PMC Survey QC Analysis
Mark Ziemann & Kaumadi Wijesooriya
2021-08-19
Intro
Here we are performing an analysis of 200 articles which is randomly selected from 1500 PMC articles.
knitr::opts_chunk$set(fig.width=7, fig.height=5)
library("wordcloud")## Loading required package: RColorBrewerlibrary("RColorBrewer")
library("wordcloud2")
library("reutils")
library("XML")
library("kableExtra")
library("Biobase")## Loading required package: BiocGenerics## Loading required package: parallel##
## Attaching package: 'BiocGenerics'## The following objects are masked from 'package:parallel':
##
## clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
## clusterExport, clusterMap, parApply, parCapply, parLapply,
## parLapplyLB, parRapply, parSapply, parSapplyLB## The following objects are masked from 'package:stats':
##
## IQR, mad, sd, var, xtabs## The following objects are masked from 'package:base':
##
## anyDuplicated, append, as.data.frame, basename, cbind, colnames,
## dirname, do.call, duplicated, eval, evalq, Filter, Find, get, grep,
## grepl, intersect, is.unsorted, lapply, Map, mapply, match, mget,
## order, paste, pmax, pmax.int, pmin, pmin.int, Position, rank,
## rbind, Reduce, rownames, sapply, setdiff, sort, table, tapply,
## union, unique, unsplit, which.max, which.min## Welcome to Bioconductor
##
## Vignettes contain introductory material; view with
## 'browseVignettes()'. To cite Bioconductor, see
## 'citation("Biobase")', and for packages 'citation("pkgname")'.##
## Attaching package: 'Biobase'## The following object is masked from 'package:reutils':
##
## contentlibrary("vioplot")## Loading required package: sm## Warning in fun(libname, pkgname): couldn't connect to display ":0"## Package 'sm', version 2.2-5.6: type help(sm) for summary information## Loading required package: zoo##
## Attaching package: 'zoo'## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numericOverview of included and excluded analyses
x <- read.table("QC-analysis.tsv",header=TRUE,fill=TRUE,sep="\t")
head(x)## Pubmed.Central.ID Article.number Allocated Journal
## 1 PMC6493771 691 Kaumadi PLoS Comput Biol
## 2 PMC6442023 462 Kaumadi Front Pharmacol
## 3 PMC6384238 213 Kaumadi Front Oncol
## 4 PMC6594459 1172 Kaumadi Ann Oncol
## 5 PMC6649552 1407 Kaumadi Cell Cycle
## 6 PMC6478283 637 Kaumadi PLoS One
## Omics.type Organism
## 1 EXCLUDE EXCLUDE
## 2 RNA-seq Homo sapiens, Rattus norvegicus
## 3 Gene expression array Homo sapiens
## 4 Database Homo sapiens
## 5 RNA-seq Mus musculus
## 6 Database Homo sapiens
## Gene.set.library GS.version Statistical.test.used
## 1 EXCLUDE EXCLUDE EXCLUDE
## 2 GEO No GSEA
## 3 GO, KEGG No Not stated
## 4 MSigDB No GSEA
## 5 GO, KEGG No Not stated
## 6 KEGG, Reactome, PID, DisGeNET, GO No Not stated
## FDR.Correction App.used App.Version Code.availability
## 1 EXCLUDE EXCLUDE EXCLUDE EXCLUDE
## 2 No GSEA Yes <NA>
## 3 Yes clusterProfiler No <NA>
## 4 No GSEA Yes <NA>
## 5 No DAVID No <NA>
## 6 No ToppGene No <NA>
## Background.gene.set Assumptions.violated Gene.lists.provided
## 1 EXCLUDE EXCLUDE EXCLUDE
## 2 <NA> FDR No
## 3 Not stated Background Yes
## 4 <NA> FDR No
## 5 Not stated Background, FDR No
## 6 Not stated Background, FDR Yescolnames(x)## [1] "Pubmed.Central.ID" "Article.number" "Allocated"
## [4] "Journal" "Omics.type" "Organism"
## [7] "Gene.set.library" "GS.version" "Statistical.test.used"
## [10] "FDR.Correction" "App.used" "App.Version"
## [13] "Code.availability" "Background.gene.set" "Assumptions.violated"
## [16] "Gene.lists.provided"dim(x)## [1] 245 16exclude <- subset(x,x$GS.version=="EXCLUDE")
nrow(exclude)## [1] 14length(unique(exclude$Pubmed.Central.ID))## [1] 14x <- subset(x,x$GS.version!="EXCLUDE")
nrow(x)## [1] 231length(unique(x$Pubmed.Central.ID))## [1] 186Journal
journal <- x$Journal
journal_split <- strsplit(journal,", ")
journal <- unlist(journal_split)
res <- table(journal)
res <- res[order(res)]
