PMC Survey Data Analysis
Mark Ziemann & Kaumadi Wijesooriya
2021-09-01
Source: https://github.com/markziemann/SurveyEnrichmentMethods
Intro
Here we are performing an analysis of the ways enrichment analysis has been done in a sample of 1500 PMC articles from 2019.
knitr::opts_chunk$set(fig.width=7, fig.height=5)
library("wordcloud")## Loading required package: RColorBrewerlibrary("RColorBrewer")
library("wordcloud2")
library("reutils")
library("XML")
library("kableExtra")
library("vioplot")## Loading required package: sm## Warning in fun(libname, pkgname): couldn't connect to display ":0"## Package 'sm', version 2.2-5.6: type help(sm) for summary information## Loading required package: zoo##
## Attaching package: 'zoo'## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numericOverview of included and excluded analyses
Here we are also using the QC2 data where possible.
x <- read.table("data/PMC_2019-analysis.tsv",header=TRUE,fill=TRUE,sep="\t")
y <- read.table("data/QC-analysis2.tsv",header=TRUE,fill=TRUE,sep="\t")
y <- y[,1:16]
x <- x[which(! x$Pubmed.Central.ID %in% y$Pubmed.Central.ID),]
x <- rbind(x,y)
head(x)## Pubmed.Central.ID Article.number Allocated Journal
## 2 PMC6317219 2 Mark J Transl Med
## 4 PMC6318897 4 Mark BMC Genomics
## 5 PMC6322516 5 Mark Cancer Manag Res
## 6 PMC6323737 6 Mark BMC Plant Biol
## 8 PMC6325784 8 Mark Respir Res
## 9 PMC6325795 9 Mark BMC Cancer
## Omics.type Organism Gene.set.library
## 2 Gene expression array Homo sapiens GO, KEGG
## 4 RNA-seq Gymnocypris przewalskii KEGG
## 5 Gene expression array Homo sapiens Ingenuity Knowledge Base
## 6 Gene expression array Arabidopsis GO
## 8 Gene expression array Homo sapiens KEGG
## 9 miRNA-seq Homo sapiens KEGG
## GS.version Statistical.test.used FDR.Correction App.used
## 2 No Not stated No DAVID
## 4 No Not stated Yes KOBAS
## 5 No Not stated No Ingenuity Pathway Analysis
## 6 Yes Not stated No topGO
## 8 No Hypergeometric Yes GeneAnswers
## 9 No Fisher No DIANA-miRPath
## App.Version Code.availability Background.gene.set Assumptions.violated
## 2 No <NA> Not stated Background, FDR
## 4 No <NA> Not stated Background
## 5 No <NA> Not stated Background, FDR
## 6 Yes No Not stated Background, FDR
## 8 No No Not stated Background
## 9 Yes <NA> Not stated Background
## Gene.lists.provided
## 2 No
## 4 Yes
## 5 No
## 6 Yes
## 8 Yes
## 9 Yescolnames(x)## [1] "Pubmed.Central.ID" "Article.number" "Allocated"
## [4] "Journal" "Omics.type" "Organism"
## [7] "Gene.set.library" "GS.version" "Statistical.test.used"
## [10] "FDR.Correction" "App.used" "App.Version"
## [13] "Code.availability" "Background.gene.set" "Assumptions.violated"
## [16] "Gene.lists.provided"dim(x)## [1] 1766 16exclude <- subset(x,x$GS.version=="EXCLUDE")
nrow(exclude)## [1] 132length(unique(exclude$Pubmed.Central.ID))## [1] 132x <- subset(x,x$GS.version!="EXCLUDE")
nrow(x)## [1] 1630length(unique(x$Pubmed.Central.ID))## [1] 1365write.table(x,file="TableS2.tsv",quote=FALSE,sep="\t",col.names = TRUE,row.names = FALSE)Journal
journal <- x$Journal
journal_split <- strsplit(journal,", ")
journal <- unlist(journal_split)
res <- table(journal)
res <- res[order(res)]
length(res)## [1] 325res## journal
## AAPS J ACS Omega
## 1 1
## Acta Cir Bras Acta Neuropathol Commun
## 1 1
## Aging Cell Am J Physiol Endocrinol Metab
## 1 1
## Am J Physiol Gastrointest Liver Physiol Anal Chim Acta
## 1 1
## Ann Clin Transl Neurol Ann Epidemiol
## 1 1
## Ann Oncol Antioxidants (Basel)
## 1 1
## Appl Environ Microbiol Aquat Toxicol
## 1 1
## Arch Gynecol Obstet Arthritis Rheumatol
## 1 1
## Asian-Australas J Anim Sci ASN Neuro
## 1 1
## Autophagy Basic Res Cardiol
## 1 1
## Biochem Biophys Rep Biol Res
## 1 1
## Biomed Eng Online Biomed Rep
## 1 1
## Blood Adv BMC Complement Altern Med
## 1 1
## BMC Infect Dis BMC Musculoskelet Disord
## 1 1
## BMC Nephrol BMC Oral Health
## 1 1
## BMC Pregnancy Childbirth BMC Psychiatry
## 1 1
## BMC Urol BMC Vet Res
## 1 1
## Bone Rep Breast Cancer Res Treat
## 1 1
## Burns Trauma Cancer Biol Ther
## 1 1
## Cancer Control Cancer Imaging
## 1 1
## Cancer Lett Cancer Sci
## 1 1
## Cell Rep Cell Stress Chaperones
## 1 1
## Circ Genom Precis Med Clin Genitourin Cancer
## 1 1
## Clin Transl Allergy Clin Transplant
## 1 1
## Differentiation