##  [55] "FOXO3"    "SMAD6"    "SMAD4"    "KDM5A"    "TAF2"     "XRCC6"   
##  [61] "ZBTB48"   "KMT2D"    "PER2"     "TBL1XR1"  "ELK1"     "ZNF579"  
##  [67] "YY1"      "GRHL1"    "DHX36"    "HMGB2"    "SMARCA2"  "TBP"     
##  [73] "TFE3"     "CTCF"     "SOX4"     "SOX12"    "TAF7"     "GABPA"   
##  [79] "FOXK1"    "CDK5RAP2" "ATF3"     "SFPQ"     "BRD7"     "CRY2"    
##  [85] "FOXK2"    "CIITA"    "ZNF335"   "TFAM"     "GABPB2"   "HMGB1"   
##  [91] "ERBB4"    "HDAC4"    "NCOR1"    "KLF4"     "XBP1"     "SOX13"   
##  [97] "MEN1"     "MEF2C"    "ATF6B"    "ARID4A"   "TCF3"     "ANKRD23" 
## [103] "REST"     "ZNF658"   "TFEB"     "EGR1"     "PRDM5"    "PIAS1"   
## [109] "TNF"      "ZNF568"   "HSF1"     "ATF4"     "ZNF281"   "BCOR"    
## [115] "ARID5A"   "ZBTB8A"   "CCNT1"    "MAFK"     "MZF1"     "XRCC5"   
## [121] "AHR"      "SUV39H2"  "HNRNPL"   "ZBTB20"   "NFYA"     "HINFP"   
## [127] "NFYB"     "RELA"     "NFYC"     "BAHD1"    "ZNF639"   "ETV5"    
## [133] "ZNF808"   "RNF10"    "CHD3"     "MTERF3"   "TCF12"    "ZNF263"  
## [139] "RBBP5"    "ATMIN"    "RFX3"     "TCF7"     "NFKB1"    "ASH2L"   
## [145] "BRCA1"    "NR1H3"    "DDIT3"    "SMAD3"   
## 
## [[1]]$`DOWN genesets.GO:0001227 DNA-binding transcription repressor activity, RNA polymerase II-specific`
##   [1] "NFATC3"   "ZBTB46"   "FOXP1"    "MAX"      "ZNF692"   "MYC"     
##   [7] "DEAF1"    "BCL6"     "MLX"      "ZNF217"   "ASCL2"    "HHEX"    
##  [13] "KLF16"    "HESX1"    "MLXIPL"   "ZEB2"     "TP53"     "ZFHX3"   
##  [19] "ZBTB7A"   "MNT"      "CEBPB"    "CC2D1A"   "ZNF134"   "KLF8"    
##  [25] "OVOL2"    "NR1D1"    "SAMD11"   "HES2"     "ZNF746"   "ZNF205"  
##  [31] "SKI"      "SNAI3"    "TRPS1"    "ELK3"     "BHLHE40"  "HES1"    
##  [37] "GFI1"     "NR2F6"    "MITF"     "ENO1"     "ZBTB1"    "JUN"     
##  [43] "ZBTB14"   "PURA"     "BATF3"    "ZBTB21"   "ATF7"     "ZBTB10"  
##  [49] "FOXO3"    "THAP1"    "ZNF219"   "ZBTB6"    "FOXO1"    "TCFL5"   
##  [55] "BCL11A"   "GZF1"     "HDGF"     "BHLHE41"  "SNAI1"    "ZNF91"   
##  [61] "ZBTB4"    "ERF"      "YY1"      "PRDM2"    "ZBTB33"   "SP3"     
##  [67] "HIC2"     "NR3C1"    "TGIF1"    "CTCF"     "SATB1"    "FOXK1"   
##  [73] "ATF3"     "ZBTB37"   "VAX2"     "NR2C1"    "LRRFIP1"  "FOXK2"   
##  [79] "HIVEP1"   "NFE2L1"   "MXI1"     "ZNF354C"  "MXD1"     "ZBTB2"   
##  [85] "IRF8"     "E2F6"     "OVOL1"    "ZC3H8"    "PRDM1"    "NFE2L3"  
##  [91] "CC2D1B"   "SOX13"    "CREM"     "ZBTB39"   "ZNF148"   "ZNF85"   
##  [97] "NFX1"     "HES6"     "SKIL"     "TCF3"     "PLAGL1"   "ETS2"    
## [103] "REST"     "ZBTB34"   "PATZ1"    "PRDM5"    "PPARA"    "ZNF224"  
## [109] "MSC"      "POU6F1"   "ZBTB5"    "HSF1"     "BACH1"    "KCNIP3"  
## [115] "ZNF281"   "ZGPAT"    "ZNF350"   "ZBTB8A"   "NACC1"    "ZNF202"  
## [121] "MAFK"     "ZKSCAN3"  "MZF1"     "FOXP4"    "PPARD"    "ZNF140"  
## [127] "ETV3"     "INSM1"    "ZBTB20"   "HINFP"    "ZNF131"   "THAP11"  
## [133] "RELA"     "TGIF2"    "ZBTB18"   "TFEC"     "ZBTB26"   "IKZF5"   
## [139] "ZNF668"   "SMAD5"    "MXD3"     "SP2"      "ZNF589"   "ZNF175"  
## [145] "ZFP90"    "ZBTB45"   "IRF3"     "KLF12"    "ZBTB25"   "ZNF512B" 
## [151] "NACC2"    "ZBTB49"   "ZNF263"   "ZNF93"    "E4F1"     "SREBF2"  
## [157] "ZBTB17"   "GTF2IRD1" "NR1D2"    "PURB"     "NFKB1"    "JDP2"    
## [163] "NFIL3"    "MYPOP"    "NFATC2"   "ETV6"    
## 
## [[1]]$`DOWN genesets.GO:0002181 cytoplasmic translation`
##  [1] "RPL10A"  "RPL12"   "RPL26"   "RPL5"    "RPL3"    "RPL36A"  "RPS23"  
##  [8] "RPL34"   "RPL32"   "RPS18"   "RPS14"   "RPS13"   "RPS24"   "RPL35A" 
## [15] "RPS8"    "RPL30"   "RPS15A"  "RPL7A"   "RPS4X"   "RPL29"   "RPL10"  
## [22] "RPL22"   "RPL37A"  "RPS3A"   "RPS6"    "RPL23"   "RPL22L1" "RPL11"  
## [29] "RPL17"   "RPS19"   "RPS9"    "RPL4"    "RPS25"   "RPL6"    "RPL37"  
## [36] "RPL24"   "RPS3"    "RPL31"   "RPL14"   "RPL39"   "RPL28"   "RPL15"  
## [43] "RPS7"    "RPS27"   "RPL7"    "RWDD1"   "RPL13"   "GTPBP1"  "RPS20"  
## [50] "RPS27A"  "RPL19"   "RPL23A"  "RPS12"   "RPLP1"   "RPL18"   "DRG2"   
## [57] "RPS11"   "RPS21"   "FAU"     "RPL8"    "RACK1"   "RPL35"   "RPL27A" 
## [64] "UBA52"   "ZC3H15"  "RPLP2"   "RPL21"   "RPS26"   "RPL41"   "RPL36"  
## [71] "RPS15"   "FTSJ1"   "DRG1"    "RPS2"    "RPL27"   "RPL26L1" "RPS17"  
## [78] "RPL38"   "RPL13A"  "RPS5"    "RPL18A"  "RPL9"    "RPS29"   "RPS10"  
## [85] "RPS16"   "RPS28"  
## 
## [[1]]$`DOWN genesets.GO:0002503 peptide antigen assembly with MHC class II protein complex`
##  [1] "HLA-DPA1" "HLA-DRA"  "HLA-DPB1" "HLA-DRB1" "HLA-DMB"  "HLA-DMA" 
##  [7] "HLA-DOA"  "HLA-DQB1" "HLA-DRB5" "HLA-DQA1" "B2M"     
## 
## [[1]]$`DOWN genesets.GO:0006325 chromatin organization`
##   [1] "OGT"      "HMGN2"    "HMGN3"    "ZMYND8"   "HDAC7"    "PWWP3A"  
##   [7] "SAMD1"    "GATAD1"   "ZBTB7A"   "NUCKS1"   "M1AP"     "HMG20A"  
##  [13] "CBX4"     "HDAC1"    "SUV39H1"  "MSL3"     "RPA1"     "HMGN1"   
##  [19] "ZNF518A"  "TRIM28"   "MRGBP"    "ABRAXAS1" "RCOR1"    "MLLT6"   
##  [25] "PARP10"   "GPX4"     "FAM50A"   "PHF20"    "MMS22L"   "HNRNPU"  
##  [31] "CBX8"     "RTF1"     "USP36"    "PHF13"    "TOX"      "RHNO1"   
##  [37] "RBL1"     "HMGN4"    "TP53BP1"  "PHF14"    "TBL1XR1"  "RNF169"  
##  [43] "L3MBTL1"  "BCORL1"   "RAG1"     "UTP3"     "EP400"    "RAD54L2" 
##  [49] "SIRT1"    "HMGB2"    "SS18L1"   "ZCWPW1"   "NR3C1"    "SATB1"   
##  [55] "SAFB"     "TDRD3"    "HDAC10"   "CBX6"     "CDAN1"    "HDAC3"   
##  [61] "MBTD1"    "L3MBTL2"  "EHMT1"    "MTA2"     "MORF4L2"  "NCOR1"   
##  [67] "IKZF1"    "L3MBTL4"  "ATRX"     "KANSL3"   "ATG5"     "HMG20B"  
##  [73] "AEBP2"    "ZMYND11"  "ENY2"     "LRWD1"    "UBN2"     "PRDM5"   
##  [79] "SMARCA5"  "BUD23"    "UBE2B"    "HIRIP3"   "KANSL2"   "BANF1"   
##  [85] "FAM50B"   "APBB1"    "CBX2"     "ZNF518B"  "KANSL1"   "RNF40"   
##  [91] "SUV39H2"  "MDC1"     "RSF1"     "ANP32E"   "PHF21A"   "EZH2"    
##  [97] "DNAJC2"   "SETD7"    "CBX7"     "HTATSF1"  "RELA"     "HMGN5"   
## [103] "HLTF"     "HDAC8"    "ASXL1"    "EMSY"     "BANP"     "SFMBT1"  
## [109] "L3MBTL3"  "RCCD1"    "THAP7"    "RBL2"     "TOPBP1"   "TADA3"   
## [115] "EPC2"     "RCBTB1"   "BRD8"     "ZZEF1"    "BAG6"     "HDAC11"  
## [121] "ATXN7L3"  "TONSL"    "MORF4L1"  "UBN1"    
## 
## [[1]]$`DOWN genesets.GO:0008286 insulin receptor signaling pathway`
##  [1] "EPHB1"    "CSF1R"    "AKT1"     "EPHB2"    "IRS2"     "FGFR1"   
##  [7] "PDK2"     "ALK"      "C2CD5"    "RHOQ"     "ZNF106"   "IGF1R"   
## [13] "SLC39A14" "MAPK3"    "INSR"     "NCOA5"    "AP3S1"    "SREBF1"  
## [19] "PIK3R1"   "PDK4"     "BCAR1"    "SMARCC1"  "TIE1"     "RAF1"    
## [25] "SOS2"     "FOXO1"    "SH2B2"    "GRB10"    "STXBP4"   "PTPRA"   
## [31] "TYRO3"    "SOS1"     "NAMPT"    "ERBB4"    "PIK3R3"   "BAIAP2"  
## [37] "GPLD1"    "MERTK"    "AKT2"     "RET"      "GSK3B"    "EIF4EBP2"
## [43] "GRB2"     "PIK3C2A"  "PTPN1"    "SLC2A8"   "FOXO4"    "GAB1"    
## [49] "PIK3R2"   "NDEL1"    "SOCS7"    "PIK3CA"   "MAPK1"    "COL6A1"  
## [55] "PTPN2"    "CAV2"     "PDGFRA"   "PHIP"     "ERBB2"    "APC"     
## [61] "APPL1"    "GSK3A"    "AXL"      "IDE"      "PDPK1"    "DDR2"    
## [67] "HRAS"     "SHC1"     "FER"     
## 
## [[1]]$`DOWN genesets.GO:0016605 PML body`
##  [1] "MAX"       "BASP1"     "TRIM8"     "RNF6"      "KLHL20"    "SUMO2"    
##  [7] "N4BP1"     "ZBED1"     "TP53"      "SP140"     "HIPK3"     "SPN"      
## [13] "TCF7L2"    "MKNK2"     "SLF2"      "CHEK2"     "SKI"       "TP53INP1" 
## [19] "EIF3E"     "WDFY3"     "RPA1"      "NSMCE2"    "HIPK1"     "LRCH4"    
## [25] "TOP3A"     "PARK7"     "ZMYM2"     "PML"       "RB1"       "RAD51"    
## [31] "RNF111"    "THAP1"     "TRIM16"    "HIRA"      "DAXX"      "SP3"      
## [37] "TOPORS"    "SIRT1"     "HMBOX1"    "CHFR"      "SRSF2"     "GCNA"     
## [43] "TDG"       "SATB1"     "IKBKE"     "NR2C1"     "HIPK2"     "CIITA"    
## [49] "RPAIN"     "TDP2"      "CSNK2A1"   "SPTBN4"    "CALCOCO2"  "BLM"      
## [55] "ATRX"      "CSNK2B"    "CDK9"      "SUMO1"     "NBN"       "SKIL"     
## [61] "RPA2"      "MTOR"      "PIAS1"     "PTEN"      "HSF1"      "MAPK7"    
## [67] "ATR"       "RGS14"     "USP7"      "UBE2I"     "TP53INP2"  "SMC5"     
## [73] "CBX5"      "MORC3"     "RNF4"      "TRIM27"    "SP100"     "PATL1"    
## [79] "EIF4ENIF1" "PIAS2"     "SIMC1"     "ELF4"      "ZNF451"    "DAPK3"    
## [85] "AKAP8L"    "SQSTM1"    "KAT6A"     "CHD3"      "SUMO3"     "PIAS4"    
## [91] "CASP8AP2"  "SENP2"     "TOPBP1"    "ISG20"     "CIART"     "UBN1"     
## [97] "MRE11"     "SMC6"      "RFWD3"    
## 
## [[1]]$`DOWN genesets.GO:0022625 cytosolic large ribosomal subunit`
##  [1] "RPL10A"  "RPL12"   "RPL26"   "RPL5"    "RPL3"    "RPL36A"  "RPL34"  
##  [8] "RPL32"   "RPL35A"  "RPL30"   "RPL7A"   "RPL29"   "RPL10"   "RPL22"  
## [15] "RPL37A"  "RPL23"   "RPL11"   "RPL17"   "RPL4"    "ZCCHC17" "RPL6"   
## [22] "RPL37"   "RPL24"   "RPL31"   "RPL14"   "RPL39"   "RPL28"   "RPL15"  
## [29] "RPL7"    "RPL13"   "RPL39L"  "RPL19"   "RPL23A"  "RPLP1"   "RPL18"  
## [36] "RPL8"    "RPL35"   "RPL27A"  "UBA52"   "RPLP2"   "RPL21"   "RPL41"  
## [43] "RPL36"   "RPL7L1"  "RPL36AL" "RPL27"   "RPL26L1" "RPL38"   "RPL13A" 
## [50] "RPL18A"  "RPL9"   
## 
## [[1]]$`DOWN genesets.GO:0022626 cytosolic ribosome`
##  [1] "RPL10A"  "RPL12"   "RPL26"   "RPL5"    "RPL3"    "APOD"    "EEF1A1" 
##  [8] "RPL36A"  "RPS23"   "RPL34"   "RPL32"   "RPS18"   "RPS14"   "RPS13"  
## [15] "RPS24"   "RPL35A"  "RPS8"    "RPL30"   "RPS15A"  "RPL7A"   "RPS4X"  
## [22] "RPL29"   "RPL10"   "RPL22"   "RPL37A"  "RPS3A"   "RPS6"    "RPL23"  
## [29] "RPL11"   "RPL17"   "RPS19"   "RPS9"    "RPL4"    "RPS25"   "RPL6"   
## [36] "RPL37"   "RPL24"   "RPS3"    "RPL31"   "RPL14"   "RPL39"   "RPL28"  
## [43] "RPL15"   "PELO"    "RPS7"    "ASCC3"   "RPS27"   "RPL7"    "GSPT1"  
## [50] "RPL13"   "RPS20"   "RPS27A"  "RPL19"   "RPL23A"  "RPS12"   "ETF1"   
## [57] "RPLP1"   "RPL18"   "RNF14"   "GCN1"    "RNF25"   "RPS11"   "RPS21"  
## [64] "FAU"     "RPL8"    "RPL35"   "RPL27A"  "UBA52"   "RPL21"   "ZNF598" 
## [71] "RPL36"   "RPS15"   "EIF2AK4" "ASCC2"   "RPS2"    "USP10"   "RPL27"  
## [78] "RPS17"   "RPL38"   "RNF10"   "METAP1"  "HBS1L"   "NEMF"    "RPL13A" 
## [85] "RPS5"    "RPL18A"  "LTN1"    "ABCE1"   "RPL9"    "RPS10"   "RPS16"  
## 
## [[1]]$`DOWN genesets.GO:0022627 cytosolic small ribosomal subunit`
##  [1] "RPS23"  "RPS18"  "RPS14"  "RPS13"  "RPS24"  "RPS8"   "RPS15A" "RPS4X" 
##  [9] "RPS3A"  "RPS6"   "RPS27L" "RPS19"  "RPS9"   "RPS25"  "RPS3"   "RPS7"  
## [17] "RPS27"  "LARP4"  "RPS20"  "RPS27A" "RPS12"  "DHX29"  "RPS11"  "RPS21" 
## [25] "FAU"    "RACK1"  "RPS26"  "RPS15"  "RPS4Y1" "RPS2"   "EIF2A"  "RPS17" 
## [33] "RPS5"   "DDX3X"  "RPS29"  "RPS10"  "RPS16"  "RPS28" 
## 
## [[1]]$`DOWN genesets.GO:0032720 negative regulation of tumor necrosis factor production`
##  [1] "VSIR"    "C5AR2"   "ARRB2"   "GPNMB"   "SYT11"   "BPI"     "RARA"   
##  [8] "GSTP1"   "BCL3"    "IGF1"    "LGALS9"  "ZC3H12A" "ARG2"    "CLEC4A" 
## [15] "IL10"    "POMC"    "RAD21"   "IL27RA"  "DICER1"  "IRAK3"   "CD33"   
## [22] "TNFAIP3" "TREM2"   "PTPN6"   "FXR1"    "CACTIN"  "SIRPA"   "NFKBIL1"
## [29] "GAS6"    "LILRB4"  "ILRUN"   "HAVCR2"  "LILRA4"  "MC1R"    "TRIM27" 
## [36] "PTPN22"  "AKAP8"   "TSPO"    "ELF4"    "SELENOS" "AXL"     "ACP5"   
## [43] "TLR4"    "GHRL"   
## 
## [[1]]$`DOWN genesets.GO:0042613 MHC class II protein complex`
##  [1] "CD74"     "HLA-DPA1" "HLA-DRA"  "HLA-DPB1" "HLA-DRB1" "HLA-DMB" 
##  [7] "HLA-DMA"  "HLA-DOA"  "HLA-DQB1" "HLA-DRB5" "HLA-DQA1" "B2M"     
## 
## [[1]]$`DOWN genesets.GO:0051607 defense response to virus`
##   [1] "TLR8"     "IFNGR2"   "IFI27"    "UNC93B1"  "IRF5"     "STAT2"   
##   [7] "TBKBP1"   "IFITM2"   "PCBP2"    "AZU1"     "IFI44L"   "G3BP1"   
##  [13] "SPON2"    "OAS1"     "APOBEC3H" "CARD8"    "ZC3H12A"  "TRIM56"  
##  [19] "SAMHD1"   "OAS2"     "PTPRC"    "IFITM3"   "CD40"     "ADAR"    
##  [25] "IL10RB"   "MX2"      "PYCARD"   "MAP3K14"  "TTC4"     "TLR2"    
##  [31] "LSM14A"   "MOV10"    "SLFN13"   "OAS3"     "MYD88"    "IFI6"    
##  [37] "IRF1"     "POLR3F"   "TRIM52"   "PMAIP1"   "IRF9"     "SERINC3" 
##  [43] "CRCP"     "SLFN11"   "GBP1"     "IRF2"     "BCL2L1"   "NCBP1"   
##  [49] "APOBEC3F" "DDX17"    "SKP2"     "ZNFX1"    "ILF3"     "RAB2B"   
##  [55] "IFIT5"    "ATG16L1"  "NCBP3"    "TBK1"     "IRF7"     "MX1"     
##  [61] "SHFL"     "CGAS"     "RIOK3"    "PDE12"    "POLR3E"   "DDX60L"  
##  [67] "GBP2"     "DHX36"    "AZI2"     "HYAL2"    "TICAM1"   "TRIM5"   
##  [73] "CNOT7"    "IFIT3"    "TRIM34"   "CARD9"    "RNF185"   "BNIP3"   
##  [79] "MAVS"     "IKBKE"    "DDX60"    "NLRC5"    "APOBEC3C" "EXOSC4"  
##  [85] "SERINC5"  "DDX56"    "UNC13D"   "ATG7"     "ITGAX"    "RTP4"    
##  [91] "HERC5"    "RNASE1"   "APOBEC3D" "EXOC1"    "ATG14"    "EXOSC5"  
##  [97] "TRAF3"    "VAMP8"    "DDIT4"    "SETD2"    "RNASEL"   "BECN1"   
## [103] "POLR3K"   "ATG5"     "EIF2AK4"  "ZMYND11"  "PARP9"    "DHX15"   
## [109] "IL23A"    "FADD"     "IFIT2"    "TRIM22"   "ELMOD2"   "IFIT1"   
## [115] "IFNGR1"   "STAT1"    "GBP5"     "ARMC5"    "GPAM"     "IFNLR1"  
## [121] "BNIP3L"   "PLSCR1"   "ITCH"     "EIF2AK2"  "CXADR"    "NT5C3A"  
## [127] "GBP3"     "POLR3H"   "TLR3"     "TRIM41"   "AGBL5"    "RIPK3"   
## [133] "APOBEC3A" "OASL"     "LYST"     "POLR3G"   "TANK"     "PQBP1"   
## [139] "RNASE6"   "BST2"     "RELA"     "ISG15"    "DTX3L"    "RB1CC1"  
## [145] "IFNAR2"   "NLRP1"    "ZNF175"   "IRF3"     "APOBEC3G" "POLR3A"  
## [151] "ZCCHC3"   "ABCF3"    "NDUFAF4"  "POLR3C"   "IFI16"    "MICA"    
## [157] "UBL7"     "AIMP1"    "DDX21"    "MLKL"     "ISG20"    "IFIH1"   
## [163] "POLR3B"   "ZC3HAV1"  "RSAD2"    "POLR3D"   "DNAJC3"  
## 
## [[1]]$`DOWN genesets.GO:0051726 regulation of cell cycle`
##   [1] "CEBPA"    "PPP1R9B"  "VASH1"    "JUNB"     "JUND"     "PRNP"    
##   [7] "TFDP2"    "PKD1"     "DDIAS"    "RASSF1"   "CCNL2"    "CDKN1B"  
##  [13] "PRR11"    "TP53"     "CCNG2"    "EVI2B"    "CDKL5"    "ITGB1"   
##  [19] "MECOM"    "KAT2B"    "PTPRC"    "MNT"      "ATM"      "CDK5"    
##  [25] "STAT3"    "OVOL2"    "BAX"      "MX2"      "TGFBR1"   "SIRT2"   
##  [31] "GPER1"    "CTBP1"    "MDM4"     "TP53INP1" "RIPOR2"   "CDK10"   
##  [37] "STK11"    "ACTB"     "GADD45B"  "CDKL1"    "ING3"     "JADE1"   
##  [43] "BIRC2"    "MRGBP"    "VPS72"    "IRF1"     "PML"      "TRIM36"  
##  [49] "JUN"      "MCRS1"    "PUM1"     "DMAP1"    "MBIP"     "CDKN3"   
##  [55] "BCR"      "JADE2"    "NFRKB"    "TARDBP"   "CCNF"     "SON"     
##  [61] "RB1"      "RHEB"     "SKP2"     "MADD"     "INO80B"   "HSP90AB1"
##  [67] "ACTR8"    "CDKN2A"   "NUP214"   "PPM1G"    "PCLAF"    "PER2"    
##  [73] "L3MBTL1"  "CDK7"     "LIN9"     "ING5"     "PRKACA"   "TSC2"    
##  [79] "YY1"      "ZNF703"   "MEAF6"    "INO80E"   "CDK19"    "CDKL3"   
##  [85] "BAK1"     "EP400"    "COPS5"    "HBP1"     "CABLES1"  "YY1AP1"  
##  [91] "CDK4"     "HIPK2"    "FOXM1"    "RACK1"    "MBTD1"    "GAS2"    
##  [97] "PNPT1"    "YEATS2"   "CCNL1"    "USP16"    "CSNK2A1"  "PRCC"    
## [103] "MORF4L2"  "RUVBL1"   "CDK8"     "KAT7"     "PPP1R15A" "BIRC7"   
## [109] "CDK11B"   "TSC1"     "CDK9"     "AKT2"     "ING4"     "INO80"   
## [115] "SGSM3"    "NBN"      "MASTL"    "BTRC"     "SKIL"     "PES1"    
## [121] "PLAGL1"   "CDK6"     "TBRG4"    "MAP2K6"   "TXLNG"    "NANOS3"  
## [127] "PRDM11"   "PHACTR4"  "CDK12"    "XIAP"     "WDR12"    "UBA3"    
## [133] "TADA2A"   "TRRAP"    "GADD45A"  "RAD51D"   "BAP1"     "UCHL5"   
## [139] "EIF4G2"   "SGF29"    "NF2"      "KIF20B"   "KAT2A"    "GADD45G" 
## [145] "BIRC3"    "WDR5"     "KAT14"    "CDKL4"    "INSM1"    "ACTL6A"  
## [151] "EPC1"     "CABLES2"  "BARD1"    "PPP2R3B"  "CDK13"    "BOP1"    
## [157] "DR1"      "TBRG1"    "TSG101"   "RBM38"    "ZNF268"   "UHRF2"   
## [163] "ACTR5"    "INO80D"   "CDK11A"   "PPM1A"    "CGRRF1"   "GRK5"    
## [169] "NOP53"    "ZBTB49"   "KHDRBS1"  "KAT5"     "TADA3"    "TRNP1"   
## [175] "EPC2"     "E4F1"     "YEATS4"   "FIGNL1"   "UHMK1"    "BRD8"    
## [181] "CDKL2"    "PKD2"     "HRAS"     "MORF4L1"  "ABL1"     "BRCA1"   
## [187] "RUVBL2"   "DDIT3"    "DAB2IP"  
## 
## [[1]]$`DOWN genesets.GO:0060337 type I interferon-mediated signaling pathway`
##  [1] "IFI27"  "STAT2"  "TBKBP1" "IFITM2" "OAS1"   "OAS2"   "IFITM3" "TRIM65"
##  [9] "OAS3"   "MYD88"  "TBK1"   "IRF7"   "AZI2"   "IFNAR1" "MAVS"   "IKBKE" 
## [17] "TYK2"   "HDAC4"  "TRAF3"  "STAT1"  "OASL"   "SP100"  "TANK"   "IFNAR2"
## [25] "IRF3"   "SIN3A"  "IRAK1"  "IFIH1"  "JAK1"  
## 
## [[1]]$`DOWN genesets.GO:0061158 3'-UTR-mediated mRNA destabilization`
##  [1] "ZFP36L1" "PUM2"    "ZC3H12A" "ZFP36"   "KHSRP"   "MOV10"   "PUM1"   
##  [8] "TARDBP"  "DHX36"   "HNRNPD"  "ZC3H12D" "UPF1"    "ZFP36L2" "CPEB3"  
## [15] "RC3H1"  
## 
## [[1]]$`DOWN genesets.GO:0071276 cellular response to cadmium ion`
##  [1] "HESX1" "MT2A"  "OGG1"  "MT1F"  "MT1E"  "HMOX1" "MT1X"  "CYBB"  "DAXX" 
## [10] "MT1H"  "MT1G"  "SUMO1" "HSF1"  "MT1M"  "ATP7A"
## 
## [[1]]$`DOWN genesets.GO:1990837 sequence-specific double-stranded DNA binding`
##   [1] "CEBPD"   "FOS"     "DLX3"    "EGR2"    "NFATC3"  "KLF13"   "FOXP1"  
##   [8] "MAX"     "IRF5"    "NFIC"    "ZBTB7B"  "ZNF384"  "RXRA"    "JUNB"   
##  [15] "JUND"    "PITX1"   "BCL6"    "RARA"    "MAFF"    "MLX"     "NFIX"   
##  [22] "CREB3"   "ASCL2"   "KLF16"   "HESX1"   "KLF6"    "ZNF768"  "POU3F1" 
##  [29] "ZNF174"  "ZBED1"   "ZBTB7A"  "KLF11"   "POU2F2"  "SP1"     "FOXN2"  
##  [36] "CEBPB"   "KDM5B"   "DBP"     "E2F3"    "ATF2"    "OVOL2"   "KLF10"  
##  [43] "NR1D1"   "HES2"    "FLI1"    "ZNF821"  "SNAI3"   "ZNF740"  "ZNF580" 
##  [50] "CLOCK"   "ZNF250"  "ELK3"    "LBX2"    "SREBF1"  "RFX1"    "BHLHE40"
##  [57] "HES1"    "ELF2"    "GFI1"    "NR2F6"   "CPSF4"   "BATF"    "SRF"    
##  [64] "ESRRB"   "NR4A2"   "FOSL1"   "JUN"     "RFX5"    "TFCP2"   "ZBTB14" 
##  [71] "NFATC1"  "USF2"    "IRF9"    "ZBTB22"  "ZFP41"   "IRF2"    "MAF"    
##  [78] "BATF3"   "HOXA1"   "PAX8"    "RFX2"    "HNRNPU"  "ATF7"    "ESRRA"  
##  [85] "MEF2B"   "ZNF12"   "ATF6"    "CUX1"    "TBX1"    "FOXO3"   "HOXA5"  
##  [92] "ZNF343"  "TCF4"    "GMEB2"   "ZNF449"  "CREB1"   "PKNOX1"  "TCFL5"  
##  [99] "YY2"     "HNRNPAB" "BHLHE41" "SNAI1"   "YBX1"    "ZSCAN5A" "TEF"    
## [106] "NFAT5"   "IRF7"    "ELK1"    "ELK4"    "HSF5"    "YY1"     "NFKB2"  
## [113] "ZNF274"  "RUNX2"   "ZBTB33"  "RUNX3"   "SP3"     "GRHL1"   "LMNB1"  
## [120] "CEBPG"   "HOXA10"  "THRB"    "HMBOX1"  "ZNF524"  "BBX"     "TFE3"   
## [127] "NR3C1"   "TGIF1"   "ZNF444"  "CTCF"    "SOX4"    "SOX12"   "GABPA"  
## [134] "FOXK1"   "ZSCAN29" "ATF3"    "ESR1"    "ZBTB37"  "ZNF713"  "VAX2"   
## [141] "NR2C1"   "HIVEP1"  "FOSB"    "XPA"     "ZNF296"  "RXRB"    "NPAS2"  
## [148] "ZBTB2"   "NR6A1"   "ZFP1"    "ZNF787"  "USF1"    "KLF4"    "IRF8"   
## [155] "OVOL1"   "RARG"    "KLF3"    "CEBPE"   "XBP1"    "PRDM4"   "PRDM1"  
## [162] "MTF1"    "CREB3L4" "CREM"    "MEF2C"   "E2F4"    "ATF6B"   "HES6"   
## [169] "NRL"     "ETS2"    "ELF1"    "TFEB"    "ZSCAN9"  "ZBTB43"  "ZNF704" 
## [176] "EGR1"    "RFX7"    "FOXJ3"   "MEIS3"   "MSC"     "POU6F1"  "HSF1"   
## [183] "ZNF784"  "ATF4"    "ARNT"    "ZNF281"  "FOXO4"   "CREB5"   "ZNF771" 
## [190] "HSF2"    "MAFG"    "ETV2"    "ZNF276"  "ZSCAN31" "ZNF385D" "ZNF345" 
## [197] "AHR"     "ZSCAN16" "NR3C2"   "PPARD"   "ZNF140"  "ETV3"    "ZBTB20" 
## [204] "ELF5"    "TBX19"   "ZNF597"  "ZNF76"   "ZNF75A"  "ZNF282"  "ZNF410" 
## [211] "TGIF2"   "ZBTB18"  "ELF4"    "TFEC"    "TFCP2L1" "ZBTB26"  "ZNF23"  
## [218] "E2F1"    "SMAD5"   "ETV5"    "ZNF460"  "SP2"     "UBP1"    "ZBTB45" 
## [225] "IRF3"    "MBNL2"   "ZNF396"  "KLF12"   "ZNF684"  "GMEB1"   "TCF12"  
## [232] "ZNF263"  "MEF2D"   "RFX3"    "TCF7"    "FOXJ2"   "SREBF2"  "NR1D2"  
## [239] "JDP2"    "ABL1"    "ZNF32"   "HSF4"    "ZNF501"  "NFATC2"  "NR2C2"  
## [246] "ZNF177" 
## 
## [[1]]$`DOWN genesets.GO:1990904 ribonucleoprotein complex`
##   [1] "RPL26"     "RPL5"      "ZFP36L1"   "RPS8"      "DYRK2"     "RPS4X"    
##   [7] "RPL22"     "PCBP2"     "RPS3A"     "GRSF1"     "RPS6"      "RNF135"   
##  [13] "RPL22L1"   "PABPC1"    "RPS9"      "RPL4"      "PCBP1"     "ZFP36"    
##  [19] "SLBP"      "CELF1"     "HSPA8"     "RPS3"      "RBMS3"     "FMR1"     
##  [25] "NPM1"      "RBMS1"     "GAPDH"     "LSM14A"    "PABPN1"    "ACTB"     
##  [31] "RPS7"      "RPL7"      "HNRNPK"    "HNRNPH1"   "PHAX"      "PABPC1L"  
##  [37] "TOP2B"     "DYRK1A"    "HNRNPA1"   "HNRNPA0"   "EEFSEC"    "SRA1"     
##  [43] "NCBP1"     "APOBEC3F"  "HNRNPU"    "DDX17"     "RBM14"     "GTF3C1"   
##  [49] "ILF3"      "PCBP4"     "EFL1"      "TIA1"      "HNRNPUL1"  "HNRNPH2"  
##  [55] "HNRNPAB"   "YBX1"      "CPEB1"     "SSB"       "MRPL41"    "CELF6"    
##  [61] "JMJD6"     "TEP1"      "SRRT"      "ZC3H14"    "PABPC4"    "HNRNPF"   
##  [67] "CPSF3"     "HNRNPD"    "RO60"      "HNRNPH3"   "DDX5"      "LRRK2"    
##  [73] "TOP2A"     "DAZAP1"    "CSNK1E"    "IGHMBP2"   "ATXN2"     "RUVBL1"   
##  [79] "ZNF827"    "MVP"       "PA2G4"     "RBMX"      "RBM12B"    "NSRP1"    
##  [85] "MEPCE"     "SLIRP"     "IQGAP1"    "HSF1"      "PATL2"     "TEFM"     
##  [91] "PUF60"     "LSM14B"    "ZC3H18"    "RBMS2"     "TRIM21"    "MRPL10"   
##  [97] "NUP98"     "XRCC5"     "EEF2"      "HSPA1A"    "CBX5"      "ELAVL1"   
## [103] "ZFP36L2"   "XPO1"      "HNRNPL"    "DHX9"      "RPL27"     "JRK"      
## [109] "CELF2"     "LSM1"      "BOP1"      "SYNCRIP"   "HSPA1B"    "ACTN4"    
## [115] "PCBP3"     "ILF2"      "RPS6KL1"   "AKAP8L"    "LRPPRC"    "PIH1D2"   
## [121] "APOBEC3G"  "RPL13A"    "PIH1D1"    "SECISBP2"  "RPS5"      "LARP7"    
## [127] "PARP4"     "NCL"       "RBM45"     "RBM12"     "HNRNPA2B1" "NUP62"    
## [133] "SUZ12"     "CPSF6"     "HNRNPA3"   "HNRNPR"    "BRCA1"     "NFATC2"   
## [139] "RUVBL2"    "SECISBP2L"