length(res)## [1] 101res## journal
## 3 Biotech Am J Physiol Gastrointest Liver Physiol
## 1 1
## Animals (Basel Ann Oncol
## 1 1
## Appl Environ Microbiol Biosci Rep
## 1 1
## BMC Bioinformatics. BMC Genet
## 1 1
## BMC Infect Dis BMC Med Genet
## 1 1
## BMC Med Genomics BMC Musculoskelet Disord
## 1 1
## Cancer Control Cancers (Basel)
## 1 1
## Cell Cycle Cell Death Discov
## 1 1
## Cells Chin Med
## 1 1
## Clin Epigenetics Clin Epigenetics.
## 1 1
## Commun Biol Endocrinology
## 1 1
## FEBS Open Bio Front Genet
## 1 1
## Genome Biol Evol Genomics Inform
## 1 1
## Heliyon Hepatology
## 1 1
## Int J Endocrinol Int J Nanomedicine
## 1 1
## Int J Ophthalmol J Assist Reprod Genet.
## 1 1
## J Bacteriol J Cancer
## 1 1
## J Cardiovasc Dev Dis J Diabetes Investig
## 1 1
## J Immunother Cancer J Invest Dermatol
## 1 1
## J Ovarian Res J Res Med Sci
## 1 1
## J Transl Med J Virol
## 1 1
## Medicine (Baltimore) Mol Breed
## 1 1
## Mol Ther Nucleic Acids Neurobiol Dis
## 1 1
## Nutrients Peer J
## 1 1
## Radiat Res Respir Res
## 1 1
## Stem Cells Int Thyroid
## 1 1
## Toxicol Sci Virology
## 1 1
## World J Gastrointest Oncol Am J Transl Res
## 1 2
## Arch Med Sci Biol Open
## 2 2
## BMC Bioinformatics Cell Commun Signal
## 2 2
## Cell Death Dis Clin Cancer Res
## 2 2
## Clin Proteomics Diabetes Metab Syndr Obes
## 2 2
## Dis Markers Epigenetics
## 2 2
## Front Neurosci Front Physiol
## 2 2
## Genes (Basel) J Hematol Oncol
## 2 2
## Med Sci Monit Metabolomics
## 2 2
## Mol Med Rice (N Y)
## 2 2
## Transl Psychiatry Viruses
## 2 2
## BMC Cancer Cancer Cell Int
## 3 3
## Front Immunol Int J Mol Sci
## 3 3
## J Clin Med Mol Autism
## 3 3
## Plos One RNA Biol
## 3 3
## Aging (Albany NY) Exp Ther Med
## 4 4
## Front Oncol Front Pharmacol
## 4 4
## Metabolites Mol Med Rep
## 4 4
## Oncotarget Cancer Manag Res
## 4 5
## Biomed Res Int Onco Targets Ther
## 6 6
## Front Genet Oncol Rep
## 7 7
## Oncol Lett BMC Genomics
## 9 10
## PeerJ PLoS One
## 10 10
## Sci Rep
## 12par(mar=c(1,1,1,1))
#names(res) <- gsub("Gene expression array","RNA array",names(res))
wordcloud(words = names(res), freq = res, min.freq = 1,
max.words=200, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Onco Targets Ther could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words
## = 200, : Diabetes Metab Syndr Obes could not be fit on page. It will not be
## plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Front Neurosci could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Genes (Basel) could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : J Hematol Oncol could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Med Sci Monit could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Metabolomics could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Transl Psychiatry could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Am J Physiol Gastrointest Liver Physiol could not be fit on page. It will
## not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Appl Environ Microbiol could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : BMC Infect Dis could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : BMC Med Genomics could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words
## = 200, : BMC Musculoskelet Disord could not be fit on page. It will not be
## plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Cancer Control could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Cancers (Basel) could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Cell Death Discov could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Clin Epigenetics could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Clin Epigenetics. could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Endocrinology could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : FEBS Open Bio could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Genome Biol Evol could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Genomics Inform could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Int J Endocrinol could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Int J Nanomedicine could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Int J Ophthalmol could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : J Assist Reprod Genet. could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : J Cardiovasc Dev Dis could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : J Diabetes Investig could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : J Immunother Cancer could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : J Invest Dermatol could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : J Res Med Sci could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : J Transl Med could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Medicine (Baltimore) could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Mol Ther Nucleic Acids could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Neurobiol Dis could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Radiat Res could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Respir Res could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Stem Cells Int could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Toxicol Sci could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words =
## 200, : Virology could not be fit on page. It will not be plotted.## Warning in wordcloud(words = names(res), freq = res, min.freq = 1, max.words
