For PMID36344834

Loading libraries:

library("knitr")
library("kableExtra")
library("tidyverse")
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter()     masks stats::filter()
## ✖ dplyr::group_rows() masks kableExtra::group_rows()
## ✖ dplyr::lag()        masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library("stringr")
library("tidyr")
library("eulerr")

DAVID Results from the web-tool (2023q4):

#PMID33947848_results <- read.table("../output_lists/DAVID_PMID33947848.txt", header = TRUE, sep = "\t")  #Change PMID/PMCID

PMID36344834_results <- read.table("../../output_lists/DAVID_PMID36344834.txt", header = TRUE, sep = "\t")  #Change PMID/PMCID and text after "output_lists/"
## Warning in scan(file = file, what = what, sep = sep, quote = quote, dec = dec,
## : EOF within quoted string
## Warning in scan(file = file, what = what, sep = sep, quote = quote, dec = dec,
## : number of items read is not a multiple of the number of columns
#PMID33947848_results <- read.csv("../output_lists/PMID33947848_webDAVID_20240513.tsv", header = TRUE, sep = "\t")

#split_terms <- str_split(PMID33947848_results$Term, pattern = "~")
split_terms <- str_split(PMID36344834_results$Term, pattern = "~")

#PMID33947848_results$GOID <- sapply(split_terms, "[", 1)
#PMID33947848_results$GO.Term <- sapply(split_terms, "[", 2)
PMID36344834_results$GOID <- sapply(split_terms, "[", 1)
PMID36344834_results$GO.Term <- sapply(split_terms, "[", 2)


#PMID33947848_results <- select(PMID33947848_results, GOID, GO.Term, Category, Count, X., PValue, Genes, List.Total, Pop.Hits, Pop.Total, Fold.Enrichment, Bonferroni, Benjamini, FDR)
PMID36344834_results <- select(PMID36344834_results, GOID, GO.Term, Category, Count, X., PValue, Genes, List.Total, Pop.Hits, Pop.Total, Fold.Enrichment, Bonferroni, Benjamini, FDR)

#tmp <- PMID33947848_results
tmp <- PMID36344834_results
tmp$Genes=NULL

head(tmp,20) %>%      #Change PMID/PMCID
  kbl(caption="Top results from the DAVID Website") %>%
  kable_paper("hover", full_width = F)
Top results from the DAVID Website
GOID GO.Term Category Count X. PValue List.Total Pop.Hits Pop.Total Fold.Enrichment Bonferroni Benjamini FDR
GO:0005829 cytosol GOTERM_CC_DIRECT 498 50.920245 0 971 5537 20521 1.900790 0 0 0
GO:0005515 protein binding GOTERM_MF_DIRECT 849 86.809816 0 966 12707 18883 1.306046 0 0 0
GO:0005654 nucleoplasm GOTERM_CC_DIRECT 379 38.752556 0 971 3972 20521 2.016551 0 0 0
GO:0005737 cytoplasm GOTERM_CC_DIRECT 431 44.069530 0 971 5636 20521 1.616165 0 0 0
GO:0005634 nucleus GOTERM_CC_DIRECT 433 44.274029 0 971 6021 20521 1.519842 0 0 0
GO:0019901 protein kinase binding GOTERM_MF_DIRECT 76 7.770961 0 966 483 18883 3.075816 0 0 0
GO:0070062 extracellular exosome GOTERM_CC_DIRECT 193 19.734151 0 971 2241 20521 1.820098 0 0 0
GO:0042802 identical protein binding GOTERM_MF_DIRECT 168 17.177914 0 966 1734 18883 1.893887 0 0 0
GO:0005739 mitochondrion GOTERM_CC_DIRECT 137 14.008180 0 971 1427 20521 2.028971 0 0 0
GO:0016310 phosphorylation GOTERM_BP_DIRECT 80 8.179959 0 947 623 19256 2.611067 0 0 0
GO:0019899 enzyme binding GOTERM_MF_DIRECT 60 6.134969 0 966 374 18883 3.135982 0 0 0
GO:0005524 ATP binding GOTERM_MF_DIRECT 150 15.337423 0 966 1540 18883 1.903989 0 0 0
GO:0051301 cell division GOTERM_BP_DIRECT 59 6.032720 0 947 386 19256 3.107998 0 0 0
GO:0006468 protein phosphorylation GOTERM_BP_DIRECT 58 5.930470 0 947 379 19256 3.111751 0 0 0
GO:0007049 cell cycle GOTERM_BP_DIRECT 54 5.521472 0 947 351 19256 3.128259 0 0 0
GO:0043065 positive regulation of apoptotic process GOTERM_BP_DIRECT 51 5.214724 0 947 321 19256 3.230586 0 0 0
GO:0045893 positive regulation of transcription, DNA-templated GOTERM_BP_DIRECT 83 8.486708 0 947 718 19256 2.350551 0 0 0
GO:0032991 macromolecular complex GOTERM_CC_DIRECT 79 8.077710 0 971 692 20521 2.412683 0 0 0
GO:0031625 ubiquitin protein ligase binding GOTERM_MF_DIRECT 49 5.010225 0 966 312 18883 3.069979 0 0 0
GO:0004672 protein kinase activity GOTERM_MF_DIRECT 55 5.623722 0 966 385 18883 2.792517 0 0 0