Combined.

mm1 <- merge(m1a,m1m,by=0)

head(mm1)
##   Row.names        x.x         x.y
## 1      A1BG  0.3726457  0.03903336
## 2  A1BG-AS1 -1.1015815 -0.54327750
## 3       A2M  0.8269858 -0.04242701
## 4    A4GALT  1.2356907 -1.06994742
## 5      AAAS  0.2195956 -0.35071802
## 6      AACS  2.5002124  1.18770579
rownames(mm1) <- mm1[,1]
mm1[,1]=NULL
colnames(mm1) <- c("Alv","MDM")
plot(mm1)
mylm <- lm(mm1)
abline(mylm,col="red",lty=2,lwd=3)

summary(mylm)
## 
## Call:
## lm(formula = mm1)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -7.1948 -0.6053  0.0086  0.6214  6.3079 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 0.022862   0.008593   2.661  0.00781 ** 
## MDM         0.319117   0.006259  50.989  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.9837 on 13111 degrees of freedom
## Multiple R-squared:  0.1655, Adjusted R-squared:  0.1654 
## F-statistic:  2600 on 1 and 13111 DF,  p-value: < 2.2e-16
cor.test(mm1$Alv,mm1$MDM)
## 
##  Pearson's product-moment correlation
## 
## data:  mm1$Alv and mm1$MDM
## t = 50.989, df = 13111, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.3924094 0.4209782
## sample estimates:
##       cor 
## 0.4067932
mm1r <- as.data.frame(apply(mm1,2,rank))
plot(mm1r,cex=0.3)
mylm <- lm(mm1r)
abline(mylm,col="red",lty=2,lwd=3)

summary(mylm)
## 
## Call:
## lm(formula = mm1r)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -8674.8 -2980.8   -28.6  2959.3  8837.2 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 4.184e+03  6.164e+01   67.87   <2e-16 ***
## MDM         3.620e-01  8.141e-03   44.46   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3529 on 13111 degrees of freedom
## Multiple R-squared:  0.131,  Adjusted R-squared:  0.131 
## F-statistic:  1977 on 1 and 13111 DF,  p-value: < 2.2e-16
cor.test(mm1r$Alv,mm1r$MDM)
## 
##  Pearson's product-moment correlation
## 
## data:  mm1r$Alv and mm1r$MDM
## t = 44.462, df = 13111, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.3470045 0.3767526
## sample estimates:
##       cor 
## 0.3619707

DE2 Latently-infected vs bystander cells

MDM group.

pb2m <- pbmdm[,c(grep("bystander",colnames(pbmdm)),grep("latent",colnames(pbmdm)))]
head(pb2m)
##               mdm_bystander1 mdm_bystander2 mdm_bystander3 mdm_bystander4
## HIV-Gagp17               255            254             57             61
## HIV-Gagp24                 0              0              0              0
## HIV-Gagp2p7               23             32              3              8
## HIV-Gagp1Pol              20             61             16             10
## HIV-Polprot              331            492            181             81
## HIV-Polp15p31           1033           1505            413            181
##               mdm_latent1 mdm_latent2 mdm_latent3 mdm_latent4
## HIV-Gagp17           1927        2077         566         534
## HIV-Gagp24              0           0           0           0
## HIV-Gagp2p7            51         108          37          12
## HIV-Gagp1Pol           83         129          63          24
## HIV-Polprot          1383        1587         877         250
## HIV-Polp15p31        3589        5077        2425         441
pb2mf <- pb2m[which(rowMeans(pb2m)>=10),]
head(pb2mf)
##               mdm_bystander1 mdm_bystander2 mdm_bystander3 mdm_bystander4
## HIV-Gagp17               255            254             57             61
## HIV-Gagp2p7               23             32              3              8
## HIV-Gagp1Pol              20             61             16             10
## HIV-Polprot              331            492            181             81
## HIV-Polp15p31           1033           1505            413            181
## HIV-Vif                   87             73             29             16
##               mdm_latent1 mdm_latent2 mdm_latent3 mdm_latent4
## HIV-Gagp17           1927        2077         566         534
## HIV-Gagp2p7            51         108          37          12
## HIV-Gagp1Pol           83         129          63          24
## HIV-Polprot          1383        1587         877         250
## HIV-Polp15p31        3589        5077        2425         441
## HIV-Vif               221         317         146          25
colSums(pb2mf)
## mdm_bystander1 mdm_bystander2 mdm_bystander3 mdm_bystander4    mdm_latent1 
##       70251518       68922564       26227400       36266616        2511512 
##    mdm_latent2    mdm_latent3    mdm_latent4 
##        3999100        2431331         583834
des2m <- as.data.frame(grepl("latent",colnames(pb2mf)))
colnames(des2m) <- "case"

plot(cmdscale(dist(t(pb2mf))), xlab="Coordinate 1", ylab="Coordinate 2",
  type = "p",pch=19,col="gray",cex=2)

text(cmdscale(dist(t(pb2mf))), labels=colnames(pb2mf) )

des2m$sample <- rep(1:4,2)

dds <- DESeqDataSetFromMatrix(countData = pb2mf , colData = des2m, design = ~ sample + case)
## converting counts to integer mode
##   the design formula contains one or more numeric variables with integer values,
##   specifying a model with increasing fold change for higher values.
##   did you mean for this to be a factor? if so, first convert
##   this variable to a factor using the factor() function
res <- DESeq(dds)
## estimating size factors
## estimating dispersions
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## fitting model and testing
z <- results(res)
vsd <- vst(dds, blind=FALSE)
zz <- cbind(as.data.frame(z),assay(vsd))
de <- as.data.frame(zz[order(zz$pvalue),])
de2mf <- de
write.table(de2mf,"de2mf.tsv",sep="\t")

nrow(subset(de2mf,padj<0.05 & log2FoldChange>0))
## [1] 30
nrow(subset(de2mf,padj<0.05 & log2FoldChange<0))
## [1] 19
head(subset(de2mf,log2FoldChange>0),10)[,1:6] %>%
  kbl(caption="Top upregulated genes in latent compared to bystander (MDM paired)") %>%
  kable_paper("hover", full_width = F)
Top upregulated genes in latent compared to bystander (MDM paired)
baseMean log2FoldChange lfcSE stat pvalue padj
HIV-Vif 312.16572 6.060595 0.2096421 28.90925 0 0
HIV-BaLEnv 3477.64934 6.755062 0.2431928 27.77657 0 0
HIV-Polp15p31 5133.34400 6.200422 0.3071491 20.18701 0 0
HIV-Polprot 1995.91085 6.270763 0.3209171 19.54013 0 0
HIV-Gagp17 2763.92685 7.702589 0.4093093 18.81850 0 0
HIV-Gagp2p7 95.31590 6.001675 0.3530808 16.99802 0 0
HIV-EGFP 67.19305 5.954128 0.3657873 16.27757 0 0
HIV-TatEx2Rev 79.07938 7.161458 0.4442420 16.12062 0 0
HIV-Vpu 58.00682 5.569366 0.3571472 15.59404 0 0
HIV-TatEx1 246.18840 6.224838 0.4070984 15.29075 0 0 
head(subset(de2mf,log2FoldChange<0),10)[,1:6] %>%
  kbl(caption="Top downregulated genes in latent compared to bystander (MDM paired)") %>%
  kable_paper("hover", full_width = F)
Top downregulated genes in latent compared to bystander (MDM paired)
baseMean log2FoldChange lfcSE stat pvalue padj
VIM 24783.4593 -0.6055611 0.1156514 -5.236091 2.00e-07 0.0001314
FBP1 8641.3556 -0.7193683 0.1396845 -5.149951 3.00e-07 0.0001971
MGST3 8645.8034 -0.4021467 0.0795970 -5.052285 4.00e-07 0.0002972
TMSB4X 91023.5640 -0.3227649 0.0687588 -4.694158 2.70e-06 0.0017358
CAPG 13118.9952 -0.5307891 0.1142230 -4.646953 3.40e-06 0.0020849
PRDX1 11714.8162 -0.5281115 0.1151080 -4.587966 4.50e-06 0.0026497
CYP27A1 4943.4425 -0.4045165 0.0889949 -4.545390 5.50e-06 0.0031109
TUBB 1912.4974 -0.5203904 0.1154535 -4.507360 6.60e-06 0.0034937
IFI27 121.1303 -2.2691939 0.5090422 -4.457771 8.30e-06 0.0041764
TUBB4B 608.5510 -0.7597242 0.1780907 -4.265940 1.99e-05 0.0087433 
m2m <- mitch_import(de,DEtype="deseq2",joinType="full")
## The input is a single dataframe; one contrast only. Converting
##         it to a list for you.
## Note: Mean no. genes in input = 15078
## Note: no. genes in output = 15078
## Note: estimated proportion of input genes in output = 1
mres2m <- mitch_calc(m2m,genesets=go,minsetsize=5,cores=4,priority="effect")
## Note: Enrichments with large effect sizes may not be
##             statistically significant.
res <- mres2m$enrichment_result

mitchtbl <- mres2m$enrichment_result
goid <- sapply(strsplit(mitchtbl$set," "),"[[",1)
mysplit <- strsplit(mitchtbl$set," ")
mysplit <- lapply(mysplit, function(x) { x[2:length(x)] } )
godescription <- unlist(lapply(mysplit, function(x) { paste(x,collapse=" ") } ))
em <- data.frame(goid,godescription,mitchtbl$pANOVA,mitchtbl$p.adjustANOVA,sign(mitchtbl$s.dist),mitchtbl$s.dist)
colnames(em) <- c("GO.ID","Description","p.Val","FDR","Phenotype","ES")
write.table(em,"de2mf_em.tsv",row.names = FALSE, quote=FALSE,sep="\t")

res <- subset(res,p.adjustANOVA<0.05)
resup <- subset(res,s.dist>0)
resdn <- subset(res,s.dist<0)
s <- c(head(resup$s.dist,10), head(resdn$s.dist,10))
names(s) <- c(head(resup$set,10),head(resdn$set,10))
s <- s[order(s)]
cols <- gsub("1","red",gsub("-1","blue",as.character(sign(s))))
par(mar=c(5,27,3,1))
barplot(abs(s),las=1,horiz=TRUE,col=cols,xlab="ES",cex.names=0.8,main="")

if (! file.exists("MDM_bystander_vs_latent.html") ) {
  mitch_report(mres2m,outfile="MDM_bystander_vs_latent.html")
}
networkplot(mres2m,FDR=0.05,n_sets=20)