DNA Cell Biol
## 1 1
## Dose Response eLife
## 1 1
## EMBO Mol Med Emerg Microbes Infect
## 1 1
## eNeuro Environ Entomol
## 1 1
## Environ Pollut Environ Sci Nano
## 1 1
## ESMO Open Eur J Med Res
## 1 1
## Evol Bioinform Online Exp Biol Med (Maywood)
## 1 1
## Fertil Steril Front Aging Neurosci
## 1 1
## Front Bioeng Biotechnol Front Cell Neurosci
## 1 1
## Front Med (Lausanne) Front Mol Neurosci
## 1 1
## Front Neurol Front Psychol
## 1 1
## Funct Integr Genomics Genes
## 1 1
## Genes Dis Genet Med
## 1 1
## Genome Biol Evol Genome Med
## 1 1
## Genomics Inform GM Crops Food
## 1 1
## Gut Pathog Hepatology
## 1 1
## Hum Mol Genet Hypertension
## 1 1
## Inhal Toxicol Insects
## 1 1
## Int J Biol Sci Int J Cardiol Heart Vasc
## 1 1
## Int J Immunopathol Pharmacol Int J Infect Dis
## 1 1
## Islets J Bacteriol
## 1 1
## J Biol Eng J Biol Rhythms
## 1 1
## J Breast Cancer J Cardiovasc Dev Dis
## 1 1
## J Cell Biochem J Cell Biol
## 1 1
## J Cell Physiol J Cheminform
## 1 1
## J Clin Invest J Clin Transl Endocrinol
## 1 1
## J Extracell Vesicles J Heart Lung Transplant
## 1 1
## J Invest Dermatol J Korean Med Sci
## 1 1
## J Nutr Biochem J Oncol
## 1 1
## J Orthop Surg Res J Pain
## 1 1
## J Pain Res J Pers Med
## 1 1
## J Res Med Sci J Rheumatol
## 1 1
## J Stem Cells Regen Med Lipids Health Dis
## 1 1
## Malar J mBio
## 1 1
## Microb Cell Mol Breed
## 1 1
## Mol Cell Biochem Mol Cells
## 1 1
## Mol Clin Oncol Mol Genet Metab Rep
## 1 1
## Mol Hum Reprod Mol Pain
## 1 1
## Mol Ther Mol Ther Oncolytics
## 1 1
## Mol Vis Mult Scler J Exp Transl Clin
## 1 1
## Mult Scler Relat Disord Nat Immunol
## 1 1
## Nat Neurosci Neurobiol Dis
## 1 1
## Neurol Genet Neurol Neuroimmunol Neuroinflamm
## 1 1
## Nucleic Acids Res Plant Cell
## 1 1
## Plant Physiol PLoS Biol
## 1 1
## PLoS Comput Biol Prostate Cancer
## 1 1
## Proteome Sci Proteomes
## 1 1
## Psychiatry Clin Neurosci Radiat Res
## 1 1
## Redox Biol Reproduction
## 1 1
## Stem Cells Surgery
## 1 1
## Theranostics Toxicol Appl Pharmacol
## 1 1
## Transl Vis Sci Technol Transplantation
## 1 1
## Virology World J Clin Cases
## 1 1
## Am J Clin Exp Urol AMB Express
## 2 2
## Ann Surg Treat Res Arch Med Sci
## 2 2
## Balkan Med J Bioinformatics
## 2 2
## Biomolecules BMC Genet
## 2 2
## BMC Med BMC Microbiol
## 2 2
## BMC Syst Biol Brain Behav Immun
## 2 2
## Cell Cycle Commun Biol
## 2 2
## Curr Genomics Diagnostics (Basel)
## 2 2
## Drug Des Devel Ther Ecol Evol
## 2 2
## EJNMMI Res Endocrinology
## 2 2
## Environ Int EPMA J
## 2 2
## Exp Mol Med Front Endocrinol (Lausanne)
## 2 2
## Front Pediatr Front Vet Sci
## 2 2
## Genes Nutr Healthcare (Basel)
## 2 2
## Int J Nanomedicine Int J Ophthalmol
## 2 2
## J Adv Res J Cell Mol Med
## 2 2
## J Hematol Oncol J Immunother Cancer
## 2 2
## J Neurooncol J Pathol
## 2 2
## Mar Drugs Metabolomics
## 2 2
## Mol Cell Biol Mol Med
## 2 2
## Mol Ther Nucleic Acids Nat Genet
## 2 2
## Neuropsychiatr Dis Treat Nutr Metab (Lond)
## 2 2
## Oncoimmunology Parasite
## 2 2
## Physiol Mol Biol Plants Plants (Basel)
## 2 2
## PLoS Pathog Skelet Muscle
## 2 2
## Thyroid Toxicol Sci
## 2 2
## Turk J Biol World J Gastrointest Oncol
## 2 2
## Allergy Asthma Immunol Res Biol Open
## 3 3
## Breast Cancer Res Cell Commun Signal
## 3 3
## Chin Med Clin Cancer Res
## 3 3
## Clin Transl Gastroenterol Diabetes Metab Syndr Obes
## 3 3
## FASEB J Front Cell Infect Microbiol
## 3 3
## Genet Sel Evol Heliyon
## 3 3
## Hum Genomics Int J Endocrinol
## 3 3
## Int J Environ Res Public Health Int J Oncol
## 3 3
## J Am Heart Assoc J Ovarian Res
## 3 3
## J Virol JAMA Netw Open
## 3 3
## Medicina (Kaunas) Mol Autism
## 3 3
## Mol Cell Proteomics Mol Oncol
## 3 3
## Nanomaterials (Basel) Neoplasia
## 3 3
## Nutrients Oxid Med Cell Longev
## 3 3
## Physiol Genomics PLoS Genet
## 3 3
## Rice (N Y) Technol Cancer Res Treat
## 3 3
## Transl Oncol Viruses
## 3 3
## World J Surg Oncol Am J Clin Nutr
## 3 4
## Arthritis Res Ther Cancer Inform
## 4 4
## Cell Death Dis Hortic Res
## 4 4
## J Biol Res (Thessalon) J Diabetes Investig
## 4 4
## JCI Insight Mediators Inflamm
## 4 4
## Mol Cancer Respir Res
## 4 4
## Thorac Cancer Toxins (Basel)
## 4 4
## Animals (Basel) BMC Bioinformatics
## 5 5
## BMC Med Genet Carcinogenesis
## 5 5
## Cell Death