## = 200, : World J Gastrointest Oncol could not be fit on page. It will not be
## plotted.
par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Journal", xlim=c(0,120))
grid()
other <- sum(res[1:(nrow(res)-10)])
res2 <- c(other,tail(res,9))
names(res2)[1] <- "Other"
par(mar=c(5,12,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Journal", xlim=c(0,1200))
grid()
Omics type
omics <- x$Omics.type
omics_split <- strsplit(omics,", ")
omics <- unlist(omics_split)
res <- table(omics)
res <- res[order(res)]
length(res)## [1] 20res## omics
## EST sequencing GWAS
## 1 1
## Lipidomics Metgenomics
## 1 1
## miRNA-seq NanoString gene expression
## 1 1
## PCR Array protein interaction
## 1 1
## DNA methylation sequencing miRNA array
## 2 2
## CNV array Genotype array
## 3 4
## Protein array DNA methylation array
## 6 7
## Genome sequencing Proteomics
## 10 14
## Metabolomics Database
## 15 17
## RNA-seq Gene expression array
## 73 87par(mar=c(1,1,1,1))
names(res) <- gsub("Gene expression array","RNA array",names(res))
wordcloud(words = names(res), freq = res, min.freq = 1,
max.words=200, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Omics type", xlim=c(0,600))
grid()
other <- sum(res[1:(nrow(res)-10)])
res2 <- c(other,tail(res,9))
names(res2)[1] <- "Other"
par(mar=c(5,12,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Omics type", xlim=c(0,600))
grid()
Organism
org <- x$Organism
org_split <- strsplit(org,", ")
org <- unlist(org_split)
res <- table(org)
res <- res[order(res)]
length(res)## [1] 31res## org
## Acropora cervicornis Aedes aegypti Ananas comosus
## 1 1 1
## Anas platyrhynchos Brassica napus Candida albicans
## 1 1 1
## Canis lupus familiaris Clostridium scindens Coturnix japonica
## 1 1 1
## Moschus berezovskii Mycobacterium smegmatis Oreochromis niloticus
## 1 1 1
## Oryctolagus cuniculus Pygoscelis antarcticus Pygoscelis papua
## 1 1 1
## Salvelinus alpinus Suaeda salsa Triticum aestivum
## 1 1 1
## Vicia faba Bemisia tabaci Bos grunniens
## 1 2 2
## Mauremys reevesii Mizuhopecten yessoensis Pagrus major
## 2 2 2
## Sclerotinia sclerotiorum Oryza sativa Bos taurus
## 2 5 6
## Sus scrofa Rattus norvegicus Mus musculus
## 6 10 24
## Homo sapiens
## 153par(mar=c(1,1,1,1))
names(res) <- gsub("Homo sapiens","human",names(res))
wordcloud(words = names(res), freq = res, min.freq = 1,
max.words=200, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"), scale=c(4,.5))
par(mar=c(5,12,3,1))
names(res) <- gsub("human","Homo sapiens",names(res))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Organism", xlim=c(0,1200))
grid()
other <- sum(res[1:(nrow(res)-10)])
res2 <- c(other,tail(res,9))
names(res2)[1] <- "Other"
par(mar=c(5,12,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Organism", xlim=c(0,1200))
grid()
Gene set library
GSL <-x$Gene.set.library
GSL_split <- strsplit(GSL,", ")
GSL <- unlist(GSL_split)
res <- table(GSL)
res <- res[order(res)]
length(res)## [1] 25which(names(res)=="Not stated")/sum(res)*100## [1] 6.422018res## GSL
## ChemRICH COG CYTOBAND
## 1 1 1
## DisGeNET GEO HMDB
## 1 1 1
## Ingenuity Knowledge base Jensen Diseases database MetaCore/MetaBase
## 1 1 1
## Metascape OMIM Pathway commons
## 1 1 1
## Pfam PID Signor
## 1 1 1
## Vectorbase BioCarta InterPro
## 1 2 2
## MetaboAnalyst Reactome Not stated
## 2 14 15
## MSigDB Ingenuity Knowledge Base KEGG
## 18 22 112
## GO
## 124par(mar=c(1,1,1,1))
names(res) <- gsub("Homo sapiens","human",names(res))
wordcloud(words = names(res), freq = res, min.freq = 1,
max.words=200, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Gene set library", xlim=c(0,1000))
grid()
other <- sum(res[1:(nrow(res)-10)])
res2 <- c(other,tail(res,9))
names(res2)[1] <- "Other"
par(mar=c(5,12,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Gene set library", xlim=c(0,500))
grid()
Gene set version
GSV <-x$GS.version
res <- table(GSV)
res## GSV