DAVID Results from our R script/DAVID Reborn Tool:

script_results <- readRDS("../../DAVID_vScripts/Validation_2_PMID36344834/ora_arranged2023.RDS")

script_results$GOID <- sapply(script_results$Description, function(term) strsplit(term, " ")[[1]][1])

script_results$GO.Term <- sapply(script_results$Description, function(term) paste(strsplit(term, " ")[[1]][-1], collapse = " "))

script_results <- select(script_results, S_No, GOID, GO.Term, GeneRatio, BgRatio, pvalue, p.adjust, qvalue, geneID, Count, gr, br, EnrichmentScore)

# minimum of 2 genes
script_results <- subset(script_results,Count >=2 )

tmp <- script_results
tmp$geneID=NULL

head(tmp,20) %>%
  kbl(caption="Top results from DAVID Reborn Tool") %>%
  kable_paper("hover", full_width = F)
Top results from DAVID Reborn Tool
S_No GOID GO.Term GeneRatio BgRatio pvalue p.adjust qvalue Count gr br EnrichmentScore
1 GO:0005515 MF protein binding 849/977 12707/20758 0 0 0 849 0.8689867 0.6121495 1.419566
2 GO:0005829 CC cytosol 496/977 5447/20758 0 0 0 496 0.5076766 0.2624049 1.934707
3 GO:0005654 CC nucleoplasm 378/977 3905/20758 0 0 0 378 0.3868987 0.1881202 2.056656
4 GO:0005634 CC nucleus 423/977 5680/20758 0 0 0 423 0.4329580 0.2736294 1.582279
5 GO:0005737 CC cytoplasm 392/977 5111/20758 0 0 0 392 0.4012282 0.2462183 1.629563
6 GO:0042802 MF identical protein binding 158/977 1545/20758 0 0 0 158 0.1617195 0.0744291 2.172799
7 GO:0019901 MF protein kinase binding 75/977 471/20758 0 0 0 75 0.0767656 0.0226900 3.383228
8 GO:0005524 MF ATP binding 148/977 1479/20758 0 0 0 148 0.1514841 0.0712496 2.126104
9 GO:0070062 CC extracellular exosome 192/977 2212/20758 0 0 0 192 0.1965200 0.1065613 1.844196
10 GO:0019899 MF enzyme binding 59/977 355/20758 0 0 0 59 0.0603889 0.0171018 3.531137
11 GO:0006468 BP protein phosphorylation 61/977 384/20758 0 0 0 61 0.0624360 0.0184989 3.375123
12 GO:0005739 CC mitochondrion 134/977 1363/20758 0 0 0 134 0.1371546 0.0656614 2.088815
13 GO:0051301 BP cell division 53/977 351/20758 0 0 0 53 0.0542477 0.0169091 3.208187
14 GO:0045893 BP positive regulation of DNA-templated transcription 79/977 688/20758 0 0 0 79 0.0808598 0.0331438 2.439662
15 GO:0031625 MF ubiquitin protein ligase binding 47/977 305/20758 0 0 0 47 0.0481064 0.0146931 3.274078
16 GO:0043066 BP negative regulation of apoptotic process 61/977 477/20758 0 0 0 61 0.0624360 0.0229791 2.717080
17 GO:0071456 BP cellular response to hypoxia 29/977 134/20758 0 0 0 29 0.0296827 0.0064553 4.598161
18 GO:1902895 BP positive regulation of miRNA transcription 19/977 56/20758 0 0 0 19 0.0194473 0.0026978 7.208693
19 GO:0005783 CC endoplasmic reticulum 103/977 1081/20758 0 0 0 103 0.1054248 0.0520763 2.024429
20 GO:0043065 BP positive regulation of apoptotic process 45/977 303/20758 0 0 0 45 0.0460594 0.0145968 3.155447

Compare the genes that are recognised in both analyses

Extract the gene lists from the results of the web tool and the reborn tool to see where genes are being exluded.