Discov Epigenetics
## 5 5
## Front Plant Sci Hereditas
## 5 5
## Int J Med Sci J Assist Reprod Genet
## 5 5
## J Biol Chem Mol Genet Genomic Med
## 5 5
## Parasit Vectors Proc Natl Acad Sci U S A
## 5 5
## 3 Biotech Dis Markers
## 6 6
## Nat Commun Reprod Biol Endocrinol
## 6 6
## RNA Biol Stem Cells Int
## 6 6
## Transl Psychiatry Cells
## 6 7
## Clin Epigenetics Data Brief
## 7 7
## Front Physiol J Exp Clin Cancer Res
## 7 7
## Stem Cell Res Ther Clin Proteomics
## 7 8
## FEBS Open Bio World J Gastroenterol
## 8 8
## Am J Transl Res Front Neurosci
## 9 9
## Genes (Basel) Molecules
## 9 9
## Metabolites Cancer Med
## 10 11
## Cancers (Basel) Evid Based Complement Alternat Med
## 11 11
## Front Microbiol BMC Cancer
## 11 12
## Front Immunol Int J Mol Med
## 12 12
## EBioMedicine J Clin Med
## 13 13
## Oncotarget BMC Med Genomics
## 13 15
## Aging (Albany NY) Front Oncol
## 16 16
## Medicine (Baltimore) Biosci Rep
## 16 17
## BMC Plant Biol Front Pharmacol
## 20 22
## Onco Targets Ther Cancer Manag Res
## 22 24
## J Transl Med Oncol Rep
## 24 24
## Med Sci Monit Exp Ther Med
## 25 27
## Cancer Cell Int J Cancer
## 28 28
## Biomed Res Int Mol Med Rep
## 37 40
## BMC Genomics PeerJ
## 51 57
## Front Genet Int J Mol Sci
## 58 64
## PLoS One Oncol Lett
## 66 73
## Sci Rep
## 98par(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, : Stem Cell Res 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, : Reprod Biol 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, : 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, : Mol Genet Genomic 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, : Proc Natl Acad Sci U S A 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 Biol Res (Thessalon) 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, : Mediators Inflamm 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, : Allergy Asthma Immunol 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, : Cell Commun Signal 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 Cancer 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, : Clin Transl Gastroenterol 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 Cell Infect 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, : Hum 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, : Int J Environ Res Public Health 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 Am Heart Assoc 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, : JAMA Netw Open 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, : Medicina (Kaunas) 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, : Nanomaterials (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, : Oxid Med Cell Longev 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, : Physiol 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, : Technol Cancer Res Treat 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 Surg 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, : Am J Clin Exp Urol 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, : AMB Express 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, : Ann Surg Treat 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, : Bioinformatics 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, : Brain Behav Immun 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, : Curr 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, : Diagnostics (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, : Drug Des Devel 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, : 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, : Environ 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, : Exp Mol 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, : Front Endocrinol (Lausanne) 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 Nutr 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, : Healthcare (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, : 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 Cell Mol 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, : 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 Neurooncol 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 Cell Biol 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 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, : 