Epilepsy
The Gene Signature Commons Group
2020-10-16
Source: https://github.com/markziemann/gene_sig_commons
Background
This analysis is an example of how gene signatures can be generated from publicly available omics data. In this example, we will obtain data from the DEE2 database, perform differential analysis with DESeq2 and then return the gene signature.
source("../de_functions.R")# let's assume species is human for now
SPECIES = "hsapiens"
# read in the file
x <- readLines("../contrasts/epilepsy.md")
# this is the best way to get studies with contrasts set up
x <- x[grep("RP",x)]
# how many contrasts to do?
length(x)## [1] 8# prepare by deleting the directory called "gmt"
unlink("gmt", recursive = TRUE)
# get the metadata now to save time
mdat <- getDEE2::getDEE2Metadata(species = SPECIES)
# lets prototype this: main(x[[2]],mdat)
# now go ahead and run the whole thing
data <- lapply(x,function(x) { main(x,mdat) })## SRP222346: mock treatment versus dCas9 transduced SH-SY5Y cells:mock; SRX6867493, SRX6867494: dCas9; SRX6867495 , SRX6867496 , SRX6867497;## For more information about DEE2 QC metrics, visit
## https://github.com/markziemann/dee2/blob/master/qc/qc_metrics.md## List of 8
## $ GeneCounts :'data.frame': 58302 obs. of 4 variables:
## ..$ SRR10139483: int [1:58302] 1 101 4 0 0 0 0 0 0 0 ...
## ..$ SRR10139485: int [1:58302] 1 243 0 2 0 0 0 0 0 0 ...
## ..$ SRR10139486: int [1:58302] 0 166 2 1 0 0 0 0 0 0 ...
## ..$ SRR10139487: int [1:58302] 0 107 0 1 0 0 0 0 0 0 ...
## $ TxCounts :'data.frame': 180869 obs. of 4 variables:
## ..$ SRR10139483: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139485: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139486: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139487: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## $ GeneInfo :'data.frame': 58302 obs. of 5 variables:
## ..$ GeneSymbol : chr [1:58302] "DDX11L1" "WASH7P" "MIR6859-1" "MIR1302-2HG" ...
## ..$ mean : int [1:58302] 973 1351 68 641 138 948 840 1295 2227 1082 ...
## ..$ median : int [1:58302] 632 1351 68 712 138 1187 840 1414 2618 629 ...
## ..$ longest_isoform: int [1:58302] 1657 1351 68 712 138 1187 840 1414 2618 2748 ...
## ..$ merged : int [1:58302] 1735 1351 68 1021 138 1219 840 1414 2618 3726 ...
## $ TxInfo :'data.frame': 180869 obs. of 3 variables:
## ..$ GeneID : chr [1:180869] "ENSG00000237235.2" "ENSG00000228985.1" "ENSG00000223997.1" "ENSG00000282253.1" ...
## ..$ GeneSymbol: chr [1:180869] "TRDD2" "TRDD3" "TRDD1" "AC239618.6" ...
## ..$ TxLength : int [1:180869] 9 13 8 12 12 17 20 19 16 18 ...
## $ QcMx :'data.frame': 30 obs. of 4 variables:
## ..$ SRR10139483: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139485: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139486: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139487: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## $ MetadataSummary:'data.frame': 4 obs. of 7 variables:
## ..$ QC_summary : chr [1:4] "PASS" "PASS" "PASS" "PASS"
## ..$ SRX_accession: chr [1:4] "SRX6867493" "SRX6867495" "SRX6867496" "SRX6867497"
## ..$ SRS_accession: chr [1:4] "SRS5404929" "SRS5404931" "SRS5404932" "SRS5404933"
## ..$ SRP_accession: chr [1:4] "SRP222346" "SRP222346" "SRP222346" "SRP222346"
## ..$ Sample_name : chr [1:4] "GSM4083893" "GSM4083895" "GSM4083896" "GSM4083897"
## ..$ GEO_series : chr [1:4] "GSE137663" "GSE137663" "GSE137663" "GSE137663"
## ..$ Library_name : logi [1:4] NA NA NA NA
## $ MetadataFull :'data.frame': 4 obs. of 52 variables:
## ..$ QC_summary : chr [1:4] "PASS" "PASS" "PASS" "PASS"
## ..$ SRX_accession : chr [1:4] "SRX6867493" "SRX6867495" "SRX6867496" "SRX6867497"
## ..$ SRS_accession : chr [1:4] "SRS5404929" "SRS5404931" "SRS5404932" "SRS5404933"
## ..$ SRP_accession : chr [1:4] "SRP222346" "SRP222346" "SRP222346" "SRP222346"
## ..$ Sample_name : chr [1:4] "GSM4083893" "GSM4083895" "GSM4083896" "GSM4083897"
## ..$ GEO_series : chr [1:4] "GSE137663" "GSE137663" "GSE137663" "GSE137663"
## ..$ Library_name : logi [1:4] NA NA NA NA
## ..$ SampleName : chr [1:4] "GSM4083893" "GSM4083895" "GSM4083896" "GSM4083897"
## ..$ ReleaseDate : chr [1:4] "2020-01-02 09:35:26" "2020-01-02 09:35:26" "2020-01-02 09:35:26" "2020-01-02 09:35:27"
## ..$ LoadDate : chr [1:4] "2019-09-18 16:14:29" "2019-09-18 16:31:25" "2019-09-18 16:18:21" "2019-09-18 16:16:55"
## ..$ spots : int [1:4] 22316828 35473828 21219962 19974486
## ..$ bases : num [1:4] 6.74e+09 1.07e+10 6.41e+09 6.03e+09
## ..$ spots_with_mates : int [1:4] 22316828 35473828 21219962 19974486
## ..$ avgLength : int [1:4] 302 302 302 302
## ..$ size_MB : int [1:4] 3134 4688 2798 2660
## ..$ AssemblyName : logi [1:4] NA NA NA NA
## ..$ download_path : chr [1:4] "https://sra-download.ncbi.nlm.nih.gov/traces/sra15/SRR/009901/SRR10139483" "https://sra-download.ncbi.nlm.nih.gov/traces/sra20/SRR/009901/SRR10139485" "https://sra-download.ncbi.nlm.nih.gov/traces/sra4/SRR/009901/SRR10139486" "https://sra-download.ncbi.nlm.nih.gov/traces/sra12/SRR/009901/SRR10139487"
## ..$ LibraryName : logi [1:4] NA NA NA NA
## ..$ LibraryStrategy : chr [1:4] "RNA-Seq" "RNA-Seq" "RNA-Seq" "RNA-Seq"
## ..$ LibrarySelection : chr [1:4] "cDNA" "cDNA" "cDNA" "cDNA"
## ..$ LibrarySource : chr [1:4] "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC"
## ..$ LibraryLayout : chr [1:4] "PAIRED" "PAIRED" "PAIRED" "PAIRED"
## ..$ InsertSize : int [1:4] 0 0 0 0
## ..$ InsertDev : num [1:4] 0 0 0 0
## ..$ Platform : chr [1:4] "ILLUMINA" "ILLUMINA" "ILLUMINA" "ILLUMINA"
## ..$ Model : chr [1:4] "Illumina HiSeq 4000" "Illumina HiSeq 4000" "Illumina HiSeq 4000" "Illumina HiSeq 4000"
## ..$ SRAStudy : chr [1:4] "SRP222346" "SRP222346" "SRP222346" "SRP222346"
## ..$ BioProject : chr [1:4] "PRJNA566176" "PRJNA566176" "PRJNA566176" "PRJNA566176"
## ..$ Study_Pubmed_id : int [1:4] 3 3 3 3
## ..$ ProjectID : int [1:4] 566176 566176 566176 566176
## ..$ Sample : chr [1:4] "SRS5404929" "SRS5404931" "SRS5404932" "SRS5404933"
## ..$ BioSample : chr [1:4] "SAMN12783336" "SAMN12783334" "SAMN12783333" "SAMN12783332"
## ..$ SampleType : chr [1:4] "simple" "simple" "simple" "simple"
## ..$ TaxID : int [1:4] 9606 9606 9606 9606
## ..$ ScientificName : chr [1:4] "Homo sapiens" "Homo sapiens" "Homo sapiens" "Homo sapiens"
## ..$ g1k_pop_code : logi [1:4] NA NA NA NA
## ..$ source : logi [1:4] NA NA NA NA
## ..$ g1k_analysis_group : logi [1:4] NA NA NA NA
## ..$ Subject_ID : logi [1:4] NA NA NA NA
## ..$ Sex : logi [1:4] NA NA NA NA
## ..$ Disease : logi [1:4] NA NA NA NA
## ..$ Tumor : chr [1:4] "no" "no" "no" "no"
## ..$ Affection_Status : logi [1:4] NA NA NA NA
## ..$ Analyte_Type : logi [1:4] NA NA NA NA
## ..$ Histological_Type : logi [1:4] NA NA NA NA
## ..$ Body_Site : logi [1:4] NA NA NA NA
## ..$ CenterName : chr [1:4] "GEO" "GEO" "GEO" "GEO"
## ..$ Submission : chr [1:4] "SRA964414" "SRA964414" "SRA964414" "SRA964414"
## ..$ dbgap_study_accession: logi [1:4] NA NA NA NA
## ..$ Consent : chr [1:4] "public" "public" "public" "public"
## ..$ RunHash : chr [1:4] "679F5D4FD993E5632F27FC0C8127970B" "B3CC1CCE229D0D74E282538392193341" "836DEF2E4064B5C3314275D8F3B31CA7" "BCFF9CCCF5E86A982610202D9BEBAB82"
## ..$ ReadHash : chr [1:4] "C7D1F4D497C862CFBC7A1FE93F03393A" "09C85CF051642945248374D8FE061A13" "34F36375414F117F84B38A132FD85588" "4F4FFA91983CBB24C270C65C3B8296B7"
## $ absent : chr(0)## SRP222346: dCas9 transduced versus dCas9 with TET1 co-expression in SH-SY5Y cells:dCas9; SRX6867495 , SRX6867496 , SRX6867497:dCas9+TET1; SRX6867498 ,SRX6867499;