#web_genes <- unique(gsub(" ","",unlist(strsplit(PMID33947848_results$Genes,","))))
#web_genes <- sort(web_genes)
#str(web_genes)
#481 genes
web_genes <- unique(gsub(" ","",unlist(strsplit(PMID36344834_results$Genes,","))))
web_genes <- sort(web_genes)
str(web_genes)
##  chr [1:976] "AARS1" "ABCB6" "ABCC5" "ABCF1" "ABCF3" "ABHD4" "ABHD6" "ABL1" ...
script_genes <- unique(unlist(strsplit(script_results$geneID," ")))
script_genes <- sort(script_genes)
str(script_genes)
##  chr [1:977] "AARS1" "ABCB6" "ABCC5" "ABCF1" "ABCF3" "ABHD4" "ABHD6" "ABL1" ...
# 499 genes looks right

v1 <- list("web"=web_genes,"script"=script_genes)

plot(euler(v1),quantities = list(cex = 1.0), labels = list(cex = 1.5))

message("Genes unique to web")
## Genes unique to web
setdiff(web_genes,script_genes)
## character(0)
message("Genes unique to script")
## Genes unique to script
setdiff(script_genes, web_genes)
## [1] "NT5DC2"

Comparing results from the web-server and our R script:

# From DAVID webserver table output: 
#web_split <- sapply(strsplit(PMID33947848_results$Term,"~"),"[[",1)
#web_split <- sapply(strsplit(PMID36344834_results$Term,"~"),"[[",1)

#DAVID_webserver <- PMID33947848_results %>% #Change PMID/PMCID
  #select(GOID, Count, PValue, Fold.Enrichment, FDR)
DAVID_webserver <- PMID36344834_results %>% #Change PMID/PMCID
  select(GOID, Count, PValue, Fold.Enrichment, FDR)

DAVID_reborn <- script_results %>%
  select(S_No, GOID, GO.Term, GeneRatio, pvalue, p.adjust, Count ,EnrichmentScore)

comparison_table <- merge(DAVID_webserver, DAVID_reborn, by = "GOID", all = TRUE)

comparison_table <- comparison_table[order(comparison_table$PValue),]