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, : Nat 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, : Neuropsychiatr Dis Treat 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, : Nutr Metab (Lond) 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, : Oncoimmunology 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, : Physiol Mol Biol Plants 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, : Plants (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, : PLoS Pathog 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, : Skelet Muscle 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, : World J Gastrointest 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, : 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, : Arthritis Rheumatol 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 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, : Breast Cancer Res Treat 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, : Burns Trauma 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 Imaging 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, : Emerg Microbes Infect 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 Cell 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, : Funct Integr 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, : Genome 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, : Hepatology 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 Breast 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 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 Pain 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, : J Rheumatol 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, : Neurol 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, : PLoS Comput Biol 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, : Redox Biol 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 Appl Pharmacol 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(0,100))
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))
text(y = (1:length(res2)*1.2)-1.2 , x = res2+50, label = res2, pos = 3, cex = 1, col = "black")
grid()
dir.create("images")## Warning in dir.create("images"): 'images' already existspng("images/journals1.png")
par(mar=c(5,8,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Journal", xlim=c(0,1200))
text(y = (1:length(res2)*1.2)-0.8 , x = res2+50, label = res2, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2Omics type
omics <- x$Omics.type
omics_split <- strsplit(omics,", ")
omics <- unlist(omics_split)
res <- table(omics)
res <- res[order(res)]
length(res)## [1] 32res## omics
## ATAC-seq CRISPR screen
## 1 1
## Cytokine array EST sequencing
## 1 1
## Metagenomics Metgenomics
## 1 1
## Microbiome NanoString
## 1 1
## NanoString gene expression PCR Array
## 1 1
## pyrosequencing QTL mapping
## 1 1
## RNAi screen TCGA database
## 1 1
## ChIP-seq miRNA array
## 2 2
## PPI CNV array
## 2 3
## scRNA-seq PCR array
## 4 5
## Protein array miRNA expression array
## 8 9
## DNA methylation sequencing Genome sequencing
## 13 37
## miRNA-seq DNA methylation array
## 37 42
## Genotyping array Metabolomics
## 48 73
## Proteomics Database
## 151 255
## Gene expression array RNA-seq
## 513 566par(mar=c(1,1,1,1))
names(res) <- gsub("Gene expression array","RNA array",names(res))
wordcloud(words = names(res), freq = res, min.freq = 1,
max.words=200, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
names(res) <- gsub("RNA array","Gene expression array",names(res))
par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Omics type", xlim=c(0,600))
grid()
other <- sum(res[1:(nrow(res)-10)])
res2 <- c(other,tail(res,9))
names(res2)[1] <- "Other"
par(mar=c(5,12,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Omics type", xlim=c(0,600))
text(y = (1:length(res2)*1.2)-1.2 , x = res2-20, label = res2, pos = 3, cex = 1, col = "black")
grid()
png("images/omics1.png")
par(mar=c(5,10,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Omics type", xlim=c(0,600))
text(y = (1:length(res2)*1.2)-0.8 , x = res2-20, label = res2, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2Organism
org <- x$Organism
org_split <- strsplit(org,", ")
org <- unlist(org_split)
res <- table(org)
res <- res[order(res)]