## For more information about DEE2 QC metrics, visit
## https://github.com/markziemann/dee2/blob/master/qc/qc_metrics.md## List of 8
## $ GeneCounts :'data.frame': 58302 obs. of 5 variables:
## ..$ SRR10139485: int [1:58302] 1 243 0 2 0 0 0 0 0 0 ...
## ..$ SRR10139486: int [1:58302] 0 166 2 1 0 0 0 0 0 0 ...
## ..$ SRR10139487: int [1:58302] 0 107 0 1 0 0 0 0 0 0 ...
## ..$ SRR10139488: int [1:58302] 0 236 9 2 0 0 0 0 0 0 ...
## ..$ SRR10139489: int [1:58302] 1 129 0 0 0 0 0 0 0 0 ...
## $ TxCounts :'data.frame': 180869 obs. of 5 variables:
## ..$ SRR10139485: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139486: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139487: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139488: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139489: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## $ GeneInfo :'data.frame': 58302 obs. of 5 variables:
## ..$ GeneSymbol : chr [1:58302] "DDX11L1" "WASH7P" "MIR6859-1" "MIR1302-2HG" ...
## ..$ mean : int [1:58302] 973 1351 68 641 138 948 840 1295 2227 1082 ...
## ..$ median : int [1:58302] 632 1351 68 712 138 1187 840 1414 2618 629 ...
## ..$ longest_isoform: int [1:58302] 1657 1351 68 712 138 1187 840 1414 2618 2748 ...
## ..$ merged : int [1:58302] 1735 1351 68 1021 138 1219 840 1414 2618 3726 ...
## $ TxInfo :'data.frame': 180869 obs. of 3 variables:
## ..$ GeneID : chr [1:180869] "ENSG00000237235.2" "ENSG00000228985.1" "ENSG00000223997.1" "ENSG00000282253.1" ...
## ..$ GeneSymbol: chr [1:180869] "TRDD2" "TRDD3" "TRDD1" "AC239618.6" ...
## ..$ TxLength : int [1:180869] 9 13 8 12 12 17 20 19 16 18 ...
## $ QcMx :'data.frame': 30 obs. of 5 variables:
## ..$ SRR10139485: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139486: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139487: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139488: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139489: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## $ MetadataSummary:'data.frame': 5 obs. of 7 variables:
## ..$ QC_summary : chr [1:5] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession: chr [1:5] "SRX6867495" "SRX6867496" "SRX6867497" "SRX6867498" ...
## ..$ SRS_accession: chr [1:5] "SRS5404931" "SRS5404932" "SRS5404933" "SRS5404934" ...
## ..$ SRP_accession: chr [1:5] "SRP222346" "SRP222346" "SRP222346" "SRP222346" ...
## ..$ Sample_name : chr [1:5] "GSM4083895" "GSM4083896" "GSM4083897" "GSM4083898" ...
## ..$ GEO_series : chr [1:5] "GSE137663" "GSE137663" "GSE137663" "GSE137663" ...
## ..$ Library_name : logi [1:5] NA NA NA NA NA
## $ MetadataFull :'data.frame': 5 obs. of 52 variables:
## ..$ QC_summary : chr [1:5] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession : chr [1:5] "SRX6867495" "SRX6867496" "SRX6867497" "SRX6867498" ...
## ..$ SRS_accession : chr [1:5] "SRS5404931" "SRS5404932" "SRS5404933" "SRS5404934" ...
## ..$ SRP_accession : chr [1:5] "SRP222346" "SRP222346" "SRP222346" "SRP222346" ...
## ..$ Sample_name : chr [1:5] "GSM4083895" "GSM4083896" "GSM4083897" "GSM4083898" ...
## ..$ GEO_series : chr [1:5] "GSE137663" "GSE137663" "GSE137663" "GSE137663" ...
## ..$ Library_name : logi [1:5] NA NA NA NA NA
## ..$ SampleName : chr [1:5] "GSM4083895" "GSM4083896" "GSM4083897" "GSM4083898" ...
## ..$ ReleaseDate : chr [1:5] "2020-01-02 09:35:26" "2020-01-02 09:35:26" "2020-01-02 09:35:27" "2020-01-02 09:35:27" ...
## ..$ LoadDate : chr [1:5] "2019-09-18 16:31:25" "2019-09-18 16:18:21" "2019-09-18 16:16:55" "2019-09-18 16:27:33" ...
## ..$ spots : int [1:5] 35473828 21219962 19974486 32060518 17793882
## ..$ bases : num [1:5] 1.07e+10 6.41e+09 6.03e+09 9.68e+09 5.37e+09
## ..$ spots_with_mates : int [1:5] 35473828 21219962 19974486 32060518 17793882
## ..$ avgLength : int [1:5] 302 302 302 302 302
## ..$ size_MB : int [1:5] 4688 2798 2660 4259 2350
## ..$ AssemblyName : logi [1:5] NA NA NA NA NA
## ..$ download_path : chr [1:5] "https://sra-download.ncbi.nlm.nih.gov/traces/sra20/SRR/009901/SRR10139485" "https://sra-download.ncbi.nlm.nih.gov/traces/sra4/SRR/009901/SRR10139486" "https://sra-download.ncbi.nlm.nih.gov/traces/sra12/SRR/009901/SRR10139487" "https://sra-download.ncbi.nlm.nih.gov/traces/sra11/SRR/009901/SRR10139488" ...
## ..$ LibraryName : logi [1:5] NA NA NA NA NA
## ..$ LibraryStrategy : chr [1:5] "RNA-Seq" "RNA-Seq" "RNA-Seq" "RNA-Seq" ...
## ..$ LibrarySelection : chr [1:5] "cDNA" "cDNA" "cDNA" "cDNA" ...
## ..$ LibrarySource : chr [1:5] "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" ...
## ..$ LibraryLayout : chr [1:5] "PAIRED" "PAIRED" "PAIRED" "PAIRED" ...
## ..$ InsertSize : int [1:5] 0 0 0 0 0
## ..$ InsertDev : num [1:5] 0 0 0 0 0
## ..$ Platform : chr [1:5] "ILLUMINA" "ILLUMINA" "ILLUMINA" "ILLUMINA" ...
## ..$ Model : chr [1:5] "Illumina HiSeq 4000" "Illumina HiSeq 4000" "Illumina HiSeq 4000" "Illumina HiSeq 4000" ...
## ..$ SRAStudy : chr [1:5] "SRP222346" "SRP222346" "SRP222346" "SRP222346" ...
## ..$ BioProject : chr [1:5] "PRJNA566176" "PRJNA566176" "PRJNA566176" "PRJNA566176" ...
## ..$ Study_Pubmed_id : int [1:5] 3 3 3 3 3
## ..$ ProjectID : int [1:5] 566176 566176 566176 566176 566176
## ..$ Sample : chr [1:5] "SRS5404931" "SRS5404932" "SRS5404933" "SRS5404934" ...
## ..$ BioSample : chr [1:5] "SAMN12783334" "SAMN12783333" "SAMN12783332" "SAMN12783331" ...
## ..$ SampleType : chr [1:5] "simple" "simple" "simple" "simple" ...
## ..$ TaxID : int [1:5] 9606 9606 9606 9606 9606
## ..$ ScientificName : chr [1:5] "Homo sapiens" "Homo sapiens" "Homo sapiens" "Homo sapiens" ...
## ..$ g1k_pop_code : logi [1:5] NA NA NA NA NA
## ..$ source : logi [1:5] NA NA NA NA NA
## ..$ g1k_analysis_group : logi [1:5] NA NA NA NA NA
## ..$ Subject_ID : logi [1:5] NA NA NA NA NA
## ..$ Sex : logi [1:5] NA NA NA NA NA
## ..$ Disease : logi [1:5] NA NA NA NA NA
## ..$ Tumor : chr [1:5] "no" "no" "no" "no" ...
## ..$ Affection_Status : logi [1:5] NA NA NA NA NA
## ..$ Analyte_Type : logi [1:5] NA NA NA NA NA
## ..$ Histological_Type : logi [1:5] NA NA NA NA NA
## ..$ Body_Site : logi [1:5] NA NA NA NA NA
## ..$ CenterName : chr [1:5] "GEO" "GEO" "GEO" "GEO" ...
## ..$ Submission : chr [1:5] "SRA964414" "SRA964414" "SRA964414" "SRA964414" ...
## ..$ dbgap_study_accession: logi [1:5] NA NA NA NA NA
## ..$ Consent : chr [1:5] "public" "public" "public" "public" ...
## ..$ RunHash : chr [1:5] "B3CC1CCE229D0D74E282538392193341" "836DEF2E4064B5C3314275D8F3B31CA7" "BCFF9CCCF5E86A982610202D9BEBAB82" "4DBBC0EF49E7F021A5A9F5747966C6BC" ...
## ..$ ReadHash : chr [1:5] "09C85CF051642945248374D8FE061A13" "34F36375414F117F84B38A132FD85588" "4F4FFA91983CBB24C270C65C3B8296B7" "168AF1F23FC8EEE3A7AD7CD7AF8BF088" ...
## $ absent : chr(0)## converting counts to integer mode## using supplied model matrix## estimating size factors## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testing
## SRP222346: dCas9 transduced versus dCas9 with VP64 co-expression in SH-SY5Y cells:dCas9; SRX6867495 , SRX6867496 , SRX6867497:dCas9+VP64; SRX6867500, SRX6867501, SRX6867502;## For more information about DEE2 QC metrics, visit
## https://github.com/markziemann/dee2/blob/master/qc/qc_metrics.md
## List of 8
## $ GeneCounts :'data.frame': 58302 obs. of 6 variables:
## ..$ SRR10139485: int [1:58302] 1 243 0 2 0 0 0 0 0 0 ...
## ..$ SRR10139486: int [1:58302] 0 166 2 1 0 0 0 0 0 0 ...
## ..$ SRR10139487: int [1:58302] 0 107 0 1 0 0 0 0 0 0 ...
## ..$ SRR10139490: int [1:58302] 0 151 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139491: int [1:58302] 0 146 1 1 0 0 0 0 0 0 ...