## No Yes
## 213 18res[1]/sum(res)*100## No
## 92.20779par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Gene set version defined", xlim=c(0,1600))
grid()
Statistical test used
test <-x$Statistical.test.used
test <- strsplit(test,", ")
test <- unlist(test)
res <- table(test)
res <- res[order(res)]
res[which(names(res)=="Not stated")] / sum(res) * 100## Not stated
## 59.22747res## test
## Binomial
## 1
## Chemical similarity set enrichment analysis
## 1
## GSVA
## 1
## Kruskal-Wallis
## 1
## MSEA
## 1
## EASE
## 2
## No test
## 11
## Fisher
## 21
## Hypergeometric
## 27
## GSEA
## 29
## Not stated
## 138par(mar=c(1,1,1,1))
wordcloud(words = names(res), freq = res, min.freq = 1,
max.words=200, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Test used", xlim=c(0,1200))
grid()
other <- sum(res[1:(nrow(res)-10)])
res2 <- c(other,tail(res,9))
names(res2)[1] <- "Other"
par(mar=c(5,12,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Test used", xlim=c(0,1200))
grid()
FDR Correction
fdr <-x$FDR.Correction
fdr <- strsplit(fdr,", ")
fdr <- unlist(fdr)
res <- table(fdr)
res <- res[order(res)]
sum(res[which(names(res)!="Yes")])/sum(res)*100## [1] 48.01762res## fdr
## Not stated No Yes
## 9 100 118par(mar=c(1,1,1,1))
wordcloud(words = names(res), freq = res, min.freq = 1,
max.words=200, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "FDR", xlim=c(0,800))
grid()
App used
App <-x$App.used
App_split <- strsplit(App,", ")
App <- unlist(App_split)
res <- table(App)
res <- res[order(res)]
res[which(names(res)=="Not stated")]/sum(res)*100## Not stated
## 7.359307res## App
## anamiR ChemRICH
## 1 1
## Custom R script Cytoscape
## 1 1
## EggNOG fgsea
## 1 1
## Funrich g:GOSt
## 1 1
## g:Profiler GENCLIP
## 1 1
## GeneCodis geneontology.org web app
## 1 1
## GlueGO GO::TermFinder
## 1 1
## gProfiler GSVA
## 1 1
## KSEA Limma
## 1 1
## MetaboAnalyst/Mummichog MetaCore
## 1 1
## MetaCore/MetaBase (GeneGo) Metascape
## 1 1
## Molecule Annotation System MSEA
## 1 1
## PASCAL Phyper
## 1 1
## R script ReactomePA
## 1 1
## SNP2GO R package topGO
## 1 1
## ToppGene webMeV
## 1 1
## agriGO BiNGO
## 2 2
## http://geneontology.org/ web app KAAS
## 2 2
## Mummichog STRING
## 2 2
## GOrilla ClueGO/Cytoscape
## 3 4
## Enrichr WebGestalt
## 4 4
## GOseq Blast2GO
## 5 7
## MetaboAnalyst PANTHER
## 7 7
## KOBAS clusterProfiler
## 8 10
## Not stated Ingenuity Pathway Analysis
## 17 25
## GSEA DAVID
## 31 55par(mar=c(1,1,1,1))
wordcloud(words = names(res), freq = res, min.freq = 1,
max.words=200, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "App used", xlim=c(0,400))
grid()
other <- sum(res[1:(nrow(res)-10)])
res2 <- c(other,tail(res,9))
names(res2)[1] <- "Other"
par(mar=c(5,12,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "App used", xlim=c(0,500))
grid()
App version
APV <-x$App.Version
res <- table(APV)
res## APV
## No Yes
## 164 65res[1]/sum(res)*100## No
## 71.61572par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "App version defined", xlim=c(0,1600))
grid()
Code available
code <-x$Code.availability
res <- table(code)
res## code
## No Yes
## 45 3res[1]/sum(res)*100## No
## 93.75par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Code availability", xlim=c(0,300))
grid()
Background gene set
BG <-x$Background.gene.set
res <- table(BG)
res## BG
## No Not stated Stated, but incorrect
## 5 174 4
## Yes
## 9sum(res[which(names(res)!="Yes")])/sum(res)*100## [1] 95.3125par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Background list defined", xlim=c(0,1200))
grid()
Gene lists provided
GL <-x$Gene.lists.provided
res <- table(GL)
res## GL
## No Yes
## 138 93sum(res[which(names(res)!="Yes")])/sum(res)*100## [1] 59.74026par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Gene lists provided", xlim=c(0,1200))
grid()
colnames(x)## [1] "Pubmed.Central.ID" "Article.number" "Allocated"
