Comparison_Script

For PMID33947848

Loading libraries:

library("knitr")
library("kableExtra")
library("tidyverse")
library("stringr")
library("tidyr")
library("eulerr")

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

#PMID33947848_results <- read.table("../output_lists/PMID33947848_webDAVID_20240513.tsv", header = TRUE, sep = "\t")  #Change PMID/PMCID
PMID33947848_results <- read.csv("../output_lists/PMID33947848_webDAVID_20240513.tsv", header = TRUE, sep = "\t")

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

PMID33947848_results$GOID <- sapply(split_terms, "[", 1)
PMID33947848_results$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)

tmp <- PMID33947848_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:0051301	cell division	GOTERM_BP_DIRECT	105	20.507812	0	480	386	19256	10.912565	0	0	0
GO:0005654	nucleoplasm	GOTERM_CC_DIRECT	273	53.320312	0	493	3972	20521	2.860915	0	0	0
GO:0005634	nucleus	GOTERM_CC_DIRECT	310	60.546875	0	493	6021	20521	2.143111	0	0	0
GO:0006260	DNA replication	GOTERM_BP_DIRECT	47	9.179688	0	480	121	19256	15.582507	0	0	0
GO:0007059	chromosome segregation	GOTERM_BP_DIRECT	43	8.398438	0	480	96	19256	17.968924	0	0	0
GO:0006281	DNA repair	GOTERM_BP_DIRECT	63	12.304688	0	480	302	19256	8.368709	0	0	0
GO:0005515	protein binding	GOTERM_MF_DIRECT	433	84.570312	0	480	12707	18883	1.340524	0	0	0
GO:0000776	kinetochore	GOTERM_CC_DIRECT	42	8.203125	0	493	156	20521	11.206663	0	0	0
GO:0005813	centrosome	GOTERM_CC_DIRECT	75	14.648438	0	493	651	20521	4.795478	0	0	0
GO:0005694	chromosome	GOTERM_CC_DIRECT	47	9.179688	0	493	257	20521	7.612308	0	0	0
GO:0000775	chromosome, centromeric region	GOTERM_CC_DIRECT	27	5.273438	0	493	63	20521	17.839177	0	0	0
GO:0007049	cell cycle	GOTERM_BP_DIRECT	53	10.351562	0	480	351	19256	6.057502	0	0	0
GO:0005829	cytosol	GOTERM_CC_DIRECT	233	45.507812	0	493	5537	20521	1.751592	0	0	0
GO:0000278	mitotic cell cycle	GOTERM_BP_DIRECT	33	6.445312	0	480	137	19256	9.663139	0	0	0
GO:0017116	single-stranded DNA-dependent ATP-dependent DNA helicase activity	GOTERM_MF_DIRECT	16	3.125000	0	480	20	18883	31.471667	0	0	0
GO:0000922	spindle pole	GOTERM_CC_DIRECT	30	5.859375	0	493	133	20521	9.389041	0	0	0
GO:0003697	single-stranded DNA binding	GOTERM_MF_DIRECT	28	5.468750	0	480	108	18883	10.199151	0	0	0
GO:0000070	mitotic sister chromatid segregation	GOTERM_BP_DIRECT	18	3.515625	0	480	32	19256	22.565625	0	0	0
GO:0007094	mitotic spindle assembly checkpoint	GOTERM_BP_DIRECT	17	3.320312	0	480	30	19256	22.732778	0	0	0
GO:0003682	chromatin binding	GOTERM_MF_DIRECT	52	10.156250	0	480	487	18883	4.200531	0	0	0

DAVID Results from our R script/DAVID Reborn Tool:

script_results <- readRDS("../DAVID_vScripts/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:0051301	BP cell division	100/499	351/20758	0	0	0	100	0.2004008	0.0169091	11.851624
2	GO:0005654	CC nucleoplasm	274/499	3905/20758	0	0	0	274	0.5490982	0.1881202	2.918868
3	GO:0005634	CC nucleus	295/499	5680/20758	0	0	0	295	0.5911824	0.2736294	2.160522
4	GO:0007059	BP chromosome segregation	41/499	91/20758	0	0	0	41	0.0821643	0.0043839	18.742496
5	GO:0005515	MF protein binding	434/499	12707/20758	0	0	0	434	0.8697395	0.6121495	1.420796
6	GO:0006281	BP DNA repair	55/499	247/20758	0	0	0	55	0.1102204	0.0118990	9.262979
7	GO:0006260	BP DNA replication	36/499	91/20758	0	0	0	36	0.0721443	0.0043839	16.456826
8	GO:0000776	CC kinetochore	42/499	154/20758	0	0	0	42	0.0841683	0.0074188	11.345236
9	GO:0005813	CC centrosome	75/499	637/20758	0	0	0	75	0.1503006	0.0306870	4.897865
10	GO:0000775	CC chromosome, centromeric region	25/499	56/20758	0	0	0	25	0.0501002	0.0026978	18.571071
11	GO:0005829	CC cytosol	233/499	5447/20758	0	0	0	233	0.4669339	0.2624049	1.779441
12	GO:0017116	MF single-stranded DNA helicase activity	16/499	20/20758	0	0	0	16	0.0320641	0.0009635	33.279359
13	GO:0000278	BP mitotic cell cycle	31/499	128/20758	0	0	0	31	0.0621242	0.0061663	10.074806
14	GO:0003697	MF single-stranded DNA binding	27/499	105/20758	0	0	0	27	0.0541082	0.0050583	10.696937
15	GO:0000922	CC spindle pole	29/499	128/20758	0	0	0	29	0.0581162	0.0061663	9.424818
16	GO:0000070	BP mitotic sister chromatid segregation	17/499	31/20758	0	0	0	17	0.0340681	0.0014934	22.812464
17	GO:0003682	MF chromatin binding	50/499	445/20758	0	0	0	50	0.1002004	0.0214375	4.674067
18	GO:0007094	BP mitotic spindle assembly checkpoint signaling	16/499	29/20758	0	0	0	16	0.0320641	0.0013971	22.951282
19	GO:0071162	CC CMG complex	11/499	11/20758	0	0	0	11	0.0220441	0.0005299	41.599198
20	GO:0016887	MF ATP hydrolysis activity	46/499	421/20758	0	0	0	46	0.0921844	0.0202813	4.545281

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)

##  chr [1:481] "ABHD10" "ACAT2" "AGPAT5" "ALMS1" "ALYREF" "ANLN" "ANP32B" ...

#481 genes

script_genes <- unique(unlist(strsplit(script_results$geneID," ")))
script_genes <- sort(script_genes)
str(script_genes)

##  chr [1:499] "ABHD10" "ACAT2" "AGPAT5" "ALMS1" "ALYREF" "ANLN" "ANP32B" ...

# 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)

## [1] "C18ORF54" "C4ORF46"

message("Genes unique to script")

## Genes unique to script

setdiff(script_genes, web_genes)

##  [1] "C18orf54"   "C4orf46"    "CASP8AP2"   "CCDC34"     "COQ2"      
##  [6] "DEPDC1B"    "DHRS13"     "ERVMER34-1" "EVA1C"      "FAR2"      
## [11] "FKBP11"     "HDHD5"      "LRRC58"     "MICB"       "OXCT1"     
## [16] "PIGW"       "SLC25A40"   "SLC36A4"    "STEAP1"     "UBR7"