## ..$ SRR10139492: int [1:58302] 0 187 0 0 0 0 0 0 0 0 ...
## $ TxCounts :'data.frame': 180869 obs. of 6 variables:
## ..$ SRR10139485: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139486: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139487: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139490: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139491: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139492: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## $ GeneInfo :'data.frame': 58302 obs. of 5 variables:
## ..$ GeneSymbol : chr [1:58302] "DDX11L1" "WASH7P" "MIR6859-1" "MIR1302-2HG" ...
## ..$ mean : int [1:58302] 973 1351 68 641 138 948 840 1295 2227 1082 ...
## ..$ median : int [1:58302] 632 1351 68 712 138 1187 840 1414 2618 629 ...
## ..$ longest_isoform: int [1:58302] 1657 1351 68 712 138 1187 840 1414 2618 2748 ...
## ..$ merged : int [1:58302] 1735 1351 68 1021 138 1219 840 1414 2618 3726 ...
## $ TxInfo :'data.frame': 180869 obs. of 3 variables:
## ..$ GeneID : chr [1:180869] "ENSG00000237235.2" "ENSG00000228985.1" "ENSG00000223997.1" "ENSG00000282253.1" ...
## ..$ GeneSymbol: chr [1:180869] "TRDD2" "TRDD3" "TRDD1" "AC239618.6" ...
## ..$ TxLength : int [1:180869] 9 13 8 12 12 17 20 19 16 18 ...
## $ QcMx :'data.frame': 30 obs. of 6 variables:
## ..$ SRR10139485: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139486: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139487: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139490: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139491: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139492: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## $ MetadataSummary:'data.frame': 6 obs. of 7 variables:
## ..$ QC_summary : chr [1:6] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession: chr [1:6] "SRX6867495" "SRX6867496" "SRX6867497" "SRX6867500" ...
## ..$ SRS_accession: chr [1:6] "SRS5404931" "SRS5404932" "SRS5404933" "SRS5404936" ...
## ..$ SRP_accession: chr [1:6] "SRP222346" "SRP222346" "SRP222346" "SRP222346" ...
## ..$ Sample_name : chr [1:6] "GSM4083895" "GSM4083896" "GSM4083897" "GSM4083900" ...
## ..$ GEO_series : chr [1:6] "GSE137663" "GSE137663" "GSE137663" "GSE137663" ...
## ..$ Library_name : logi [1:6] NA NA NA NA NA NA
## $ MetadataFull :'data.frame': 6 obs. of 52 variables:
## ..$ QC_summary : chr [1:6] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession : chr [1:6] "SRX6867495" "SRX6867496" "SRX6867497" "SRX6867500" ...
## ..$ SRS_accession : chr [1:6] "SRS5404931" "SRS5404932" "SRS5404933" "SRS5404936" ...
## ..$ SRP_accession : chr [1:6] "SRP222346" "SRP222346" "SRP222346" "SRP222346" ...
## ..$ Sample_name : chr [1:6] "GSM4083895" "GSM4083896" "GSM4083897" "GSM4083900" ...
## ..$ GEO_series : chr [1:6] "GSE137663" "GSE137663" "GSE137663" "GSE137663" ...
## ..$ Library_name : logi [1:6] NA NA NA NA NA NA
## ..$ SampleName : chr [1:6] "GSM4083895" "GSM4083896" "GSM4083897" "GSM4083900" ...
## ..$ ReleaseDate : chr [1:6] "2020-01-02 09:35:26" "2020-01-02 09:35:26" "2020-01-02 09:35:27" "2020-01-02 09:35:27" ...
## ..$ LoadDate : chr [1:6] "2019-09-18 16:31:25" "2019-09-18 16:18:21" "2019-09-18 16:16:55" "2019-09-18 16:15:58" ...
## ..$ spots : int [1:6] 35473828 21219962 19974486 23399667 21270835 28393231
## ..$ bases : num [1:6] 1.07e+10 6.41e+09 6.03e+09 7.07e+09 6.42e+09 ...
## ..$ spots_with_mates : int [1:6] 35473828 21219962 19974486 23399667 21270835 28393231
## ..$ avgLength : int [1:6] 302 302 302 302 302 302
## ..$ size_MB : int [1:6] 4688 2798 2660 3114 2785 3823
## ..$ AssemblyName : logi [1:6] NA NA NA NA NA NA
## ..$ download_path : chr [1:6] "https://sra-download.ncbi.nlm.nih.gov/traces/sra20/SRR/009901/SRR10139485" "https://sra-download.ncbi.nlm.nih.gov/traces/sra4/SRR/009901/SRR10139486" "https://sra-download.ncbi.nlm.nih.gov/traces/sra12/SRR/009901/SRR10139487" "https://sra-download.ncbi.nlm.nih.gov/traces/sra7/SRR/009901/SRR10139490" ...
## ..$ LibraryName : logi [1:6] NA NA NA NA NA NA
## ..$ LibraryStrategy : chr [1:6] "RNA-Seq" "RNA-Seq" "RNA-Seq" "RNA-Seq" ...
## ..$ LibrarySelection : chr [1:6] "cDNA" "cDNA" "cDNA" "cDNA" ...
## ..$ LibrarySource : chr [1:6] "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" ...
## ..$ LibraryLayout : chr [1:6] "PAIRED" "PAIRED" "PAIRED" "PAIRED" ...
## ..$ InsertSize : int [1:6] 0 0 0 0 0 0
## ..$ InsertDev : num [1:6] 0 0 0 0 0 0
## ..$ Platform : chr [1:6] "ILLUMINA" "ILLUMINA" "ILLUMINA" "ILLUMINA" ...
## ..$ Model : chr [1:6] "Illumina HiSeq 4000" "Illumina HiSeq 4000" "Illumina HiSeq 4000" "Illumina HiSeq 4000" ...
## ..$ SRAStudy : chr [1:6] "SRP222346" "SRP222346" "SRP222346" "SRP222346" ...
## ..$ BioProject : chr [1:6] "PRJNA566176" "PRJNA566176" "PRJNA566176" "PRJNA566176" ...
## ..$ Study_Pubmed_id : int [1:6] 3 3 3 3 3 3
## ..$ ProjectID : int [1:6] 566176 566176 566176 566176 566176 566176
## ..$ Sample : chr [1:6] "SRS5404931" "SRS5404932" "SRS5404933" "SRS5404936" ...
## ..$ BioSample : chr [1:6] "SAMN12783334" "SAMN12783333" "SAMN12783332" "SAMN12783329" ...
## ..$ SampleType : chr [1:6] "simple" "simple" "simple" "simple" ...
## ..$ TaxID : int [1:6] 9606 9606 9606 9606 9606 9606
## ..$ ScientificName : chr [1:6] "Homo sapiens" "Homo sapiens" "Homo sapiens" "Homo sapiens" ...
## ..$ g1k_pop_code : logi [1:6] NA NA NA NA NA NA
## ..$ source : logi [1:6] NA NA NA NA NA NA
## ..$ g1k_analysis_group : logi [1:6] NA NA NA NA NA NA
## ..$ Subject_ID : logi [1:6] NA NA NA NA NA NA
## ..$ Sex : logi [1:6] NA NA NA NA NA NA
## ..$ Disease : logi [1:6] NA NA NA NA NA NA
## ..$ Tumor : chr [1:6] "no" "no" "no" "no" ...
## ..$ Affection_Status : logi [1:6] NA NA NA NA NA NA
## ..$ Analyte_Type : logi [1:6] NA NA NA NA NA NA
## ..$ Histological_Type : logi [1:6] NA NA NA NA NA NA
## ..$ Body_Site : logi [1:6] NA NA NA NA NA NA
## ..$ CenterName : chr [1:6] "GEO" "GEO" "GEO" "GEO" ...
## ..$ Submission : chr [1:6] "SRA964414" "SRA964414" "SRA964414" "SRA964414" ...
## ..$ dbgap_study_accession: logi [1:6] NA NA NA NA NA NA
## ..$ Consent : chr [1:6] "public" "public" "public" "public" ...
## ..$ RunHash : chr [1:6] "B3CC1CCE229D0D74E282538392193341" "836DEF2E4064B5C3314275D8F3B31CA7" "BCFF9CCCF5E86A982610202D9BEBAB82" "AB961A1C70527C0654007911E28B43CA" ...
## ..$ ReadHash : chr [1:6] "09C85CF051642945248374D8FE061A13" "34F36375414F117F84B38A132FD85588" "4F4FFA91983CBB24C270C65C3B8296B7" "101A2F2F4B233E6533B2885FBAFB5A61" ...
## $ absent : chr(0)## converting counts to integer mode## using supplied model matrix## estimating size factors## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testing
## SRP222346: dCas9 transduced versus dCas9 with TET1+VP64 co-expression in SH-SY5Y cells:dCas9; SRX6867495 , SRX6867496 , SRX6867497:TET1+VP64; SRX6867503, SRX6867504, SRX6867505;## For more information about DEE2 QC metrics, visit
## https://github.com/markziemann/dee2/blob/master/qc/qc_metrics.md
## List of 8
## $ GeneCounts :'data.frame': 58302 obs. of 6 variables:
## ..$ SRR10139485: int [1:58302] 1 243 0 2 0 0 0 0 0 0 ...
## ..$ SRR10139486: int [1:58302] 0 166 2 1 0 0 0 0 0 0 ...
## ..$ SRR10139487: int [1:58302] 0 107 0 1 0 0 0 0 0 0 ...
## ..$ SRR10139493: int [1:58302] 0 134 3 0 0 0 0 0 1 0 ...
## ..$ SRR10139494: int [1:58302] 0 216 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139495: int [1:58302] 0 75 0 0 0 0 0 0 0 0 ...
## $ TxCounts :'data.frame': 180869 obs. of 6 variables:
## ..$ SRR10139485: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139486: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139487: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139493: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139494: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR10139495: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## $ GeneInfo :'data.frame': 58302 obs. of 5 variables:
## ..$ GeneSymbol : chr [1:58302] "DDX11L1" "WASH7P" "MIR6859-1" "MIR1302-2HG" ...
## ..$ mean : int [1:58302] 973 1351 68 641 138 948 840 1295 2227 1082 ...
## ..$ median : int [1:58302] 632 1351 68 712 138 1187 840 1414 2618 629 ...
## ..$ longest_isoform: int [1:58302] 1657 1351 68 712 138 1187 840 1414 2618 2748 ...
## ..$ merged : int [1:58302] 1735 1351 68 1021 138 1219 840 1414 2618 3726 ...
## $ TxInfo :'data.frame': 180869 obs. of 3 variables:
## ..$ GeneID : chr [1:180869] "ENSG00000237235.2" "ENSG00000228985.1" "ENSG00000223997.1" "ENSG00000282253.1" ...
## ..$ GeneSymbol: chr [1:180869] "TRDD2" "TRDD3" "TRDD1" "AC239618.6" ...
## ..$ TxLength : int [1:180869] 9 13 8 12 12 17 20 19 16 18 ...
## $ QcMx :'data.frame': 30 obs. of 6 variables:
## ..$ SRR10139485: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139486: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139487: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139493: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139494: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## ..$ SRR10139495: chr [1:30] "PE" "Sanger/Illumina1.9" "151" "151" ...