network_genes(mres2m,FDR=0.05,n_sets=20)
## [[1]]
## [[1]]$`UP genesets.GO:0000122 negative regulation of transcription by RNA polymerase II`
##  [1] "EGR1"    "ZBTB10"  "ELK4"    "CIITA"   "RB1"     "MAFB"    "ZNF133" 
##  [8] "SNCA"    "FOXO1"   "ZHX2"    "CRY1"    "MDM2"    "MEF2C"   "HES1"   
## [15] "CBFA2T2" "PRKN"    "ETS2"    "URI1"    "SP2"     "PLAGL1"  "ZBTB20" 
## [22] "BCOR"    "NR6A1"   "KLF4"    "ASCL2"   "ZNF354C" "CUX1"    "WWC2"   
## [29] "ZFP36"   "NRIP1"  
## 
## [[1]]$`UP genesets.GO:0000785 chromatin`
##  [1] "EGR1"   "ELK4"   "AHR"    "DDB2"   "RB1"    "SPIN1"  "KDM3A"  "MAFB"  
##  [9] "KAT6A"  "TRIM24" "PDS5B"  "FOXO1"  "ZHX2"   "HES4"   "MEF2C"  "HES1"  
## [17] "ARID2"  "ETS2"   "TFCP2"  "SP2"    "RFX3"   "RCC1"   "HOXA10" "FANCC" 
## [25] "NR6A1"  "NFIA"   "POLA1"  "KLF4"   "ASCL2"  "ZBED4"  "CBX1"   "ESCO2" 
## [33] "CUX1"   "ASF1B"  "PBX2"   "NRIP1" 
## 
## [[1]]$`UP genesets.GO:0000977 RNA polymerase II transcription regulatory region sequence-specific DNA binding`
##  [1] "EGR1"   "ZBTB10" "RB1"    "ZNF133" "MEF2C"  "ZNF180" "ZNF391" "PLAGL1"
##  [9] "BCOR"   "ASCL2"  "ZBED4"  "CUX1"   "ZNF550" "PBX2"   "ZNF124"
## 
## [[1]]$`UP genesets.GO:0000978 RNA polymerase II cis-regulatory region sequence-specific DNA binding`
##  [1] "EGR1"    "ELK4"    "MAFB"    "FOXO1"   "HES4"    "ZNF718"  "ZNF658" 
##  [8] "MEF2C"   "ETS2"    "TFCP2"   "SP2"     "RFX3"    "ZNF37A"  "ZNF765" 
## [15] "ZNF713"  "PLAGL1"  "HOXA10"  "ZBTB20"  "NFIA"    "KLF4"    "ASCL2"  
## [22] "ZNF354C" "ZNF75D"  "ZNF678"  "NRIP1"  
## 
## [[1]]$`UP genesets.GO:0000981 DNA-binding transcription factor activity, RNA polymerase II-specific`
##  [1] "EGR1"    "ELK4"    "AHR"     "MAFB"    "ZNF133"  "FOXO1"   "ZHX2"   
##  [8] "HES4"    "ZNF718"  "MEF2C"   "HES1"    "ETS2"    "TFCP2"   "SP2"    
## [15] "RFX3"    "ZNF180"  "ZNF37A"  "ZNF391"  "ZNF765"  "ZNF713"  "HOXA10" 
## [22] "NR6A1"   "NFIA"    "ZNF654"  "KLF4"    "ASCL2"   "ZBED4"   "ZNF354C"
## [29] "ZNF75D"  "CUX1"    "ZNF678"  "ZNF550"  "PBX2"    "ZNF124" 
## 
## [[1]]$`UP genesets.GO:0001228 DNA-binding transcription activator activity, RNA polymerase II-specific`
##  [1] "EGR1"   "ELK4"   "MAFB"   "FOXO1"  "ZNF658" "MEF2C"  "TFCP2"  "PLAGL1"
##  [9] "HOXA10" "NR6A1"  "NFIA"   "KLF4"   "ASCL2"  "ZBED4"  "PBX2"  
## 
## [[1]]$`UP genesets.GO:0003682 chromatin binding`
##  [1] "TOP2A"  "ELK4"   "KAT6A"  "ERCC6"  "TRIM24" "FOXO1"  "MCM8"   "HES1"  
##  [9] "URI1"   "RCC1"   "NFIA"   "POLA1"  "CBX1"   "PBX2"  
## 
## [[1]]$`UP genesets.GO:0004672 protein kinase activity`
##  [1] "STK3"   "CCL2"   "TRIM24" "GUCY2C" "KSR1"   "DYRK1A" "TNNI3K" "GRK4"  
##  [9] "MAP3K1" "RASSF2" "PDK3"  
## 
## [[1]]$`UP genesets.GO:0005814 centriole`
## [1] "TOP2A"  "FBF1"   "TUBD1"  "CEP192" "SCLT1"  "CEP128" "CEP83"  "CEP97" 
## 
## [[1]]$`UP genesets.GO:0006355 regulation of DNA-templated transcription`
##  [1] "EMSY"    "AHR"     "RB1"     "SPIN1"   "MAFB"    "KAT6A"   "SLC39A8"
##  [8] "ZNF718"  "MEF2C"   "ATF7IP2" "SSBP2"   "RFX3"    "ZNF37A"  "ZNF713" 
## [15] "NFIA"    "ZNF654"  "WWC2"    "MTERF1"  "MLF1"    "ZNF678" 
## 
## [[1]]$`UP genesets.GO:0006357 regulation of transcription by RNA polymerase II`
##  [1] "EGR1"    "ZBTB10"  "ELK4"    "AHR"     "KDM3A"   "MAFB"    "KAT6A"  
##  [8] "ZNF133"  "FOXO1"   "ZHX2"    "HES4"    "ZNF718"  "ZNF658"  "HES1"   
## [15] "ARID2"   "ETS2"    "URI1"    "TFCP2"   "SP2"     "DYRK1A"  "PHIP"   
## [22] "RFX3"    "ZNF180"  "ZNF37A"  "ZNF391"  "ZNF765"  "ZNF713"  "HOXA10" 
## [29] "NR6A1"   "NFIA"    "ZNF654"  "EPM2A"   "KLF4"    "ZNF354C" "ZNF75D" 
## [36] "SSH2"    "CUX1"    "TCF20"   "ZNF678"  "ZNF550"  "ZNF124" 
## 
## [[1]]$`UP genesets.GO:0008270 zinc ion binding`
##  [1] "EGR1"    "ADA"     "ZCWPW2"  "RNF19B"  "KAT6A"   "TRIM24"  "SNCA"   
##  [8] "TAB3"    "MDM2"    "PRKN"    "ZMYND11" "ZFAND3"  "RC3H1"   "TUT7"   
## [15] "NR6A1"   "UBR7"    "AGTPBP1" "POLA1"   "KLF4"    "ZFAND4"  "MAP3K1" 
## [22] "ZNF75D"  "TIMP1"  
## 
## [[1]]$`UP genesets.GO:0030509 BMP signaling pathway`
## [1] "EGR1"   "SMURF1" "HES1"   "NFIA"  
## 
## [[1]]$`UP genesets.GO:0030658 transport vesicle membrane`
## [1] "ITPR2"    "HLA-DPB1"
## 
## [[1]]$`UP genesets.GO:0032395 MHC class II receptor activity`
## [1] "HLA-DOA"
## 
## [[1]]$`UP genesets.GO:0045944 positive regulation of transcription by RNA polymerase II`
##  [1] "TOP2A"   "PIK3R1"  "EGR1"    "ELK4"    "CIITA"   "AHR"     "RB1"    
##  [8] "HGF"     "KDM3A"   "MAFB"    "ERCC6"   "IGF1"    "FOXO1"   "PPP3R1" 
## [15] "TLR2"    "SLC40A1" "GTF2A1"  "ZNF658"  "MEF2C"   "HES1"    "PRKN"   
## [22] "ETS2"    "TFCP2"   "PHIP"    "SSBP2"   "RFX3"    "PLAGL1"  "HOXA10" 
## [29] "PAXBP1"  "NR6A1"   "NFIA"    "KLF4"    "ASCL2"   "ZBED4"   "SENP1"  
## [36] "TCF20"   "PPP2R5B" "PBX2"    "PPP3CA"  "NRIP1"  
## 
## [[1]]$`UP genesets.GO:0051056 regulation of small GTPase mediated signal transduction`
##  [1] "GARNL3"    "ARHGEF10L" "RHOD"      "ARHGAP6"   "STARD13"   "RAP1GAP2" 
##  [7] "NET1"      "VAV3"      "ARHGAP26"  "SRGAP3"   
## 
## [[1]]$`UP genesets.GO:0060070 canonical Wnt signaling pathway`
## [1] "EDA"   "STK3"  "FOXO1" "KLF4" 
## 
## [[1]]$`UP genesets.GO:0061470 T follicular helper cell differentiation`
## [1] "PIK3R1" "RC3H1"  "ASCL2" 
## 
## [[1]]$`UP genesets.GO:0071168 protein localization to chromatin`
## [1] "SPIN1" "MCM8"  "ESCO2"
## 
## [[1]]$`DOWN genesets.GO:0002181 cytoplasmic translation`
##  [1] "RPL7A"   "RPL3"    "RPS3"    "RPL8"    "RPS13"   "RACK1"   "RPL14"  
##  [8] "RPL29"   "RPL15"   "RPS9"    "RPL5"    "RPL11"   "RPL10"   "RPL12"  
## [15] "RPL28"   "RPS23"   "RPL6"    "RPL18"   "RPS8"    "DRG2"    "RPL10A" 
## [22] "RPS2"    "RPS5"    "RPL22"   "RPL17"   "RPS14"   "RPS7"    "RPS15"  
## [29] "RPL19"   "RPL4"    "RPS4X"   "RPS11"   "RPL26"   "RPL35A"  "RPL7"   
## [36] "RPL32"   "RPL22L1" "RPS15A"  "RPL24"   "RPS6"    "RPS25"   "RPL27"  
## [43] "RPS3A"   "UBA52"   "RPL23"   "RPL18A"  "RPL13A"  "RPL23A"  "RPS18"  
## [50] "RPL30"   "RPS24"   "RPL34"   "RPS27A"  "RPL31"   "FAU"     "RPL13"  
## [57] "RPS10"   "RPS16"   "RPL39"   "RPL37"   "RPL26L1" "RPS12"   "RPL21"  
## [64] "RPL41"   "RPL9"    "RPS27"   "RPL37A"  "RPL27A"  "RPS26"   "RPS21"  
## [71] "RPL36A"  "RPL36"   "RPS28"   "RPLP0"   "RPLP2"   "FTSJ1"   "RPL38"  
## [78] "DRG1"    "RPS29"   "RPS17"   "GTPBP1"  "RPL35"   "RPSA"    "RPS19"  
## [85] "ZC3H15"  "RPS20"   "RWDD1"   "RPLP1"  
## 
## [[1]]$`DOWN genesets.GO:0003985 acetyl-CoA C-acetyltransferase activity`
## [1] "ACAA1" "HADHB" "ACAT2" "ACAA2" "HADHA" "ACAT1"
## 
## [[1]]$`DOWN genesets.GO:0004298 threonine-type endopeptidase activity`
## [1] "PSMB10" "PSMB8"  "PSMB6"  "PSMB5"  "PSMB9"  "PSMB7"  "TASP1" 
## 
## [[1]]$`DOWN genesets.GO:0005839 proteasome core complex`
##  [1] "PSMB1"  "PSMA7"  "PSMB10" "PSMA3"  "PSMA2"  "PSMA6"  "PSMA5"  "PSMB8" 
##  [9] "PSMB3"  "PSMB6"  "PSMA1"  "PSMA4"  "PSMB4"  "PSMB5"  "PSMB9"  "PSMB2" 
## [17] "PSMF1"  "PSMB7" 
## 
## [[1]]$`DOWN genesets.GO:0006739 NADP metabolic process`
## [1] "G6PD"   "MDH1"   "DCXR"   "IDH1"   "IDH2"   "TP53I3" "PC"     "ME1"   
## [9] "NOCT"  
## 
## [[1]]$`DOWN genesets.GO:0015935 small ribosomal subunit`
##  [1] "RACK1"  "RPS4X"  "RPS6"   "RPS25"  "RPS18"  "RPS24"  "RPS27A" "FAU"   
##  [9] "RPS16"  "RPS26"  "RPS21"  "RPS28"  "RPS29"  "MRPS6" 
## 
## [[1]]$`DOWN genesets.GO:0015986 proton motive force-driven ATP synthesis`
##  [1] "ATP5PB"  "ATP5F1C" "ATP5PO"  "ATP5F1B" "ATP5MC3" "ATP5MG"  "ATP5MGL"
##  [8] "ATP5MC2" "ATP6V1A" "ATP5F1A" "ATP5F1D" "ATP5PD"  "ATP5ME"  "ATP5MF" 
## [15] "ATP6V0C" "ATP5PF"  "ATP5MC1" "ATP5F1E" "VPS9D1"  "MT-ATP8" "MT-ATP6"
## 
## [[1]]$`DOWN genesets.GO:0016018 cyclosporin A binding`
##  [1] "PPIA"  "PPIB"  "PPIE"  "PPIF"  "PPIG"  "NKTR"  "PPID"  "PPIH"  "PPIC" 
## [10] "PPIL6"
## 
## [[1]]$`DOWN genesets.GO:0019773 proteasome core complex, alpha-subunit complex`
## [1] "PSMA7" "PSMA3" "PSMA2" "PSMA6" "PSMA5" "PSMA1" "PSMA4"
## 
## [[1]]$`DOWN genesets.GO:0019774 proteasome core complex, beta-subunit complex`
##  [1] "PSMB1"  "PSMB10" "PSMB8"  "PSMB3"  "PSMB6"  "PSMB4"  "PSMB5"  "PSMB9" 
##  [9] "PSMB2"  "PSMB7" 
## 
## [[1]]$`DOWN genesets.GO:0019941 modification-dependent protein catabolic process`
## [1] "UBC"    "UBB"    "UBA52"  "NEDD8"  "RPS27A" "FAU"    "ISG15"  "UBA7"  
## 
## [[1]]$`DOWN genesets.GO:0022625 cytosolic large ribosomal subunit`
##  [1] "RPL7A"   "RPL3"    "RPL8"    "RPL14"   "RPL29"   "RPL15"   "RPL5"   
##  [8] "RPL11"   "RPL10"   "RPL12"   "RPL28"   "RPL6"    "RPL18"   "RPL10A" 
## [15] "RPL22"   "RPL17"   "RPL19"   "RPL4"    "RPL26"   "RPL35A"  "RPL7"   
## [22] "RPL36AL" "RPL32"   "RPL24"   "RPL27"   "UBA52"   "RPL23"   "RPL18A" 
## [29] "RPL13A"  "RPL23A"  "RPL30"   "RPL34"   "RPL31"   "RPL13"   "RPL39"  
## [36] "RPL37"   "RPL26L1" "RPL21"   "RPL41"   "RPL9"    "RPL37A"  "RPL27A" 
## [43] "RPL36A"  "RPL36"   "RPLP0"   "RPLP2"   "RPL38"   "RPL7L1"  "RPL35"  
## [50] "ZCCHC17" "RPL39L"  "RPLP1"  
## 
## [[1]]$`DOWN genesets.GO:0022627 cytosolic small ribosomal subunit`
##  [1] "RPS3"   "RPS13"  "RACK1"  "RPS9"   "RPS23"  "EIF2A"  "RPS8"   "RPS2"  
##  [9] "RPS5"   "RPS14"  "RPS7"   "RPS15"  "RPS4X"  "RPS11"  "RPS15A" "RPS6"  
## [17] "RPS25"  "RPS3A"  "RPS18"  "RPS24"  "RPS27A" "FAU"    "RPS10"  "RPS16" 
## [25] "RPS12"  "RPS27"  "LARP4"  "RPS26"  "RPS21"  "RPS28"  "RPS29"  "RPS17" 
## [33] "RPSA"   "RPS27L" "RPS19"  "DHX29"  "RPS20"  "RPS4Y1" "DDX3X" 
## 
## [[1]]$`DOWN genesets.GO:0034663 endoplasmic reticulum chaperone complex`
## [1] "PPIB"    "HSP90B1" "PDIA6"   "P4HB"    "HSPA5"   "DNAJB11" "DNAJC10"
## [8] "SDF2L1"  "HYOU1"  
## 
## [[1]]$`DOWN genesets.GO:0042776 proton motive force-driven mitochondrial ATP synthesis`
##  [1] "NDUFB5"  "NDUFB9"  "SDHD"    "SDHB"    "ATP5PB"  "NDUFC2"  "ATP5F1C"
##  [8] "ATP5PO"  "ATP5F1B" "NDUFA8"  "ATP5MG"  "NDUFA9"  "NDUFA10" "NDUFAB1"
## [15] "NDUFS2"  "NDUFA13" "NDUFS3"  "NDUFA12" "NDUFA3"  "NDUFS8"  "ATP5F1A"
## [22] "SDHC"    "STOML2"  "NDUFB11" "NDUFS4"  "NDUFB3"  "NDUFS7"  "NDUFB8" 
## [29] "ATP5F1D" "NDUFB4"  "NDUFA2"  "NDUFA7"  "NDUFV1"  "ATP5PD"  "ATP5ME" 
## [36] "NDUFV2"  "NDUFB10" "NDUFA5"  "NDUFC1"  "MT-ND6"  "NDUFA11" "ATP5MF" 
## [43] "NDUFS5"  "NDUFA1"  "NDUFB7"  "ATP5PF"  "NDUFS1"  "NDUFB2"  "NDUFB1" 
## [50] "ATP5F1E" "NDUFA6"  "MT-ND3"  "NDUFS6"  "MT-ND4"  "NDUFB6"  "MT-ATP8"
## [57] "MT-ATP6" "NDUFV3"  "MT-ND4L" "SDHA"    "MT-ND1"  "MT-ND5"  "MT-ND2" 
## 
## [[1]]$`DOWN genesets.GO:0045259 proton-transporting ATP synthase complex`
##  [1] "ATP5PB"  "ATP5F1C" "ATP5PO"  "ATP5F1B" "ATP5MG"  "ATP5F1A" "ATP5F1D"
##  [8] "ATP5PD"  "ATP5ME"  "ATP5MF"  "ATP5PF"  "ATP5MC1" "ATP5F1E" "MT-ATP8"
## [15] "MT-ATP6"
## 
## [[1]]$`DOWN genesets.GO:0045271 respiratory chain complex I`
##  [1] "NDUFB5"  "NDUFB9"  "NDUFC2"  "NDUFA8"  "NDUFA9"  "NDUFA10" "NDUFAB1"
##  [8] "NDUFS2"  "NDUFA13" "NDUFS3"  "NDUFA12" "NDUFA3"  "NDUFS8"  "NDUFB11"
## [15] "NDUFS4"  "NDUFB3"  "NDUFS7"  "NDUFB8"  "NDUFB4"  "NDUFA2"  "NDUFA7" 
## [22] "NDUFV1"  "NDUFV2"  "NDUFB10" "NDUFA5"  "NDUFC1"  "MT-ND6"  "NDUFA11"
## [29] "NDUFS5"  "NDUFA1"  "NDUFB7"  "NDUFS1"  "NDUFB2"  "NDUFB1"  "NDUFA6" 
## [36] "MT-ND3"  "NDUFS6"  "MT-ND4"  "NDUFB6"  "NDUFV3"  "MT-ND4L" "MT-ND1" 
## [43] "MT-ND5"  "MT-ND2" 
## 
## [[1]]$`DOWN genesets.GO:0045275 respiratory chain complex III`
##  [1] "CYC1"    "UQCRB"   "UQCRFS1" "BCS1L"   "UQCRH"   "UQCRC2"  "UQCR10" 
##  [8] "UQCR11"  "UQCRC1"  "UQCRQ"   "MT-CYB"  "UQCRHL" 
## 
## [[1]]$`DOWN genesets.GO:0046933 proton-transporting ATP synthase activity, rotational mechanism`
##  [1] "ATP5PB"  "ATP5F1C" "ATP5PO"  "ATP5F1B" "ATP5MG"  "ATP5MGL" "ATP6V1A"
##  [8] "ATP5F1A" "ATP5F1D" "ATP5PD"  "ATP5ME"  "ATP5MF"  "ATP6V0C" "ATP5PF" 
## [15] "ATP5F1E" "MT-ATP8" "MT-ATP6"
## 
## [[1]]$`DOWN genesets.GO:0071541 eukaryotic translation initiation factor 3 complex, eIF3m`
## [1] "EIF3D" "EIF3M" "EIF3I" "EIF3F" "EIF3H" "EIF3A" "EIF3B"

Alv cells.

pb2a <- pbalv[,c(grep("bystander",colnames(pbalv)),grep("latent",colnames(pbalv)))]
head(pb2a)
##               alv_bystander1 alv_bystander2 alv_bystander3 alv_latent1
## HIV-Gagp17               106            162            183        2306
## HIV-Gagp24                 0              0              0           0
## HIV-Gagp2p7               16             26             17          69
## HIV-Gagp1Pol              26             50             42         129
## HIV-Polprot              208            515            534        1465
## HIV-Polp15p31            476           1203           1151        2414
##               alv_latent2 alv_latent3
## HIV-Gagp17           1784        2576
## HIV-Gagp24              0           0
## HIV-Gagp2p7           104         121
## HIV-Gagp1Pol          163         210
## HIV-Polprot          2065        3280
## HIV-Polp15p31        4070        5631
pb2af <- pb2a[which(rowMeans(pb2a)>=10),]
head(pb2af)
##               alv_bystander1 alv_bystander2 alv_bystander3 alv_latent1
## HIV-Gagp17               106            162            183        2306
## HIV-Gagp2p7               16             26             17          69
## HIV-Gagp1Pol              26             50             42         129
## HIV-Polprot              208            515            534        1465
## HIV-Polp15p31            476           1203           1151        2414
## HIV-Vif                   31             78             86         173
##               alv_latent2 alv_latent3
## HIV-Gagp17           1784        2576
## HIV-Gagp2p7           104         121
## HIV-Gagp1Pol          163         210
## HIV-Polprot          2065        3280
## HIV-Polp15p31        4070        5631
## HIV-Vif               322         423
colSums(pb2af)
## alv_bystander1 alv_bystander2 alv_bystander3    alv_latent1    alv_latent2 
##       58217374       65486247       58735478        7238086        4203761 
##    alv_latent3 
##        5271201
des2a <- as.data.frame(grepl("latent",colnames(pb2af)))
colnames(des2a) <- "case"

plot(cmdscale(dist(t(pb2af))), xlab="Coordinate 1", ylab="Coordinate 2",
  type = "p",pch=19,col="gray",cex=2)

text(cmdscale(dist(t(pb2af))), labels=colnames(pb2af) )

des2a$sample <- rep(1:3,2)

dds <- DESeqDataSetFromMatrix(countData = pb2af , colData = des2a, design = ~ sample + case)
## converting counts to integer mode
##   the design formula contains one or more numeric variables with integer values,
##   specifying a model with increasing fold change for higher values.
##   did you mean for this to be a factor? if so, first convert
##   this variable to a factor using the factor() function
res <- DESeq(dds)
## estimating size factors
## estimating dispersions
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## fitting model and testing
z <- results(res)
vsd <- vst(dds, blind=FALSE)
zz <- cbind(as.data.frame(z),assay(vsd))
de <- as.data.frame(zz[order(zz$pvalue),])
de2af <- de
write.table(de2af,"de2af.tsv",sep="\t")

nrow(subset(de2af,padj<0.05 & log2FoldChange>0))
## [1] 129
nrow(subset(de2af,padj<0.05 & log2FoldChange<0))
## [1] 18
head(subset(de2af, log2FoldChange>0),10)[,1:6] %>%
  kbl(caption="Top upregulated genes in latent compared to bystander (Alv paired)") %>%
  kable_paper("hover", full_width = F)
Top upregulated genes in latent compared to bystander (Alv paired)
baseMean log2FoldChange lfcSE stat pvalue padj
HIV-Gagp17 3883.4893 7.478760 0.1268825 58.94243 0 0
HIV-BaLEnv 7093.0345 6.767764 0.2077302 32.57959 0 0
HIV-Polprot 4223.1618 6.055481 0.2108850 28.71461 0 0
HIV-TatEx1 884.5283 6.048266 0.2361235 25.61484 0 0
HIV-Nef 4865.1335 5.228768 0.2168170 24.11604 0 0
HIV-Polp15p31 7626.1756 5.722092 0.2567299 22.28837 0 0
HIV-Gagp1Pol 309.1866 5.696556 0.2731985 20.85134 0 0
HIV-Vif 580.6007 5.886159 0.2911749 20.21520 0 0
HIV-EnvStart 143.5971 5.560129 0.2872099 19.35911 0 0
HIV-TatEx2Rev 174.7315 6.304501 0.3579902 17.61082 0 0 
head(subset(de2af, log2FoldChange<0),10)[,1:6] %>%
  kbl(caption="Top downregulated genes in latent compared to bystander (Alv paired)") %>%
  kable_paper("hover", full_width = F)
Top downregulated genes in latent compared to bystander (Alv paired)
baseMean log2FoldChange lfcSE stat pvalue padj
FBP1 11600.57229 -0.5316647 0.1131745 -4.697742 0.0000026 0.0007527
KCNMA1 2773.61123 -0.6607014 0.1536891 -4.298948 0.0000172 0.0038464
ERP29 2954.75815 -0.5833641 0.1433450 -4.069650 0.0000471 0.0087342
HIST1H1C 789.48480 -0.8612194 0.2124561 -4.053634 0.0000504 0.0091643
FLRT2 460.87686 -0.7263502 0.1795683 -4.044980 0.0000523 0.0093827
MT-ND6 821.08506 -0.9093873 0.2275406 -3.996593 0.0000643 0.0108022
ZNF804A 1304.54050 -0.6201855 0.1647291 -3.764882 0.0001666 0.0214047
TNIK 1315.46385 -0.5598225 0.1512009 -3.702508 0.0002135 0.0251830
ATP8B4 1444.11342 -0.6842583 0.1859069 -3.680651 0.0002326 0.0269701
LTB4R 65.70184 -1.3610716 0.3737966 -3.641210 0.0002714 0.0306660 
m2a <- mitch_import(de,DEtype="deseq2",joinType="full")
## The input is a single dataframe; one contrast only. Converting
##         it to a list for you.
## Note: Mean no. genes in input = 16291
## Note: no. genes in output = 16291
## Note: estimated proportion of input genes in output = 1
mres2a <- mitch_calc(m2a,genesets=go,minsetsize=5,cores=4,priority="effect")
## Note: Enrichments with large effect sizes may not be
##             statistically significant.
res <- mres2a$enrichment_result