## [4] "Journal" "Omics.type" "Organism"
## [7] "Gene.set.library" "GS.version" "Statistical.test.used"
## [10] "FDR.Correction" "App.used" "App.Version"
## [13] "Code.availability" "Background.gene.set" "Assumptions.violated"
## [16] "Gene.lists.provided"Assumptions violated
ok <- nrow(subset(x,Assumptions.violated=="No"))
ok## [1] 35bad <- nrow(subset(x,Assumptions.violated!="No"))
bad## [1] 196ok/sum(bad,ok)*100## [1] 15.15152ass <-x$Assumptions.violated
ass <- strsplit(ass,", ")
ass <- unlist(ass)
res <- table(ass)
res <- res[order(res)]
res## ass
## Misinterpreted FDR values Inference without test No data shown
## 1 11 13
## No FDR Background
## 35 93 173par(mar=c(1,1,1,1))
wordcloud(words = names(res), freq = res, min.freq = 1,
max.words=200, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Assumptions violated", xlim=c(0,1400))
grid()
Cross check
y <- read.table("PMC_2019-analysis.tsv",header=TRUE,fill=TRUE,sep="\t")
y <- y[which(isUnique(y$Pubmed.Central.ID)),]
x <- x[which(isUnique(x$Pubmed.Central.ID)),]
yunique <- y[which(isUnique(y$Pubmed.Central.ID)),"Pubmed.Central.ID"]
xunique <- x[which(isUnique(x$Pubmed.Central.ID)),"Pubmed.Central.ID"]
xyunique <- intersect(yunique,xunique)
head(xyunique)## [1] "PMC6317205" "PMC6318854" "PMC6323741" "PMC6328465" "PMC6333785"
## [6] "PMC6341096"res <- sapply(xyunique,function(myid){
myqc <- x[which(x$Pubmed.Central.ID==myid),,drop=TRUE]
ydat <- y[which(y$Pubmed.Central.ID==myid),,drop=TRUE]
qcres <- sapply(5:16, function(m) {
mqc <- myqc[[m]]
mqc <- unlist(strsplit(mqc,", "))
mqc <- gsub("Not stated","No",mqc)
myy <- ydat[[m]]
myy <- unlist(strsplit(myy,", "))
myy <- gsub("Not stated","No",myy)
length(intersect(mqc,myy)) / length(union(mqc,myy))
})
return(qcres)
})
rownames(res) <- colnames(x)[5:16]
categoryMeans <- rowMeans(res)
categoryMeans## Omics.type Organism Gene.set.library
## 0.7591241 0.9708029 0.8990268
## GS.version Statistical.test.used FDR.Correction
## 0.9270073 0.8941606 0.8175182
## App.used App.Version Code.availability
## 0.8832117 0.9270073 0.8540146
## Background.gene.set Assumptions.violated Gene.lists.provided
## 0.8832117 0.7785888 0.8540146tres <- t(res)
head(tres)## Omics.type Organism Gene.set.library GS.version
## PMC6317205 0 1 1.0 1
## PMC6318854 1 1 1.0 1
## PMC6323741 1 1 1.0 1
## PMC6328465 1 1 1.0 1
## PMC6333785 0 1 0.5 1
## PMC6341096 1 1 1.0 1
## Statistical.test.used FDR.Correction App.used App.Version
## PMC6317205 1 0 1 1
## PMC6318854 0 0 1 0
## PMC6323741 1 1 1 1
## PMC6328465 1 1 1 1
## PMC6333785 1 1 1 1
## PMC6341096 1 1 1 1
## Code.availability Background.gene.set Assumptions.violated
## PMC6317205 1 1 1.0
## PMC6318854 1 1 0.5
## PMC6323741 1 1 1.0
## PMC6328465 1 1 1.0
## PMC6333785 1 1 1.0
## PMC6341096 1 1 1.0
## Gene.lists.provided
## PMC6317205 0
## PMC6318854 1
## PMC6323741 1
## PMC6328465 1
## PMC6333785 1
## PMC6341096 1par(mar=c(5,12,3,1))
vioplot(tres,horizontal=TRUE,las=1,xlab="mean Jaccard score")
par(mar=c(5,12,3,1))
barplot(categoryMeans,horiz=TRUE,las=1,xlim=c(0,1),xlab="mean Jaccard score")
articleMeans <- colMeans(res)
hist(articleMeans)
# PMCs that need to be redone
tres[which(rowMeans(tres)<1),] %>% kbl() %>% kable_paper("hover", full_width = F)| Omics.type | Organism | Gene.set.library | GS.version | Statistical.test.used | FDR.Correction | App.used | App.Version | Code.availability | Background.gene.set | Assumptions.violated | Gene.lists.provided | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| PMC6317205 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 1.0000000 | 0 |
| PMC6318854 | 1.0 | 1.0 | 1.0000000 | 1 | 0.0 | 0 | 1 | 0 | 1 | 1 | 0.5000000 | 1 |
| PMC6333785 | 0.0 | 1.0 | 0.5000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6342918 | 1.0 | 1.0 | 1.0000000 | 0 | 1.0 | 1 | 0 | 1 | 0 | 0 | 0.0000000 | 1 |
| PMC6347630 | 1.0 | 0.5 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6350566 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 0 |