## $ MetadataSummary:'data.frame': 6 obs. of 7 variables:
## ..$ QC_summary : chr [1:6] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession: chr [1:6] "SRX6867495" "SRX6867496" "SRX6867497" "SRX6867503" ...
## ..$ SRS_accession: chr [1:6] "SRS5404931" "SRS5404932" "SRS5404933" "SRS5404939" ...
## ..$ SRP_accession: chr [1:6] "SRP222346" "SRP222346" "SRP222346" "SRP222346" ...
## ..$ Sample_name : chr [1:6] "GSM4083895" "GSM4083896" "GSM4083897" "GSM4083903" ...
## ..$ GEO_series : chr [1:6] "GSE137663" "GSE137663" "GSE137663" "GSE137663" ...
## ..$ Library_name : logi [1:6] NA NA NA NA NA NA
## $ MetadataFull :'data.frame': 6 obs. of 52 variables:
## ..$ QC_summary : chr [1:6] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession : chr [1:6] "SRX6867495" "SRX6867496" "SRX6867497" "SRX6867503" ...
## ..$ SRS_accession : chr [1:6] "SRS5404931" "SRS5404932" "SRS5404933" "SRS5404939" ...
## ..$ SRP_accession : chr [1:6] "SRP222346" "SRP222346" "SRP222346" "SRP222346" ...
## ..$ Sample_name : chr [1:6] "GSM4083895" "GSM4083896" "GSM4083897" "GSM4083903" ...
## ..$ GEO_series : chr [1:6] "GSE137663" "GSE137663" "GSE137663" "GSE137663" ...
## ..$ Library_name : logi [1:6] NA NA NA NA NA NA
## ..$ SampleName : chr [1:6] "GSM4083895" "GSM4083896" "GSM4083897" "GSM4083903" ...
## ..$ ReleaseDate : chr [1:6] "2020-01-02 09:35:26" "2020-01-02 09:35:26" "2020-01-02 09:35:27" "2020-01-02 09:35:27" ...
## ..$ LoadDate : chr [1:6] "2019-09-18 16:31:25" "2019-09-18 16:18:21" "2019-09-18 16:16:55" "2019-09-18 16:27:41" ...
## ..$ spots : int [1:6] 35473828 21219962 19974486 25790794 31037480 13625963
## ..$ bases : num [1:6] 1.07e+10 6.41e+09 6.03e+09 7.79e+09 9.37e+09 ...
## ..$ spots_with_mates : int [1:6] 35473828 21219962 19974486 25790794 31037480 13625963
## ..$ avgLength : int [1:6] 302 302 302 302 302 302
## ..$ size_MB : int [1:6] 4688 2798 2660 3438 4147 1761
## ..$ AssemblyName : logi [1:6] NA NA NA NA NA NA
## ..$ download_path : chr [1:6] "https://sra-download.ncbi.nlm.nih.gov/traces/sra20/SRR/009901/SRR10139485" "https://sra-download.ncbi.nlm.nih.gov/traces/sra4/SRR/009901/SRR10139486" "https://sra-download.ncbi.nlm.nih.gov/traces/sra12/SRR/009901/SRR10139487" "https://sra-download.ncbi.nlm.nih.gov/traces/sra21/SRR/009901/SRR10139493" ...
## ..$ LibraryName : logi [1:6] NA NA NA NA NA NA
## ..$ LibraryStrategy : chr [1:6] "RNA-Seq" "RNA-Seq" "RNA-Seq" "RNA-Seq" ...
## ..$ LibrarySelection : chr [1:6] "cDNA" "cDNA" "cDNA" "cDNA" ...
## ..$ LibrarySource : chr [1:6] "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" ...
## ..$ LibraryLayout : chr [1:6] "PAIRED" "PAIRED" "PAIRED" "PAIRED" ...
## ..$ InsertSize : int [1:6] 0 0 0 0 0 0
## ..$ InsertDev : num [1:6] 0 0 0 0 0 0
## ..$ Platform : chr [1:6] "ILLUMINA" "ILLUMINA" "ILLUMINA" "ILLUMINA" ...
## ..$ Model : chr [1:6] "Illumina HiSeq 4000" "Illumina HiSeq 4000" "Illumina HiSeq 4000" "Illumina HiSeq 4000" ...
## ..$ SRAStudy : chr [1:6] "SRP222346" "SRP222346" "SRP222346" "SRP222346" ...
## ..$ BioProject : chr [1:6] "PRJNA566176" "PRJNA566176" "PRJNA566176" "PRJNA566176" ...
## ..$ Study_Pubmed_id : int [1:6] 3 3 3 3 3 3
## ..$ ProjectID : int [1:6] 566176 566176 566176 566176 566176 566176
## ..$ Sample : chr [1:6] "SRS5404931" "SRS5404932" "SRS5404933" "SRS5404939" ...
## ..$ BioSample : chr [1:6] "SAMN12783334" "SAMN12783333" "SAMN12783332" "SAMN12783324" ...
## ..$ SampleType : chr [1:6] "simple" "simple" "simple" "simple" ...
## ..$ TaxID : int [1:6] 9606 9606 9606 9606 9606 9606
## ..$ ScientificName : chr [1:6] "Homo sapiens" "Homo sapiens" "Homo sapiens" "Homo sapiens" ...
## ..$ g1k_pop_code : logi [1:6] NA NA NA NA NA NA
## ..$ source : logi [1:6] NA NA NA NA NA NA
## ..$ g1k_analysis_group : logi [1:6] NA NA NA NA NA NA
## ..$ Subject_ID : logi [1:6] NA NA NA NA NA NA
## ..$ Sex : logi [1:6] NA NA NA NA NA NA
## ..$ Disease : logi [1:6] NA NA NA NA NA NA
## ..$ Tumor : chr [1:6] "no" "no" "no" "no" ...
## ..$ Affection_Status : logi [1:6] NA NA NA NA NA NA
## ..$ Analyte_Type : logi [1:6] NA NA NA NA NA NA
## ..$ Histological_Type : logi [1:6] NA NA NA NA NA NA
## ..$ Body_Site : logi [1:6] NA NA NA NA NA NA
## ..$ CenterName : chr [1:6] "GEO" "GEO" "GEO" "GEO" ...
## ..$ Submission : chr [1:6] "SRA964414" "SRA964414" "SRA964414" "SRA964414" ...
## ..$ dbgap_study_accession: logi [1:6] NA NA NA NA NA NA
## ..$ Consent : chr [1:6] "public" "public" "public" "public" ...
## ..$ RunHash : chr [1:6] "B3CC1CCE229D0D74E282538392193341" "836DEF2E4064B5C3314275D8F3B31CA7" "BCFF9CCCF5E86A982610202D9BEBAB82" "3F0DB7C42A0D23A91FB4586084D16799" ...
## ..$ ReadHash : chr [1:6] "09C85CF051642945248374D8FE061A13" "34F36375414F117F84B38A132FD85588" "4F4FFA91983CBB24C270C65C3B8296B7" "C6B074B3BC2B6BA7F20F02E73C416DFB" ...
## $ absent : chr(0)## converting counts to integer mode## using supplied model matrix## estimating size factors## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testing
## SRP061192: non-silencing control in neural progenitor cell lines 553.C2 versus CYFIP1 knockdown:non-silencing control; SRX1097862, SRX1097863, SRX1097864:CYFIP1 knockdown; SRX1097865,SRX1097866, SRX1097867;## For more information about DEE2 QC metrics, visit
## https://github.com/markziemann/dee2/blob/master/qc/qc_metrics.md
## List of 8
## $ GeneCounts :'data.frame': 58302 obs. of 5 variables:
## ..$ SRR2103291: int [1:58302] 0 71 24 2 0 0 0 0 0 4 ...
## ..$ SRR2103292: int [1:58302] 0 74 12 1 0 0 0 0 0 1 ...
## ..$ SRR2103293: int [1:58302] 1 61 18 3 0 0 0 0 0 0 ...
## ..$ SRR2103294: int [1:58302] 0 74 24 4 0 0 0 0 0 0 ...
## ..$ SRR2103295: int [1:58302] 0 81 4 4 0 0 0 0 0 0 ...
## $ TxCounts :'data.frame': 180869 obs. of 5 variables:
## ..$ SRR2103291: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103292: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103293: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103294: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103295: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## $ GeneInfo :'data.frame': 58302 obs. of 5 variables:
## ..$ GeneSymbol : chr [1:58302] "DDX11L1" "WASH7P" "MIR6859-1" "MIR1302-2HG" ...
## ..$ mean : int [1:58302] 973 1351 68 641 138 948 840 1295 2227 1082 ...
## ..$ median : int [1:58302] 632 1351 68 712 138 1187 840 1414 2618 629 ...
## ..$ longest_isoform: int [1:58302] 1657 1351 68 712 138 1187 840 1414 2618 2748 ...
## ..$ merged : int [1:58302] 1735 1351 68 1021 138 1219 840 1414 2618 3726 ...
## $ TxInfo :'data.frame': 180869 obs. of 3 variables:
## ..$ GeneID : chr [1:180869] "ENSG00000237235.2" "ENSG00000228985.1" "ENSG00000223997.1" "ENSG00000282253.1" ...
## ..$ GeneSymbol: chr [1:180869] "TRDD2" "TRDD3" "TRDD1" "AC239618.6" ...
## ..$ TxLength : int [1:180869] 9 13 8 12 12 17 20 19 16 18 ...
## $ QcMx :'data.frame': 30 obs. of 5 variables:
## ..$ SRR2103291: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103292: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103293: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103294: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103295: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## $ MetadataSummary:'data.frame': 5 obs. of 7 variables:
## ..$ QC_summary : chr [1:5] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession: chr [1:5] "SRX1097862" "SRX1097863" "SRX1097864" "SRX1097865" ...
## ..$ SRS_accession: chr [1:5] "SRS992840" "SRS992839" "SRS992837" "SRS992836" ...
## ..$ SRP_accession: chr [1:5] "SRP061192" "SRP061192" "SRP061192" "SRP061192" ...
## ..$ Sample_name : chr [1:5] "GSM1823306" "GSM1823309" "GSM1823311" "GSM1823314" ...
## ..$ GEO_series : chr [1:5] "GSE70935" "GSE70935" "GSE70935" "GSE70935" ...
## ..$ Library_name : logi [1:5] NA NA NA NA NA
## $ MetadataFull :'data.frame': 5 obs. of 52 variables:
## ..$ QC_summary : chr [1:5] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession : chr [1:5] "SRX1097862" "SRX1097863" "SRX1097864" "SRX1097865" ...