comparison_table$geneID=NULL

head(comparison_table,50) %>%
  kbl(caption="Top replication results") %>%
  kable_paper("hover", full_width = F)
Top replication results
GOID Count.x PValue Fold.Enrichment FDR S_No GO.Term GeneRatio pvalue p.adjust Count.y EnrichmentScore
487 GO:0005829 498 0e+00 1.900790 0.00e+00 2 CC cytosol 496/977 0.0000000 0.0000000 496 1.934707
402 GO:0005515 849 0e+00 1.306046 0.00e+00 1 MF protein binding 849/977 0.0000000 0.0000000 849 1.419566
427 GO:0005654 379 0e+00 2.016551 0.00e+00 3 CC nucleoplasm 378/977 0.0000000 0.0000000 378 2.056656
446 GO:0005737 431 0e+00 1.616165 0.00e+00 5 CC cytoplasm 392/977 0.0000000 0.0000000 392 1.629563
420 GO:0005634 433 0e+00 1.519842 0.00e+00 4 CC nucleus 423/977 0.0000000 0.0000000 423 1.582279
1206 GO:0019901 76 0e+00 3.075816 0.00e+00 7 MF protein kinase binding 75/977 0.0000000 0.0000000 75 3.383228
2677 GO:0070062 193 0e+00 1.820098 0.00e+00 9 CC extracellular exosome 192/977 0.0000000 0.0000000 192 1.844196
1915 GO:0042802 168 0e+00 1.893887 0.00e+00 6 MF identical protein binding 158/977 0.0000000 0.0000000 158 2.172799
447 GO:0005739 137 0e+00 2.028971 0.00e+00 12 CC mitochondrion 134/977 0.0000000 0.0000000 134 2.088815
1101 GO:0016310 80 0e+00 2.611067 0.00e+00 342 BP phosphorylation 27/977 0.0007437 0.0150603 27 1.951225
1204 GO:0019899 60 0e+00 3.135982 0.00e+00 10 MF enzyme binding 59/977 0.0000000 0.0000000 59 3.531137
408 GO:0005524 150 0e+00 1.903989 0.00e+00 8 MF ATP binding 148/977 0.0000000 0.0000000 148 2.126104
2455 GO:0051301 59 0e+00 3.107998 0.00e+00 13 BP cell division 53/977 0.0000000 0.0000000 53 3.208187
596 GO:0006468 58 0e+00 3.111751 0.00e+00 11 BP protein phosphorylation 61/977 0.0000000 0.0000000 61 3.375123
713 GO:0007049 54 0e+00 3.128259 0.00e+00 34 BP cell cycle 40/977 0.0000000 0.0000002 40 2.940716
1936 GO:0043065 51 0e+00 3.230586 0.00e+00 20 BP positive regulation of apoptotic process 45/977 0.0000000 0.0000000 45 3.155447
2182 GO:0045893 83 0e+00 2.350551 0.00e+00 14 BP positive regulation of DNA-templated transcription 79/977 0.0000000 0.0000000 79 2.439662
1603 GO:0032991 79 0e+00 2.412683 0.00e+00 21 CC protein-containing complex 71/977 0.0000000 0.0000000 71 2.390672
1476 GO:0031625 49 0e+00 3.069979 0.00e+00 15 MF ubiquitin protein ligase binding 47/977 0.0000000 0.0000000 47 3.274078
331 GO:0004672 55 0e+00 2.792517 0.00e+00 55 MF protein kinase activity 30/977 0.0000000 0.0000058 30 3.064424
1937 GO:0043066 63 0e+00 2.531664 0.00e+00 16 BP negative regulation of apoptotic process 61/977 0.0000000 0.0000000 61 2.717080
3133 GO:1902895 20 0e+00 6.777895 0.00e+00 18 BP positive regulation of miRNA transcription 19/977 0.0000000 0.0000000 19 7.208693
905 GO:0009410 40 0e+00 3.253390 1.00e-07 30 BP response to xenobiotic stimulus 36/977 0.0000000 0.0000001 36 3.200336
510 GO:0005925 54 0e+00 2.666424 0.00e+00 22 CC focal adhesion 55/977 0.0000000 0.0000000 55 2.756054
2808 GO:0071456 29 0e+00 4.242280 1.00e-07 17 BP cellular response to hypoxia 29/977 0.0000000 0.0000000 29 4.598161
469 GO:0005783 104 0e+00 1.916237 0.00e+00 19 CC endoplasmic reticulum 103/977 0.0000000 0.0000000 103 2.024429
2189 GO:0045944 112 0e+00 1.851523 1.00e-07 23 BP positive regulation of transcription by RNA polymerase II 108/977 0.0000000 0.0000000 108 1.923421
2650 GO:0061629 34 0e+00 3.592535 0.00e+00 24 MF RNA polymerase II-specific DNA-binding transcription factor binding 32/977 0.0000000 0.0000000 32 3.885106
3265 GO:2000045 18 0e+00 6.777895 2.00e-07 27 BP regulation of G1/S transition of mitotic cell cycle 17/977 0.0000000 0.0000000 17 6.946028
2100 GO:0045296 45 0e+00 2.748884 3.00e-07 25 MF cadherin binding 45/977 0.0000000 0.0000000 45 3.016089
673 GO:0006915 65 0e+00 2.225067 1.10e-06 43 BP apoptotic process 58/977 0.0000000 0.0000019 58 2.216380
2187 GO:0045931 14 0e+00 8.133474 1.60e-06 31 BP positive regulation of mitotic cell cycle 13/977 0.0000000 0.0000002 13 8.631461
7 GO:0000079 16 0e+00 6.777895 1.60e-06 28 BP regulation of cyclin-dependent protein serine/threonine kinase activity 16/977 0.0000000 0.0000001 16 7.082224
2906 GO:0090398 17 0e+00 6.064432 2.60e-06 29 BP cellular senescence 17/977 0.0000000 0.0000001 17 6.336727
851 GO:0008284 57 0e+00 2.299643 2.80e-06 32 BP positive regulation of cell population proliferation 56/977 0.0000000 0.0000002 56 2.428191
332 GO:0004674 48 0e+00 2.424511 3.90e-06 33 MF protein serine/threonine kinase activity 46/977 0.0000000 0.0000002 46 2.699854
2166 GO:0045786 16 0e+00 5.915254 1.03e-05 42 BP negative regulation of cell cycle 15/977 0.0000000 0.0000016 15 6.128848
482 GO:0005813 64 1e-07 2.077678 4.20e-06 41 CC centrosome 64/977 0.0000000 0.0000015 64 2.134674
12 GO:0000122 90 1e-07 1.810120 1.41e-05 26 BP negative regulation of transcription by RNA polymerase II 89/977 0.0000000 0.0000000 89 2.062109
2462 GO:0051402 19 1e-07 4.711464 1.58e-05 38 BP neuron apoptotic process 19/977 0.0000000 0.0000007 19 5.046085
2296 GO:0048471 70 1e-07 1.985734 4.90e-06 73 CC perinuclear region of cytoplasm 65/977 0.0000003 0.0000292 65 1.928818
10 GO:0000086 15 1e-07 6.100106 1.58e-05 52 BP G2/M transition of mitotic cell cycle 14/977 0.0000000 0.0000034 14 6.196946
1169 GO:0018108 15 1e-07 6.100106 1.58e-05 40 BP peptidyl-tyrosine phosphorylation 15/977 0.0000000 0.0000012 15 6.249022
2261 GO:0048013 15 1e-07 6.100106 1.58e-05 39 BP ephrin receptor signaling pathway 15/977 0.0000000 0.0000007 15 6.504084
2790 GO:0071364 14 1e-07 6.469809 2.19e-05 37 BP cellular response to epidermal growth factor stimulus 14/977 0.0000000 0.0000007 14 7.082224
2181 GO:0045892 59 1e-07 2.097356 2.62e-05 36 BP negative regulation of DNA-templated transcription 60/977 0.0000000 0.0000003 60 2.301084
1345 GO:0030335 35 1e-07 2.769179 2.62e-05 49 BP positive regulation of cell migration 34/977 0.0000000 0.0000031 34 2.912850
173 GO:0001934 31 2e-07 2.959363 3.44e-05 62 BP positive regulation of protein phosphorylation 28/977 0.0000001 0.0000142 28 3.066530
1538 GO:0032465 13 2e-07 6.777895 3.53e-05 44 BP regulation of cytokinesis 13/977 0.0000000 0.0000021 13 7.082224
2008 GO:0043524 25 2e-07 3.434744 3.85e-05 82 BP negative regulation of neuron apoptotic process 22/977 0.0000006 0.0000478 22 3.362783