| PMC6350986 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 0 | 0 | 1 | 1 | 1.0000000 | 1 |
| PMC6363745 | 1.0 | 1.0 | 0.5000000 | 0 | 0.0 | 1 | 1 | 1 | 1 | 1 | 0.0000000 | 0 |
| PMC6364390 | 1.0 | 1.0 | 0.5000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 0 | 0.3333333 | 1 |
| PMC6370049 | 1.0 | 1.0 | 1.0000000 | 1 | 0.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 0 |
| PMC6377753 | 1.0 | 1.0 | 0.5000000 | 1 | 1.0 | 1 | 0 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6379932 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6383095 | 1.0 | 1.0 | 0.5000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6383344 | 1.0 | 1.0 | 0.3333333 | 1 | 1.0 | 1 | 0 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6383401 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 0 |
| PMC6384238 | 0.5 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6387216 | 1.0 | 0.0 | 1.0000000 | 1 | 1.0 | 1 | 0 | 1 | 1 | 1 | 0.0000000 | 1 |
| PMC6388971 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6399257 | 0.0 | 1.0 | 0.0000000 | 1 | 0.0 | 1 | 0 | 1 | 0 | 1 | 0.0000000 | 1 |
| PMC6412147 | 0.0 | 1.0 | 0.5000000 | 1 | 1.0 | 1 | 1 | 1 | 0 | 1 | 0.3333333 | 1 |
| PMC6425643 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 0 | 1 | 1.0000000 | 1 |
| PMC6441198 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 0 | 1 | 1.0000000 | 0 |
| PMC6447890 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 0 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6459169 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6463024 | 1.0 | 1.0 | 1.0000000 | 0 | 1.0 | 1 | 1 | 0 | 0 | 1 | 1.0000000 | 1 |
| PMC6463198 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 0 | 1 | 0.3333333 | 0 |
| PMC6465396 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 0 | 1.0000000 | 1 |
| PMC6468815 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 0 |
| PMC6471048 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 0 | 1 | 0.5000000 | 1 |
| PMC6472139 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6478283 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 0 |
| PMC6478396 | 1.0 | 1.0 | 1.0000000 | 1 | 0.0 | 1 | 1 | 1 | 1 | 0 | 0.0000000 | 0 |
| PMC6480502 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 0 | 1 | 1 | 0 | 1.0000000 | 0 |
| PMC6486412 | 0.5 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6489005 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6489013 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.3333333 | 1 |
| PMC6492420 | 0.5 | 1.0 | 0.3333333 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 0.3333333 | 1 |
| PMC6498668 | 0.5 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 0 | 0.0000000 | 1 |
| PMC6503205 | 0.0 | 1.0 | 1.0000000 | 0 | 1.0 | 1 | 1 | 1 | 1 | 0 | 0.0000000 | 1 |
| PMC6506780 | 1.0 | 1.0 | 0.0000000 | 1 | 0.0 | 1 | 1 | 1 | 0 | 1 | 1.0000000 | 1 |
| PMC6507394 | 0.0 | 1.0 | 1.0000000 | 0 | 1.0 | 0 | 0 | 0 | 1 | 1 | 0.5000000 | 1 |
| PMC6507459 | 0.5 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6515108 | 0.5 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6518761 | 0.5 | 0.5 | 1.0000000 | 1 | 0.0 | 1 | 1 | 1 | 0 | 1 | 1.0000000 | 1 |
| PMC6519025 | 1.0 | 1.0 | 0.5000000 | 1 | 1.0 | 1 | 1 | 0 | 0 | 1 | 1.0000000 | 1 |
| PMC6520261 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6522869 | 0.5 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6523927 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 0 | 0.0000000 | 1 |
| PMC6524193 | 0.5 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 0.6666667 | 1 |
| PMC6526173 | 0.5 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6528264 | 0.5 | 1.0 | 0.5000000 | 1 | 0.0 | 1 | 1 | 1 | 1 | 0 | 0.0000000 | 1 |
| PMC6541682 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 0 | 0.0000000 | 1 |
| PMC6542760 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 0 | 1 | 0.5000000 | 1 |