## ..$ SRS_accession : chr [1:5] "SRS992840" "SRS992839" "SRS992837" "SRS992836" ...
## ..$ SRP_accession : chr [1:5] "SRP061192" "SRP061192" "SRP061192" "SRP061192" ...
## ..$ Sample_name : chr [1:5] "GSM1823306" "GSM1823309" "GSM1823311" "GSM1823314" ...
## ..$ GEO_series : chr [1:5] "GSE70935" "GSE70935" "GSE70935" "GSE70935" ...
## ..$ Library_name : logi [1:5] NA NA NA NA NA
## ..$ SampleName : chr [1:5] "GSM1823306" "GSM1823309" "GSM1823311" "GSM1823314" ...
## ..$ ReleaseDate : chr [1:5] "2016-09-22 08:20:01" "2016-09-22 08:20:01" "2016-09-22 08:20:01" "2016-09-22 08:20:01" ...
## ..$ LoadDate : chr [1:5] "2015-07-15 10:20:24" "2015-07-15 10:16:06" "2015-07-15 10:09:15" "2015-07-15 10:09:08" ...
## ..$ spots : int [1:5] 27869676 30061162 31668142 30410060 31929378
## ..$ bases : num [1:5] 5.63e+09 6.07e+09 6.40e+09 6.14e+09 6.45e+09
## ..$ spots_with_mates : int [1:5] 27869676 30061162 31668142 30410060 31929378
## ..$ avgLength : int [1:5] 202 202 202 202 202
## ..$ size_MB : int [1:5] 1935 2038 2157 2080 2165
## ..$ AssemblyName : logi [1:5] NA NA NA NA NA
## ..$ download_path : chr [1:5] "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103291/SRR2103291.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103292/SRR2103292.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103293/SRR2103293.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103294/SRR2103294.1" ...
## ..$ LibraryName : logi [1:5] NA NA NA NA NA
## ..$ LibraryStrategy : chr [1:5] "RNA-Seq" "RNA-Seq" "RNA-Seq" "RNA-Seq" ...
## ..$ LibrarySelection : chr [1:5] "cDNA" "cDNA" "cDNA" "cDNA" ...
## ..$ LibrarySource : chr [1:5] "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" ...
## ..$ LibraryLayout : chr [1:5] "PAIRED" "PAIRED" "PAIRED" "PAIRED" ...
## ..$ InsertSize : int [1:5] 0 0 0 0 0
## ..$ InsertDev : num [1:5] 0 0 0 0 0
## ..$ Platform : chr [1:5] "ILLUMINA" "ILLUMINA" "ILLUMINA" "ILLUMINA" ...
## ..$ Model : chr [1:5] "Illumina HiSeq 2000" "Illumina HiSeq 2000" "Illumina HiSeq 2000" "Illumina HiSeq 2000" ...
## ..$ SRAStudy : chr [1:5] "SRP061192" "SRP061192" "SRP061192" "SRP061192" ...
## ..$ BioProject : chr [1:5] "PRJNA289973" "PRJNA289973" "PRJNA289973" "PRJNA289973" ...
## ..$ Study_Pubmed_id : int [1:5] 2 2 2 2 2
## ..$ ProjectID : int [1:5] 289973 289973 289973 289973 289973
## ..$ Sample : chr [1:5] "SRS992840" "SRS992839" "SRS992837" "SRS992836" ...
## ..$ BioSample : chr [1:5] "SAMN03860338" "SAMN03860339" "SAMN03860340" "SAMN03860341" ...
## ..$ SampleType : chr [1:5] "simple" "simple" "simple" "simple" ...
## ..$ TaxID : int [1:5] 9606 9606 9606 9606 9606
## ..$ ScientificName : chr [1:5] "Homo sapiens" "Homo sapiens" "Homo sapiens" "Homo sapiens" ...
## ..$ g1k_pop_code : logi [1:5] NA NA NA NA NA
## ..$ source : logi [1:5] NA NA NA NA NA
## ..$ g1k_analysis_group : logi [1:5] NA NA NA NA NA
## ..$ Subject_ID : logi [1:5] NA NA NA NA NA
## ..$ Sex : logi [1:5] NA NA NA NA NA
## ..$ Disease : logi [1:5] NA NA NA NA NA
## ..$ Tumor : chr [1:5] "no" "no" "no" "no" ...
## ..$ Affection_Status : logi [1:5] NA NA NA NA NA
## ..$ Analyte_Type : logi [1:5] NA NA NA NA NA
## ..$ Histological_Type : logi [1:5] NA NA NA NA NA
## ..$ Body_Site : logi [1:5] NA NA NA NA NA
## ..$ CenterName : chr [1:5] "GEO" "GEO" "GEO" "GEO" ...
## ..$ Submission : chr [1:5] "SRA278090" "SRA278090" "SRA278090" "SRA278090" ...
## ..$ dbgap_study_accession: logi [1:5] NA NA NA NA NA
## ..$ Consent : chr [1:5] "public" "public" "public" "public" ...
## ..$ RunHash : chr [1:5] "6A29463380A95F0D6D50DA3BB281F844" "755758B5A71319F696D8BCFC8BD49F2D" "75AC2FD3F44B3D6557366181FE4CF385" "E77C999EA43F9762EFE68DE6DF952EF0" ...
## ..$ ReadHash : chr [1:5] "BD388243657CE0BADD15A96669526D13" "14A2DD42678ACB68BDAAEE7FCA90BC4A" "DE9776954558841740755A2E8E0ED7EA" "E6B06DEC437DBB2FAC0CFCD4731E968C" ...
## $ absent : chr(0)## converting counts to integer mode## using supplied model matrix## estimating size factors## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testing
## SRP061192: non-silencing control in neural progenitor cell lines 690.C5 versus CYFIP1 knockdown:non-silencing control; SRX1097868, SRX1097869, SRX1097870:CYFIP1 knockdown; SRX1097871,SRX1097872,SRX1097873;## For more information about DEE2 QC metrics, visit
## https://github.com/markziemann/dee2/blob/master/qc/qc_metrics.md
## List of 8
## $ GeneCounts :'data.frame': 58302 obs. of 6 variables:
## ..$ SRR2103297: int [1:58302] 0 109 8 0 0 0 0 0 0 0 ...
## ..$ SRR2103298: int [1:58302] 0 77 13 0 0 0 0 0 0 0 ...
## ..$ SRR2103299: int [1:58302] 0 88 18 5 0 0 0 0 0 0 ...
## ..$ SRR2103300: int [1:58302] 0 44 3 0 0 0 0 0 0 0 ...
## ..$ SRR2103301: int [1:58302] 0 69 20 0 0 0 0 0 0 0 ...
## ..$ SRR2103302: int [1:58302] 0 79 17 0 0 0 0 0 0 2 ...
## $ TxCounts :'data.frame': 180869 obs. of 6 variables:
## ..$ SRR2103297: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103298: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103299: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103300: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103301: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103302: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## $ GeneInfo :'data.frame': 58302 obs. of 5 variables:
## ..$ GeneSymbol : chr [1:58302] "DDX11L1" "WASH7P" "MIR6859-1" "MIR1302-2HG" ...
## ..$ mean : int [1:58302] 973 1351 68 641 138 948 840 1295 2227 1082 ...
## ..$ median : int [1:58302] 632 1351 68 712 138 1187 840 1414 2618 629 ...
## ..$ longest_isoform: int [1:58302] 1657 1351 68 712 138 1187 840 1414 2618 2748 ...
## ..$ merged : int [1:58302] 1735 1351 68 1021 138 1219 840 1414 2618 3726 ...
## $ TxInfo :'data.frame': 180869 obs. of 3 variables:
## ..$ GeneID : chr [1:180869] "ENSG00000237235.2" "ENSG00000228985.1" "ENSG00000223997.1" "ENSG00000282253.1" ...
## ..$ GeneSymbol: chr [1:180869] "TRDD2" "TRDD3" "TRDD1" "AC239618.6" ...
## ..$ TxLength : int [1:180869] 9 13 8 12 12 17 20 19 16 18 ...
## $ QcMx :'data.frame': 30 obs. of 6 variables:
## ..$ SRR2103297: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103298: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103299: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103300: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103301: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103302: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## $ MetadataSummary:'data.frame': 6 obs. of 7 variables:
## ..$ QC_summary : chr [1:6] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession: chr [1:6] "SRX1097868" "SRX1097869" "SRX1097870" "SRX1097871" ...
## ..$ SRS_accession: chr [1:6] "SRS992834" "SRS992833" "SRS992832" "SRS992831" ...
## ..$ SRP_accession: chr [1:6] "SRP061192" "SRP061192" "SRP061192" "SRP061192" ...
## ..$ Sample_name : chr [1:6] "GSM1823321" "GSM1823323" "GSM1823325" "GSM1823328" ...
## ..$ GEO_series : chr [1:6] "GSE70935" "GSE70935" "GSE70935" "GSE70935" ...
## ..$ Library_name : logi [1:6] NA NA NA NA NA NA
## $ MetadataFull :'data.frame': 6 obs. of 52 variables:
## ..$ QC_summary : chr [1:6] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession : chr [1:6] "SRX1097868" "SRX1097869" "SRX1097870" "SRX1097871" ...
## ..$ SRS_accession : chr [1:6] "SRS992834" "SRS992833" "SRS992832" "SRS992831" ...
## ..$ SRP_accession : chr [1:6] "SRP061192" "SRP061192" "SRP061192" "SRP061192" ...
## ..$ Sample_name : chr [1:6] "GSM1823321" "GSM1823323" "GSM1823325" "GSM1823328" ...
## ..$ GEO_series : chr [1:6] "GSE70935" "GSE70935" "GSE70935" "GSE70935" ...
## ..$ Library_name : logi [1:6] NA NA NA NA NA NA
## ..$ SampleName : chr [1:6] "GSM1823321" "GSM1823323" "GSM1823325" "GSM1823328" ...
## ..$ ReleaseDate : chr [1:6] "2016-09-22 08:20:01" "2016-09-22 08:20:01" "2016-09-22 08:20:01" "2016-09-22 08:20:01" ...