Compare p-values directly.

comparison_table$fdrdiff <- abs(-log10(comparison_table$FDR) - -log10(comparison_table$p.adjust))

hist( comparison_table$fdrdiff / -log10(comparison_table$FDR) )

table(comparison_table$fdrdiff / -log10(comparison_table$FDR) < 1)
## 
## FALSE  TRUE 
##  1596   494
comparison_table$fdrcheck  <- comparison_table$fdrdiff / -log10(comparison_table$FDR) < 1

Compare fold enrichments directly.

comparison_table$folddiff <- abs( comparison_table$Fold.Enrichment - comparison_table$EnrichmentScore)

hist( comparison_table$folddiff / comparison_table$Fold.Enrichment )

table( comparison_table$folddiff / comparison_table$Fold.Enrichment <0.3)
## 
## FALSE  TRUE 
##    60  2030
comparison_table$foldcheck  <- comparison_table$folddiff / comparison_table$Fold.Enrichment <0.3

Now look at the significant sets and see if they classify as replicated.

sig <- subset(comparison_table, FDR <0.05)

repro <- subset(sig, fdrcheck == "TRUE" & foldcheck == "TRUE")

notrepro <- subset(sig, fdrcheck != "TRUE" | foldcheck != "TRUE")

message("No. significant results from paper")
## No. significant results from paper
nrow(sig)
## [1] 266
message("No. replicated results")
## No. replicated results
nrow(repro)
## [1] 263
message("No. non-replicated results")
## No. non-replicated results
nrow(notrepro)
## [1] 3
message("Success rate")
## Success rate
nrow(repro) / nrow(sig)
## [1] 0.9887218
head(repro,50) %>%
  kbl(caption="Top reproduced results") %>%
  kable_paper("hover", full_width = F)
Top reproduced results
GOID Count.x PValue Fold.Enrichment FDR S_No GO.Term GeneRatio pvalue p.adjust Count.y EnrichmentScore fdrdiff fdrcheck folddiff foldcheck
487 GO:0005829 498 0e+00 1.900790 0.00e+00 2 CC cytosol 496/977 0.0000000 0.0000000 496 1.934707 1.5334373 TRUE 0.0339173 TRUE
402 GO:0005515 849 0e+00 1.306046 0.00e+00 1 MF protein binding 849/977 0.0000000 0.0000000 849 1.419566 20.8675813 TRUE 0.1135199 TRUE
427 GO:0005654 379 0e+00 2.016551 0.00e+00 3 CC nucleoplasm 378/977 0.0000000 0.0000000 378 2.056656 1.2538178 TRUE 0.0401050 TRUE
446 GO:0005737 431 0e+00 1.616165 0.00e+00 5 CC cytoplasm 392/977 0.0000000 0.0000000 392 1.629563 3.8640991 TRUE 0.0133984 TRUE
420 GO:0005634 433 0e+00 1.519842 0.00e+00 4 CC nucleus 423/977 0.0000000 0.0000000 423 1.582279 1.9669073 TRUE 0.0624363 TRUE
1206 GO:0019901 76 0e+00 3.075816 0.00e+00 7 MF protein kinase binding 75/977 0.0000000 0.0000000 75 3.383228 2.2731719 TRUE 0.3074124 TRUE
2677 GO:0070062 193 0e+00 1.820098 0.00e+00 9 CC extracellular exosome 192/977 0.0000000 0.0000000 192 1.844196 0.2188497 TRUE 0.0240980 TRUE
1915 GO:0042802 168 0e+00 1.893887 0.00e+00 6 MF identical protein binding 158/977 0.0000000 0.0000000 158 2.172799 4.3582496 TRUE 0.2789120 TRUE
447 GO:0005739 137 0e+00 2.028971 0.00e+00 12 CC mitochondrion 134/977 0.0000000 0.0000000 134 2.088815 0.3200390 TRUE 0.0598434 TRUE
1101 GO:0016310 80 0e+00 2.611067 0.00e+00 342 BP phosphorylation 27/977 0.0007437 0.0150603 27 1.951225 8.6238206 TRUE 0.6598420 TRUE
1204 GO:0019899 60 0e+00 3.135982 0.00e+00 10 MF enzyme binding 59/977 0.0000000 0.0000000 59 3.531137 2.2421750 TRUE 0.3951556 TRUE
408 GO:0005524 150 0e+00 1.903989 0.00e+00 8 MF ATP binding 148/977 0.0000000 0.0000000 148 2.126104 3.6334081 TRUE 0.2221150 TRUE