length(res)## [1] 174res## org
## Acinetobacter baumannii Acropora cervicornis
## 1 1
## Agave tequilana Ailuropoda melanoleuca
## 1 1
## Alternanthera philoxeroides Ananas comosus
## 1 1
## Anas platyrhynchus domesticus Annona × atemoya
## 1 1
## Apostichopus japonicus Arabidopsis
## 1 1
## Artemia franciscana Bacillus cereus
## 1 1
## Bombus Bubalus bubalis
## 1 1
## Cairina moschata Camellia oleifera
## 1 1
## Campylomormyrus compressirostris Campylomormyrus tshokwe
## 1 1
## Candida albicans Capra hircus
## 1 1
## Caragana intermedia Careolus capreolus
## 1 1
## Catalpa fargesii Catharanthus roseus
## 1 1
## Chlorella pyrenoidosa Chromochloris zofingiensis
## 1 1
## Clostridium scindens Coturnix japonica
## 1 1
## Ctenopharyngodon idella Cucumis sativus
## 1 1
## Cupriavidus necator Damnacanthus indicus
## 1 1
## Desmosdesmus sp. Diabrotica virgifera
## 1 1
## Drosophila Dugesia ryukyuensis
## 1 1
## Dunaliella salina Eisenia fetida
## 1 1
## Enterococcus faecalis Equus ferus caballus
## 1 1
## Eriobotrya japonica Eriocheir sinensis
## 1 1
## Euphorbia kansui Exaiptasia pallida
## 1 1
## Fundulus majalis Gerbera hybrida
## 1 1
## Gnathonemus petersii Gossypium arboreum
## 1 1
## Gossypium barbadense Gymnocypris przewalskii
## 1 1
## Haemaphysalis longicornis Haemophilus influenzae
## 1 1
## Hypophthalmichthys nobilis Incilaria fruhstorferi
## 1 1
## Juncus effusus Legionella pneumophila
## 1 1
## Lilium pumilum Linum usitatissimum
## 1 1
## Lolium perenne Lolium temulentum
## 1 1
## Longissimus thoracis Lupinus albus
## 1 1
## Lycoris longituba Lymantria dispar dispar
## 1 1
## Malapterurus electricus Malus sieversii
## 1 1
## Microbiota Moschus berezovskii
## 1 1
## Mycobacterium smegmatis Mycobacterium tuberculosis
## 1 1
## Mytilus galloprovincialis Mytilus sp.
## 1 1
## Nicotiana benthamiana Ocimum tenuiflorum
## 1 1
## Oreochromis niloticus Oryza Sativa
## 1 1
## Panax ginseng Papio anubis
## 1 1
## Phellinus igniarius Phyllosticta
## 1 1
## Plasmodium falciparum Pleurotus tuoliensis
## 1 1
## Populus deltoides Pseudomonas aeruginosa
## 1 1
## Pygoscelis antarcticus Pygoscelis papua
## 1 1
## Ribes nigrum Saccharomyces cerevisiae
## 1 1
## Saccharomyces cerevisiae\n Saccharum officinarum
## 1 1
## Saccharum sp. Salvelinus alpinus
## 1 1
## Serratia marcescens Setaria italica
## 1 1
## Sillago sihama Simiiformes catarrhini
## 1 1
## Sorghum bicolor Spica prunellae
## 1 1
## Sternopygus macrurus Suaeda salsa
## 1 1
## Taraxacum kok-saghyz Taxus sp.
## 1 1
## Trachemys scripta elegans Trollius chinensis Bunge
## 1 1
## Various order Chiroptera Vertebrata
## 1 1
## Vicia faba Vicia sativa
## 1 1
## Xanthomonas citri Zonotrichia albicollis
## 1 1
## Zootermopsis nevadensis Zygnema circumcarinatum
## 1 1
## Abelmoschus esculentus Aequipecten opercularis
## 2 2
## Anas platyrhynchos Apis mellifera
## 2 2
## Auricularia cornea Bemisia tabaci
## 2 2
## Brachymeria lasus Brassica alboglabra
## 2 2
## Brassica oleracea Brassica rapa
## 2 2
## Caenorhabditis elegans Danio rerio
## 2 2
## Fenneropenaeus chinensis Granulicatella adiacens
## 2 2
## Hordeum vulgare Humulus lupulus
## 2 2
## Ipomoea batatas Magnolia wufengensis
## 2 2
## Malus domestica Mauremys reevesii
## 2 2
## Megalobrama amblycephala Meleagris gallopavo silvestris
## 2 2
## Mesocricetus auratus Mizuhopecten yessoensis
## 2 2
## Morchella importuna Nicotiana glutinosa
## 2 2
## Nicotiana tabaccum Oreochromis aureus
## 2 2
## Pagrus major Pseudotsuga menziesii
## 2 2
## Raphanus sativus Rhacophorus omeimontis
## 2 2
## Schistosoma japonicum Sclerotinia sclerotiorum
## 2 2
## Solanum sisymbriifolium Vibrio parahaemolyticus
## 2 2
## Vitis vinifera Aedes aegypti
## 2 3
## Carica papaya Macaca mulatta
## 3 3
## Zea mays Bos grunniens
## 3 4
## Canis lupus familiaris Capra aegagrus hircus
## 4 4
## Citrus sinensis Cyprinus carpio
## 4 4
## Oryctolagus cuniculus Camellia sinensis
## 4 5
## Equus caballus Glycine max
## 5 5
## Triticum aestivum Gossypium hirsutum
## 6 8
## Ovis aries Arabidopsis thaliana
## 8 9
## Brassica napus Gallus gallus
## 9 16
## Oryza sativa Sus scrofa
## 17 27
## Bos taurus Rattus norvegicus
## 29 55
## Mus musculus Homo sapiens
## 138 1106par(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(0,1300))
text(y = (1:length(res2)*1.2)-1.2 , x = res2+60, label = res2, pos = 3, cex = 1, col = "black")