## ..$ LoadDate : chr [1:6] "2015-07-15 10:08:30" "2015-07-15 10:06:55" "2015-07-15 10:09:29" "2015-07-15 10:05:04" ...
## ..$ spots : int [1:6] 29191689 26677414 31600289 23593877 29971636 25629352
## ..$ bases : num [1:6] 5.90e+09 5.39e+09 6.38e+09 4.77e+09 6.05e+09 ...
## ..$ spots_with_mates : int [1:6] 29191689 26677414 31600289 23593877 29971636 25629352
## ..$ avgLength : int [1:6] 202 202 202 202 202 202
## ..$ size_MB : int [1:6] 1993 1808 2151 1549 1980 1689
## ..$ AssemblyName : logi [1:6] NA NA NA NA NA NA
## ..$ download_path : chr [1:6] "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103297/SRR2103297.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103298/SRR2103298.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103299/SRR2103299.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103300/SRR2103300.1" ...
## ..$ LibraryName : logi [1:6] NA NA NA NA NA NA
## ..$ LibraryStrategy : chr [1:6] "RNA-Seq" "RNA-Seq" "RNA-Seq" "RNA-Seq" ...
## ..$ LibrarySelection : chr [1:6] "cDNA" "cDNA" "cDNA" "cDNA" ...
## ..$ LibrarySource : chr [1:6] "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" ...
## ..$ LibraryLayout : chr [1:6] "PAIRED" "PAIRED" "PAIRED" "PAIRED" ...
## ..$ InsertSize : int [1:6] 0 0 0 0 0 0
## ..$ InsertDev : num [1:6] 0 0 0 0 0 0
## ..$ Platform : chr [1:6] "ILLUMINA" "ILLUMINA" "ILLUMINA" "ILLUMINA" ...
## ..$ Model : chr [1:6] "Illumina HiSeq 2000" "Illumina HiSeq 2000" "Illumina HiSeq 2000" "Illumina HiSeq 2000" ...
## ..$ SRAStudy : chr [1:6] "SRP061192" "SRP061192" "SRP061192" "SRP061192" ...
## ..$ BioProject : chr [1:6] "PRJNA289973" "PRJNA289973" "PRJNA289973" "PRJNA289973" ...
## ..$ Study_Pubmed_id : int [1:6] 2 2 2 2 2 2
## ..$ ProjectID : int [1:6] 289973 289973 289973 289973 289973 289973
## ..$ Sample : chr [1:6] "SRS992834" "SRS992833" "SRS992832" "SRS992831" ...
## ..$ BioSample : chr [1:6] "SAMN03860344" "SAMN03860345" "SAMN03860346" "SAMN03860347" ...
## ..$ SampleType : chr [1:6] "simple" "simple" "simple" "simple" ...
## ..$ TaxID : int [1:6] 9606 9606 9606 9606 9606 9606
## ..$ ScientificName : chr [1:6] "Homo sapiens" "Homo sapiens" "Homo sapiens" "Homo sapiens" ...
## ..$ g1k_pop_code : logi [1:6] NA NA NA NA NA NA
## ..$ source : logi [1:6] NA NA NA NA NA NA
## ..$ g1k_analysis_group : logi [1:6] NA NA NA NA NA NA
## ..$ Subject_ID : logi [1:6] NA NA NA NA NA NA
## ..$ Sex : logi [1:6] NA NA NA NA NA NA
## ..$ Disease : logi [1:6] NA NA NA NA NA NA
## ..$ Tumor : chr [1:6] "no" "no" "no" "no" ...
## ..$ Affection_Status : logi [1:6] NA NA NA NA NA NA
## ..$ Analyte_Type : logi [1:6] NA NA NA NA NA NA
## ..$ Histological_Type : logi [1:6] NA NA NA NA NA NA
## ..$ Body_Site : logi [1:6] NA NA NA NA NA NA
## ..$ CenterName : chr [1:6] "GEO" "GEO" "GEO" "GEO" ...
## ..$ Submission : chr [1:6] "SRA278090" "SRA278090" "SRA278090" "SRA278090" ...
## ..$ dbgap_study_accession: logi [1:6] NA NA NA NA NA NA
## ..$ Consent : chr [1:6] "public" "public" "public" "public" ...
## ..$ RunHash : chr [1:6] "CD14891D6BB595AEFDD5CF642F9C4C34" "5B2BCF9B6769B540407E8183E3CF72E9" "03FC5254892ED9567D156428CD6AD603" "66CA9CDE6D9E48F1AB57BE01E9EEECF8" ...
## ..$ ReadHash : chr [1:6] "F56059D594D99A3BE10C1CC09DD4F0E3" "FC19F3B9B84376DC69492272BBD0BAAC" "C84741D9145531F98EB16F8C7306CFE4" "CA35F2C25DD798C3348A8DC366FC9E20" ...
## $ absent : chr(0)## converting counts to integer mode## using supplied model matrix## estimating size factors## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testing
## SRP061192: non-silencing control in neural progenitor cell lines iPS5.C4 versus CYFIP1 knockdown:non-silencing control; SRX1097874, SRX1097875, SRX1097876:CYFIP1 knockdown; SRX1097877,SRX1097878,SRX1097879;## For more information about DEE2 QC metrics, visit
## https://github.com/markziemann/dee2/blob/master/qc/qc_metrics.md
## List of 8
## $ GeneCounts :'data.frame': 58302 obs. of 6 variables:
## ..$ SRR2103303: int [1:58302] 0 32 3 0 0 0 0 0 0 0 ...
## ..$ SRR2103304: int [1:58302] 0 37 9 0 0 0 0 0 0 0 ...
## ..$ SRR2103305: int [1:58302] 0 33 7 0 0 0 0 0 0 0 ...
## ..$ SRR2103306: int [1:58302] 0 52 12 1 0 0 0 0 0 0 ...
## ..$ SRR2103307: int [1:58302] 4 57 15 0 0 0 0 0 0 0 ...
## ..$ SRR2103308: int [1:58302] 0 45 4 3 0 0 0 0 0 0 ...
## $ TxCounts :'data.frame': 180869 obs. of 6 variables:
## ..$ SRR2103303: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103304: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103305: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103306: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103307: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2103308: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## $ GeneInfo :'data.frame': 58302 obs. of 5 variables:
## ..$ GeneSymbol : chr [1:58302] "DDX11L1" "WASH7P" "MIR6859-1" "MIR1302-2HG" ...
## ..$ mean : int [1:58302] 973 1351 68 641 138 948 840 1295 2227 1082 ...
## ..$ median : int [1:58302] 632 1351 68 712 138 1187 840 1414 2618 629 ...
## ..$ longest_isoform: int [1:58302] 1657 1351 68 712 138 1187 840 1414 2618 2748 ...
## ..$ merged : int [1:58302] 1735 1351 68 1021 138 1219 840 1414 2618 3726 ...
## $ TxInfo :'data.frame': 180869 obs. of 3 variables:
## ..$ GeneID : chr [1:180869] "ENSG00000237235.2" "ENSG00000228985.1" "ENSG00000223997.1" "ENSG00000282253.1" ...
## ..$ GeneSymbol: chr [1:180869] "TRDD2" "TRDD3" "TRDD1" "AC239618.6" ...
## ..$ TxLength : int [1:180869] 9 13 8 12 12 17 20 19 16 18 ...
## $ QcMx :'data.frame': 30 obs. of 6 variables:
## ..$ SRR2103303: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103304: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103305: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103306: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103307: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## ..$ SRR2103308: chr [1:30] "PE" "Sanger/Illumina1.9" "101" "101" ...
## $ MetadataSummary:'data.frame': 6 obs. of 7 variables:
## ..$ QC_summary : chr [1:6] "PASS" "PASS" "PASS" "WARN(8)" ...
## ..$ SRX_accession: chr [1:6] "SRX1097874" "SRX1097875" "SRX1097876" "SRX1097877" ...
## ..$ SRS_accession: chr [1:6] "SRS992828" "SRS992826" "SRS992827" "SRS992825" ...
## ..$ SRP_accession: chr [1:6] "SRP061192" "SRP061192" "SRP061192" "SRP061192" ...
## ..$ Sample_name : chr [1:6] "GSM1823333" "GSM1823335" "GSM1823338" "GSM1823340" ...
## ..$ GEO_series : chr [1:6] "GSE70935" "GSE70935" "GSE70935" "GSE70935" ...
## ..$ Library_name : logi [1:6] NA NA NA NA NA NA
## $ MetadataFull :'data.frame': 6 obs. of 52 variables:
## ..$ QC_summary : chr [1:6] "PASS" "PASS" "PASS" "WARN(8)" ...
## ..$ SRX_accession : chr [1:6] "SRX1097874" "SRX1097875" "SRX1097876" "SRX1097877" ...
## ..$ SRS_accession : chr [1:6] "SRS992828" "SRS992826" "SRS992827" "SRS992825" ...
## ..$ SRP_accession : chr [1:6] "SRP061192" "SRP061192" "SRP061192" "SRP061192" ...
## ..$ Sample_name : chr [1:6] "GSM1823333" "GSM1823335" "GSM1823338" "GSM1823340" ...
## ..$ GEO_series : chr [1:6] "GSE70935" "GSE70935" "GSE70935" "GSE70935" ...
## ..$ Library_name : logi [1:6] NA NA NA NA NA NA
## ..$ SampleName : chr [1:6] "GSM1823333" "GSM1823335" "GSM1823338" "GSM1823340" ...
## ..$ ReleaseDate : chr [1:6] "2016-09-22 08:20:01" "2016-09-22 08:20:01" "2016-09-22 08:20:01" "2016-09-22 08:20:01" ...
## ..$ LoadDate : chr [1:6] "2015-07-15 10:14:48" "2015-07-15 10:16:37" "2015-07-15 10:19:22" "2015-07-15 10:17:41" ...
## ..$ spots : int [1:6] 24545612 25812967 27194777 24255459 25370877 29731120
## ..$ bases : num [1:6] 4.96e+09 5.21e+09 5.49e+09 4.90e+09 5.12e+09 ...
## ..$ spots_with_mates : int [1:6] 24545612 25812967 27194777 24255459 25370877 29731120
## ..$ avgLength : int [1:6] 202 202 202 202 202 202
## ..$ size_MB : int [1:6] 1636 1706 1806 1636 1697 1986
## ..$ AssemblyName : logi [1:6] NA NA NA NA NA NA
## ..$ download_path : chr [1:6] "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103303/SRR2103303.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103304/SRR2103304.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103305/SRR2103305.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2103306/SRR2103306.1" ...