2455 GO:0051301 59 0e+00 3.107998 0.00e+00 13 BP cell division 53/977 0.0000000 0.0000000 53 3.208187 0.3157693 TRUE 0.1001886 TRUE
596 GO:0006468 58 0e+00 3.111751 0.00e+00 11 BP protein phosphorylation 61/977 0.0000000 0.0000000 61 3.375123 3.2731178 TRUE 0.2633713 TRUE
713 GO:0007049 54 0e+00 3.128259 0.00e+00 34 BP cell cycle 40/977 0.0000000 0.0000002 40 2.940716 2.7934141 TRUE 0.1875432 TRUE
1936 GO:0043065 51 0e+00 3.230586 0.00e+00 20 BP positive regulation of apoptotic process 45/977 0.0000000 0.0000000 45 3.155447 0.8661148 TRUE 0.0751390 TRUE
2182 GO:0045893 83 0e+00 2.350551 0.00e+00 14 BP positive regulation of DNA-templated transcription 79/977 0.0000000 0.0000000 79 2.439662 0.8143112 TRUE 0.0891103 TRUE
1603 GO:0032991 79 0e+00 2.412683 0.00e+00 21 CC protein-containing complex 71/977 0.0000000 0.0000000 71 2.390672 1.4944858 TRUE 0.0220115 TRUE
1476 GO:0031625 49 0e+00 3.069979 0.00e+00 15 MF ubiquitin protein ligase binding 47/977 0.0000000 0.0000000 47 3.274078 0.6664312 TRUE 0.2040989 TRUE
331 GO:0004672 55 0e+00 2.792517 0.00e+00 55 MF protein kinase activity 30/977 0.0000000 0.0000058 30 3.064424 3.3846929 TRUE 0.2719071 TRUE
1937 GO:0043066 63 0e+00 2.531664 0.00e+00 16 BP negative regulation of apoptotic process 61/977 0.0000000 0.0000000 61 2.717080 1.5735299 TRUE 0.1854155 TRUE
3133 GO:1902895 20 0e+00 6.777895 0.00e+00 18 BP positive regulation of miRNA transcription 19/977 0.0000000 0.0000000 19 7.208693 1.1039919 TRUE 0.4307977 TRUE
905 GO:0009410 40 0e+00 3.253390 1.00e-07 30 BP response to xenobiotic stimulus 36/977 0.0000000 0.0000001 36 3.200336 0.3286086 TRUE 0.0530539 TRUE
510 GO:0005925 54 0e+00 2.666424 0.00e+00 22 CC focal adhesion 55/977 0.0000000 0.0000000 55 2.756054 0.6742218 TRUE 0.0896299 TRUE
2808 GO:0071456 29 0e+00 4.242280 1.00e-07 17 BP cellular response to hypoxia 29/977 0.0000000 0.0000000 29 4.598161 1.6393738 TRUE 0.3558810 TRUE
469 GO:0005783 104 0e+00 1.916237 0.00e+00 19 CC endoplasmic reticulum 103/977 0.0000000 0.0000000 103 2.024429 0.9607952 TRUE 0.1081917 TRUE
2189 GO:0045944 112 0e+00 1.851523 1.00e-07 23 BP positive regulation of transcription by RNA polymerase II 108/977 0.0000000 0.0000000 108 1.923421 1.0373080 TRUE 0.0718980 TRUE
2650 GO:0061629 34 0e+00 3.592535 0.00e+00 24 MF RNA polymerase II-specific DNA-binding transcription factor binding 32/977 0.0000000 0.0000000 32 3.885106 0.6294467 TRUE 0.2925706 TRUE
3265 GO:2000045 18 0e+00 6.777895 2.00e-07 27 BP regulation of G1/S transition of mitotic cell cycle 17/977 0.0000000 0.0000000 17 6.946028 0.7593623 TRUE 0.1681328 TRUE
2100 GO:0045296 45 0e+00 2.748884 3.00e-07 25 MF cadherin binding 45/977 0.0000000 0.0000000 45 3.016089 1.4446050 TRUE 0.2672054 TRUE
673 GO:0006915 65 0e+00 2.225067 1.10e-06 43 BP apoptotic process 58/977 0.0000000 0.0000019 58 2.216380 0.2579959 TRUE 0.0086870 TRUE
2187 GO:0045931 14 0e+00 8.133474 1.60e-06 31 BP positive regulation of mitotic cell cycle 13/977 0.0000000 0.0000002 13 8.631461 0.9552565 TRUE 0.4979870 TRUE
7 GO:0000079 16 0e+00 6.777895 1.60e-06 28 BP regulation of cyclin-dependent protein serine/threonine kinase activity 16/977 0.0000000 0.0000001 16 7.082224 1.3536469 TRUE 0.3043294 TRUE
2906 GO:0090398 17 0e+00 6.064432 2.60e-06 29 BP cellular senescence 17/977 0.0000000 0.0000001 17 6.336727 1.2850156 TRUE 0.2722947 TRUE