grid()
png("images/organisms1.png")
par(mar=c(5,10,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Organism", xlim=c(0,1300))
text(y = (1:length(res2)*1.2)-0.8 , x = res2+60, label = res2, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2Gene 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] 101which(names(res)=="Not stated")/sum(res)*100## [1] 3.850782res## GSL
## Arabidopsis thaliana metabolic pathway AraCyc
## 1 1
## CCGA ChEMBL
## 1 1
## ChemRICH ChemSpider
## 1 1
## ConsensusPathDB Custom
## 1 1
## Cytoband CYTOBAND
## 1 1
## DGIdb DISEASES
## 1 1
## DSigDB EcoCyc
## 1 1
## eggNOG EHMN
## 1 1
## FUMA FunDO
## 1 1
## G2SBC Gene Set Knowledgebase
## 1 1
## GenMAPP GEO
## 1 1
## GOslim GSEA
## 1 1
## GWAS-catalog Human Metabolome Database
## 1 1
## IMPaLA Ingenuity Canonical Pathways
## 1 1
## Ingenuity Knowledge base INOH
## 1 1
## Jensen Diseases database MetaboLync
## 1 1
## Metascape METLIN
## 1 1
## MGI miEAA
## 1 1
## miRBase NCBI
## 1 1
## NCBI PubChem BioAssay NCI
## 1 1
## NDeX Omic Path
## 1 1
## pathDIP Pathway commons
## 1 1
## Pathway Ontology Pathway Studio
## 1 1
## Pathway Studio Ontology PDSP Ki DB
## 1 1
## PharmGKB PHAROS
## 1 1
## Phytozome annotations plantCyc
## 1 1
## PubChem REACTOME
## 1 1
## Schizo-Pi SGD
## 1 1
## SignaLink SIGNOR
## 1 1
## SMART SMPDB
## 1 1
## STITCH STRING
## 1 1
## ToppCluster ToppFun
## 1 1
## Vectorbase Vesiclepedia
## 1 1
## YEASTRACT Hallmark
## 1 2
## HPO HumanCyc
## 2 2
## JASPAR MapMan
## 2 2
## Mummichog NetPath
## 2 2
## NHGRI OMIM
## 2 2
## Swiss-Prot TRANSFAC
## 2 2
## CORUM DisGeNET
## 3 3
## DO KOG
## 3 3
## COG WikiPathway
## 4 4
## HMDB PFAM
## 5 6
## BioCyc UniProt
## 7 7
## InterPro PID
## 8 10
## WikiPathways MetaCore
## 13 14
## MetaboAnalyst PANTHER
## 15 17
## BioCarta Not stated
## 29 87
## Reactome MSigDB
## 88 107
## Ingenuity Knowledge Base KEGG
## 139 883
## GO
## 949par(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(0,1100))
text(y = (1:length(res2)*1.2)-1.2 , x = res2+60, label = res2, pos = 3, cex = 1, col = "black")
grid()
png("images/genesetlib1.png")
par(mar=c(5,12,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Gene set library", xlim=c(0,1100))
text(y = (1:length(res2)*1.2)-0.8 , x = res2+60, label = res2, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2Gene set version
GSV <-x$GS.version
res <- table(GSV)
res## GSV
## No Yes
## 1517 113res[1]/sum(res)*100## No
## 93.06748par(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))
text(y = (1:length(res)*1.2) - 0.6 , x = res-65, label = res, pos = 3, cex = 1, col = "black")
grid()
png("images/genesetvers1.png",width = 260, height = 260)
par(mar=c(5,7,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Gene set version defined", xlim=c(0,1900))
text(y = (1:length(res)*1.2) - 0.6 , x = res+200, label = res, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2Statistical test used
test <-x$Statistical.test.used
test <- strsplit(test,", ")
test <- unlist(test)
res <- table(test)
res <- res[order(res)]
res[which(names(res)=="Not stated")] / sum(res) * 100## Not stated
## 63.6695res## test
## Kruskal-Wallis Kruskal–Wallis
## 1 1
## modified Chi-squared Pascal
## 1 1
## Singular Enrichment Analysis (SEA) SPIA
## 1 1
## Kolmogorov–Smirnov Chi-squared
## 2 3
## GSVA Permutation
## 3 3
## ssGSEA Binomial
## 3 4
## MSEA ANOVA
## 5 6
## EASE No test
## 10 69
## Hypergeometric Fisher
## 128 169
## GSEA Not stated
## 187 1048par(mar=c(1,1,1,1))
wordcloud(words = names(res), freq = res, min.freq = 1,