## ..$ LibraryName : logi [1:6] NA NA NA NA NA NA
## ..$ LibraryStrategy : chr [1:6] "RNA-Seq" "RNA-Seq" "RNA-Seq" "RNA-Seq" ...
## ..$ LibrarySelection : chr [1:6] "cDNA" "cDNA" "cDNA" "cDNA" ...
## ..$ LibrarySource : chr [1:6] "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" ...
## ..$ LibraryLayout : chr [1:6] "PAIRED" "PAIRED" "PAIRED" "PAIRED" ...
## ..$ InsertSize : int [1:6] 0 0 0 0 0 0
## ..$ InsertDev : num [1:6] 0 0 0 0 0 0
## ..$ Platform : chr [1:6] "ILLUMINA" "ILLUMINA" "ILLUMINA" "ILLUMINA" ...
## ..$ Model : chr [1:6] "Illumina HiSeq 2000" "Illumina HiSeq 2000" "Illumina HiSeq 2000" "Illumina HiSeq 2000" ...
## ..$ SRAStudy : chr [1:6] "SRP061192" "SRP061192" "SRP061192" "SRP061192" ...
## ..$ BioProject : chr [1:6] "PRJNA289973" "PRJNA289973" "PRJNA289973" "PRJNA289973" ...
## ..$ Study_Pubmed_id : int [1:6] 2 2 2 2 2 2
## ..$ ProjectID : int [1:6] 289973 289973 289973 289973 289973 289973
## ..$ Sample : chr [1:6] "SRS992828" "SRS992826" "SRS992827" "SRS992825" ...
## ..$ BioSample : chr [1:6] "SAMN03860350" "SAMN03860351" "SAMN03860352" "SAMN03860353" ...
## ..$ SampleType : chr [1:6] "simple" "simple" "simple" "simple" ...
## ..$ TaxID : int [1:6] 9606 9606 9606 9606 9606 9606
## ..$ ScientificName : chr [1:6] "Homo sapiens" "Homo sapiens" "Homo sapiens" "Homo sapiens" ...
## ..$ g1k_pop_code : logi [1:6] NA NA NA NA NA NA
## ..$ source : logi [1:6] NA NA NA NA NA NA
## ..$ g1k_analysis_group : logi [1:6] NA NA NA NA NA NA
## ..$ Subject_ID : logi [1:6] NA NA NA NA NA NA
## ..$ Sex : logi [1:6] NA NA NA NA NA NA
## ..$ Disease : logi [1:6] NA NA NA NA NA NA
## ..$ Tumor : chr [1:6] "no" "no" "no" "no" ...
## ..$ Affection_Status : logi [1:6] NA NA NA NA NA NA
## ..$ Analyte_Type : logi [1:6] NA NA NA NA NA NA
## ..$ Histological_Type : logi [1:6] NA NA NA NA NA NA
## ..$ Body_Site : logi [1:6] NA NA NA NA NA NA
## ..$ CenterName : chr [1:6] "GEO" "GEO" "GEO" "GEO" ...
## ..$ Submission : chr [1:6] "SRA278090" "SRA278090" "SRA278090" "SRA278090" ...
## ..$ dbgap_study_accession: logi [1:6] NA NA NA NA NA NA
## ..$ Consent : chr [1:6] "public" "public" "public" "public" ...
## ..$ RunHash : chr [1:6] "A72C04B812EB38E036DF0CF62D881955" "C23308A046920A217ADA2084F22559C0" "71257B63570E944B5EA98C25F2178B33" "7F94CA317D26B7BF8F8BEBE91D738FEF" ...
## ..$ ReadHash : chr [1:6] "BDFBCC404C44376FFA4E9C67F43A515A" "0F02D2E51DA2AF1ED5F3F36BA92EB228" "A81536C0D248D10A7AEBC90AFD2A542F" "466EEAB3C38F2EEE81303F8CB7E78F04" ...
## $ absent : chr(0)## converting counts to integer mode## using supplied model matrix## estimating size factors## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testing
## SRP061286: dentate granule cells from patients with mesial tempora lobe epilepsy with hippocampal sclerosis versus dentate granule cells from patients with mesial tempora lobe epilepsy without hippocampal sclerosis:with hippocampal sclerosis; SRX1100259, SRX1100260, SRX1100261, SRX1100262, SRX1100265, SRX1100266, SRX1100269, SRX1100272 :without hippocampal sclerosis; SRX1100273, SRX1100274, SRX1100275, SRX1100276, SRX1100277, SRX1100278, SRX1100279, SRX1100280, SRX1100267, SRX1100268, SRX1100270, SRX1100271, SRX1100263, SRX1100264; sex## For more information about DEE2 QC metrics, visit
## https://github.com/markziemann/dee2/blob/master/qc/qc_metrics.md
## List of 8
## $ GeneCounts :'data.frame': 58302 obs. of 13 variables:
## ..$ SRR2106309: int [1:58302] 0 4 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106310: int [1:58302] 0 18 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106311: int [1:58302] 0 7 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106313: int [1:58302] 0 1 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106318: int [1:58302] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106319: int [1:58302] 0 24 0 0 0 0 0 0 0 2 ...
## ..$ SRR2106322: int [1:58302] 0 10 0 0 0 0 0 0 0 1 ...
## ..$ SRR2106323: int [1:58302] 0 22 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106324: int [1:58302] 0 18 0 0 0 0 0 0 0 1 ...
## ..$ SRR2143509: int [1:58302] 0 0 0 0 0 0 0 0 3 0 ...
## ..$ SRR2143510: int [1:58302] 0 0 0 0 0 4 0 0 0 1 ...
## ..$ SRR2143511: int [1:58302] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2143513: int [1:58302] 0 0 0 0 0 0 0 1 0 0 ...
## $ TxCounts :'data.frame': 180869 obs. of 13 variables:
## ..$ SRR2106309: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106310: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106311: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106313: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106318: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106319: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106322: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106323: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2106324: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2143509: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2143510: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2143511: int [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ SRR2143513: num [1:180869] 0 0 0 0 0 0 0 0 0 0 ...
## $ GeneInfo :'data.frame': 58302 obs. of 5 variables:
## ..$ GeneSymbol : chr [1:58302] "DDX11L1" "WASH7P" "MIR6859-1" "MIR1302-2HG" ...
## ..$ mean : int [1:58302] 973 1351 68 641 138 948 840 1295 2227 1082 ...
## ..$ median : int [1:58302] 632 1351 68 712 138 1187 840 1414 2618 629 ...
## ..$ longest_isoform: int [1:58302] 1657 1351 68 712 138 1187 840 1414 2618 2748 ...
## ..$ merged : int [1:58302] 1735 1351 68 1021 138 1219 840 1414 2618 3726 ...
## $ TxInfo :'data.frame': 180869 obs. of 3 variables:
## ..$ GeneID : chr [1:180869] "ENSG00000237235.2" "ENSG00000228985.1" "ENSG00000223997.1" "ENSG00000282253.1" ...
## ..$ GeneSymbol: chr [1:180869] "TRDD2" "TRDD3" "TRDD1" "AC239618.6" ...
## ..$ TxLength : int [1:180869] 9 13 8 12 12 17 20 19 16 18 ...
## $ QcMx :'data.frame': 30 obs. of 13 variables:
## ..$ SRR2106309: chr [1:30] "PE" "Sanger/Illumina1.9" "126" "126" ...
## ..$ SRR2106310: chr [1:30] "PE" "Sanger/Illumina1.9" "126" "126" ...
## ..$ SRR2106311: chr [1:30] "PE" "Sanger/Illumina1.9" "126" "126" ...
## ..$ SRR2106313: chr [1:30] "PE" "Sanger/Illumina1.9" "126" "126" ...
## ..$ SRR2106318: chr [1:30] "PE" "Sanger/Illumina1.9" "126" "126" ...
## ..$ SRR2106319: chr [1:30] "PE" "Sanger/Illumina1.9" "22" "101" ...
## ..$ SRR2106322: chr [1:30] "PE" "Sanger/Illumina1.9" "22" "101" ...
## ..$ SRR2106323: chr [1:30] "PE" "Sanger/Illumina1.9" "19" "101" ...
## ..$ SRR2106324: chr [1:30] "PE" "Sanger/Illumina1.9" "24" "101" ...
## ..$ SRR2143509: chr [1:30] "PE" "Sanger/Illumina1.9" "126" "126" ...
## ..$ SRR2143510: chr [1:30] "PE" "Sanger/Illumina1.9" "126" "126" ...
## ..$ SRR2143511: chr [1:30] "PE" "Sanger/Illumina1.9" "126" "126" ...
## ..$ SRR2143513: chr [1:30] "PE" "Sanger/Illumina1.9" "126" "126" ...
## $ MetadataSummary:'data.frame': 13 obs. of 7 variables:
## ..$ QC_summary : chr [1:13] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession: chr [1:13] "SRX1100259" "SRX1100260" "SRX1100261" "SRX1100263" ...
## ..$ SRS_accession: chr [1:13] "SRS994882" "SRS994881" "SRS994880" "SRS994878" ...
## ..$ SRP_accession: chr [1:13] "SRP061286" "SRP061286" "SRP061286" "SRP061286" ...
## ..$ Sample_name : chr [1:13] "GSM1826292" "GSM1826293" "GSM1826294" "GSM1826296" ...
## ..$ GEO_series : chr [1:13] "GSE71058" "GSE71058" "GSE71058" "GSE71058" ...
## ..$ Library_name : logi [1:13] NA NA NA NA NA NA ...
## $ MetadataFull :'data.frame': 13 obs. of 52 variables:
## ..$ QC_summary : chr [1:13] "PASS" "PASS" "PASS" "PASS" ...
## ..$ SRX_accession : chr [1:13] "SRX1100259" "SRX1100260" "SRX1100261" "SRX1100263" ...
## ..$ SRS_accession : chr [1:13] "SRS994882" "SRS994881" "SRS994880" "SRS994878" ...
## ..$ SRP_accession : chr [1:13] "SRP061286" "SRP061286" "SRP061286" "SRP061286" ...
## ..$ Sample_name : chr [1:13] "GSM1826292" "GSM1826293" "GSM1826294" "GSM1826296" ...
## ..$ GEO_series : chr [1:13] "GSE71058" "GSE71058" "GSE71058" "GSE71058" ...
## ..$ Library_name : logi [1:13] NA NA NA NA NA NA ...
## ..$ SampleName : chr [1:13] "GSM1826292" "GSM1826293" "GSM1826294" "GSM1826296" ...
## ..$ ReleaseDate : chr [1:13] "2016-06-29 16:08:19" "2016-06-29 16:08:19" "2016-06-29 16:08:19" "2016-06-29 16:08:19" ...