mitchtbl <- mres2a$enrichment_result
goid <- sapply(strsplit(mitchtbl$set," "),"[[",1)
mysplit <- strsplit(mitchtbl$set," ")
mysplit <- lapply(mysplit, function(x) { x[2:length(x)] } )
godescription <- unlist(lapply(mysplit, function(x) { paste(x,collapse=" ") } ))
em <- data.frame(goid,godescription,mitchtbl$pANOVA,mitchtbl$p.adjustANOVA,sign(mitchtbl$s.dist),mitchtbl$s.dist)
colnames(em) <- c("GO.ID","Description","p.Val","FDR","Phenotype","ES")
write.table(em,"de2af_em.tsv",row.names = FALSE, quote=FALSE,sep="\t")

res <- subset(res,p.adjustANOVA<0.05)
resup <- subset(res,s.dist>0)
resdn <- subset(res,s.dist<0)
s <- c(head(resup$s.dist,10), head(resdn$s.dist,10))
names(s) <- c(head(resup$set,10),head(resdn$set,10))
s <- s[order(s)]
cols <- gsub("1","red",gsub("-1","blue",as.character(sign(s))))
par(mar=c(5,27,3,1))
barplot(abs(s),las=1,horiz=TRUE,col=cols,xlab="ES",cex.names=0.8,main="")

if (! file.exists("Alv_bystander_vs_latent.html") ) {
  mitch_report(mres2a,outfile="Alv_bystander_vs_latent.html")
}
networkplot(mres2a,FDR=0.05,n_sets=20)

network_genes(mres2a,FDR=0.05,n_sets=20)
## [[1]]
## [[1]]$`UP genesets.GO:0003925 G protein activity`
## [1] "RALA"  "RAB1B" "GNA13" "NRAS"  "GNAS" 
## 
## [[1]]$`UP genesets.GO:0004017 adenylate kinase activity`
## [1] "AK3" "AK8" "AK1"
## 
## [[1]]$`UP genesets.GO:0005744 TIM23 mitochondrial import inner membrane translocase complex`
## character(0)
## 
## [[1]]$`UP genesets.GO:0005758 mitochondrial intermembrane space`
##  [1] "ARL2BP"  "CMC4"    "TRIAP1"  "REXO2"   "TIMM10B" "HAX1"    "TIMM8A" 
##  [8] "NDUFS5"  "COX17"   "BLOC1S1" "CHCHD7" 
## 
## [[1]]$`UP genesets.GO:0005762 mitochondrial large ribosomal subunit`
## [1] "MRPL41" "MRPL33" "MRPL52" "MRPL42"
## 
## [[1]]$`UP genesets.GO:0006091 generation of precursor metabolites and energy`
## [1] "COX17" "POMC"  "COX7C"
## 
## [[1]]$`UP genesets.GO:0006626 protein targeting to mitochondrion`
## [1] "BID"   "TOMM5"
## 
## [[1]]$`UP genesets.GO:0006695 cholesterol biosynthetic process`
## [1] "INSIG1" "DHCR24" "DHCR7"  "EBP"    "CYB5R3"
## 
## [[1]]$`UP genesets.GO:0006783 heme biosynthetic process`
## [1] "SLC25A39" "TMEM14C"  "UROS"    
## 
## [[1]]$`UP genesets.GO:0006882 intracellular zinc ion homeostasis`
## [1] "MT1G"     "ATP13A2"  "MT1H"     "MT1F"     "MT1X"     "SLC39A13"
## 
## [[1]]$`UP genesets.GO:0016226 iron-sulfur cluster assembly`
## [1] "FDX2"  "ISCA1" "CIAO1" "BOLA3" "ISCU"  "LYRM4"
## 
## [[1]]$`UP genesets.GO:0032418 lysosome localization`
## [1] "BLOC1S2" "RNF167"  "DEF8"    "BLOC1S1" "PLEKHM1"
## 
## [[1]]$`UP genesets.GO:0033617 mitochondrial cytochrome c oxidase assembly`
## [1] "COX17" "SURF1" "COX18" "COA8" 
## 
## [[1]]$`UP genesets.GO:0044571 [2Fe-2S] cluster assembly`
## [1] "FDX2"  "ISCU"  "LYRM4"
## 
## [[1]]$`UP genesets.GO:0051537 2 iron, 2 sulfur cluster binding`
## [1] "FDX2"     "SLC25A39" "CISD3"    "ISCA1"    "CISD2"    "ISCU"    
## 
## [[1]]$`UP genesets.GO:0051881 regulation of mitochondrial membrane potential`
## [1] "TUSC2" "SOD2" 
## 
## [[1]]$`UP genesets.GO:0071280 cellular response to copper ion`
## [1] "SNCA" "MT1G" "MT1H" "MT1F" "MT1X"
## 
## [[1]]$`UP genesets.GO:0098803 respiratory chain complex`
## [1] "COX7A2" "UQCRH"  "SURF1" 
## 
## [[1]]$`UP genesets.GO:0106035 protein maturation by [4Fe-4S] cluster transfer`
## [1] "BOLA3"
## 
## [[1]]$`UP genesets.GO:1990229 iron-sulfur cluster assembly complex`
## [1] "FDX2"  "BOLA3" "ISCU"  "LYRM4"
## 
## [[1]]$`DOWN genesets.GO:0000228 nuclear chromosome`
##  [1] "BIRC5"   "PBRM1"   "SPIDR"   "SETX"    "RAD51"   "TOP1"    "EXOSC9" 
##  [8] "HNRNPU"  "HDAC8"   "IK"      "TOP2A"   "TERF2IP" "BAZ1A"   "SMARCE1"
## [15] "PINX1"   "SMARCB1" "ATRX"    "BLM"     "FIGNL1"  "JUN"     "NCAPD2" 
## [22] "SMC2"    "CHD1"   
## 
## [[1]]$`DOWN genesets.GO:0000727 double-strand break repair via break-induced replication`
##  [1] "CDC45"  "MCM7"   "MCM3"   "MCM6"   "MCM2"   "MCM4"   "GINS4"  "GINS2" 
##  [9] "CDC7"   "MUS81"  "MCMDC2" "MCM5"  
## 
## [[1]]$`DOWN genesets.GO:0003688 DNA replication origin binding`
##  [1] "POLA1" "CDC45" "DHX9"  "HSPD1" "MCM10" "ORC1"  "MCM2"  "ORC4"  "KAT7" 
## [10] "CDC6"  "ORC5"  "DDX11" "GRWD1" "ORC3"  "ORC2"  "MCM5" 
## 
## [[1]]$`DOWN genesets.GO:0006265 DNA topological change`
##  [1] "TDRD3"  "HMGB2"  "TOP1"   "TOP2A"  "TOP1MT" "TOP2B"  "HMGB1"  "ERCC3" 
##  [9] "TOP3B"  "TOP3A" 
## 
## [[1]]$`DOWN genesets.GO:0006271 DNA strand elongation involved in DNA replication`
## [1] "POLA1" "RFC3"  "MCM7"  "MCM3"  "POLD2" "MCM4"  "POLD3" "RFC4" 
## 
## [[1]]$`DOWN genesets.GO:0006353 DNA-templated transcription termination`
##  [1] "SMN1"   "SETX"   "DHX9"   "TTF2"   "POLR2A" "PRMT5"  "WDR82"  "TTF1"  
##  [9] "MTERF1" "ZC3H4" 
## 
## [[1]]$`DOWN genesets.GO:0008094 ATP-dependent activity, acting on DNA`
##  [1] "RAD51B"   "RFC3"     "RBBP4"    "SMARCA2"  "RAD51"    "XRCC5"   
##  [7] "INO80"    "XRCC6"    "BPTF"     "CHD6"     "TOP2A"    "TTF2"    
## [13] "MSH6"     "IGHMBP2"  "BTAF1"    "SMARCA4"  "ERCC6"    "MSH2"    
## [19] "HLTF"     "CDK7"     "DDX11"    "BLM"      "SMARCAL1" "DHX36"   
## [25] "RAD51D"   "MYO18A"  
## 
## [[1]]$`DOWN genesets.GO:0008353 RNA polymerase II CTD heptapeptide repeat kinase activity`
## [1] "CDK1"   "CDK13"  "DYRK1A" "CDK12"  "CDK9"   "BRD4"   "CDK7"   "MAPK1" 
## [9] "CCNK"  
## 
## [[1]]$`DOWN genesets.GO:0019864 IgG binding`
## [1] "FCER1G" "FCGRT"  "FCGR1A" "FCGR2B" "FCGR3A" "FCGR2A"
## 
## [[1]]$`DOWN genesets.GO:0038094 Fc-gamma receptor signaling pathway`
## [1] "FCER1G" "FCGR1A" "FCGR2B" "FCGR3A" "CD247"  "CLEC4E" "FCGR2A" "CD33"  
## 
## [[1]]$`DOWN genesets.GO:0042555 MCM complex`
##  [1] "MCM7"   "MCM3"   "MCM6"   "MCMBP"  "MCM2"   "MCM4"   "MCM9"   "MCM8"  
##  [9] "MMS22L" "TONSL"  "MCM5"  
## 
## [[1]]$`DOWN genesets.GO:0044027 negative regulation of gene expression via chromosomal CpG island methylation`
##  [1] "HELLS"    "DNMT1"    "MECP2"    "CTCF"     "MYC"      "BRCA1"   
##  [7] "UHRF1"    "UHRF2"    "DNMT3A"   "PRMT5"    "MPHOSPH8" "USP7"    
## [13] "ZNF445"   "EHMT2"   
## 
## [[1]]$`DOWN genesets.GO:0071162 CMG complex`
##  [1] "CDC45" "MCM7"  "MCM3"  "MCM6"  "MCM2"  "MCM4"  "GINS4" "GINS2" "GINS1"
## [10] "GINS3" "MCM5" 
## 
## [[1]]$`DOWN genesets.GO:0140092 bBAF complex`
## [1] "SMARCA2" "ARID1A"  "SMARCC2" "SMARCA4" "ARID1B"  "SMARCE1" "SMARCD2"
## [8] "SMARCB1" "ACTB"   
## 
## [[1]]$`DOWN genesets.GO:0140833 RNA polymerase II CTD heptapeptide repeat Y1 kinase activity`
## [1] "CDK1"  "CDK13" "CDK8"  "CDK12" "CDK9"  "CDK7" 
## 
## [[1]]$`DOWN genesets.GO:0140834 RNA polymerase II CTD heptapeptide repeat S2 kinase activity`
## [1] "CDK1"  "CDK13" "CDK8"  "CDK12" "CDK9"  "CDK7" 
## 
## [[1]]$`DOWN genesets.GO:0140835 RNA polymerase II CTD heptapeptide repeat T4 kinase activity`
## [1] "CDK1"  "CDK13" "CDK8"  "CDK12" "CDK9"  "CDK7" 
## 
## [[1]]$`DOWN genesets.GO:0140836 RNA polymerase II CTD heptapeptide repeat S5 kinase activity`
## [1] "CDK1"  "CDK13" "CDK8"  "CDK12" "CDK9"  "CDK7" 
## 
## [[1]]$`DOWN genesets.GO:0140837 RNA polymerase II CTD heptapeptide repeat S7 kinase activity`
## [1] "CDK1"  "CDK13" "CDK8"  "CDK12" "CDK9"  "CDK7" 
## 
## [[1]]$`DOWN genesets.GO:1905665 positive regulation of calcium ion import across plasma membrane`
## [1] "AKAP5"  "PPP3CA" "PPP3CC" "PPP3R1" "P2RX1"  "PPP3CB" "P2RX5"

Combined.

mm2 <- merge(m2a,m2m,by=0)

head(mm2)
##   Row.names        x.x         x.y
## 1      A1BG  1.4498277 -0.31296863
## 2  A1BG-AS1  0.5306624  0.30818540
## 3       A2M -0.4846264 -0.60355175
## 4   A2M-AS1 -0.8483824  0.03503586
## 5 A2ML1-AS1 -1.1363073  0.63891414
## 6      AAAS  0.3012506  0.06893024
rownames(mm2) <- mm2[,1]
mm2[,1]=NULL
colnames(mm2) <- c("Alv","MDM")
plot(mm2)
mylm <- lm(mm2)
abline(mylm,col="red",lty=2,lwd=3)

summary(mylm)
## 
## Call:
## lm(formula = mm2)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -4.415 -0.782 -0.072  0.679 53.901 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 0.055151   0.011184   4.931 8.26e-07 ***
## MDM         0.264968   0.009284  28.539  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.357 on 14736 degrees of freedom
## Multiple R-squared:  0.05238,    Adjusted R-squared:  0.05231 
## F-statistic: 814.5 on 1 and 14736 DF,  p-value: < 2.2e-16
cor.test(mm2$Alv,mm2$MDM)
## 
##  Pearson's product-moment correlation
## 
## data:  mm2$Alv and mm2$MDM
## t = 28.539, df = 14736, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.2135053 0.2441043
## sample estimates:
##       cor 
## 0.2288613
mm2r <- as.data.frame(apply(mm2,2,rank))
plot(mm2r,cex=0.3)
mylm <- lm(mm2r)
abline(mylm,col="red",lty=2,lwd=3)

summary(mylm)
## 
## Call:
## lm(formula = mm2r)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -7715.4 -3694.2   -10.7  3673.6  7715.2 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  7.716e+03  7.002e+01 110.202  < 2e-16 ***
## MDM         -4.708e-02  8.229e-03  -5.722 1.07e-08 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4250 on 14736 degrees of freedom
## Multiple R-squared:  0.002217,   Adjusted R-squared:  0.002149 
## F-statistic: 32.74 on 1 and 14736 DF,  p-value: 1.075e-08
cor.test(mm2r$Alv,mm2r$MDM)
## 
##  Pearson's product-moment correlation
## 
## data:  mm2r$Alv and mm2r$MDM
## t = -5.7218, df = 14736, p-value = 1.075e-08
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.06317936 -0.03096113
## sample estimates:
##         cor 
## -0.04708249

DE3 Active vs mock

MDM group.

pb3m <- pbmdm[,c(grep("active",colnames(pbmdm)),grep("mock",colnames(pbmdm)))]

head(pb3m)
##               mdm_active1 mdm_active2 mdm_active3 mdm_active4 mdm_mock1
## HIV-Gagp17          38092       23541       40568       15110       117
## HIV-Gagp24              0           0           0           0         0
## HIV-Gagp2p7          1462        1021        2365         414         5
## HIV-Gagp1Pol         2021        1375        3032         785         7
## HIV-Polprot         27388       18583       44857        9126       136
## HIV-Polp15p31       75686       55267      105649       14984       341
##               mdm_mock2 mdm_mock3 mdm_mock4
## HIV-Gagp17          253        37       159
## HIV-Gagp24            0         0         0
## HIV-Gagp2p7           8         1         5
## HIV-Gagp1Pol         14         3        13
## HIV-Polprot         196        47       146
## HIV-Polp15p31       550       101       257
pb3mf <- pb3m[which(rowMeans(pb3m)>=10),]
head(pb3mf)
##               mdm_active1 mdm_active2 mdm_active3 mdm_active4 mdm_mock1
## HIV-Gagp17          38092       23541       40568       15110       117
## HIV-Gagp2p7          1462        1021        2365         414         5
## HIV-Gagp1Pol         2021        1375        3032         785         7
## HIV-Polprot         27388       18583       44857        9126       136
## HIV-Polp15p31       75686       55267      105649       14984       341
## HIV-Vif              5276        4254        7255        1109        15
##               mdm_mock2 mdm_mock3 mdm_mock4
## HIV-Gagp17          253        37       159
## HIV-Gagp2p7           8         1         5
## HIV-Gagp1Pol         14         3        13
## HIV-Polprot         196        47       146
## HIV-Polp15p31       550       101       257
## HIV-Vif              45         8        17
colSums(pb3mf)
## mdm_active1 mdm_active2 mdm_active3 mdm_active4   mdm_mock1   mdm_mock2 
##    29532716    22439063    25242866    13852866    28545021    20536722 
##   mdm_mock3   mdm_mock4 
##     7022107    20628091
des3m <- as.data.frame(grepl("active",colnames(pb3mf)))
colnames(des3m) <- "case"

plot(cmdscale(dist(t(pb3mf))), xlab="Coordinate 1", ylab="Coordinate 2",
  type = "p",pch=19,col="gray",cex=2)

text(cmdscale(dist(t(pb3mf))), labels=colnames(pb3mf) )

des3m$sample <- rep(1:4,2)

dds <- DESeqDataSetFromMatrix(countData = pb3mf , colData = des3m, design = ~ sample + case)
## converting counts to integer mode
##   the design formula contains one or more numeric variables with integer values,
##   specifying a model with increasing fold change for higher values.
##   did you mean for this to be a factor? if so, first convert
##   this variable to a factor using the factor() function
res <- DESeq(dds)
## estimating size factors
## estimating dispersions
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## fitting model and testing
z <- results(res)
vsd <- vst(dds, blind=FALSE)
zz <- cbind(as.data.frame(z),assay(vsd))
de <- as.data.frame(zz[order(zz$pvalue),])
de3mf <- de
write.table(de3mf,"de3mf.tsv",sep="\t")

nrow(subset(de3mf,padj<0.05 & log2FoldChange>0))
## [1] 331
nrow(subset(de3mf,padj<0.05 & log2FoldChange<0))
## [1] 482
head(subset(de3mf,padj<0.05 & log2FoldChange>0),10)[,1:6] %>%
  kbl(caption="Top upregulated genes in active MDM cells compared to mock") %>%
  kable_paper("hover", full_width = F)
Top upregulated genes in active MDM cells compared to mock
baseMean log2FoldChange lfcSE stat pvalue padj
HIV-Gagp17 12498.4369 7.501364 0.3158859 23.74707 0 0
HIV-Polprot 10407.8721 7.303870 0.3339530 21.87096 0 0
HIV-TatEx1 1135.6725 7.144389 0.3282006 21.76836 0 0
HIV-BaLEnv 16603.6070 7.389094 0.3399286 21.73719 0 0
HIV-Polp15p31 25546.9540 7.367479 0.3816660 19.30347 0 0
HIV-Gagp1Pol 760.7351 7.361945 0.3950080 18.63746 0 0
HIV-Vpu 279.0444 5.666870 0.3114660 18.19418 0 0
HIV-EGFP 391.0342 7.640811 0.4461126 17.12754 0 0
HIV-EnvStart 232.1886 6.838465 0.4214554 16.22583 0 0
HIV-Vif 1824.6706 7.384595 0.4563273 16.18267 0 0 
head(subset(de1mf,padj<0.05 & log2FoldChange<0),10)[,1:6] %>%
  kbl(caption="Top downregulated genes in active MDM cells compared to mock") %>%
  kable_paper("hover", full_width = F)
Top downregulated genes in active MDM cells compared to mock
baseMean log2FoldChange lfcSE stat pvalue padj
PDE4B 111.80062 -3.307095 0.3853403 -8.582270 0 0.0e+00
STAB1 58.70194 -5.220943 0.6780455 -7.699988 0 0.0e+00
VAMP5 158.27240 -1.835932 0.2578050 -7.121397 0 0.0e+00
FCN1 82.63210 -3.108742 0.4481621 -6.936648 0 0.0e+00
VCAN 16.54526 -4.682256 0.7056837 -6.635063 0 1.0e-07
PDE7B 32.06724 -3.887577 0.6089721 -6.383836 0 3.0e-07
SESN3 60.20373 -2.125609 0.3342092 -6.360116 0 3.0e-07
MS4A6A 293.46672 -3.015229 0.4809701 -6.269057 0 5.0e-07
FGL2 72.58902 -3.292405 0.5370701 -6.130308 0 1.1e-06
SSBP2 60.95534 -3.024786 0.4988879 -6.063057 0 1.3e-06 
m3m <- mitch_import(de,DEtype="deseq2",joinType="full")
## The input is a single dataframe; one contrast only. Converting
##         it to a list for you.
## Note: Mean no. genes in input = 14556
## Note: no. genes in output = 14556
## Note: estimated proportion of input genes in output = 1
mres3m <- mitch_calc(m3m,genesets=go,minsetsize=5,cores=4,priority="effect")
## Note: Enrichments with large effect sizes may not be
##             statistically significant.
res <- mres3m$enrichment_result

mitchtbl <- mres3m$enrichment_result
goid <- sapply(strsplit(mitchtbl$set," "),"[[",1)
mysplit <- strsplit(mitchtbl$set," ")
mysplit <- lapply(mysplit, function(x) { x[2:length(x)] } )
godescription <- unlist(lapply(mysplit, function(x) { paste(x,collapse=" ") } ))
em <- data.frame(goid,godescription,mitchtbl$pANOVA,mitchtbl$p.adjustANOVA,sign(mitchtbl$s.dist),mitchtbl$s.dist)
colnames(em) <- c("GO.ID","Description","p.Val","FDR","Phenotype","ES")
write.table(em,"de3mf_em.tsv",row.names = FALSE, quote=FALSE,sep="\t")

res <- subset(res,p.adjustANOVA<0.05)
resup <- subset(res,s.dist>0)
resdn <- subset(res,s.dist<0)
s <- c(head(resup$s.dist,10), head(resdn$s.dist,10))
names(s) <- c(head(resup$set,10),head(resdn$set,10))
s <- s[order(s)]
cols <- gsub("1","red",gsub("-1","blue",as.character(sign(s))))
par(mar=c(5,27,3,1))
barplot(abs(s),las=1,horiz=TRUE,col=cols,xlab="ES",cex.names=0.8,main="")

if (! file.exists("MDM_mock_vs_active.html") ) {
  mitch_report(mres3m,outfile="MDM_mock_vs_active.html")
}
networkplot(mres3m,FDR=0.05,n_sets=20)