| PMC6549663 | 0.5 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6556043 | 0.0 | 1.0 | 1.0000000 | 1 | 0.0 | 1 | 1 | 1 | 1 | 1 | 0.3333333 | 1 |
| PMC6557548 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6568258 | 1.0 | 1.0 | 1.0000000 | 0 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 0 |
| PMC6572139 | 1.0 | 1.0 | 0.0000000 | 1 | 1.0 | 1 | 1 | 0 | 1 | 1 | 1.0000000 | 0 |
| PMC6572621 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6579764 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 0 | 1 | 0.5000000 | 1 |
| PMC6580234 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 0 |
| PMC6580941 | 1.0 | 1.0 | 0.5000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6582507 | 1.0 | 1.0 | 1.0000000 | 1 | 0.5 | 1 | 0 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6584587 | 0.0 | 1.0 | 0.0000000 | 0 | 1.0 | 1 | 0 | 1 | 0 | 1 | 1.0000000 | 1 |
| PMC6585500 | 0.5 | 0.0 | 0.0000000 | 0 | 0.0 | 0 | 0 | 0 | 0 | 0 | 0.0000000 | 0 |
| PMC6585899 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 0 |
| PMC6586291 | 0.5 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6588443 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 0 | 1 | 1 | 1.0000000 | 1 |
| PMC6591089 | 0.5 | 0.5 | 0.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 0.0000000 | 1 |
| PMC6591379 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6595412 | 1.0 | 1.0 | 1.0000000 | 1 | 0.0 | 1 | 1 | 1 | 1 | 1 | 0.5000000 | 0 |
| PMC6596368 | 0.5 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6598377 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 0 | 0 | 1 | 1.0000000 | 1 |
| PMC6599230 | 1.0 | 1.0 | 0.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 0 |
| PMC6607081 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 0 | 1 | 0.5000000 | 1 |
| PMC6607232 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 0 | 0.5000000 | 1 |
| PMC6609559 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6614665 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 0 | 1 | 1.0000000 | 1 |
| PMC6614983 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6619257 | 0.0 | 0.5 | 1.0000000 | 1 | 0.0 | 1 | 1 | 1 | 1 | 1 | 0.0000000 | 1 |
| PMC6620395 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 0 | 1 | 1 | 1.0000000 | 1 |
| PMC6620582 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 0 | 0 | 1 | 1 | 0 | 0.5000000 | 0 |
| PMC6626515 | 1.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 0 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6627192 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6636026 | 0.0 | 1.0 | 0.5000000 | 0 | 0.0 | 1 | 0 | 1 | 0 | 1 | 1.0000000 | 1 |
| PMC6650071 | 1.0 | 1.0 | 0.5000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 1 | 1.0000000 | 1 |
| PMC6651993 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 1 | 0 | 0.5000000 | 1 |
| PMC6653643 | 1.0 | 1.0 | 1.0000000 | 0 | 1.0 | 1 | 0 | 1 | 1 | 0 | 0.0000000 | 1 |
| PMC6657577 | 0.0 | 1.0 | 1.0000000 | 1 | 0.0 | 0 | 1 | 1 | 1 | 1 | 0.5000000 | 1 |
| PMC6677090 | 0.0 | 1.0 | 1.0000000 | 1 | 1.0 | 1 | 1 | 1 | 0 | 0 | 1.0000000 | 0 |
ppl <- sapply(xyunique,function(myid){
myqc <- x[which(x$Pubmed.Central.ID==myid),,drop=TRUE]
ydat <- y[which(y$Pubmed.Central.ID==myid),,drop=TRUE]
px <- myqc[[3]]
py <- ydat[[3]]
return(c(py,px))
})
tppl <- t(ppl)
tppl_comb <- paste(tppl[,1],tppl[,2])
tppl_combs <- unique(tppl_comb)
cres <- lapply(tppl_combs,function(comb){
combres <- tres[which(tppl_comb %in% comb),]
})
names(cres) <- tppl_combs
str(cres)## List of 8
## $ Mark Mark : num [1:20, 1:12] 0 1 0 1 0 1 1 1 1 1 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:20] "PMC6317205" "PMC6318854" "PMC6333785" "PMC6341096" ...
## .. ..$ : chr [1:12] "Omics.type" "Organism" "Gene.set.library" "GS.version" ...
## $ Mark Kaumadi : num [1:21, 1:12] 1 1 1 1 1 1 1 1 1 1 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:21] "PMC6323741" "PMC6328465" "PMC6342918" "PMC6347630" ...