max.words=200, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Test used", xlim=c(0,1200))
grid()
other <- sum(res[1:(nrow(res)-10)])
res2 <- c(other,tail(res,9))
names(res2)[1] <- "Other"
par(mar=c(5,12,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 0.7, xlab="no. analyses",
main = "Test used", xlim=c(0,1200))
text(y = (1:length(res2)*1.2)-1.2 , x = res2+60, label = res2, pos = 3, cex = 1, col = "black")
grid()
png("images/stattest1.png")
par(mar=c(5,10,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Test used", xlim=c(0,1200))
text(y = (1:length(res2)*1.2)-0.8 , x = res2+60, label = res2, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2FDR Correction
fdr <-x$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] 53.50123res## fdr
## Not stated No test No Yes
## 45 69 757 757par(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 = "FDR", xlim=c(0,900))
text(y = (1:length(res)*1.2)-0.7 , x = res-30, label = res, pos = 3, cex = 1, col = "black")
grid()
png("images/fdr1.png",width = 260, height = 260)
par(mar=c(5,7,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "FDR", xlim=c(0,1000))
text(y = (1:length(res)*1.2)-0.7 , x = res+80, label = res, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2App used
App <-x$App.used
App_split <- strsplit(App,", ")
App <- unlist(App_split)
res <- table(App)
res <- res[order(res)]
res[which(names(res)=="Not stated")]/sum(res)*100## Not stated
## 10.594length(unique(subset(x,App.used=="Not stated")$Journal))## [1] 87unique(subset(x,App.used=="Not stated")$Journal)## [1] "J Cancer" "PLoS Comput Biol"
## [3] "PLoS Pathog" "Int J Mol Sci"
## [5] "BMC Genomics" "Transl Vis Sci Technol"
## [7] "Arthritis Res Ther" "Stem Cell Res Ther"
## [9] "Proc Natl Acad Sci U S A" "Chin Med"
## [11] "Clin Proteomics" "PeerJ"
## [13] "Front Microbiol" "Oncol Lett"
## [15] "Aging (Albany NY)" "Biomed Res Int"
## [17] "Front Immunol" "Cancer Manag Res"
## [19] "BMC Plant Biol" "Dis Markers"
## [21] "Thorac Cancer" "Evid Based Complement Alternat Med"
## [23] "Mol Ther" "Bone Rep"
## [25] "J Clin Med" "Cells"
## [27] "Genes (Basel)" "Transl Oncol"
## [29] "Molecules" "Am J Transl Res"
## [31] "JCI Insight" "Int J Mol Med"
## [33] "BMC Bioinformatics" "Front Med (Lausanne)"
## [35] "Mol Med Rep" "Front Cell Neurosci"
## [37] "Hum Genomics" "Sci Rep"
## [39] "Front Pharmacol" "Exp Ther Med"
## [41] "DNA Cell Biol" "Parasite"
## [43] "FASEB J" "Hortic Res"
## [45] "Cell Death Dis" "Curr Genomics"
## [47] "Plant Physiol" "PLoS One"
## [49] "Emerg Microbes Infect" "Med Sci Monit"
## [51] "Biosci Rep" "Mol Cell Proteomics"
## [53] "Front Neurosci" "Cell Death Discov"
## [55] "World J Gastroenterol" "Front Genet"
## [57] "Environ Int" "Mediators Inflamm"
## [59] "J Cell Mol Med" "Int J Med Sci"
## [61] "Oxid Med Cell Longev" "J Transl Med"
## [63] "J Biol Eng" "Genes Dis"
## [65] "Clin Transplant" "Onco Targets Ther"
## [67] "Cancer Med" "Genes"
## [69] "Evol Bioinform Online" "Int J Biol Sci"
## [71] "Mol Cell Biol" "Acta Cir Bras"
## [73] "3 Biotech" "BMC Pregnancy Childbirth"
## [75] "Arch Gynecol Obstet" "Nat Commun"
## [77] "Turk J Biol" "Carcinogenesis"
## [79] "Front Aging Neurosci" "Dose Response"
## [81] "Cancer Cell Int" "Breast Cancer Res"
## [83] "J Immunother Cancer" "Int J Ophthalmol"
## [85] "Mol Breed" "Clin Cancer Res"
## [87] "Rice (N Y)"length(res)## [1] 146res## App
## anamiR Basespace Correlation engine
## 1 1
## BioCloud Biosystem
## 1 1
## BlastKOALA BLASTx
## 1 1
## CAMERA ChemRICH
## 1 1
## CluePedia ConsensuspathDB
## 1 1
## CPDB Custom MATLAB script
## 1 1
## Custom Perl script DEPICT
## 1 1
## DIAMOND EggNOG
## 1 1
## ESGEA exRNA atlas
## 1 1
## fgsea FUMA gene2func
## 1 1
## g:GOSt GENCLIP
## 1 1
## Genelibs GeneMANIA
## 1 1
## GeneSpring GeneTrail2
## 1 1
## GenFam GenGen
## 1 1
## globaltest GO-Elite
## 1 1
## GO: TermFinder GSA-SNP
## 1 1
## i‐Gsea4Gwas KSEA
## 1 1
## Limma limma goana
## 1 1
## limma kegga LinkedOmics
## 1 