network_genes(mres3m,FDR=0.05,n_sets=20)
## [[1]]
## [[1]]$`UP genesets.GO:0000502 proteasome complex`
##  [1] "PSMD8"  "RAD23A" "PSMC5"  "PSMB2"  "PSMA7"  "RAD23B" "PSMC4"  "PSMA4" 
##  [9] "PSMA6"  "PSMC3"  "PSMD3"  "PSMB1" 
## 
## [[1]]$`UP genesets.GO:0004532 RNA exonuclease activity`
## [1] "EXOSC1" "EXOSC8"
## 
## [[1]]$`UP genesets.GO:0005179 hormone activity`
## [1] "GDF15" "STC2"  "CCN3"  "EDN1"  "ADM2"  "NMB"  
## 
## [[1]]$`UP genesets.GO:0005744 TIM23 mitochondrial import inner membrane translocase complex`
## character(0)
## 
## [[1]]$`UP genesets.GO:0005761 mitochondrial ribosome`
## [1] "MRPL18" "MRPS22" "MRPL43"
## 
## [[1]]$`UP genesets.GO:0005762 mitochondrial large ribosomal subunit`
## [1] "MRPL18" "MRPL42" "MRPL43" "MRPL3" 
## 
## [[1]]$`UP genesets.GO:0005763 mitochondrial small ribosomal subunit`
## [1] "MRPS16"   "MRPL42"   "MRPS15"   "MRPS10"   "MRPS22"   "AURKAIP1"
## 
## [[1]]$`UP genesets.GO:0005839 proteasome core complex`
## [1] "PSMB2" "PSMA7" "PSMA4" "PSMA6" "PSMB1"
## 
## [[1]]$`UP genesets.GO:0008540 proteasome regulatory particle, base subcomplex`
## [1] "PSMC5" "PSMC4" "PSMC3"
## 
## [[1]]$`UP genesets.GO:0008541 proteasome regulatory particle, lid subcomplex`
## [1] "PSMD8" "PSMD3"
## 
## [[1]]$`UP genesets.GO:0016226 iron-sulfur cluster assembly`
## [1] "CIAO2B" "NUBPL"  "BOLA1" 
## 
## [[1]]$`UP genesets.GO:0019773 proteasome core complex, alpha-subunit complex`
## [1] "PSMA7" "PSMA4" "PSMA6"
## 
## [[1]]$`UP genesets.GO:0022624 proteasome accessory complex`
## [1] "PSMD8" "PSMC5" "PSMC4" "PSMC3" "PSMD3"
## 
## [[1]]$`UP genesets.GO:0030150 protein import into mitochondrial matrix`
## character(0)
## 
## [[1]]$`UP genesets.GO:0032543 mitochondrial translation`
## [1] "MRPS16"   "MRPL18"   "MRPL42"   "MRPS15"   "MRPS10"   "MRPS22"   "MRPL43"  
## [8] "MRPL3"    "AURKAIP1"
## 
## [[1]]$`UP genesets.GO:0036402 proteasome-activating activity`
## [1] "PSMC5" "PSMC4" "PSMC3"
## 
## [[1]]$`UP genesets.GO:0061025 membrane fusion`
## [1] "DPP4"  "VTI1B" "YKT6" 
## 
## [[1]]$`UP genesets.GO:0101019 nucleolar exosome (RNase complex)`
## [1] "EXOSC1" "EXOSC8"
## 
## [[1]]$`UP genesets.GO:0101031 protein folding chaperone complex`
## [1] "PSMG1"  "DNAJC9" "SPAG1"  "UXT"    "BAG3"   "CCDC47"
## 
## [[1]]$`UP genesets.GO:1990229 iron-sulfur cluster assembly complex`
## [1] "BOLA1"
## 
## [[1]]$`DOWN genesets.GO:0002503 peptide antigen assembly with MHC class II protein complex`
##  [1] "HLA-DPA1" "HLA-DMA"  "HLA-DPB1" "HLA-DRA"  "HLA-DRB1" "HLA-DMB" 
##  [7] "HLA-DOA"  "HLA-DQA1" "HLA-DQB1" "HLA-DRB5" "HLA-DQA2" "B2M"     
## 
## [[1]]$`DOWN genesets.GO:0005942 phosphatidylinositol 3-kinase complex`
## [1] "PIK3CD" "PIK3R5" "PIK3CB" "PIK3CA" "PIK3R6" "PIK3R1"
## 
## [[1]]$`DOWN genesets.GO:0007019 microtubule depolymerization`
##  [1] "KIF14"   "BMERB1"  "STMN1"   "KIF2C"   "NCKAP5L" "CKAP5"   "KIF18A" 
##  [8] "KIF24"   "KIF2A"   "KATNB1" 
## 
## [[1]]$`DOWN genesets.GO:0008330 protein tyrosine/threonine phosphatase activity`
## [1] "DUSP16" "DUSP7"  "DUSP10" "DUSP4"  "DUSP6" 
## 
## [[1]]$`DOWN genesets.GO:0019864 IgG binding`
## [1] "FCGR3A" "FCGR2B" "FCGR1A" "FCGRT"  "FCGR2A" "FCER1G"
## 
## [[1]]$`DOWN genesets.GO:0019886 antigen processing and presentation of exogenous peptide antigen via MHC class II`
##  [1] "HLA-DPA1" "HLA-DMA"  "HLA-DPB1" "HLA-DRA"  "CD74"     "CTSS"    
##  [7] "HLA-DRB1" "HLA-DMB"  "IFI30"    "HLA-DOA"  "FCGR2B"   "CTSF"    
## [13] "CTSV"     "HLA-DQA1" "UNC93B1"  "DNM2"     "PIKFYVE"  "HLA-DQB1"
## [19] "CTSD"     "FCER1G"   "HLA-DRB5" "HLA-DQA2" "CTSL"     "B2M"     
## [25] "LGMN"     "TRAF6"   
## 
## [[1]]$`DOWN genesets.GO:0031123 RNA 3'-end processing`
## [1] "TENT4B" "TENT4A" "PAPOLG" "TUT7"   "TUT1"   "CSTF3"  "TENT2"  "TUT4"  
## [9] "MTPAP" 
## 
## [[1]]$`DOWN genesets.GO:0032395 MHC class II receptor activity`
## [1] "HLA-DPA1" "HLA-DRA"  "HLA-DRB1" "HLA-DOA"  "HLA-DQA1" "HLA-DQB1" "HLA-DQA2"
## 
## [[1]]$`DOWN genesets.GO:0032873 negative regulation of stress-activated MAPK cascade`
## [1] "PBK"    "FOXM1"  "IGBP1"  "DUSP10" "MYC"    "FOXO1"  "PPIA"   "GSTP1" 
## 
## [[1]]$`DOWN genesets.GO:0036150 phosphatidylserine acyl-chain remodeling`
## [1] "MBOAT1" "MBOAT2" "LPCAT3" "OSBPL8" "OSBPL5" "PLA1A"  "LPCAT4"
## 
## [[1]]$`DOWN genesets.GO:0038094 Fc-gamma receptor signaling pathway`
## [1] "FCGR3A" "CD247"  "FCGR2B" "FCGR1A" "FCGR2A" "CD33"   "CLEC4E" "FCER1G"
## 
## [[1]]$`DOWN genesets.GO:0042555 MCM complex`
##  [1] "MCM5"   "MCM7"   "MCM3"   "MCM4"   "MCM6"   "MCM2"   "TONSL"  "MCM9"  
##  [9] "MCMBP"  "MCM8"   "MMS22L"
## 
## [[1]]$`DOWN genesets.GO:0042613 MHC class II protein complex`
##  [1] "HLA-DPA1" "HLA-DMA"  "HLA-DPB1" "HLA-DRA"  "CD74"     "HLA-DRB1"
##  [7] "HLA-DMB"  "HLA-DOA"  "HLA-DQA1" "HLA-DQB1" "HLA-DRB5" "HLA-DQA2"
## [13] "B2M"     
## 
## [[1]]$`DOWN genesets.GO:0051450 myoblast proliferation`
## [1] "HGF"    "IGF1"   "FOS"    "FGR"    "ABL1"   "CTNNB1" "FES"    "SRC"   
## 
## [[1]]$`DOWN genesets.GO:0051983 regulation of chromosome segregation`
##  [1] "MKI67"   "CDCA2"   "BUB1"    "KIF2C"   "AURKB"   "ZNF207"  "PUM1"   
##  [8] "PUM2"    "PPP2R2D" "PPP2R2A"
## 
## [[1]]$`DOWN genesets.GO:0071162 CMG complex`
##  [1] "MCM5"  "GINS2" "MCM7"  "MCM3"  "MCM4"  "MCM6"  "MCM2"  "GINS4" "GINS1"
## [10] "GINS3"
## 
## [[1]]$`DOWN genesets.GO:0071476 cellular hypotonic response`
## [1] "CAB39"   "MYLK"    "OXSR1"   "TRPV4"   "STK39"   "SLC12A6" "SLC4A11"
## [8] "TSPO"   
## 
## [[1]]$`DOWN genesets.GO:1900744 regulation of p38MAPK cascade`
## [1] "HGF"    "PHLPP1" "PER1"   "LGALS9" "AGER"   "DAB2IP" "ULK4"  
## 
## [[1]]$`DOWN genesets.GO:1905870 positive regulation of 3'-UTR-mediated mRNA stabilization`
## [1] "TENT4B" "TENT4A" "LARP4B" "ARID5A" "ELAVL4"
## 
## [[1]]$`DOWN genesets.GO:2000179 positive regulation of neural precursor cell proliferation`
## [1] "NAP1L1" "MDK"    "NES"    "GNAI2"  "KDM1A"  "INSM1"  "FLNA"
pb3a <- pbalv[,c(grep("active",colnames(pbalv)),grep("mock",colnames(pbalv)))]

head(pb3a)
##               alv_active1 alv_active2 alv_active3 alv_mock1 alv_mock2 alv_mock3
## HIV-Gagp17          32789       27176       17079       106       178      1530
## HIV-Gagp24              0           0           0         0         0         0
## HIV-Gagp2p7          1201        1242         744         2         7        52
## HIV-Gagp1Pol         2100        2334        1592         6        21        94
## HIV-Polprot         23710       30544       21871        95       230      1596
## HIV-Polp15p31       38437       59592       41124       164       360      2804
pb3af <- pb3a[which(rowMeans(pb3a)>=10),]
head(pb3af)
##               alv_active1 alv_active2 alv_active3 alv_mock1 alv_mock2 alv_mock3
## HIV-Gagp17          32789       27176       17079       106       178      1530
## HIV-Gagp2p7          1201        1242         744         2         7        52
## HIV-Gagp1Pol         2100        2334        1592         6        21        94
## HIV-Polprot         23710       30544       21871        95       230      1596
## HIV-Polp15p31       38437       59592       41124       164       360      2804
## HIV-Vif              3140        4489        3034        10        33       162
colSums(pb3af)
## alv_active1 alv_active2 alv_active3   alv_mock1   alv_mock2   alv_mock3 
##    29735667    28374259    23458113    20217498    24567251    33158713
des3a <- as.data.frame(grepl("active",colnames(pb3af)))
colnames(des3a) <- "case"

plot(cmdscale(dist(t(pb3af))), xlab="Coordinate 1", ylab="Coordinate 2",
  type = "p",pch=19,col="gray",cex=2)

text(cmdscale(dist(t(pb3af))), labels=colnames(pb3af) )

des3a$sample <- rep(1:3,2)

dds <- DESeqDataSetFromMatrix(countData = pb3af , colData = des3a, design = ~ sample + case)
## converting counts to integer mode
##   the design formula contains one or more numeric variables with integer values,
##   specifying a model with increasing fold change for higher values.
##   did you mean for this to be a factor? if so, first convert
##   this variable to a factor using the factor() function
res <- DESeq(dds)
## estimating size factors
## estimating dispersions
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## fitting model and testing
z <- results(res)
vsd <- vst(dds, blind=FALSE)
zz <- cbind(as.data.frame(z),assay(vsd))
de <- as.data.frame(zz[order(zz$pvalue),])
de3af <- de
write.table(de3af,"de3af.tsv",sep="\t")

nrow(subset(de3af,padj<0.05 & log2FoldChange>0))
## [1] 1317
nrow(subset(de3af,padj<0.05 & log2FoldChange<0))
## [1] 1016
head(subset(de3af,padj<0.05 & log2FoldChange>0),10)[,1:6] %>%
  kbl(caption="Top upregulated genes in active Alv cells compared to mock") %>%
  kable_paper("hover", full_width = F)
Top upregulated genes in active Alv cells compared to mock
baseMean log2FoldChange lfcSE stat pvalue padj
SDS 4663.3040 2.108601 0.0864428 24.39301 0 0
SNCA 867.9473 2.918705 0.1394669 20.92757 0 0
CDKN1A 5259.6829 1.545713 0.0976608 15.82736 0 0
AL157912.1 745.8582 2.694261 0.1808349 14.89901 0 0
MDM2 4016.2286 1.414654 0.1006816 14.05077 0 0
OCIAD2 348.2412 2.488586 0.1919387 12.96553 0 0
CIR1 37209.1545 1.641934 0.1269746 12.93120 0 0
HES4 377.0144 2.345086 0.1948713 12.03403 0 0
CCL22 32869.2636 2.170492 0.1824300 11.89767 0 0
NSMCE1-DT 476.6261 1.629657 0.1379713 11.81157 0 0 
head(subset(de3af,padj<0.05 & log2FoldChange<0),10)[,1:6] %>%
  kbl(caption="Top upregulated genes in active Alv cells compared to mock") %>%
  kable_paper("hover", full_width = F)
Top upregulated genes in active Alv cells compared to mock
baseMean log2FoldChange lfcSE stat pvalue padj
LYZ 45445.6900 -1.182497 0.1060701 -11.148260 0 0
FLRT2 555.0481 -1.674158 0.1507768 -11.103553 0 0
RARRES1 2017.6675 -1.682100 0.1523915 -11.038017 0 0
LTA4H 3441.6154 -1.205164 0.1092833 -11.027887 0 0
NDRG2 315.7674 -1.821109 0.1715017 -10.618605 0 0
HIST1H1C 782.9297 -1.170697 0.1105688 -10.587949 0 0
ADA2 1768.1605 -1.060889 0.1038563 -10.214968 0 0
CEBPD 682.1436 -1.482679 0.1479936 -10.018537 0 0
STAB1 103.2025 -3.424849 0.3429959 -9.985102 0 0
ANPEP 1143.3202 -1.288540 0.1335019 -9.651850 0 0 
m3a <- mitch_import(de,DEtype="deseq2",joinType="full")
## The input is a single dataframe; one contrast only. Converting
##         it to a list for you.
## Note: Mean no. genes in input = 15728
## Note: no. genes in output = 15728
## Note: estimated proportion of input genes in output = 1
mres3a <- mitch_calc(m3a,genesets=go,minsetsize=5,cores=4,priority="effect")
## Note: Enrichments with large effect sizes may not be
##             statistically significant.
res <- mres3a$enrichment_result

mitchtbl <- mres3a$enrichment_result
goid <- sapply(strsplit(mitchtbl$set," "),"[[",1)
mysplit <- strsplit(mitchtbl$set," ")
mysplit <- lapply(mysplit, function(x) { x[2:length(x)] } )
godescription <- unlist(lapply(mysplit, function(x) { paste(x,collapse=" ") } ))
em <- data.frame(goid,godescription,mitchtbl$pANOVA,mitchtbl$p.adjustANOVA,sign(mitchtbl$s.dist),mitchtbl$s.dist)
colnames(em) <- c("GO.ID","Description","p.Val","FDR","Phenotype","ES")
write.table(em,"de3af_em.tsv",row.names = FALSE, quote=FALSE,sep="\t")

res <- subset(res,p.adjustANOVA<0.05)
resup <- subset(res,s.dist>0)
resdn <- subset(res,s.dist<0)
s <- c(head(resup$s.dist,10), head(resdn$s.dist,10))
names(s) <- c(head(resup$set,10),head(resdn$set,10))
s <- s[order(s)]
cols <- gsub("1","red",gsub("-1","blue",as.character(sign(s))))
par(mar=c(5,27,3,1))
barplot(abs(s),las=1,horiz=TRUE,col=cols,xlab="ES",cex.names=0.8,main="")

if (! file.exists("Alv_mock_vs_active.html") ) {
  mitch_report(mres3a,outfile="Alv_mock_vs_active.html")
}
networkplot(mres3a,FDR=0.05,n_sets=20)

network_genes(mres3a,FDR=0.05,n_sets=20)
## [[1]]
## [[1]]$`UP genesets.GO:0004017 adenylate kinase activity`
## [1] "AK3" "AK8" "AK4"
## 
## [[1]]$`UP genesets.GO:0005758 mitochondrial intermembrane space`
##  [1] "TRIAP1"  "TIMM10B" "UQCC2"   "CMC4"    "TIMM8A"  "NDUFS5"  "BLOC1S1"
##  [8] "CHCHD7"  "REXO2"   "THEM4"   "HAX1"    "TIMM9"   "COX6C"   "SOD1"   
## [15] "CYCS"    "ARL2BP"  "COX17"   "NDUFA8"  "PRELID2" "GATM"    "SDHAF3" 
## [22] "THOP1"   "PRELID1" "ALPL"    "TIMM8B"  "GFER"    "CHCHD4" 
## 
## [[1]]$`UP genesets.GO:0005762 mitochondrial large ribosomal subunit`
##  [1] "MRPL52" "MRPL41" "MRPL42" "MRPL18" "MRPS30" "MRPL57" "MRPL40" "MRPL35"
##  [9] "MRPL33" "MRPL39" "MRPL47" "MRPL12" "MRPL43" "MRPL15" "MRPL27" "MTERF4"
## 
## [[1]]$`UP genesets.GO:0005763 mitochondrial small ribosomal subunit`
##  [1] "MRPS33"   "MRPS18C"  "MRPS6"    "MRPS16"   "MRPL42"   "MRPS28"  
##  [7] "AURKAIP1" "MRPS10"   "MRPS12"   "MRPS34"   "MRPS17"   "MRPS15"  
## [13] "CHCHD1"  
## 
## [[1]]$`UP genesets.GO:0006091 generation of precursor metabolites and energy`
##  [1] "FDXR"    "POMC"    "ATP5IF1" "PPP1R2"  "COX7C"   "CROT"    "COX6C"  
##  [8] "GIPR"    "SLC25A4" "COX17"   "COX6A1" 
## 
## [[1]]$`UP genesets.GO:0006626 protein targeting to mitochondrion`
##  [1] "BID"     "GDAP1"   "TOMM5"   "TIMM9"   "TIMM17A" "PITRM1"  "TIMM8B" 
##  [8] "MFN2"    "TOMM34"  "MTERF4" 
## 
## [[1]]$`UP genesets.GO:0006826 iron ion transport`
## [1] "FTL"     "SFXN1"   "FTH1"    "SLC11A2" "TFRC"    "FXN"    
## 
## [[1]]$`UP genesets.GO:0016226 iron-sulfur cluster assembly`
##  [1] "BOLA3"   "CIAO1"   "LYRM4"   "XDH"     "ISCA1"   "FDX2"    "NDUFAB1"
##  [8] "NUBPL"   "CIAO2B"  "HSPA9"   "FXN"     "GLRX3"  
## 
## [[1]]$`UP genesets.GO:0032402 melanosome transport`
## [1] "BBS7"   "MREG"   "MLPH"   "RAB1A"  "RAB27A" "RAB11A"
## 
## [[1]]$`UP genesets.GO:0032543 mitochondrial translation`
##  [1] "MRPS33"   "MRPL52"   "MRPS18C"  "MRPL41"   "MRPS6"    "MRPS16"  
##  [7] "MRPL42"   "MRPL18"   "MRPS30"   "MRPL57"   "MRPL40"   "MRPL35"  
## [13] "MRPL33"   "MRPS28"   "AURKAIP1" "MRPL39"   "MRPS10"   "MRPL47"  
## [19] "MRPS12"   "MRPL12"   "MRPS34"   "MRPS17"   "MRPL43"   "MRPS15"  
## [25] "CHCHD1"   "MRPL15"   "MRPL27"  
## 
## [[1]]$`UP genesets.GO:0033617 mitochondrial cytochrome c oxidase assembly`
## [1] "COX14" "COA1"  "COX17" "COA8"  "COA3" 
## 
## [[1]]$`UP genesets.GO:0042719 mitochondrial intermembrane space protein transporter complex`
## [1] "TIMM10B" "TIMM8A"  "TIMM9"   "TIMM8B" 
## 
## [[1]]$`UP genesets.GO:0044571 [2Fe-2S] cluster assembly`
## [1] "LYRM4"   "FDX2"    "NDUFAB1" "FXN"     "GLRX3"  
## 
## [[1]]$`UP genesets.GO:0045039 protein insertion into mitochondrial inner membrane`
## [1] "TIMM10B" "TIMM8A"  "NDUFA13" "ROMO1"   "TIMM9"   "TIMM8B" 
## 
## [[1]]$`UP genesets.GO:0045071 negative regulation of viral genome replication`
##  [1] "ISG15"    "EIF2AK2"  "OAS1"     "BST2"     "OAS3"     "OASL"    
##  [7] "TNIP1"    "OAS2"     "PLSCR1"   "RSAD2"    "IFIT1"    "ISG20"   
## [13] "IFIH1"    "ZC3HAV1"  "TRIM6"    "APOBEC3A" "APOBEC3C" "IFITM3"  
## [19] "SHFL"    
## 
## [[1]]$`UP genesets.GO:0045569 TRAIL binding`
## [1] "TNFRSF10B" "TNFRSF10A" "TNFRSF10C"
## 
## [[1]]$`UP genesets.GO:0046961 proton-transporting ATPase activity, rotational mechanism`
## [1] "ATP6V1D"  "ATP6V1G1" "ATP6V0E1" "ATP6V0E2" "ATP6V0D2" "ATP6V1H"  "ATP6V0C" 
## [8] "ATP6V1C1" "ATP6V1E1"
## 
## [[1]]$`UP genesets.GO:0051537 2 iron, 2 sulfur cluster binding`
## [1] "SLC25A39" "CISD3"    "GLRX2"    "XDH"      "ISCA1"    "FDX2"     "UQCRFS1" 
## [8] "FDX1"     "FXN"     
## 
## [[1]]$`UP genesets.GO:0070106 interleukin-27-mediated signaling pathway`
## [1] "OAS1"  "OAS3"  "OASL"  "OAS2"  "STAT1" "IL6ST"
## 
## [[1]]$`UP genesets.GO:1990229 iron-sulfur cluster assembly complex`
## [1] "BOLA3"   "LYRM4"   "FDX2"    "NDUFAB1" "FXN"     "GLRX3"  
## 
## [[1]]$`DOWN genesets.GO:0002437 inflammatory response to antigenic stimulus`
##  [1] "RBPJ"     "HLA-DRB1" "HMGB2"    "PNMA1"    "KDM6B"    "NOTCH2"  
##  [7] "HMGB1"    "NOTCH1"   "CYSLTR1"  "IL20RB"   "CD68"     "RASGRP1" 
## 
## [[1]]$`DOWN genesets.GO:0006265 DNA topological change`
##  [1] "HMGB2"  "TDRD3"  "HMGB1"  "TOP2B"  "TOP1"   "TOP1MT" "TOP3A"  "TOP2A" 
##  [9] "ERCC3"  "TOP3B" 
## 
## [[1]]$`DOWN genesets.GO:0006271 DNA strand elongation involved in DNA replication`
## [1] "MCM7"  "MCM3"  "RFC3"  "MCM4"  "POLD3" "POLA1" "RFC4" 
## 
## [[1]]$`DOWN genesets.GO:0014898 cardiac muscle hypertrophy in response to stress`
## [1] "HDAC4"  "PPP3CA" "ATP2A2" "INPP5F" "CAMTA2" "SMAD4"  "EZH2"   "KDM4A" 
## 
## [[1]]$`DOWN genesets.GO:0019864 IgG binding`
## [1] "FCGRT"  "FCER1G" "FCGR1A" "FCGR3A" "FCGR2A" "FCGR2B"
## 
## [[1]]$`DOWN genesets.GO:0030292 protein tyrosine kinase inhibitor activity`
## [1] "PTPRC"  "RACK1"  "DUSP22" "IBTK"   "SOCS3" 
## 
## [[1]]$`DOWN genesets.GO:0032489 regulation of Cdc42 protein signal transduction`
## [1] "APOA1"  "APOE"   "NRP1"   "ABL1"   "RALBP1" "ABCA1" 
## 
## [[1]]$`DOWN genesets.GO:0036002 pre-mRNA binding`
##  [1] "TRA2B"   "HNRNPA1" "DDX5"    "HNRNPU"  "ARGLU1"  "CELF1"   "SRSF3"  
##  [8] "RBM22"   "CELF2"   "SRSF2"   "PTBP1"   "TARBP2"  "SRSF6"  
## 
## [[1]]$`DOWN genesets.GO:0038094 Fc-gamma receptor signaling pathway`
## [1] "FCER1G" "FCGR1A" "CD33"   "FCGR3A" "CD247"  "FCGR2A" "CLEC4E" "FCGR2B"
## 
## [[1]]$`DOWN genesets.GO:0038156 interleukin-3-mediated signaling pathway`
## [1] "CSF2RB" "FCER1G" "IL3RA"  "JAK2"   "STAT5A" "SYK"   
## 
## [[1]]$`DOWN genesets.GO:0042555 MCM complex`
##  [1] "MCM7"   "MCM3"   "MCM4"   "MCM6"   "MCM9"   "MCM2"   "MMS22L" "MCMBP" 
##  [9] "MCM8"   "MCM5"   "TONSL" 
## 
## [[1]]$`DOWN genesets.GO:0042800 histone H3K4 methyltransferase activity`
##  [1] "KMT2C"  "SETD3"  "ASH1L"  "SETD1B" "KMT2D"  "KMT2B"  "KMT2A"  "SETD1A"
##  [9] "SETD4"  "SETBP1" "SETMAR" "WDR5"  
## 
## [[1]]$`DOWN genesets.GO:0044027 negative regulation of gene expression via chromosomal CpG island methylation`
##  [1] "DNMT1"    "MYC"      "HELLS"    "BRCA1"    "CTCF"     "UHRF1"   
##  [7] "DNMT3A"   "MECP2"    "MPHOSPH8" "UHRF2"    "ZNF445"   "EHMT2"   
## [13] "PRMT5"    "USP7"    
## 
## [[1]]$`DOWN genesets.GO:0045656 negative regulation of monocyte differentiation`
## [1] "GPR68"  "MYC"    "ZBTB46" "INPP5D" "CDK6"  
## 
## [[1]]$`DOWN genesets.GO:0046974 histone H3K9 methyltransferase activity`
## [1] "SETDB1"  "ASH1L"   "EHMT1"   "SETD5"   "SETDB2"  "SUV39H1" "EHMT2"  
## [8] "SUV39H2" "MECOM"  
## 
## [[1]]$`DOWN genesets.GO:0060766 negative regulation of androgen receptor signaling pathway`
## [1] "FOXP1"   "DAB2"    "ZBTB7A"  "HDAC1"   "NCOR1"   "NCOR2"   "SIRT1"  
## [8] "SMARCA4" "PIAS2"  
## 
## [[1]]$`DOWN genesets.GO:0070578 RISC-loading complex`
## [1] "AGO3"   "DICER1" "DHX9"   "AGO1"   "AGO2"   "AGO4"   "PRKRA"  "TARBP2"
## 
## [[1]]$`DOWN genesets.GO:0071541 eukaryotic translation initiation factor 3 complex, eIF3m`
## [1] "EIF3H" "EIF3F" "EIF3D" "EIF3A" "EIF3B" "EIF3M" "EIF3I"
## 
## [[1]]$`DOWN genesets.GO:0097100 supercoiled DNA binding`
## [1] "HMGB2" "RPS3"  "ABL1"  "PSIP1" "HMGB1" "TOP1" 
## 
## [[1]]$`DOWN genesets.GO:0106222 lncRNA binding`
##  [1] "DNMT1"  "HADHB"  "HNRNPU" "PCBP2"  "ATP2A2" "DNMT3A" "RAD21"  "PUM2"  
##  [9] "BRD3"   "STAT3"  "RBM33"  "EZH2"   "SUZ12"  "CSDE1"  "ELAVL1" "SUGT1"