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

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

DAVID_webserver <- PMID33947848_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
783	GO:0051301	105	0	10.912565	0e+00	1	BP cell division	100/499	0	0	100	11.851624
168	GO:0005654	273	0	2.860915	0e+00	2	CC nucleoplasm	274/499	0	0	274	2.918868
163	GO:0005634	310	0	2.143111	0e+00	3	CC nucleus	295/499	0	0	295	2.160522
229	GO:0006260	47	0	15.582507	0e+00	7	BP DNA replication	36/499	0	0	36	16.456826
304	GO:0007059	43	0	17.968924	0e+00	4	BP chromosome segregation	41/499	0	0	41	18.742496
239	GO:0006281	63	0	8.368709	0e+00	6	BP DNA repair	55/499	0	0	55	9.262979
155	GO:0005515	433	0	1.340524	0e+00	5	MF protein binding	434/499	0	0	434	1.420796
46	GO:0000776	42	0	11.206663	0e+00	8	CC kinetochore	42/499	0	0	42	11.345236
201	GO:0005813	75	0	4.795478	0e+00	9	CC centrosome	75/499	0	0	75	4.897865
182	GO:0005694	47	0	7.612308	0e+00	22	CC chromosome	32/499	0	0	32	6.249645
45	GO:0000775	27	0	17.839177	0e+00	10	CC chromosome, centromeric region	25/499	0	0	25	18.571071
300	GO:0007049	53	0	6.057502	0e+00	49	BP cell cycle	30/499	0	0	30	4.318256
206	GO:0005829	233	0	1.751592	0e+00	11	CC cytosol	233/499	0	0	233	1.779441
26	GO:0000278	33	0	9.663139	0e+00	13	BP mitotic cell cycle	31/499	0	0	31	10.074806
445	GO:0017116	16	0	31.471667	0e+00	12	MF single-stranded DNA helicase activity	16/499	0	0	16	33.279359
58	GO:0000922	30	0	9.389041	0e+00	15	CC spindle pole	29/499	0	0	29	9.424818
107	GO:0003697	28	0	10.199151	0e+00	14	MF single-stranded DNA binding	27/499	0	0	27	10.696937
2	GO:0000070	18	0	22.565625	0e+00	16	BP mitotic sister chromatid segregation	17/499	0	0	17	22.812464
312	GO:0007094	17	0	22.732778	0e+00	18	BP mitotic spindle assembly checkpoint signaling	16/499	0	0	16	22.951282
102	GO:0003682	52	0	4.200531	0e+00	17	MF chromatin binding	50/499	0	0	50	4.674067
302	GO:0007052	20	0	14.327381	0e+00	29	BP mitotic spindle organization	17/499	0	0	17	13.343139
48	GO:0000781	30	0	7.218164	0e+00	21	CC chromosome, telomeric region	30/499	0	0	30	7.298105
204	GO:0005819	28	0	7.769953	0e+00	28	CC spindle	25/499	0	0	25	7.703555
234	GO:0006270	15	0	22.287037	0e+00	24	BP DNA replication initiation	14/499	0	0	14	22.399568
841	GO:0071162	11	0	41.624747	0e+00	19	CC CMG complex	11/499	0	0	11	41.599198
439	GO:0016887	46	0	4.218230	0e+00	20	MF ATP hydrolysis activity	46/499	0	0	46	4.545281
563	GO:0032508	19	0	12.293817	0e+00	43	BP DNA duplex unwinding	15/499	0	0	15	11.142642
99	GO:0003677	85	0	2.476937	0e+00	26	MF DNA binding	69/499	0	0	69	3.018238
233	GO:0006268	13	0	24.834127	0e+00	23	BP DNA unwinding involved in DNA replication	13/499	0	0	13	25.751885
60	GO:0000939	12	0	29.382174	0e+00	25	CC inner kinetochore	12/499	0	0	12	29.364140
343	GO:0008017	34	0	4.917448	0e+00	27	MF microtubule binding	34/499	0	0	34	5.398369
288	GO:0006974	35	0	4.743525	0e+00	34	BP DNA damage response	33/499	0	0	33	4.938034
863	GO:0072686	24	0	6.985971	0e+00	33	CC mitotic spindle	24/499	0	0	24	7.234643
42	GO:0000727	10	0	33.430556	0e+00	30	BP double-strand break repair via break-induced replication	10/499	0	0	10	34.665999
41	GO:0000724	21	0	8.179126	0e+00	32	BP double-strand break repair via homologous recombination	21/499	0	0	21	8.824072
103	GO:0003684	18	0	10.262500	0e+00	41	MF damaged DNA binding	16/499	0	0	16	10.399800
157	GO:0005524	87	0	2.222431	0e+00	31	MF ATP binding	87/499	0	0	87	2.447012
61	GO:0000940	9	0	34.056611	0e+00	35	CC outer kinetochore	9/499	0	0	9	34.035708
496	GO:0030496	25	0	5.564806	0e+00	42	CC midbody	25/499	0	0	25	5.682951
27	GO:0000281	16	0	10.029167	0e+00	36	BP mitotic cytokinesis	16/499	0	0	16	10.735277
518	GO:0031297	13	0	13.372222	0e+00	52	BP replication fork processing	12/499	0	0	12	13.491632
53	GO:0000794	13	0	13.198090	0e+00	44	CC condensed nuclear chromosome	13/499	0	0	13	13.866399
3	GO:0000076	9	0	27.773077	0e+00	37	BP DNA replication checkpoint signaling	9/499	0	0	9	28.799445
477	GO:0030174	9	0	27.773077	0e+00	38	BP regulation of DNA-templated DNA replication initiation	9/499	0	0	9	28.799445
787	GO:0051382	9	0	27.773077	0e+00	39	BP kinetochore assembly	9/499	0	0	9	28.799445
801	GO:0051984	9	0	25.789286	0e+00	40	BP positive regulation of chromosome segregation	9/499	0	0	9	28.799445
580	GO:0034080	8	0	32.093333	0e+00	45	BP CENP-A containing chromatin assembly	8/499	0	0	8	33.279359
400	GO:0010971	11	0	15.760119	0e+00	51	BP positive regulation of G2/M transition of mitotic cell cycle	11/499	0	0	11	16.342542
785	GO:0051315	9	0	24.070000	0e+00	46	BP attachment of mitotic spindle microtubules to kinetochore	9/499	0	0	9	24.959519
612	GO:0036297	12	0	13.010811	1e-07	53	BP interstrand cross-link repair	12/499	0	0	12	13.491632