## .. ..$ : chr [1:12] "Omics.type" "Organism" "Gene.set.library" "GS.version" ...
## $ Kaumadi Kaumadi : num [1:18, 1:12] 1 1 1 1 1 1 1 1 0 1 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:18] "PMC6405989" "PMC6425643" "PMC6432904" "PMC6435965" ...
## .. ..$ : chr [1:12] "Omics.type" "Organism" "Gene.set.library" "GS.version" ...
## $ Kaumadi Mark : num [1:13, 1:12] 1 0 1 1 1 1 0 1 1 0 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:13] "PMC6406182" "PMC6412147" "PMC6433918" "PMC6441198" ...
## .. ..$ : chr [1:12] "Omics.type" "Organism" "Gene.set.library" "GS.version" ...
## $ Kaushalya Mark : num [1:16, 1:12] 0 1 1 1 0.5 1 0 0.5 0 0 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:16] "PMC6472139" "PMC6476004" "PMC6478396" "PMC6480502" ...
## .. ..$ : chr [1:12] "Omics.type" "Organism" "Gene.set.library" "GS.version" ...
## $ Kaushalya Kaumadi: num [1:15, 1:12] 1 0.5 1 1 0.5 0.5 0.5 0 0 1 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:15] "PMC6478283" "PMC6498668" "PMC6506780" "PMC6507312" ...
## .. ..$ : chr [1:12] "Omics.type" "Organism" "Gene.set.library" "GS.version" ...
## $ Sameer Kaumadi : num [1:21, 1:12] 1 1 1 0 0.5 1 1 1 1 1 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:21] "PMC6548796" "PMC6572139" "PMC6580485" "PMC6584587" ...
## .. ..$ : chr [1:12] "Omics.type" "Organism" "Gene.set.library" "GS.version" ...
## $ Sameer Mark : num [1:13, 1:12] 0.5 0 1 1 1 1 1 1 1 0.5 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:13] "PMC6549663" "PMC6556043" "PMC6557548" "PMC6568258" ...
## .. ..$ : chr [1:12] "Omics.type" "Organism" "Gene.set.library" "GS.version" ...cres2 <- lapply(cres,mean)
cres2## $`Mark Mark`
## [1] 0.8361111
##
## $`Mark Kaumadi`
## [1] 0.9107143
##
## $`Kaumadi Kaumadi`
## [1] 0.9699074
##
## $`Kaumadi Mark`
## [1] 0.8215812
##
## $`Kaushalya Mark`
## [1] 0.8081597
##
## $`Kaushalya Kaumadi`
## [1] 0.8972222
##
## $`Sameer Kaumadi`
## [1] 0.8988095
##
## $`Sameer Mark`
## [1] 0.7713675par(mar=c(5,12,3,1))
barplot(unlist(cres2),horiz=TRUE,las=1,xlim=c(0,1),xlab="mean Jaccard score")
Session information
sessionInfo()## R version 4.1.0 (2021-05-18)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.2 LTS
##
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.9.0
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.9.0
##
## 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
##
## attached base packages:
## [1] parallel stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] vioplot_0.3.7 zoo_1.8-9 sm_2.2-5.6
## [4] Biobase_2.52.0 BiocGenerics_0.38.0 kableExtra_1.3.4
## [7] XML_3.99-0.6 reutils_0.2.3 wordcloud2_0.2.1
## [10] wordcloud_2.6 RColorBrewer_1.1-2
##
## loaded via a namespace (and not attached):
## [1] Rcpp_1.0.7 highr_0.9 bslib_0.2.5.1 compiler_4.1.0
## [5] jquerylib_0.1.4 bitops_1.0-7 tools_4.1.0 digest_0.6.27
## [9] lattice_0.20-44 viridisLite_0.4.0 jsonlite_1.7.2 evaluate_0.14
## [13] lifecycle_1.0.0 rlang_0.4.11 rstudioapi_0.13 yaml_2.2.1
## [17] xfun_0.25 stringr_1.4.0 httr_1.4.2 knitr_1.33
## [21] xml2_1.3.2 htmlwidgets_1.5.3 sass_0.4.0 systemfonts_1.0.2
## [25] grid_4.1.0 webshot_0.5.2 svglite_2.0.0 glue_1.4.2
## [29] R6_2.5.0 tcltk_4.1.0 rmarkdown_2.10 magrittr_2.0.1
## [33] scales_1.1.1 htmltools_0.5.1.1 rvest_1.0.1 colorspace_2.0-2
## [37] stringi_1.7.3 RCurl_1.98-1.3 munsell_0.5.0