## ..$ LoadDate : chr [1:13] "2015-07-17 17:59:48" "2015-07-17 17:25:07" "2015-07-17 17:37:31" "2015-07-17 17:55:24" ...
## ..$ spots : int [1:13] 58853446 58632885 74880070 64691354 52317366 44519513 41707817 43854927 46400302 64411333 ...
## ..$ bases : num [1:13] 1.48e+10 1.48e+10 1.89e+10 1.63e+10 1.32e+10 ...
## ..$ spots_with_mates : int [1:13] 58853446 58632885 74880070 64691354 52317366 34114964 32006533 34685036 36840143 64411333 ...
## ..$ avgLength : int [1:13] 252 252 252 252 252 173 173 176 177 252 ...
## ..$ size_MB : int [1:13] 6617 7006 8448 7145 5854 3865 3646 3789 4012 7116 ...
## ..$ AssemblyName : chr [1:13] "" "" "" "" ...
## ..$ download_path : chr [1:13] "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2106309/SRR2106309.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2106310/SRR2106310.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2106311/SRR2106311.1" "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-run-5/SRR2106313/SRR2106313.1" ...
## ..$ LibraryName : logi [1:13] NA NA NA NA NA NA ...
## ..$ LibraryStrategy : chr [1:13] "RNA-Seq" "RNA-Seq" "RNA-Seq" "RNA-Seq" ...
## ..$ LibrarySelection : chr [1:13] "cDNA" "cDNA" "cDNA" "cDNA" ...
## ..$ LibrarySource : chr [1:13] "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" "TRANSCRIPTOMIC" ...
## ..$ LibraryLayout : chr [1:13] "PAIRED" "PAIRED" "PAIRED" "PAIRED" ...
## ..$ InsertSize : int [1:13] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ InsertDev : num [1:13] 0 0 0 0 0 0 0 0 0 0 ...
## ..$ Platform : chr [1:13] "ILLUMINA" "ILLUMINA" "ILLUMINA" "ILLUMINA" ...
## ..$ Model : chr [1:13] "Illumina HiSeq 2000" "Illumina HiSeq 2000" "Illumina HiSeq 2000" "Illumina HiSeq 2000" ...
## ..$ SRAStudy : chr [1:13] "SRP061286" "SRP061286" "SRP061286" "SRP061286" ...
## ..$ BioProject : chr [1:13] "PRJNA290212" "PRJNA290212" "PRJNA290212" "PRJNA290212" ...
## ..$ Study_Pubmed_id : int [1:13] 2 2 2 2 2 2 2 2 2 2 ...
## ..$ ProjectID : int [1:13] 290212 290212 290212 290212 290212 290212 290212 290212 290212 290212 ...
## ..$ Sample : chr [1:13] "SRS994882" "SRS994881" "SRS994880" "SRS994878" ...
## ..$ BioSample : chr [1:13] "SAMN03877308" "SAMN03877309" "SAMN03877310" "SAMN03877312" ...
## ..$ SampleType : chr [1:13] "simple" "simple" "simple" "simple" ...
## ..$ TaxID : int [1:13] 9606 9606 9606 9606 9606 9606 9606 9606 9606 9606 ...
## ..$ ScientificName : chr [1:13] "Homo sapiens" "Homo sapiens" "Homo sapiens" "Homo sapiens" ...
## ..$ g1k_pop_code : logi [1:13] NA NA NA NA NA NA ...
## ..$ source : logi [1:13] NA NA NA NA NA NA ...
## ..$ g1k_analysis_group : logi [1:13] NA NA NA NA NA NA ...
## ..$ Subject_ID : logi [1:13] NA NA NA NA NA NA ...
## ..$ Sex : logi [1:13] NA NA NA NA NA NA ...
## ..$ Disease : logi [1:13] NA NA NA NA NA NA ...
## ..$ Tumor : chr [1:13] "no" "no" "no" "no" ...
## ..$ Affection_Status : logi [1:13] NA NA NA NA NA NA ...
## ..$ Analyte_Type : logi [1:13] NA NA NA NA NA NA ...
## ..$ Histological_Type : logi [1:13] NA NA NA NA NA NA ...
## ..$ Body_Site : logi [1:13] NA NA NA NA NA NA ...
## ..$ CenterName : chr [1:13] "GEO" "GEO" "GEO" "GEO" ...
## ..$ Submission : chr [1:13] "SRA278454" "SRA278454" "SRA278454" "SRA278454" ...
## ..$ dbgap_study_accession: logi [1:13] NA NA NA NA NA NA ...
## ..$ Consent : chr [1:13] "public" "public" "public" "public" ...
## ..$ RunHash : chr [1:13] "A30B2F8A392BB75B9208945CBD79CD18" "B3B195C4FEEFC7E061B98BE9BFAF4ED1" "AD9D6B846200674A0C02E650A94AAA5A" "0877BCB579AC36BA7F29911634CD5D3F" ...
## ..$ ReadHash : chr [1:13] "1AD98473580780DBCFDD13179E71A4ED" "6755E70F869C1F1A3AF67930335C7A26" "4D17103D456A6A15D7E35FBB775103E5" "F919FD938669B67B075E12FE00A430A4" ...
## $ absent : chr(0)## converting counts to integer mode## using supplied model matrix## estimating size factors## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testing
lapply(data,length)## [[1]]
## [1] 1
##
## [[2]]
## [1] 8
##
## [[3]]
## [1] 8
##
## [[4]]
## [1] 8
##
## [[5]]
## [1] 8
##
## [[6]]
## [1] 8
##
## [[7]]
## [1] 8
##
## [[8]]
## [1] 8data <- data[which(lapply(data,length)>1)]
data <- data[which(lapply(data,function(x) length(x[[5]] ))>0)]
saveRDS(data,"epilepsy_data.rds")
gs1 <- lapply(data, function(x) { x[5] })
gs2 <- lapply(data, function(x) { x[6] })
gs <- c(gs1,gs2)
gs <- lapply(gs,function(x) x[[1]] )
attributes(gs)$class <- "GMT"
write.GMT(gs,"epilepsy_ensemblIDs.gmt")
gs1 <- lapply(data, function(x) { x[7] })
gs2 <- lapply(data, function(x) { x[8] })
gs <- c(gs1,gs2)
gs <- lapply(gs,function(x) x[[1]] )
gs <- lapply(gs,function(x) { x[[3]] <- unique(x[[3]] ) ; return(x) } )
attributes(gs)$class <- "GMT"
write.GMT(gs,"epilepsy_genesymbols.gmt")sessionInfo()## R version 4.0.2 (2020-06-22)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 18.04.5 LTS
##
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.7.1
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.7.1
##
## locale:
## [1] LC_CTYPE=en_AU.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_AU.UTF-8 LC_COLLATE=en_AU.UTF-8
## [5] LC_MONETARY=en_AU.UTF-8 LC_MESSAGES=en_AU.UTF-8
## [7] LC_PAPER=en_AU.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_AU.UTF-8 LC_IDENTIFICATION=C
##
## attached base packages:
## [1] parallel stats4 stats graphics grDevices utils datasets
## [8] methods base
##
## other attached packages:
## [1] edgeR_3.30.3 limma_3.44.3
## [3] DESeq2_1.28.1 SummarizedExperiment_1.18.2
## [5] DelayedArray_0.14.1 matrixStats_0.57.0
## [7] Biobase_2.48.0 GenomicRanges_1.40.0
## [9] GenomeInfoDb_1.24.2 IRanges_2.22.2
## [11] S4Vectors_0.26.1 BiocGenerics_0.34.0
## [13] getDEE2_0.99.30 gplots_3.1.0
## [15] ActivePathways_1.0.2 devtools_2.3.2
## [17] usethis_1.6.3
##
## loaded via a namespace (and not attached):
## [1] bitops_1.0-6 fs_1.5.0 bit64_4.0.5
## [4] RColorBrewer_1.1-2 rprojroot_1.3-2 tools_4.0.2
## [7] backports_1.1.10 R6_2.4.1 KernSmooth_2.23-17
## [10] DBI_1.1.0 colorspace_1.4-1 htm2txt_2.1.1
## [13] withr_2.3.0 tidyselect_1.1.0 prettyunits_1.1.1
## [16] processx_3.4.4 bit_4.0.4 compiler_4.0.2
## [19] cli_2.0.2 desc_1.2.0 caTools_1.18.0
## [22] scales_1.1.1 genefilter_1.70.0 callr_3.5.0
## [25] stringr_1.4.0 digest_0.6.25 rmarkdown_2.4
## [28] XVector_0.28.0 pkgconfig_2.0.3 htmltools_0.5.0
## [31] sessioninfo_1.1.1 rlang_0.4.8 RSQLite_2.2.1
## [34] generics_0.0.2 BiocParallel_1.22.0 gtools_3.8.2
## [37] dplyr_1.0.2 RCurl_1.98-1.2 magrittr_1.5
## [40] GenomeInfoDbData_1.2.3 Matrix_1.2-18 Rcpp_1.0.5
## [43] munsell_0.5.0 fansi_0.4.1 lifecycle_0.2.0
## [46] stringi_1.5.3 yaml_2.2.1 zlibbioc_1.34.0
## [49] pkgbuild_1.1.0 grid_4.0.2 blob_1.2.1
## [52] crayon_1.3.4 lattice_0.20-41 splines_4.0.2
## [55] annotate_1.66.0 locfit_1.5-9.4 knitr_1.30
## [58] ps_1.4.0 pillar_1.4.6 geneplotter_1.66.0
## [61] pkgload_1.1.0 XML_3.99-0.5 glue_1.4.2
## [64] evaluate_0.14 data.table_1.13.0 remotes_2.2.0
## [67] vctrs_0.3.4 testthat_2.3.2 gtable_0.3.0
## [70] purrr_0.3.4 assertthat_0.2.1 ggplot2_3.3.2
## [73] xfun_0.18 xtable_1.8-4 survival_3.2-7
## [76] tibble_3.0.3 AnnotationDbi_1.50.3 memoise_1.1.0
## [79] ellipsis_0.3.1