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 
##    76   213

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 
##    11   278

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] 235

message("No. replicated results")

## No. replicated results

nrow(repro)

## [1] 184

message("No. non-replicated results")

## No. non-replicated results

nrow(notrepro)

## [1] 8

message("Success rate")

## Success rate

nrow(repro) / nrow(sig)

## [1] 0.7829787

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
783	GO:0051301	105	0	10.912565	0e+00	1	BP cell division	100/499	0	0	100	11.851624	0.7031536	TRUE	0.9390587	TRUE
168	GO:0005654	273	0	2.860915	0e+00	2	CC nucleoplasm	274/499	0	0	274	2.918868	2.0207354	TRUE	0.0579529	TRUE
163	GO:0005634	310	0	2.143111	0e+00	3	CC nucleus	295/499	0	0	295	2.160522	4.0418644	TRUE	0.0174107	TRUE
229	GO:0006260	47	0	15.582507	0e+00	7	BP DNA replication	36/499	0	0	36	16.456826	7.2840140	TRUE	0.8743189	TRUE
304	GO:0007059	43	0	17.968924	0e+00	4	BP chromosome segregation	41/499	0	0	41	18.742496	0.3368262	TRUE	0.7735724	TRUE
239	GO:0006281	63	0	8.368709	0e+00	6	BP DNA repair	55/499	0	0	55	9.262979	1.5481233	TRUE	0.8942708	TRUE
155	GO:0005515	433	0	1.340524	0e+00	5	MF protein binding	434/499	0	0	434	1.420796	5.2976842	TRUE	0.0802717	TRUE
46	GO:0000776	42	0	11.206663	0e+00	8	CC kinetochore	42/499	0	0	42	11.345236	1.1275630	TRUE	0.1385734	TRUE
201	GO:0005813	75	0	4.795478	0e+00	9	CC centrosome	75/499	0	0	75	4.897865	0.9055141	TRUE	0.1023871	TRUE
182	GO:0005694	47	0	7.612308	0e+00	22	CC chromosome	32/499	0	0	32	6.249645	10.3028214	TRUE	1.3626629	TRUE
45	GO:0000775	27	0	17.839177	0e+00	10	CC chromosome, centromeric region	25/499	0	0	25	18.571071	0.3954923	TRUE	0.7318937	TRUE
300	GO:0007049	53	0	6.057502	0e+00	49	BP cell cycle	30/499	0	0	30	4.318256	13.1677765	TRUE	1.7392465	TRUE
206	GO:0005829	233	0	1.751592	0e+00	11	CC cytosol	233/499	0	0	233	1.779441	0.4014327	TRUE	0.0278485	TRUE
26	GO:0000278	33	0	9.663139	0e+00	13	BP mitotic cell cycle	31/499	0	0	31	10.074806	0.5412033	TRUE	0.4116672	TRUE
445	GO:0017116	16	0	31.471667	0e+00	12	MF single-stranded DNA helicase activity	16/499	0	0	16	33.279359	2.7607129	TRUE	1.8076921	TRUE
58	GO:0000922	30	0	9.389041	0e+00	15	CC spindle pole	29/499	0	0	29	9.424818	0.0183731	TRUE	0.0357778	TRUE
107	GO:0003697	28	0	10.199151	0e+00	14	MF single-stranded DNA binding	27/499	0	0	27	10.696937	1.0773716	TRUE	0.4977855	TRUE
2	GO:0000070	18	0	22.565625	0e+00	16	BP mitotic sister chromatid segregation	17/499	0	0	17	22.812464	0.8917532	TRUE	0.2468386	TRUE
312	GO:0007094	17	0	22.732778	0e+00	18	BP mitotic spindle assembly checkpoint signaling	16/499	0	0	16	22.951282	0.8729929	TRUE	0.2185041	TRUE
102	GO:0003682	52	0	4.200531	0e+00	17	MF chromatin binding	50/499	0	0	50	4.674067	1.9341931	TRUE	0.4735368	TRUE