Combined.

mm3 <- merge(m3a,m3m,by=0)

head(mm3)
##   Row.names        x.x         x.y
## 1      A1BG  1.3424630  0.37551812
## 2  A1BG-AS1 -0.6793356 -1.10527413
## 3       A2M -1.4968521 -0.53690564
## 4 A2ML1-AS1 -0.3449972  0.43165967
## 5    A4GALT  3.0879136  0.09420681
## 6      AAAS  0.7838179 -0.43417325
rownames(mm3) <- mm3[,1]
mm3[,1]=NULL
colnames(mm3) <- c("Alv","MDM")
plot(mm3)
mylm <- lm(mm3)
abline(mylm,col="red",lty=2,lwd=3)

summary(mylm)
## 
## Call:
## lm(formula = mm3)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -11.8814  -0.9832  -0.1177   0.8530  23.0640 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 0.094008   0.013892   6.767 1.36e-11 ***
## MDM         0.790663   0.008554  92.428  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.662 on 14306 degrees of freedom
## Multiple R-squared:  0.3739, Adjusted R-squared:  0.3738 
## F-statistic:  8543 on 1 and 14306 DF,  p-value: < 2.2e-16
cor.test(mm3$Alv,mm3$MDM)
## 
##  Pearson's product-moment correlation
## 
## data:  mm3$Alv and mm3$MDM
## t = 92.428, df = 14306, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.6011007 0.6216213
## sample estimates:
##       cor 
## 0.6114638
mm3r <- as.data.frame(apply(mm3,2,rank))
plot(mm3r,cex=0.3)
mylm <- lm(mm3r)
abline(mylm,col="red",lty=2,lwd=3)

summary(mylm)
## 
## Call:
## lm(formula = mm3r)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -9934.7 -2510.9   -90.8  2409.6 11085.2 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 2.818e+03  5.493e+01   51.30   <2e-16 ***
## MDM         6.061e-01  6.650e-03   91.15   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3285 on 14306 degrees of freedom
## Multiple R-squared:  0.3674, Adjusted R-squared:  0.3674 
## F-statistic:  8309 on 1 and 14306 DF,  p-value: < 2.2e-16
cor.test(mm3r$Alv,mm3r$MDM)
## 
##  Pearson's product-moment correlation
## 
## data:  mm3r$Alv and mm3r$MDM
## t = 91.152, df = 14306, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.5956684 0.6164016
## sample estimates:
##      cor 
## 0.606138

DE4 Mock vs bystander

MDM group.

pb4m <- pbmdm[,c(grep("mock",colnames(pbmdm)),grep("bystander",colnames(pbmdm)))]

head(pb4m)
##               mdm_mock1 mdm_mock2 mdm_mock3 mdm_mock4 mdm_bystander1
## HIV-Gagp17          117       253        37       159            255
## HIV-Gagp24            0         0         0         0              0
## HIV-Gagp2p7           5         8         1         5             23
## HIV-Gagp1Pol          7        14         3        13             20
## HIV-Polprot         136       196        47       146            331
## HIV-Polp15p31       341       550       101       257           1033
##               mdm_bystander2 mdm_bystander3 mdm_bystander4
## HIV-Gagp17               254             57             61
## HIV-Gagp24                 0              0              0
## HIV-Gagp2p7               32              3              8
## HIV-Gagp1Pol              61             16             10
## HIV-Polprot              492            181             81
## HIV-Polp15p31           1505            413            181
pb4mf <- pb4m[which(rowMeans(pb4m)>=10),]
head(pb4mf)
##               mdm_mock1 mdm_mock2 mdm_mock3 mdm_mock4 mdm_bystander1
## HIV-Gagp17          117       253        37       159            255
## HIV-Gagp2p7           5         8         1         5             23
## HIV-Gagp1Pol          7        14         3        13             20
## HIV-Polprot         136       196        47       146            331
## HIV-Polp15p31       341       550       101       257           1033
## HIV-Vif              15        45         8        17             87
##               mdm_bystander2 mdm_bystander3 mdm_bystander4
## HIV-Gagp17               254             57             61
## HIV-Gagp2p7               32              3              8
## HIV-Gagp1Pol              61             16             10
## HIV-Polprot              492            181             81
## HIV-Polp15p31           1505            413            181
## HIV-Vif                   73             29             16
colSums(pb4mf)
##      mdm_mock1      mdm_mock2      mdm_mock3      mdm_mock4 mdm_bystander1 
##       28557312       20547234        7025832       20638609       70265280 
## mdm_bystander2 mdm_bystander3 mdm_bystander4 
##       68938388       26232912       36276740
des4m <- as.data.frame(grepl("bystander",colnames(pb4mf)))
colnames(des4m) <- "case"

plot(cmdscale(dist(t(pb4mf))), xlab="Coordinate 1", ylab="Coordinate 2",
  type = "p",pch=19,col="gray",cex=2)

text(cmdscale(dist(t(pb4mf))), labels=colnames(pb4mf) )

des4m$sample <- rep(1:4,2)

dds <- DESeqDataSetFromMatrix(countData = pb4mf , colData = des4m, design = ~ sample + case)
## converting counts to integer mode
##   the design formula contains one or more numeric variables with integer values,
##   specifying a model with increasing fold change for higher values.
##   did you mean for this to be a factor? if so, first convert
##   this variable to a factor using the factor() function
res <- DESeq(dds)
## estimating size factors
## estimating dispersions
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## fitting model and testing
z <- results(res)
vsd <- vst(dds, blind=FALSE)
zz <- cbind(as.data.frame(z),assay(vsd))
de <- as.data.frame(zz[order(zz$pvalue),])
de4mf <- de
write.table(de4mf,"de4mf.tsv",sep="\t")

nrow(subset(de4mf,padj<0.05 & log2FoldChange>0))
## [1] 0
nrow(subset(de4mf,padj<0.05 & log2FoldChange<0))
## [1] 8
head(subset(de4mf, log2FoldChange>0),10)[,1:6] %>%
  kbl(caption="Top upregulated genes in bystander MDM cells compared to mock") %>%
  kable_paper("hover", full_width = F)
Top upregulated genes in bystander MDM cells compared to mock
baseMean log2FoldChange lfcSE stat pvalue padj
IFI27 398.48186 1.5360241 0.3730761 4.117188 0.0000384 0.0595815
TNFRSF10B 502.55437 0.4963497 0.1259997 3.939292 0.0000817 0.0642395
PLAAT3 27.49546 1.3240300 0.3502151 3.780619 0.0001564 0.0910935
CCL8 11.08084 2.8264229 0.7498256 3.769440 0.0001636 0.0910935
NCF1 239.01747 0.8313951 0.2259180 3.680075 0.0002332 0.1071642
ISG15 1232.21671 0.6854540 0.1868554 3.668365 0.0002441 0.1088930
PSME2 4609.35725 0.3424031 0.0953156 3.592311 0.0003278 0.1380863
PRPH 29.76869 1.5668278 0.4411072 3.552034 0.0003823 0.1486619
TNFAIP6 147.61999 1.1343811 0.3244416 3.496411 0.0004716 0.1723480
AFF3 72.03688 1.1232639 0.3320915 3.382393 0.0007186 0.2270539 
head(subset(de4mf, log2FoldChange<0),10)[,1:6] %>%
  kbl(caption="Top downregulated genes in bystander MDM cells compared to mock") %>%
  kable_paper("hover", full_width = F)
Top downregulated genes in bystander MDM cells compared to mock
baseMean log2FoldChange lfcSE stat pvalue padj
CDK1 83.35505 -2.2505422 0.4688702 -4.799926 1.60e-06 0.0240737
RRM2 66.74492 -1.9768888 0.4371513 -4.522208 6.10e-06 0.0335727
TK1 127.38681 -1.3066986 0.2901141 -4.504085 6.70e-06 0.0335727
CENPK 158.41357 -0.9379988 0.2110985 -4.443416 8.90e-06 0.0335727
UBE2C 94.86970 -2.9161884 0.6642659 -4.390092 1.13e-05 0.0343692
CENPF 169.31681 -2.1460422 0.4963458 -4.323684 1.53e-05 0.0371842
PBK 22.44710 -3.0058997 0.6992662 -4.298649 1.72e-05 0.0371842
CLSPN 111.53747 -1.0670283 0.2499335 -4.269249 1.96e-05 0.0371842
CIT 29.18619 -1.7288869 0.4204846 -4.111653 3.93e-05 0.0595815
TIMP3 2878.07690 -0.8631982 0.2126014 -4.060171 4.90e-05 0.0642395 
m4m <- mitch_import(de,DEtype="deseq2",joinType="full")
## The input is a single dataframe; one contrast only. Converting
##         it to a list for you.
## Note: Mean no. genes in input = 15779
## Note: no. genes in output = 15779
## Note: estimated proportion of input genes in output = 1
mres4m <- mitch_calc(m4m,genesets=go,minsetsize=5,cores=4,priority="effect")
## Note: Enrichments with large effect sizes may not be
##             statistically significant.
res <- mres4m$enrichment_result

mitchtbl <- mres4m$enrichment_result
goid <- sapply(strsplit(mitchtbl$set," "),"[[",1)
mysplit <- strsplit(mitchtbl$set," ")
mysplit <- lapply(mysplit, function(x) { x[2:length(x)] } )
godescription <- unlist(lapply(mysplit, function(x) { paste(x,collapse=" ") } ))
em <- data.frame(goid,godescription,mitchtbl$pANOVA,mitchtbl$p.adjustANOVA,sign(mitchtbl$s.dist),mitchtbl$s.dist)
colnames(em) <- c("GO.ID","Description","p.Val","FDR","Phenotype","ES")
write.table(em,"de4mf_em.tsv",row.names = FALSE, quote=FALSE,sep="\t")

res <- subset(res,p.adjustANOVA<0.05)
resup <- subset(res,s.dist>0)
resdn <- subset(res,s.dist<0)
s <- c(head(resup$s.dist,10), head(resdn$s.dist,10))
names(s) <- c(head(resup$set,10),head(resdn$set,10))
s <- s[order(s)]
cols <- gsub("1","red",gsub("-1","blue",as.character(sign(s))))
par(mar=c(5,27,3,1))
barplot(abs(s),las=1,horiz=TRUE,col=cols,xlab="ES",cex.names=0.8,main="")

if (! file.exists("MDM_mock_vs_bystander.html") ) {
  mitch_report(mres4m,outfile="MDM_mock_vs_bystander.html")
}
networkplot(mres4m,FDR=0.05,n_sets=20)

network_genes(mres4m,FDR=0.05,n_sets=20)
## [[1]]
## [[1]]$`UP genesets.GO:0000502 proteasome complex`
## [1] "PSME2" "PSMC4" "PSMB2"
## 
## [[1]]$`UP genesets.GO:0002181 cytoplasmic translation`
## [1] "RPL18" "RPL15" "RPS6"  "RPL7A"
## 
## [[1]]$`UP genesets.GO:0002476 antigen processing and presentation of endogenous peptide antigen via MHC class Ib`
## character(0)
## 
## [[1]]$`UP genesets.GO:0002486 antigen processing and presentation of endogenous peptide antigen via MHC class I via ER pathway, TAP-independent`
## character(0)
## 
## [[1]]$`UP genesets.GO:0004298 threonine-type endopeptidase activity`
## character(0)
## 
## [[1]]$`UP genesets.GO:0005839 proteasome core complex`
## [1] "PSMB2"
## 
## [[1]]$`UP genesets.GO:0006693 prostaglandin metabolic process`
## character(0)
## 
## [[1]]$`UP genesets.GO:0007342 fusion of sperm to egg plasma membrane involved in single fertilization`
## character(0)
## 
## [[1]]$`UP genesets.GO:0008097 5S rRNA binding`
## [1] "MDM2"
## 
## [[1]]$`UP genesets.GO:0010273 detoxification of copper ion`
## [1] "MT1H"   "MT1M"   "MT1F"   "MT1HL1"
## 
## [[1]]$`UP genesets.GO:0019773 proteasome core complex, alpha-subunit complex`
## character(0)
## 
## [[1]]$`UP genesets.GO:0019774 proteasome core complex, beta-subunit complex`
## [1] "PSMB2"
## 
## [[1]]$`UP genesets.GO:0022624 proteasome accessory complex`
## [1] "PSMC4"
## 
## [[1]]$`UP genesets.GO:0022625 cytosolic large ribosomal subunit`
## [1] "RPL18" "RPL15" "RPL7A"
## 
## [[1]]$`UP genesets.GO:0022627 cytosolic small ribosomal subunit`
## [1] "RPS6"
## 
## [[1]]$`UP genesets.GO:0032308 positive regulation of prostaglandin secretion`
## character(0)
## 
## [[1]]$`UP genesets.GO:0042612 MHC class I protein complex`
## character(0)
## 
## [[1]]$`UP genesets.GO:0045926 negative regulation of growth`
## [1] "MT1H" "MT1M" "MT1F"
## 
## [[1]]$`UP genesets.GO:0070106 interleukin-27-mediated signaling pathway`
## [1] "MX1"  "OASL" "OAS2"
## 
## [[1]]$`UP genesets.GO:1902254 negative regulation of intrinsic apoptotic signaling pathway by p53 class mediator`
## [1] "MDM2"
## 
## [[1]]$`DOWN genesets.GO:0000727 double-strand break repair via break-induced replication`
##  [1] "GINS2"  "MCM3"   "MCM7"   "CDC7"   "MCM5"   "MCM4"   "MCM2"   "CDC45" 
##  [9] "GINS4"  "MCMDC2" "MCM6"   "MUS81" 
## 
## [[1]]$`DOWN genesets.GO:0000796 condensin complex`
## [1] "NCAPG"  "NCAPG2" "NCAPD3" "NCAPD2" "SMC2"   "NCAPH2" "NCAPH"  "SMC4"  
## 
## [[1]]$`DOWN genesets.GO:0000940 outer kinetochore`
##  [1] "CENPF" "CCNB1" "KNL1"  "SPC25" "NUF2"  "PLK1"  "ZWINT" "SKA3"  "BUB1B"
## [10] "SKA2"  "BUB1"  "NDC80" "SPDL1" "DSN1"  "NSL1"  "MIS12" "BOD1"  "PMF1" 
## 
## [[1]]$`DOWN genesets.GO:0007076 mitotic chromosome condensation`
##  [1] "NCAPG"  "PLK1"   "AKAP8"  "PHF13"  "CDCA5"  "NCAPD3" "NCAPD2" "NUSAP1"
##  [9] "SMC2"   "NCAPH2" "CHMP1A" "NCAPH"  "SMC4"   "AKAP8L" "TENT4A" "KMT5A" 
## [17] "TTN"   
## 
## [[1]]$`DOWN genesets.GO:0010032 meiotic chromosome condensation`
## [1] "NCAPD3" "NCAPD2" "SMC2"   "NCAPH2" "NCAPH"  "SMC4"  
## 
## [[1]]$`DOWN genesets.GO:0017116 single-stranded DNA helicase activity`
##  [1] "MCM3"   "MCM7"   "POLQ"   "DSCC1"  "RFC5"   "MCM5"   "MCM4"   "MCM2"  
##  [9] "MCM8"   "WRNIP1" "CHTF18" "RAD51"  "MCM9"   "RFC2"   "RFC3"   "CHTF8" 
## [17] "DNA2"   "HELB"   "RFC4"   "PIF1"  
## 
## [[1]]$`DOWN genesets.GO:0030174 regulation of DNA-templated DNA replication initiation`
##  [1] "MCM3"   "MCM7"   "CDT1"   "MCM5"   "MCM4"   "MCM2"   "WRNIP1" "GMNN"  
##  [9] "MCM6"   "NBN"    "KAT7"  
## 
## [[1]]$`DOWN genesets.GO:0030263 apoptotic chromosome condensation`
## [1] "TOP2A" "ACIN1" "DFFB"  "KDM4A" "GPER1"
## 
## [[1]]$`DOWN genesets.GO:0030594 neurotransmitter receptor activity`
## [1] "HRH2"   "P2RY11" "HTR2B"  "HTR2A"  "GRIN3B"
## 
## [[1]]$`DOWN genesets.GO:0042555 MCM complex`
##  [1] "MCM3"   "MCM7"   "MCM5"   "MCM4"   "MCM2"   "MCM8"   "MCM9"   "MCMBP" 
##  [9] "TONSL"  "MMS22L" "MCM6"  
## 
## [[1]]$`DOWN genesets.GO:0043534 blood vessel endothelial cell migration`
## [1] "CYP1B1" "EMP2"   "PTK2B"  "MYH9"   "CLN3"   "SCARB1"
## 
## [[1]]$`DOWN genesets.GO:0045322 unmethylated CpG binding`
## [1] "KMT2B"  "KDM2B"  "MECP2"  "DNMT3A" "KDM2A"  "KMT2A"  "FBXL19" "MBD1"  
## [9] "CXXC1" 
## 
## [[1]]$`DOWN genesets.GO:0048407 platelet-derived growth factor binding`
## [1] "COL6A1" "PDGFA"  "COL4A1" "PDGFRA" "PDGFB" 
## 
## [[1]]$`DOWN genesets.GO:0050790 regulation of catalytic activity`
## [1] "SGK1"   "CAPN3"  "PARP1"  "ANKLE2" "CAPN1" 
## 
## [[1]]$`DOWN genesets.GO:0051983 regulation of chromosome segregation`
##  [1] "MKI67"   "CDCA2"   "BUB1"    "KIF2C"   "ZNF207"  "AURKB"   "PPP2R2D"
##  [8] "PUM1"    "PPP2R2A" "PUM2"   
## 
## [[1]]$`DOWN genesets.GO:0051984 positive regulation of chromosome segregation`
##  [1] "NCAPG"  "CDC6"   "NCAPG2" "NCAPD3" "NCAPD2" "NUMA1"  "RAD18"  "SMC2"  
##  [9] "NCAPH2" "NCAPH"  "SMC4"   "SMC6"   "SMC5"  
## 
## [[1]]$`DOWN genesets.GO:0071162 CMG complex`
##  [1] "GINS2" "MCM3"  "MCM7"  "MCM5"  "MCM4"  "GINS1" "MCM2"  "CDC45" "GINS4"
## [10] "MCM6"  "GINS3"
## 
## [[1]]$`DOWN genesets.GO:1902975 mitotic DNA replication initiation`
## [1] "MCM3"  "MCM4"  "MCM2"  "POLA1" "GINS3"
## 
## [[1]]$`DOWN genesets.GO:1905820 positive regulation of chromosome separation`
##  [1] "NCAPG"  "NCAPG2" "NCAPD3" "NCAPD2" "PLSCR1" "NUMA1"  "SMC2"   "NCAPH2"
##  [9] "NCAPH"  "SMC4"  
## 
## [[1]]$`DOWN genesets.GO:1905821 positive regulation of chromosome condensation`
## [1] "NCAPG"  "NCAPG2" "NCAPD3" "NCAPD2" "SMC2"   "NCAPH2" "NCAPH"  "SMC4"

Alv cells.