851 GO:0008284 57 0e+00 2.299643 2.80e-06 32 BP positive regulation of cell population proliferation 56/977 0.0000000 0.0000002 56 2.428191 1.1986957 TRUE 0.1285483 TRUE
332 GO:0004674 48 0e+00 2.424511 3.90e-06 33 MF protein serine/threonine kinase activity 46/977 0.0000000 0.0000002 46 2.699854 1.3036646 TRUE 0.2753426 TRUE
2166 GO:0045786 16 0e+00 5.915254 1.03e-05 42 BP negative regulation of cell cycle 15/977 0.0000000 0.0000016 15 6.128848 0.8090315 TRUE 0.2135942 TRUE
482 GO:0005813 64 1e-07 2.077678 4.20e-06 41 CC centrosome 64/977 0.0000000 0.0000015 64 2.134674 0.4325447 TRUE 0.0569955 TRUE
12 GO:0000122 90 1e-07 1.810120 1.41e-05 26 BP negative regulation of transcription by RNA polymerase II 89/977 0.0000000 0.0000000 89 2.062109 2.9321044 TRUE 0.2519886 TRUE
2462 GO:0051402 19 1e-07 4.711464 1.58e-05 38 BP neuron apoptotic process 19/977 0.0000000 0.0000007 19 5.046085 1.3612400 TRUE 0.3346213 TRUE
2296 GO:0048471 70 1e-07 1.985734 4.90e-06 73 CC perinuclear region of cytoplasm 65/977 0.0000003 0.0000292 65 1.928818 0.7752540 TRUE 0.0569158 TRUE
10 GO:0000086 15 1e-07 6.100106 1.58e-05 52 BP G2/M transition of mitotic cell cycle 14/977 0.0000000 0.0000034 14 6.196946 0.6644158 TRUE 0.0968408 TRUE
1169 GO:0018108 15 1e-07 6.100106 1.58e-05 40 BP peptidyl-tyrosine phosphorylation 15/977 0.0000000 0.0000012 15 6.249022 1.1044736 TRUE 0.1489160 TRUE
2261 GO:0048013 15 1e-07 6.100106 1.58e-05 39 BP ephrin receptor signaling pathway 15/977 0.0000000 0.0000007 15 6.504084 1.3612400 TRUE 0.4039781 TRUE
2790 GO:0071364 14 1e-07 6.469809 2.19e-05 37 BP cellular response to epidermal growth factor stimulus 14/977 0.0000000 0.0000007 14 7.082224 1.5038425 TRUE 0.6124155 TRUE
2181 GO:0045892 59 1e-07 2.097356 2.62e-05 36 BP negative regulation of DNA-templated transcription 60/977 0.0000000 0.0000003 60 2.301084 1.9221630 TRUE 0.2037281 TRUE
1345 GO:0030335 35 1e-07 2.769179 2.62e-05 49 BP positive regulation of cell migration 34/977 0.0000000 0.0000031 34 2.912850 0.9274529 TRUE 0.1436715 TRUE
173 GO:0001934 31 2e-07 2.959363 3.44e-05 62 BP positive regulation of protein phosphorylation 28/977 0.0000001 0.0000142 28 3.066530 0.3831931 TRUE 0.1071675 TRUE
1538 GO:0032465 13 2e-07 6.777895 3.53e-05 44 BP regulation of cytokinesis 13/977 0.0000000 0.0000021 13 7.082224 1.2255948 TRUE 0.3043294 TRUE
2008 GO:0043524 25 2e-07 3.434744 3.85e-05 82 BP negative regulation of neuron apoptotic process 22/977 0.0000006 0.0000478 22 3.362783 0.0941283 TRUE 0.0719613 TRUE 
head(notrepro,50) %>%
  kbl(caption="Top un-reproduced results") %>%
  kable_paper("hover", full_width = F)
Top un-reproduced results
GOID Count.x PValue Fold.Enrichment FDR S_No GO.Term GeneRatio pvalue p.adjust Count.y EnrichmentScore fdrdiff fdrcheck folddiff foldcheck
1099 GO:0016301 30 0.0000131 2.463986 0.0009073 214 MF kinase activity 11/977 0.0001330 0.0043019 11 3.769571 0.6759028 TRUE 1.3055855 FALSE
278 GO:0003723 111 0.0000336 1.471041 0.0017157 46 MF RNA binding 111/977 0.0000000 0.0000026 111 1.707734 2.8233451 FALSE 0.2366929 TRUE
2780 GO:0071310 9 0.0001525 5.545551 0.0076096 1649 BP cellular response to organic substance 3/977 0.0431592 0.1507773 3 3.749413 1.2969713 TRUE 1.7961376 FALSE