302	GO:0007052	20	0	14.327381	0e+00	29	BP mitotic spindle organization	17/499	0	0	17	13.343139	1.4284328	TRUE	0.9842418	TRUE
48	GO:0000781	30	0	7.218164	0e+00	21	CC chromosome, telomeric region	30/499	0	0	30	7.298105	0.7036854	TRUE	0.0799409	TRUE
204	GO:0005819	28	0	7.769953	0e+00	28	CC spindle	25/499	0	0	25	7.703555	1.1195085	TRUE	0.0663974	TRUE
234	GO:0006270	15	0	22.287037	0e+00	24	BP DNA replication initiation	14/499	0	0	14	22.399568	0.8586387	TRUE	0.1125313	TRUE
841	GO:0071162	11	0	41.624747	0e+00	19	CC CMG complex	11/499	0	0	11	41.599198	2.2054610	TRUE	0.0255481	TRUE
439	GO:0016887	46	0	4.218230	0e+00	20	MF ATP hydrolysis activity	46/499	0	0	46	4.545281	1.9727878	TRUE	0.3270502	TRUE
563	GO:0032508	19	0	12.293817	0e+00	43	BP DNA duplex unwinding	15/499	0	0	15	11.142642	2.0568979	TRUE	1.1511748	TRUE
99	GO:0003677	85	0	2.476937	0e+00	26	MF DNA binding	69/499	0	0	69	3.018238	1.9268526	TRUE	0.5413016	TRUE
233	GO:0006268	13	0	24.834127	0e+00	23	BP DNA unwinding involved in DNA replication	13/499	0	0	13	25.751885	2.2266553	TRUE	0.9177577	TRUE
60	GO:0000939	12	0	29.382174	0e+00	25	CC inner kinetochore	12/499	0	0	12	29.364140	1.5531701	TRUE	0.0180339	TRUE
343	GO:0008017	34	0	4.917448	0e+00	27	MF microtubule binding	34/499	0	0	34	5.398369	2.0135258	TRUE	0.4809213	TRUE
288	GO:0006974	35	0	4.743525	0e+00	34	BP DNA damage response	33/499	0	0	33	4.938034	0.8325972	TRUE	0.1945096	TRUE
863	GO:0072686	24	0	6.985971	0e+00	33	CC mitotic spindle	24/499	0	0	24	7.234643	0.9874631	TRUE	0.2486718	TRUE
42	GO:0000727	10	0	33.430556	0e+00	30	BP double-strand break repair via break-induced replication	10/499	0	0	10	34.665999	2.5824333	TRUE	1.2354431	TRUE
41	GO:0000724	21	0	8.179126	0e+00	32	BP double-strand break repair via homologous recombination	21/499	0	0	21	8.824072	1.9663638	TRUE	0.6449462	TRUE
103	GO:0003684	18	0	10.262500	0e+00	41	MF damaged DNA binding	16/499	0	0	16	10.399800	0.0035403	TRUE	0.1372996	TRUE
157	GO:0005524	87	0	2.222431	0e+00	31	MF ATP binding	87/499	0	0	87	2.447012	2.7031167	TRUE	0.2245807	TRUE
61	GO:0000940	9	0	34.056611	0e+00	35	CC outer kinetochore	9/499	0	0	9	34.035708	1.8039202	TRUE	0.0209030	TRUE
496	GO:0030496	25	0	5.564806	0e+00	42	CC midbody	25/499	0	0	25	5.682951	0.7713253	TRUE	0.1181449	TRUE
27	GO:0000281	16	0	10.029167	0e+00	36	BP mitotic cytokinesis	16/499	0	0	16	10.735277	1.9051426	TRUE	0.7061103	TRUE
518	GO:0031297	13	0	13.372222	0e+00	52	BP replication fork processing	12/499	0	0	12	13.491632	0.9459925	TRUE	0.1194097	TRUE
53	GO:0000794	13	0	13.198090	0e+00	44	CC condensed nuclear chromosome	13/499	0	0	13	13.866399	1.3368147	TRUE	0.6683091	TRUE
3	GO:0000076	9	0	27.773077	0e+00	37	BP DNA replication checkpoint signaling	9/499	0	0	9	28.799445	2.2754036	TRUE	1.0263681	TRUE
477	GO:0030174	9	0	27.773077	0e+00	38	BP regulation of DNA-templated DNA replication initiation	9/499	0	0	9	28.799445	2.2754036	TRUE	1.0263681	TRUE