pb4a <- pbalv[,c(grep("mock",colnames(pbalv)),grep("bystander",colnames(pbalv)))]

head(pb4a)
##               alv_mock1 alv_mock2 alv_mock3 alv_bystander1 alv_bystander2
## HIV-Gagp17          106       178      1530            106            162
## HIV-Gagp24            0         0         0              0              0
## HIV-Gagp2p7           2         7        52             16             26
## HIV-Gagp1Pol          6        21        94             26             50
## HIV-Polprot          95       230      1596            208            515
## HIV-Polp15p31       164       360      2804            476           1203
##               alv_bystander3
## HIV-Gagp17               183
## HIV-Gagp24                 0
## HIV-Gagp2p7               17
## HIV-Gagp1Pol              42
## HIV-Polprot              534
## HIV-Polp15p31           1151
pb4af <- pb4a[which(rowMeans(pb4a)>=10),]
head(pb4af)
##               alv_mock1 alv_mock2 alv_mock3 alv_bystander1 alv_bystander2
## HIV-Gagp17          106       178      1530            106            162
## HIV-Gagp2p7           2         7        52             16             26
## HIV-Gagp1Pol          6        21        94             26             50
## HIV-Polprot          95       230      1596            208            515
## HIV-Polp15p31       164       360      2804            476           1203
## HIV-Vif              10        33       162             31             78
##               alv_bystander3
## HIV-Gagp17               183
## HIV-Gagp2p7               17
## HIV-Gagp1Pol              42
## HIV-Polprot              534
## HIV-Polp15p31           1151
## HIV-Vif                   86
colSums(pb4af)
##      alv_mock1      alv_mock2      alv_mock3 alv_bystander1 alv_bystander2 
##       20228192       24576310       33170699       58232744       65496965 
## alv_bystander3 
##       58745079
des4a <- as.data.frame(grepl("bystander",colnames(pb4af)))
colnames(des4a) <- "case"

plot(cmdscale(dist(t(pb4af))), xlab="Coordinate 1", ylab="Coordinate 2",
  type = "p",pch=19,col="gray",cex=2)

text(cmdscale(dist(t(pb4af))), labels=colnames(pb4af) )

des4a$sample <- rep(1:3,2)

dds <- DESeqDataSetFromMatrix(countData = pb4af , colData = des4a, design = ~ sample + case)
## converting counts to integer mode
##   the design formula contains one or more numeric variables with integer values,
##   specifying a model with increasing fold change for higher values.
##   did you mean for this to be a factor? if so, first convert
##   this variable to a factor using the factor() function
res <- DESeq(dds)
## estimating size factors
## estimating dispersions
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## fitting model and testing
z <- results(res)
vsd <- vst(dds, blind=FALSE)
zz <- cbind(as.data.frame(z),assay(vsd))
de <- as.data.frame(zz[order(zz$pvalue),])
de4af <- de
write.table(de4af,"de4af.tsv",sep="\t")

nrow(subset(de4af,padj<0.05 & log2FoldChange>0))
## [1] 47
nrow(subset(de4af,padj<0.05 & log2FoldChange<0))
## [1] 4
head(subset(de4af,padj<0.05 & log2FoldChange>0),10)[,1:6] %>%
  kbl(caption="Top upregulated genes in latent Alv cells compared to ") %>%
  kable_paper("hover", full_width = F)
Top upregulated genes in latent Alv cells compared to
baseMean log2FoldChange lfcSE stat pvalue padj
PARP14 2649.6649 1.1809110 0.1535856 7.688944 0e+00 0.0000000
LY6E 13662.4198 1.2547553 0.1704800 7.360134 0e+00 0.0000000
OAS1 1040.3169 1.6357335 0.2558141 6.394227 0e+00 0.0000008
XAF1 1087.1096 2.0282937 0.3214543 6.309743 0e+00 0.0000010
SAMD9L 1541.9550 1.0993464 0.1794907 6.124809 0e+00 0.0000026
GMPR 436.2431 0.9746833 0.1727695 5.641524 0e+00 0.0000339
CMPK2 128.1722 2.9552388 0.5361132 5.512341 0e+00 0.0000623
EIF2AK2 2205.7316 0.9177018 0.1681172 5.458701 0e+00 0.0000750
IRF7 293.0091 1.6134171 0.2969970 5.432436 1e-07 0.0000782
LGALS3BP 1670.7932 1.1213907 0.2095225 5.352124 1e-07 0.0001041 
head(subset(de4af, log2FoldChange<0),10)[,1:6] %>%
  kbl(caption="Top upregulated genes in active Alv cells") %>%
  kable_paper("hover", full_width = F)
Top upregulated genes in active Alv cells
baseMean log2FoldChange lfcSE stat pvalue padj
CCL4 473.46252 -2.2023606 0.3850376 -5.719859 0.0000000 0.0000250
SPP1 81304.43380 -0.4227772 0.0801142 -5.277184 0.0000001 0.0001231
ACTG1 23356.92294 -0.2965569 0.0766674 -3.868099 0.0001097 0.0328408
AC007952.4 956.05946 -0.7087295 0.1849711 -3.831568 0.0001273 0.0373287
HIV-Gagp17 441.21001 -2.4064383 0.6601073 -3.645526 0.0002668 0.0661083
C9 459.15120 -0.6017109 0.1781765 -3.377050 0.0007327 0.1412362
ERVMER61-1 42.24601 -1.2723297 0.3899306 -3.262964 0.0011025 0.2068647
AC078850.1 367.64916 -0.5486816 0.1710904 -3.206970 0.0013414 0.2420043
HPGDS 4522.18706 -0.2945729 0.0955298 -3.083571 0.0020453 0.3553306
ACTB 119698.37379 -0.2226873 0.0729501 -3.052596 0.0022687 0.3800627 
m4a <- mitch_import(de,DEtype="deseq2",joinType="full")
## The input is a single dataframe; one contrast only. Converting
##         it to a list for you.
## Note: Mean no. genes in input = 17047
## Note: no. genes in output = 17047
## Note: estimated proportion of input genes in output = 1
mres4a <- mitch_calc(m4a,genesets=go,minsetsize=5,cores=4,priority="effect")
## Note: Enrichments with large effect sizes may not be
##             statistically significant.
res <- mres4a$enrichment_result

mitchtbl <- mres4a$enrichment_result
goid <- sapply(strsplit(mitchtbl$set," "),"[[",1)
mysplit <- strsplit(mitchtbl$set," ")
mysplit <- lapply(mysplit, function(x) { x[2:length(x)] } )
godescription <- unlist(lapply(mysplit, function(x) { paste(x,collapse=" ") } ))
em <- data.frame(goid,godescription,mitchtbl$pANOVA,mitchtbl$p.adjustANOVA,sign(mitchtbl$s.dist),mitchtbl$s.dist)
colnames(em) <- c("GO.ID","Description","p.Val","FDR","Phenotype","ES")
write.table(em,"de4af_em.tsv",row.names = FALSE, quote=FALSE,sep="\t")

res <- subset(res,p.adjustANOVA<0.05)
resup <- subset(res,s.dist>0)
resdn <- subset(res,s.dist<0)
s <- c(head(resup$s.dist,10), head(resdn$s.dist,10))
names(s) <- c(head(resup$set,10),head(resdn$set,10))
s <- s[order(s)]
cols <- gsub("1","red",gsub("-1","blue",as.character(sign(s))))
par(mar=c(5,27,3,1))
barplot(abs(s),las=1,horiz=TRUE,col=cols,xlab="ES",cex.names=0.8,main="")

if (! file.exists("Alv_mock_vs_bystander.html") ) {
  mitch_report(mres4a,outfile="Alv_mock_vs_bystander.html")
}
networkplot(mres4a,FDR=0.05,n_sets=20)

network_genes(mres4a,FDR=0.05,n_sets=20)
## [[1]]
## [[1]]$`UP genesets.GO:0002503 peptide antigen assembly with MHC class II protein complex`
## [1] "B2M"
## 
## [[1]]$`UP genesets.GO:0002726 positive regulation of T cell cytokine production`
## [1] "B2M"
## 
## [[1]]$`UP genesets.GO:0004126 cytidine deaminase activity`
## [1] "APOBEC3A"
## 
## [[1]]$`UP genesets.GO:0016554 cytidine to uridine editing`
## [1] "APOBEC3A"
## 
## [[1]]$`UP genesets.GO:0019885 antigen processing and presentation of endogenous peptide antigen via MHC class I`
## [1] "TAP1" "TAP2" "B2M" 
## 
## [[1]]$`UP genesets.GO:0032020 ISG15-protein conjugation`
## [1] "ISG15"  "UBE2L6" "HERC5" 
## 
## [[1]]$`UP genesets.GO:0032395 MHC class II receptor activity`
## character(0)
## 
## [[1]]$`UP genesets.GO:0032693 negative regulation of interleukin-10 production`
## character(0)
## 
## [[1]]$`UP genesets.GO:0035455 response to interferon-alpha`
## [1] "EIF2AK2" "IFITM3"  "ADAR"    "BST2"    "MX2"     "IFITM2" 
## 
## [[1]]$`UP genesets.GO:0035456 response to interferon-beta`
## [1] "XAF1"   "IFITM3" "PLSCR1" "STAT1"  "BST2"   "SHFL"   "IFITM2"
## 
## [[1]]$`UP genesets.GO:0042157 lipoprotein metabolic process`
## [1] "APOL6"
## 
## [[1]]$`UP genesets.GO:0042612 MHC class I protein complex`
## [1] "HLA-C" "HLA-F" "B2M"   "HLA-B"
## 
## [[1]]$`UP genesets.GO:0042613 MHC class II protein complex`
## [1] "B2M"
## 
## [[1]]$`UP genesets.GO:0045071 negative regulation of viral genome replication`
##  [1] "OAS1"     "EIF2AK2"  "IFITM3"   "PLSCR1"   "OASL"     "IFIT1"   
##  [7] "OAS2"     "IFIH1"    "BST2"     "SHFL"     "IFIT5"    "ZC3HAV1" 
## [13] "ISG15"    "OAS3"     "RSAD2"    "ISG20"    "MX1"      "N4BP1"   
## [19] "APOBEC3A" "IFITM2"   "IFI16"   
## 
## [[1]]$`UP genesets.GO:0051715 cytolysis in another organism`
## [1] "GBP1" "GBP3"
## 
## [[1]]$`UP genesets.GO:0060337 type I interferon-mediated signaling pathway`
##  [1] "OAS1"   "IRF7"   "IFITM3" "IFI27"  "OASL"   "STAT1"  "OAS2"   "IFIH1" 
##  [9] "OAS3"   "STAT2"  "SP100"  "IFITM2" "MYD88" 
## 
## [[1]]$`UP genesets.GO:0070106 interleukin-27-mediated signaling pathway`
## [1] "OAS1"  "OASL"  "STAT1" "OAS2"  "OAS3"  "MX1"  
## 
## [[1]]$`UP genesets.GO:0070212 protein poly-ADP-ribosylation`
## [1] "PARP14"  "PARP9"   "ZC3HAV1" "PARP10" 
## 
## [[1]]$`UP genesets.GO:0070383 DNA cytosine deamination`
## [1] "APOBEC3A"
## 
## [[1]]$`UP genesets.GO:1902554 serine/threonine protein kinase complex`
## character(0)
## 
## [[1]]$`DOWN genesets.GO:0000727 double-strand break repair via break-induced replication`
##  [1] "MCM3"   "MCM7"   "GINS4"  "GINS2"  "MCM6"   "MCM5"   "MUS81"  "CDC7"  
##  [9] "MCMDC2" "MCM2"   "CDC45"  "MCM4"  
## 
## [[1]]$`DOWN genesets.GO:0000774 adenyl-nucleotide exchange factor activity`
##  [1] "PFN1"   "BAG1"   "HSPA4L" "HSPBP1" "BAG2"   "GRPEL1" "HYOU1"  "BAG5"  
##  [9] "GRPEL2" "HSPA4"  "CCAR2"  "HSPH1"  "BAG3"   "SIL1"   "BAG4"  
## 
## [[1]]$`DOWN genesets.GO:0002181 cytoplasmic translation`
##  [1] "RPLP0"   "RPLP1"   "GTPBP1"  "RPS12"   "RPS3A"   "ZC3H15"  "RPS6"   
##  [8] "RPS17"   "RACK1"   "RPL7"    "RPL23"   "RPS21"   "RPSA"    "RPS5"   
## [15] "RPS20"   "RPL27A"  "RPS23"   "RPL4"    "RPS2"    "RPL27"   "RPS11"  
## [22] "UBA52"   "RPLP2"   "RPL23A"  "DRG1"    "RPL21"   "RPL13"   "RPS24"  
## [29] "RPL9"    "RPS13"   "RPL24"   "RWDD1"   "RPL13A"  "RPL5"    "RPL14"  
## [36] "DRG2"    "RPS7"    "RPS18"   "RPL3"    "RPS29"   "RPL22L1" "RPS3"   
## [43] "RPL35"   "RPL38"   "RPL8"    "RPS27A"  "RPL18A"  "RPL31"   "RPL7A"  
## [50] "RPS15A"  "RPL15"   "RPL22"   "RPL10"   "RPS25"   "RPL6"    "RPS14"  
## [57] "RPL41"   "RPL37A"  "RPL12"   "RPL10A"  "RPL18"   "RPS28"   "RPL34"  
## [64] "RPS8"    "RPS16"   "RPL35A"  "RPL39"   "FTSJ1"   "RPL37"   "RPS27"  
## [71] "RPL26L1" "RPS4X"   "RPL17"   "RPL26"   "RPL28"   "RPL11"   "RPL36"  
## [78] "FAU"     "RPL19"   "RPL32"   "RPS19"   "RPS15"   "RPS26"   "RPS9"   
## [85] "RPS10"   "RPL30"   "RPL36A"  "RPL29"  
## 
## [[1]]$`DOWN genesets.GO:0005852 eukaryotic translation initiation factor 3 complex`
##  [1] "EIF3J" "EIF3M" "EIF3D" "EIF3E" "COPS5" "EIF3A" "EIF3I" "EIF3L" "EIF3B"
## [10] "EIF3K" "EIF3C" "DDX3X" "EIF3H" "EIF3G" "EIF3F"
## 
## [[1]]$`DOWN genesets.GO:0005885 Arp2/3 protein complex`
## [1] "ARPC2"  "ACTR3"  "ARPC5"  "ARPC3"  "ARPC4"  "ARPC5L" "ACTR2"  "ARPC1B"
## [9] "ARPC1A"
## 
## [[1]]$`DOWN genesets.GO:0008250 oligosaccharyltransferase complex`
##  [1] "RPN2"    "DDOST"   "STT3B"   "MLEC"    "STT3A"   "RPN1"    "OSTC"   
##  [8] "KRTCAP2" "DAD1"    "OST4"    "MAGT1"   "TMEM258"
## 
## [[1]]$`DOWN genesets.GO:0015935 small ribosomal subunit`
##  [1] "RPS6"   "RACK1"  "RPS21"  "RPS24"  "RPS18"  "RPS29"  "RPS27A" "RPS25" 
##  [9] "RPS28"  "RPS16"  "MRPS6"  "RPS4X"  "FAU"    "RPS26" 
## 
## [[1]]$`DOWN genesets.GO:0016282 eukaryotic 43S preinitiation complex`
##  [1] "EIF1"   "EIF3J"  "EIF3M"  "EIF3D"  "EIF1B"  "EIF1AX" "EIF3E"  "EIF3A" 
##  [9] "EIF3I"  "EIF3L"  "EIF3B"  "EIF3K"  "DHX29"  "EIF3C"  "EIF3H"  "EIF3G" 
## [17] "EIF3F" 
## 
## [[1]]$`DOWN genesets.GO:0022625 cytosolic large ribosomal subunit`
##  [1] "RPLP0"   "RPLP1"   "RPL7"    "RPL23"   "RPL27A"  "RPL4"    "RPL27"  
##  [8] "RPL39L"  "UBA52"   "RPLP2"   "RPL23A"  "RPL21"   "RPL13"   "RPL9"   
## [15] "RPL24"   "RPL13A"  "RPL5"    "RPL14"   "RPL3"    "RPL35"   "RPL38"  
## [22] "RPL8"    "RPL18A"  "ZCCHC17" "RPL31"   "RPL7A"   "RPL15"   "RPL22"  
## [29] "RPL10"   "RPL6"    "RPL41"   "RPL37A"  "RPL12"   "RPL10A"  "RPL18"  
## [36] "RPL34"   "RPL36AL" "RPL35A"  "RPL39"   "RPL37"   "RPL26L1" "RPL17"  
## [43] "RPL26"   "RPL28"   "RPL11"   "RPL36"   "RPL19"   "RPL32"   "RPL30"  
## [50] "RPL36A"  "RPL7L1"  "RPL29"  
## 
## [[1]]$`DOWN genesets.GO:0022627 cytosolic small ribosomal subunit`
##  [1] "RPS12"  "RPS3A"  "RPS6"   "RPS17"  "RACK1"  "RPS21"  "RPSA"   "RPS5"  
##  [9] "RPS20"  "RPS23"  "RPS2"   "RPS11"  "RPS24"  "RPS13"  "RPS7"   "RPS18" 
## [17] "RPS29"  "LARP4"  "RPS3"   "RPS27A" "RPS15A" "RPS25"  "RPS14"  "EIF2A" 
## [25] "DHX29"  "RPS28"  "RPS8"   "DDX3X"  "RPS16"  "RPS27L" "RPS27"  "RPS4X" 
## [33] "FAU"    "RPS19"  "RPS15"  "RPS26"  "RPS9"   "RPS10"  "RPS4Y1"
## 
## [[1]]$`DOWN genesets.GO:0030003 intracellular monoatomic cation homeostasis`
##  [1] "SLC39A8"  "SLC39A4"  "SLC39A12" "ATP13A2"  "MINPP1"   "SLC39A10"
##  [7] "CNNM4"    "SLC39A14" "COX11"    "SLC39A6"  "SLC4A11" 
## 
## [[1]]$`DOWN genesets.GO:0030687 preribosome, large subunit precursor`
##  [1] "EBNA1BP2" "PPAN"     "WDR74"    "MAK16"    "WDR12"    "RRP15"   
##  [7] "NIP7"     "MRTO4"    "RRS1"     "ZNF622"   "FTSJ3"    "BOP1"    
## [13] "NSA2"     "RPF1"     "PES1"     "MDN1"    
## 
## [[1]]$`DOWN genesets.GO:0042555 MCM complex`
##  [1] "MCM3"   "MCM7"   "MCM6"   "MCM9"   "TONSL"  "MCM8"   "MCM5"   "MMS22L"
##  [9] "MCM2"   "MCM4"   "MCMBP" 
## 
## [[1]]$`DOWN genesets.GO:0045040 protein insertion into mitochondrial outer membrane`
##  [1] "HSP90AA1" "SAMM50"   "MTX1"     "TOMM40"   "TOMM5"    "TOMM70"  
##  [7] "MTCH2"    "TOMM22"   "HSPA4"    "MTX2"     "TOMM7"    "TOMM6"   
## [13] "MTCH1"    "TOMM20"  
## 
## [[1]]$`DOWN genesets.GO:0045277 respiratory chain complex IV`
##  [1] "MT-CO1"  "MT-CO3"  "COX7A2L" "COX7A2"  "COX4I1"  "COX5A"   "MT-CO2" 
##  [8] "COX7C"   "COX6A1"  "COX7A1"  "COX6C"   "COX7B"   "COX6B1"  "NDUFA4" 
## [15] "COX8A"   "COX5B"  
## 
## [[1]]$`DOWN genesets.GO:0046933 proton-transporting ATP synthase activity, rotational mechanism`
##  [1] "MT-ATP8" "ATP5PD"  "ATP5PB"  "ATP5MGL" "ATP6V0C" "ATP5PF"  "MT-ATP6"
##  [8] "ATP5F1B" "ATP5PO"  "ATP5MG"  "ATP5F1C" "ATP5MF"  "ATP5F1A" "ATP6V1A"
## [15] "ATP5F1D" "ATP5F1E" "ATP5ME" 
## 
## [[1]]$`DOWN genesets.GO:0051086 chaperone mediated protein folding independent of cofactor`
## [1] "CCT5"  "CCT2"  "CCT8"  "CCT7"  "CCT4"  "TCP1"  "CCT6A" "CCT3" 
## 
## [[1]]$`DOWN genesets.GO:0140410 monoatomic cation:bicarbonate symporter activity`
## [1] "SLC39A8"  "SLC39A4"  "SLC39A12" "SLC39A10" "SLC39A14" "SLC39A6" 
## 
## [[1]]$`DOWN genesets.GO:1904874 positive regulation of telomerase RNA localization to Cajal body`
## [1] "CCT5"  "CCT2"  "CCT8"  "CCT7"  "CCT4"  "TCP1"  "DKC1"  "CCT6A" "CCT3" 
## 
## [[1]]$`DOWN genesets.GO:2000001 regulation of DNA damage checkpoint`
##  [1] "RNASEH2B" "ETAA1"    "BARD1"    "WDR76"    "BRCA1"    "RAD51"   
##  [7] "CUL4A"    "BRCC3"    "RFWD3"    "BRCA2"    "FEM1B"    "FBXO4"   
## [13] "RPA2"     "CRY1"     "BABAM2"

Combined.

mm4 <- merge(m4a,m4m,by=0)

head(mm4)
##   Row.names         x.x         x.y
## 1      A1BG -0.73042642  0.58959250
## 2  A1BG-AS1  0.02730344 -0.86115057
## 3       A2M -2.85879532 -0.09167325
## 4   A2M-AS1  0.06208747  0.45344070
## 5 A2ML1-AS1  0.83144312 -0.16587319
## 6      AAAS  0.08514238 -0.13528728
rownames(mm4) <- mm4[,1]
mm4[,1]=NULL
colnames(mm4) <- c("Alv","MDM")
plot(mm4)
mylm <- lm(mm4)
abline(mylm,col="red",lty=2,lwd=3)

summary(mylm)
## 
## Call:
## lm(formula = mm4)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -5.6127 -0.4063 -0.0135  0.3781  7.6324 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) -0.008888   0.005744  -1.547    0.122    
## MDM          0.084249   0.007116  11.840   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.7137 on 15437 degrees of freedom
## Multiple R-squared:  0.008999,   Adjusted R-squared:  0.008935 
## F-statistic: 140.2 on 1 and 15437 DF,  p-value: < 2.2e-16
cor.test(mm4$Alv,mm4$MDM)
## 
##  Pearson's product-moment correlation
## 
## data:  mm4$Alv and mm4$MDM
## t = 11.84, df = 15437, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.07920745 0.11047183
## sample estimates:
##        cor 
## 0.09486303
mm4r <- as.data.frame(apply(mm4,2,rank))
plot(mm4r,cex=0.3)
mylm <- lm(mm4r)
abline(mylm,col="red",lty=2,lwd=3)

summary(mylm)
## 
## Call:
## lm(formula = mm4r)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -7983.3 -3873.6     1.1  3878.5  7904.0 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 7.417e+03  7.169e+01 103.456  < 2e-16 ***
## MDM         3.927e-02  8.042e-03   4.882 1.06e-06 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4454 on 15437 degrees of freedom
## Multiple R-squared:  0.001542,   Adjusted R-squared:  0.001477 
## F-statistic: 23.84 on 1 and 15437 DF,  p-value: 1.058e-06
cor.test(mm4r$Alv,mm4r$MDM)
## 
##  Pearson's product-moment correlation
## 
## data:  mm4r$Alv and mm4r$MDM
## t = 4.8824, df = 15437, p-value = 1.058e-06
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.02350650 0.05500608
## sample estimates:
##        cor 
## 0.03926604

Cross comparison pathway enrichment heatmap

l1 <- list("de1a"=de1af,"de1m"=de1mf,"de2a"=de2af,"de2m"=de2mf,
  "de3a"=de3af,"de3m"=de3mf,"de4a"=de4af,"de4m"=de4mf)

lm <- mitch_import(x=l1,DEtype="deseq2",joinType="inner")
## Note: Mean no. genes in input = 15289.5
## Note: no. genes in output = 13075
## Note: estimated proportion of input genes in output = 0.855
lmres <- mitch_calc(x=lm,genesets=go,minsetsize=5,cores=8,priority="effect")
## Note: Enrichments with large effect sizes may not be 
##             statistically significant.
top <- head(lmres$enrichment_result,50)