Session information

For reproducibility

sessionInfo()
## R version 4.4.0 (2024-04-24)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 22.04.4 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
## 
## 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       
## 
## time zone: Australia/Melbourne
## tzcode source: system (glibc)
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
##  [1] eulerr_7.0.2     lubridate_1.9.3  forcats_1.0.0    stringr_1.5.1   
##  [5] dplyr_1.1.4      purrr_1.0.2      readr_2.1.5      tidyr_1.3.1     
##  [9] tibble_3.2.1     ggplot2_3.5.1    tidyverse_2.0.0  kableExtra_1.4.0
## [13] knitr_1.47      
## 
## loaded via a namespace (and not attached):
##  [1] sass_0.4.9        utf8_1.2.4        generics_0.1.3    xml2_1.3.6       
##  [5] polylabelr_0.2.0  stringi_1.8.4     hms_1.1.3         digest_0.6.35    
##  [9] magrittr_2.0.3    evaluate_0.24.0   grid_4.4.0        timechange_0.3.0 
## [13] fastmap_1.2.0     jsonlite_1.8.8    fansi_1.0.6       viridisLite_0.4.2
## [17] scales_1.3.0      jquerylib_0.1.4   cli_3.6.2         rlang_1.1.4      
## [21] polyclip_1.10-6   munsell_0.5.1     withr_3.0.0       cachem_1.1.0     
## [25] yaml_2.3.8        tools_4.4.0       tzdb_0.4.0        colorspace_2.1-0 
## [29] vctrs_0.6.5       R6_2.5.1          lifecycle_1.0.4   pkgconfig_2.0.3  
## [33] pillar_1.9.0      bslib_0.7.0       gtable_0.3.5      glue_1.7.0       
## [37] Rcpp_1.0.12       systemfonts_1.1.0 xfun_0.44         tidyselect_1.2.1 
## [41] highr_0.11        rstudioapi_0.16.0 htmltools_0.5.8.1 rmarkdown_2.27   
## [45] svglite_2.1.3     compiler_4.4.0