787	GO:0051382	9	0	27.773077	0e+00	39	BP kinetochore assembly	9/499	0	0	9	28.799445	2.2754036	TRUE	1.0263681	TRUE
801	GO:0051984	9	0	25.789286	0e+00	40	BP positive regulation of chromosome segregation	9/499	0	0	9	28.799445	2.6126516	TRUE	3.0101593	TRUE
580	GO:0034080	8	0	32.093333	0e+00	45	BP CENP-A containing chromatin assembly	8/499	0	0	8	33.279359	2.4347639	TRUE	1.1860254	TRUE
400	GO:0010971	11	0	15.760119	0e+00	51	BP positive regulation of G2/M transition of mitotic cell cycle	11/499	0	0	11	16.342542	1.8719387	TRUE	0.5824232	TRUE
785	GO:0051315	9	0	24.070000	0e+00	46	BP attachment of mitotic spindle microtubules to kinetochore	9/499	0	0	9	24.959519	2.1041022	TRUE	0.8895190	TRUE
612	GO:0036297	12	0	13.010811	1e-07	53	BP interstrand cross-link repair	12/499	0	0	12	13.491632	1.7434210	TRUE	0.4808211	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
390	GO:0010369	5	0.0004724	13.007733	0.0028857	124	CC chromocenter	5/499	0.0000054	0.0000701	5	17.332999	1.614763	TRUE	4.3252661	FALSE
298	GO:0007019	5	0.0005425	12.536458	0.0089192	116	BP microtubule depolymerization	6/499	0.0000019	0.0000256	6	14.682070	2.542656	FALSE	2.1456117	TRUE
426	GO:0016538	6	0.0011761	7.376172	0.0212344	143	MF cyclin-dependent protein serine/threonine kinase regulator activity	6/499	0.0000361	0.0004043	6	9.244266	1.720303	FALSE	1.8680944	TRUE
247	GO:0006303	6	0.0018606	6.686111	0.0270936	141	BP double-strand break repair via nonhomologous end joining	7/499	0.0000294	0.0003345	7	7.663010	1.908529	FALSE	0.9768991	TRUE
743	GO:0048304	4	0.0021746	14.587879	0.0302276	153	BP positive regulation of isotype switching to IgG isotypes	4/499	0.0000618	0.0006458	4	16.639679	1.670287	FALSE	2.0518006	TRUE
712	GO:0045842	4	0.0028463	13.372222	0.0375607	164	BP positive regulation of mitotic metaphase/anaphase transition	4/499	0.0001401	0.0013610	4	13.866399	1.440877	FALSE	0.4941772	TRUE
391	GO:0010389	4	0.0036323	12.343590	0.0462602	163	BP regulation of G2/M transition of mitotic cell cycle	4/499	0.0001401	0.0013610	4	13.866399	1.531351	FALSE	1.5228097	TRUE
864	GO:0072687	4	0.0060786	10.406187	0.0268739	165	CC meiotic spindle	4/499	0.0001401	0.0013610	4	13.866399	1.295474	TRUE	3.4602129	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_1.46      
## 
## 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_1.8.3     hms_1.1.3         digest_0.6.35    
##  [9] magrittr_2.0.3    evaluate_0.23     grid_4.4.0        timechange_0.3.0 
## [13] fastmap_1.1.1     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_1.1.3      
## [21] polyclip_1.10-6   munsell_0.5.1     cachem_1.0.8      withr_3.0.0      
## [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_1.0.6 highr_0.10        xfun_0.43        
## [41] tidyselect_1.2.1  rstudioapi_0.16.0 htmltools_0.5.8.1 rmarkdown_2.26   
## [45] svglite_2.1.3     compiler_4.4.0