top %>%
  kbl(caption="Top pathways across all contrasts") %>%
  kable_paper("hover", full_width = F)
Top pathways across all contrasts
set setSize pMANOVA s.de1a s.de1m s.de2a s.de2m s.de3a s.de3m s.de4a s.de4m p.de1a p.de1m p.de2a p.de2m p.de3a p.de3m p.de4a p.de4m s.dist SD p.adjustMANOVA
1987 GO:0019773 proteasome core complex, alpha-subunit complex 7 0.0000001 0.7198609 0.9220779 -0.1322970 -0.9440072 0.2348157 0.7565919 -0.4139446 0.8932616 0.0009727 0.0000239 0.5444849 0.0000152 0.2820643 0.0005269 0.0579106 0.0000425 1.968227 0.6923635 0.0000059
2525 GO:0032395 MHC class II receptor activity 6 0.0000000 -0.7071951 -0.9471268 -0.3660061 0.8306425 -0.4173489 -0.8384472 0.8101615 -0.0952636 0.0027005 0.0000586 0.1205668 0.0004254 0.0766951 0.0003752 0.0005884 0.6861840 1.940029 0.6958394 0.0000002
827 GO:0005942 phosphatidylinositol 3-kinase complex 6 0.0015315 -0.6404979 -0.8948402 -0.5544928 0.6804142 -0.5647206 -0.7413217 0.6072130 -0.5483715 0.0065896 0.0001469 0.0186729 0.0038983 0.0166027 0.0016624 0.0100044 0.0200171 1.875977 0.6137806 0.0197460
3196 GO:0042613 MHC class II protein complex 12 0.0000000 -0.6734670 -0.8492689 -0.4110720 0.3985430 -0.4513384 -0.8054429 0.7589247 0.0315395 0.0000535 0.0000003 0.0136879 0.0168395 0.0067913 0.0000014 0.0000053 0.8499894 1.712319 0.5893394 0.0000000
368 GO:0002503 peptide antigen assembly with MHC class II protein complex 11 0.0000000 -0.6442409 -0.8375271 -0.4341563 0.3513890 -0.4085899 -0.7894004 0.7419557 0.0894895 0.0002157 0.0000015 0.0126652 0.0436235 0.0189657 0.0000058 0.0000203 0.6073812 1.666454 0.5745726 0.0000002
3599 GO:0045656 negative regulation of monocyte differentiation 5 0.0607948 -0.6818057 -0.5468401 -0.7133588 0.2757460 -0.8536802 -0.6190666 0.3223259 -0.4089671 0.0082853 0.0342194 0.0057372 0.2856664 0.0009463 0.0165204 0.2120156 0.1132974 1.652867 0.4521965 0.2427435
1998 GO:0019864 IgG binding 6 0.0000005 -0.2400847 -0.4122988 -0.8498227 -0.6933966 -0.7784579 -0.7599918 -0.3389956 0.0269340 0.3085439 0.0803309 0.0003119 0.0032677 0.0009588 0.0012643 0.1504835 0.9090523 1.652228 0.3124731 0.0000176
3042 GO:0036402 proteasome-activating activity 6 0.0000074 0.6538118 0.6682990 -0.4381360 -0.4924376 0.1339302 0.8059020 -0.4419364 0.6542964 0.0055475 0.0045845 0.0631162 0.0367320 0.5700103 0.0006290 0.0608624 0.0055125 1.612259 0.5733972 0.0002037
1418 GO:0008541 proteasome regulatory particle, lid subcomplex 8 0.0000072 0.6482743 0.7791000 -0.2373728 -0.5253119 0.1988023 0.7245925 -0.5180034 0.6246652 0.0014972 0.0001355 0.2450538 0.0100884 0.3302775 0.0003864 0.0111813 0.0022168 1.607061 0.5636140 0.0002012
3179 GO:0042555 MCM complex 10 0.0000007 -0.1325679 -0.2704937 -0.6551856 0.0448220 -0.7115653 -0.6742595 -0.5801760 -0.8623957 0.4679831 0.1386309 0.0003335 0.8061596 0.0000975 0.0002223 0.0014888 0.0000023 1.601031 0.3203459 0.0000265
791 GO:0005839 proteasome core complex 18 0.0000000 0.5116285 0.6724022 -0.2888617 -0.8836299 0.1834520 0.4267358 -0.2009905 0.8395922 0.0001714 0.0000008 0.0339042 0.0000000 0.1779540 0.0017245 0.1399772 0.0000000 1.593487 0.5782545 0.0000000
3678 GO:0045987 positive regulation of smooth muscle contraction 5 0.0304436 0.7642846 0.2450803 0.4784698 0.4037643 0.8009793 0.7751186 -0.0646366 0.4513236 0.0030793 0.3426531 0.0639260 0.1179592 0.0019231 0.0026850 0.8023825 0.0805386 1.576833 0.2998493 0.1547700
4054 GO:0051086 chaperone mediated protein folding independent of cofactor 8 0.0000000 0.6631400 0.5788819 -0.5599028 -0.6193273 -0.2695913 0.2913446 -0.7399939 0.4717227 0.0011619 0.0045793 0.0061021 0.0024183 0.1867562 0.1536451 0.0002893 0.0208734 1.549061 0.5849751 0.0000014
4429 GO:0070106 interleukin-27-mediated signaling pathway 8 0.0000000 -0.4298615 -0.5672304 -0.4150149 0.0131055 0.6358575 0.0347249 0.7889340 0.8283845 0.0352726 0.0054670 0.0421037 0.9488285 0.0018433 0.8649722 0.0001113 0.0000495 1.546964 0.5725046 0.0000000
3077 GO:0038156 interleukin-3-mediated signaling pathway 5 0.0117161 -0.6956389 -0.2021423 -0.7019434 -0.0579648 -0.8949350 -0.6255241 0.3069931 -0.2623106 0.0070643 0.4338160 0.0065634 0.8224207 0.0005285 0.0154260 0.2345694 0.3097945 1.541460 0.4051056 0.0839876
105 GO:0000727 double-strand break repair via break-induced replication 8 0.0000074 0.0594819 -0.0634040 -0.6668707 -0.2268118 -0.6160366 -0.6618007 -0.6697597 -0.7734752 0.7708341 0.7561878 0.0010895 0.2666861 0.0025507 0.0011890 0.0010362 0.0001514 1.538844 0.3231958 0.0002037
5226 GO:1902254 negative regulation of intrinsic apoptotic signaling pathway by p53 class mediator 6 0.0000509 0.2606167 -0.1558650 0.6989568 0.3803913 0.6752366 0.5100110 0.5718877 0.7534114 0.2689995 0.5085675 0.0030273 0.1066535 0.0041793 0.0305194 0.0152748 0.0013933 1.528461 0.2999742 0.0011203
1213 GO:0007221 positive regulation of transcription of Notch receptor target 6 0.0012151 -0.7492795 -0.6390185 -0.2336828 0.6810263 -0.6974520 -0.3394547 -0.3012727 -0.3577677 0.0014804 0.0067156 0.3216229 0.0038663 0.0030907 0.1499316 0.2013142 0.1291522 1.519408 0.4534699 0.0165078
3024 GO:0036150 phosphatidylserine acyl-chain remodeling 5 0.0466374 -0.3938179 -0.2743994 -0.7995103 -0.3382402 -0.7624484 -0.7507269 0.0714920 -0.4165876 0.1272889 0.2880258 0.0019604 0.1903088 0.0031512 0.0036469 0.7819274 0.1067327 1.519074 0.2998225 0.2042221
47 GO:0000221 vacuolar proton-transporting V-type ATPase, V1 domain 8 0.0009809 0.5838371 0.7287059 0.5061414 -0.6398179 0.5702916 0.2829839 -0.5789776 0.1417311 0.0042430 0.0003579 0.0131799 0.0017257 0.0052199 0.1657999 0.0045726 0.4876413 1.515929 0.5318536 0.0138446
483 GO:0004045 aminoacyl-tRNA hydrolase activity 5 0.0974190 0.6869472 0.6803060 0.2182402 -0.4733282 0.6134353 0.6534353 -0.1540015 0.4813466 0.0078110 0.0084284 0.3981053 0.0668347 0.0175300 0.0113956 0.5509893 0.0623447 1.505016 0.4390754 0.3151987
4734 GO:0075525 viral translational termination-reinitiation 5 0.0030691 -0.5858914 0.0003673 -0.3707728 -0.7438409 -0.7521041 -0.5903902 -0.5181943 0.1986228 0.0232854 0.9988654 0.1511044 0.0039703 0.0035852 0.0222458 0.0447990 0.4418631 1.502078 0.3470666 0.0328751
3573 GO:0045569 TRAIL binding 5 0.0001069 0.3922265 0.3068707 0.5321500 0.3189594 0.8076205 0.5745371 0.4373986 0.6606274 0.1288335 0.2347561 0.0393427 0.2168281 0.0017625 0.0260984 0.0903328 0.0105220 1.497672 0.1742388 0.0021352
5277 GO:1903238 positive regulation of leukocyte tethering or rolling 5 0.0614689 -0.7262739 -0.5791584 -0.5320888 0.0113236 -0.6599847 -0.6715532 0.2380413 -0.3060444 0.0049163 0.0249198 0.0393654 0.9650290 0.0105976 0.0093087 0.3566952 0.2360188 1.477510 0.3550376 0.2435149
3067 GO:0038094 Fc-gamma receptor signaling pathway 7 0.0000070 -0.3132625 -0.3504744 -0.6935808 -0.6609384 -0.7200140 -0.6897547 -0.1716297 0.0763698 0.1512631 0.1083681 0.0014837 0.0024599 0.0009703 0.0015760 0.4317329 0.7264559 1.472525 0.2968016 0.0001954
790 GO:0005838 proteasome regulatory particle 8 0.0000133 0.6499388 0.6285490 -0.3504247 -0.5342466 0.1046338 0.6050547 -0.5018367 0.5546989 0.0014557 0.0020800 0.0861381 0.0088822 0.6083741 0.0030420 0.0139797 0.0065926 1.470470 0.5338718 0.0003458
4491 GO:0070508 cholesterol import 5 0.0368607 0.7091660 0.4615149 0.5840857 0.2861209 0.7674981 0.6108340 -0.1312930 -0.1997552 0.0060291 0.0739317 0.0237143 0.2679268 0.0029572 0.0180143 0.6112062 0.4392648 1.469097 0.3715114 0.1750331
4645 GO:0071541 eukaryotic translation initiation factor 3 complex, eIF3m 7 0.0000192 -0.2418121 0.1148498 -0.6186978 -0.7476497 -0.6903231 -0.3655822 -0.5852901 0.4374481 0.2679718 0.5988052 0.0045878 0.0006133 0.0015620 0.0939756 0.0073286 0.0450631 1.468861 0.4222876 0.0004778
479 GO:0004017 adenylate kinase activity 6 0.0312317 0.4048767 0.4351264 0.7712653 0.0001785 0.7461168 0.6452419 0.1156171 0.4480833 0.0859272 0.0649496 0.0010686 0.9993958 0.0015504 0.0061996 0.6238759 0.0573584 1.461261 0.2791026 0.1569463
1598 GO:0010756 positive regulation of plasminogen activation 5 0.0248233 0.3962663 0.8354093 0.2491813 -0.6272992 0.2024178 0.3537567 -0.7884009 0.1645907 0.1249407 0.0012154 0.3346372 0.0151365 0.4331898 0.1707650 0.0022647 0.5239431 1.457846 0.5409126 0.1355548
1132 GO:0007006 mitochondrial membrane organization 5 0.0283058 0.6815608 0.3571538 0.6098852 0.1513083 0.7026779 0.4737873 -0.6112318 0.1861974 0.0083085 0.1666941 0.0181938 0.5579760 0.0065072 0.0665706 0.0179395 0.4709466 1.453768 0.4309087 0.1474869
4847 GO:0097250 mitochondrial respirasome assembly 6 0.0121684 0.1389293 0.7539980 0.7679241 -0.5550539 0.4332900 0.4157676 -0.3547071 0.3588390 0.5557008 0.0013813 0.0011235 0.0185537 0.0660897 0.0778189 0.1324602 0.1280097 1.449411 0.4812318 0.0860124
3206 GO:0042719 mitochondrial intermembrane space protein transporter complex 6 0.0332854 0.6409570 0.5807891 0.6859744 -0.2810978 0.7625679 0.4160992 -0.1625730 0.0887086 0.0065509 0.0137563 0.0036158 0.2331665 0.0012169 0.0775822 0.4904955 0.7067403 1.444530 0.4060402 0.1636840
1988 GO:0019774 proteasome core complex, beta-subunit complex 10 0.0000000 0.3595561 0.5088404 -0.4429698 -0.8605587 0.1021202 0.2054650 -0.1294910 0.8272331 0.0490020 0.0053344 0.0152933 0.0000024 0.5761132 0.2606453 0.4783746 0.0000059 1.441773 0.5395857 0.0000000
349 GO:0002260 lymphocyte homeostasis 5 0.0763802 -0.3490130 -0.5455853 -0.4410712 0.3204591 -0.5092578 -0.7122265 -0.1585004 -0.7523795 0.1765734 0.0346336 0.0876611 0.2146748 0.0486178 0.0058147 0.5394151 0.0035730 1.440319 0.3456082 0.2733027
5361 GO:1904874 positive regulation of telomerase RNA localization to Cajal body 9 0.0000001 0.6159498 0.5780907 -0.4853819 -0.5394493 -0.2369679 0.3240642 -0.7264826 0.3747470 0.0013753 0.0026729 0.0116917 0.0050748 0.2183919 0.0923292 0.0001605 0.0515914 1.438599 0.5435899 0.0000040
340 GO:0002199 zona pellucida receptor complex 5 0.0006480 0.6785922 0.4699311 -0.4676052 -0.4716450 -0.1518592 0.3176435 -0.7005356 0.5753022 0.0085947 0.0688156 0.0701995 0.0678102 0.5565434 0.2187306 0.0066724 0.0259000 1.438092 0.5425214 0.0097283
2053 GO:0021952 central nervous system projection neuron axonogenesis 5 0.0003197 -0.7886764 -0.4321653 -0.3825861 0.1517674 -0.4785922 -0.2923336 0.6062127 0.6254323 0.0022566 0.0942528 0.1385036 0.5567821 0.0638580 0.2576739 0.0189036 0.0154411 1.432254 0.5248954 0.0054794
2110 GO:0030091 protein repair 5 0.0171208 0.6043152 0.6302372 0.2398470 -0.3611324 0.3477276 0.5656924 -0.3666412 0.7218669 0.0192798 0.0146679 0.3530590 0.1620198 0.1781724 0.0284887 0.1557118 0.0051836 1.430657 0.4371319 0.1077385
2924 GO:0035456 response to interferon-beta 9 0.0000000 -0.5181047 -0.5177645 -0.3364457 0.1702638 0.5500791 -0.0961103 0.9119853 0.4642924 0.0071166 0.0071544 0.0805408 0.3765123 0.0042701 0.6176478 0.0000022 0.0158765 1.427518 0.5329806 0.0000000
830 GO:0005955 calcineurin complex 5 0.0402599 -0.0792655 -0.6097934 -0.7821882 0.6596480 -0.5644070 -0.3829839 0.0060903 -0.3624178 0.7589146 0.0182113 0.0024531 0.0106373 0.0288513 0.1380937 0.9811870 0.1605309 1.421865 0.4570682 0.1853168
3765 GO:0046934 1-phosphatidylinositol-4,5-bisphosphate 3-kinase activity 7 0.0216895 -0.2101098 -0.7934103 -0.3800560 0.5776160 -0.2936071 -0.6384844 0.4108400 -0.4456469 0.3357929 0.0002775 0.0816654 0.0081363 0.1786141 0.0034410 0.0598158 0.0411881 1.418798 0.4810864 0.1233487
3578 GO:0045588 positive regulation of gamma-delta T cell differentiation 6 0.0151118 -0.5740046 -0.3755452 -0.4383146 -0.0854184 -0.5340373 -0.7198204 0.2007040 -0.7043130 0.0149009 0.1111910 0.0630088 0.7171407 0.0234995 0.0022620 0.3946306 0.0028110 1.417606 0.3173303 0.1005647
2069 GO:0022624 proteasome accessory complex 17 0.0000000 0.6215167 0.5722253 -0.3529592 -0.4353608 0.1177822 0.6302109 -0.4833728 0.5707928 0.0000091 0.0000441 0.0117669 0.0018877 0.4006185 0.0000068 0.0005602 0.0000461 1.413625 0.5079197 0.0000000
3504 GO:0045053 protein retention in Golgi apparatus 5 0.0677346 -0.1715073 -0.7837796 -0.5359143 0.6868248 -0.4174445 -0.5554705 0.0175363 -0.3243152 0.5066520 0.0024035 0.0379715 0.0078220 0.1060137 0.0314840 0.9458664 0.2092084 1.411011 0.4548209 0.2568466
2188 GO:0030292 protein tyrosine kinase inhibitor activity 5 0.0996089 -0.7665800 -0.3145830 -0.4962510 -0.2270543 -0.7956848 -0.5987758 0.0598011 0.0261056 0.0029916 0.2232012 0.0546616 0.3793262 0.0020606 0.0204155 0.8168935 0.9194889 1.407242 0.3314399 0.3186797
4570 GO:0071162 CMG complex 9 0.0000184 0.0238107 -0.0541184 -0.5460313 -0.1770669 -0.4902971 -0.6644727 -0.4695308 -0.8599078 0.9015767 0.7786458 0.0045618 0.3577418 0.0108699 0.0005565 0.0147297 0.0000079 1.405281 0.3081155 0.0004594
2351 GO:0031123 RNA 3’-end processing 9 0.0063220 -0.1621851 -0.7052741 -0.5452999 0.4007177 -0.3891695 -0.6810041 0.3025154 -0.5133935 0.3995755 0.0002483 0.0046164 0.0373930 0.0432329 0.0004033 0.1161132 0.0076563 1.397122 0.4300608 0.0558947
4567 GO:0071139 resolution of DNA recombination intermediates 5 0.1149487 -0.5222035 -0.3285386 -0.3625096 0.0632594 -0.7061056 -0.7176129 -0.0635960 -0.6463351 0.0431698 0.2033379 0.1604250 0.8065087 0.0062505 0.0054541 0.8054996 0.0123206 1.396924 0.2936489 0.3409436
4270 GO:0060316 positive regulation of ryanodine-sensitive calcium-release channel activity 5 0.0014582 0.1617445 0.7330681 -0.2814384 -0.8426626 -0.1401989 0.0746748 -0.7278041 0.1735272 0.5311453 0.0045286 0.2758372 0.0011010 0.5872431 0.7724805 0.0048265 0.5016596 1.392078 0.5137761 0.0189773 
colfunc <- colorRampPalette(c("blue", "white", "red"))

mx <- top[,grep("^s\\.",colnames(top))]
mx <- mx[,-ncol(mx)]
rownames(mx) <- top$set

heatmap.2(as.matrix(mx),scale="none",trace="none",margins=c(6,25),
  col=colfunc(25),cexRow=0.6,cexCol=0.8)

Session information

For reproducibility.

save.image("scanalysis.Rdata")

sessionInfo()
## R version 4.5.0 (2025-04-11)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 22.04.5 LTS
## 
## Matrix products: default
## BLAS:   /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.10.0 
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0  LAPACK version 3.10.0
## 
## locale:
##  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
##  [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
##  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
##  [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
##  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
## 
## time zone: Australia/Melbourne
## tzcode source: system (glibc)
## 
## attached base packages:
## [1] parallel  stats4    stats     graphics  grDevices utils     datasets 
## [8] methods   base     
## 
## other attached packages:
##  [1] future_1.40.0               gplots_3.2.0               
##  [3] limma_3.64.0                SingleR_2.10.0             
##  [5] celldex_1.18.0              harmony_1.2.3              
##  [7] Rcpp_1.0.14                 mitch_1.20.0               
##  [9] DESeq2_1.48.0               muscat_1.22.0              
## [11] beeswarm_0.4.0              stringi_1.8.7              
## [13] SingleCellExperiment_1.30.0 SummarizedExperiment_1.38.0
## [15] Biobase_2.68.0              GenomicRanges_1.60.0       
## [17] GenomeInfoDb_1.44.0         IRanges_2.42.0             
## [19] S4Vectors_0.46.0            BiocGenerics_0.54.0        
## [21] generics_0.1.3              MatrixGenerics_1.20.0      
## [23] matrixStats_1.5.0           hdf5r_1.3.12               
## [25] Seurat_5.3.0                SeuratObject_5.1.0         
## [27] sp_2.2-0                    plyr_1.8.9                 
## [29] ggplot2_3.5.2               kableExtra_1.4.0           
## 
## loaded via a namespace (and not attached):
##   [1] dichromat_2.0-0.1         progress_1.2.3           
##   [3] goftest_1.2-3             HDF5Array_1.36.0         
##   [5] Biostrings_2.76.0         vctrs_0.6.5              
##   [7] spatstat.random_3.3-3     digest_0.6.37            
##   [9] png_0.1-8                 corpcor_1.6.10           
##  [11] shape_1.4.6.1             gypsum_1.4.0             
##  [13] ggrepel_0.9.6             echarts4r_0.4.5          
##  [15] deldir_2.0-4              parallelly_1.43.0        
##  [17] MASS_7.3-65               reshape2_1.4.4           
##  [19] httpuv_1.6.16             foreach_1.5.2            
##  [21] withr_3.0.2               xfun_0.52                
##  [23] survival_3.8-3            memoise_2.0.1.9000       
##  [25] ggbeeswarm_0.7.2          systemfonts_1.2.2        
##  [27] zoo_1.8-14                GlobalOptions_0.1.2      
##  [29] gtools_3.9.5              pbapply_1.7-2            
##  [31] prettyunits_1.2.0         GGally_2.2.1             
##  [33] KEGGREST_1.48.0           promises_1.3.2           
##  [35] httr_1.4.7                globals_0.17.0           
##  [37] fitdistrplus_1.2-2        rhdf5filters_1.20.0      
##  [39] rhdf5_2.52.0              rstudioapi_0.17.1        
##  [41] UCSC.utils_1.4.0          miniUI_0.1.2             
##  [43] curl_6.2.2                h5mread_1.0.0            
##  [45] ScaledMatrix_1.16.0       polyclip_1.10-7          
##  [47] GenomeInfoDbData_1.2.14   ExperimentHub_2.16.0     
##  [49] SparseArray_1.8.0         xtable_1.8-4             
##  [51] stringr_1.5.1             doParallel_1.0.17        
##  [53] evaluate_1.0.3            S4Arrays_1.8.0           
##  [55] BiocFileCache_2.16.0      hms_1.1.3                
##  [57] irlba_2.3.5.1             colorspace_2.1-1         
##  [59] filelock_1.0.3            ROCR_1.0-11              
##  [61] reticulate_1.42.0         spatstat.data_3.1-6      
##  [63] magrittr_2.0.3            lmtest_0.9-40            
##  [65] later_1.4.2               viridis_0.6.5            
##  [67] lattice_0.22-7            spatstat.geom_3.3-6      
##  [69] future.apply_1.11.3       scattermore_1.2          
##  [71] scuttle_1.18.0            cowplot_1.1.3            
##  [73] RcppAnnoy_0.0.22          pillar_1.10.2            
##  [75] nlme_3.1-168              iterators_1.0.14         
##  [77] caTools_1.18.3            compiler_4.5.0           
##  [79] beachmat_2.24.0           RSpectra_0.16-2          
##  [81] tensor_1.5                minqa_1.2.8              
##  [83] crayon_1.5.3              abind_1.4-8              
##  [85] scater_1.36.0             blme_1.0-6               
##  [87] locfit_1.5-9.12           bit_4.6.0                
##  [89] dplyr_1.1.4               codetools_0.2-20         
##  [91] BiocSingular_1.24.0       bslib_0.9.0              
##  [93] alabaster.ranges_1.8.0    GetoptLong_1.0.5         
##  [95] plotly_4.10.4             remaCor_0.0.18           
##  [97] mime_0.13                 splines_4.5.0            
##  [99] circlize_0.4.16           fastDummies_1.7.5        
## [101] dbplyr_2.5.0              sparseMatrixStats_1.20.0 
## [103] knitr_1.50                blob_1.2.4               
## [105] clue_0.3-66               BiocVersion_3.21.1       
## [107] lme4_1.1-37               listenv_0.9.1            
## [109] DelayedMatrixStats_1.30.0 Rdpack_2.6.4             
## [111] tibble_3.2.1              Matrix_1.7-3             
## [113] statmod_1.5.0             svglite_2.1.3            
## [115] fANCOVA_0.6-1             pkgconfig_2.0.3          
## [117] network_1.19.0            tools_4.5.0              
## [119] cachem_1.1.0              RhpcBLASctl_0.23-42      
## [121] rbibutils_2.3             RSQLite_2.3.9            
## [123] viridisLite_0.4.2         DBI_1.2.3                
## [125] numDeriv_2016.8-1.1       fastmap_1.2.0            
## [127] rmarkdown_2.29            scales_1.4.0             
## [129] grid_4.5.0                ica_1.0-3                
## [131] broom_1.0.8               AnnotationHub_3.16.0     
## [133] sass_0.4.10               patchwork_1.3.0          
## [135] coda_0.19-4.1             BiocManager_1.30.25      
## [137] ggstats_0.9.0             dotCall64_1.2            
## [139] RANN_2.6.2                alabaster.schemas_1.8.0  
## [141] farver_2.1.2              reformulas_0.4.0         
## [143] aod_1.3.3                 mgcv_1.9-3               
## [145] yaml_2.3.10               cli_3.6.5                
## [147] purrr_1.0.4               lifecycle_1.0.4          
## [149] uwot_0.2.3                glmmTMB_1.1.11           
## [151] mvtnorm_1.3-3             backports_1.5.0          
## [153] BiocParallel_1.42.0       gtable_0.3.6             
## [155] rjson_0.2.23              ggridges_0.5.6           
## [157] progressr_0.15.1          jsonlite_2.0.0           
## [159] edgeR_4.6.1               RcppHNSW_0.6.0           
## [161] bitops_1.0-9              bit64_4.6.0-1            
## [163] Rtsne_0.17                alabaster.matrix_1.8.0   
## [165] spatstat.utils_3.1-3      BiocNeighbors_2.2.0      
## [167] alabaster.se_1.8.0        jquerylib_0.1.4          
## [169] spatstat.univar_3.1-2     pbkrtest_0.5.4           
## [171] lazyeval_0.2.2            alabaster.base_1.8.0     
## [173] shiny_1.10.0              htmltools_0.5.8.1        
## [175] sctransform_0.4.1         rappdirs_0.3.3           
## [177] glue_1.8.0                spam_2.11-1              
## [179] httr2_1.1.2               XVector_0.48.0           
## [181] gridExtra_2.3             EnvStats_3.1.0           
## [183] boot_1.3-31               igraph_2.1.4             
## [185] variancePartition_1.38.0  TMB_1.9.17               
## [187] R6_2.6.1                  tidyr_1.3.1              
## [189] labeling_0.4.3            cluster_2.1.8.1          
## [191] Rhdf5lib_1.30.0           nloptr_2.2.1             
## [193] statnet.common_4.11.0     DelayedArray_0.34.1      
## [195] tidyselect_1.2.1          vipor_0.4.7              
## [197] xml2_1.3.8                AnnotationDbi_1.70.0     
## [199] rsvd_1.0.5                KernSmooth_2.23-26       
## [201] data.table_1.17.0         htmlwidgets_1.6.4        
## [203] ComplexHeatmap_2.24.0     RColorBrewer_1.1-3       
## [205] rlang_1.1.6               spatstat.sparse_3.1-0    
## [207] spatstat.explore_3.4-2    lmerTest_3.1-3