1
## MAGENTA MATHT
## 1 1
## Metabolon MetaboLync
## 1 1
## MiRNet miRSystem
## 1 1
## missMethyl missMethyl R package
## 1 1
## Molecule Annotation System MS Excel
## 1 1
## NOA web app Omicshare
## 1 1
## PANOGA PAPi
## 1 1
## Path-Finder pathDIP
## 1 1
## Pathifier pathVar
## 1 1
## Pathview Pathway Studio
## 1 1
## PathwayConnector PIGE
## 1 1
## Plant Pathway Studio PlantGSEA
## 1 1
## ProteINSIDE PSEA
## 1 1
## QuickGO R script
## 1 1
## SEA SetRank
## 1 1
## SGD Gene Ontology Slim Mapper SNP2GO R package
## 1 1
## Speed SPIA
## 1 1
## SPSS ssGSEA (GenePattern)
## 1 1
## STEM topGo
## 1 1
## ToppCluster Uniprot/GOA
## 1 1
## VLAD webMeV
## 1 1
## BiNGO Cluepedia
## 2 2
## ConsensusPathDB DOSE
## 2 2
## FGSEA GenCLiP
## 2 2
## GeneAnswers GO::TermFinder
## 2 2
## GOEAST i-GSEA4GWAS
## 2 2
## MapMan MeTPA
## 2 2
## OmicsBean PathVisio
## 2 2
## PIANO Reactome FI/Cytoscape
## 2 2
## ReactomePA ToppFun
## 2 2
## Custom script FUMA
## 3 3
## g:Profiler GAGE
## 3 3
## GeneCodis GOstats
## 3 3
## GREAT GSEA web app
## 3 3
## MetPA MSEA
## 3 3
## NetworkAnalyst Partek
## 3 3
## Pascal AmiGO
## 3 4
## GSVA Reactome web app
## 4 4
## REVIGO WEGO
## 4 4
## Cytoscape (No plugin stated) GOATOOLS
## 6 6
## KEGG mapper MAGMA
## 6 6
## Mummichog GOrilla
## 6 7
## DIANA-miRPath BiNGO/Cytoscape
## 8 9
## topGO ToppGene
## 10 10
## KAAS Custom R script
## 11 12
## Metascape FunRich
## 12 14
## STRING agriGO
## 18 19
## MetaCore Blast2GO
## 19 21
## Enrichr WebGestalt
## 29 30
## MetaboAnalyst ClueGO/Cytoscape
## 31 33
## GOseq PANTHER
## 38 43
## KOBAS clusterProfiler
## 69 86
## Ingenuity Pathway Analysis Not stated
## 159 173
## GSEA DAVID
## 188 379par(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))
text(y = (1:length(res2)*1.2)-1.2 , x = res2-20, label = res2, pos = 3, cex = 1, col = "black")
grid()
png("images/app1.png")
par(mar=c(5,12,3,1))
barplot(res2,horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "App used", xlim=c(0,500))
text(y = (1:length(res2)*1.2)-0.8 , x = res2-20, label = res2, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2length(unique(subset(x,App.used=="Not stated")$Journal))## [1] 87App version
APV <-x$App.Version
res <- table(APV)
res## APV
## No Yes
## 1196 424res[1]/sum(res)*100## No
## 73.82716par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "App version defined", xlim=c(0,1600))
text(y = (1:length(res)*1.2) - 0.6 , x = res-70, label = res, pos = 3, cex = 1, col = "black")
grid()
png("images/appvers1.png",width = 260, height = 260)
par(mar=c(5,7,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "App version defined", xlim=c(0,1600))
text(y = (1:length(res)*1.2) - 0.6 , x = res-200, label = res, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2Code available
code <-x$Code.availability
res <- table(code)
res## code
## No Yes
## 284 12res[1]/sum(res)*100## No
## 95.94595par(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(0,330))
text(y = (1:length(res)*1.2) - 0.6 , x = res+15, label = res, pos = 3, cex = 1, col = "black")
grid()
png("images/code1.png",width = 260, height = 260)
par(mar=c(5,7,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Code availability", xlim=c(0,350))
text(y = (1:length(res)*1.2) - 0.6 , x = res+30, label = res, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2Background gene set
BG <-x$Background.gene.set
res <- table(BG)
res## BG
## No Not stated Stated, but incorrect
## 194 1178 17
## Yes
## 65sum(res[which(names(res)!="Yes")])/sum(res)*100## [1] 95.52957par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Background list defined", xlim=c(0,1300))
text(y = (1:length(res)*1.2)-0.7 , x = res+60, label = res, pos = 3, cex = 1, col = "black")
grid()
png("images/bg1.png")
par(mar=c(5,12,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Background list defined", xlim=c(0,1400))
text(y = (1:length(res)*1.2)-0.7 , x = res+80, label = res, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2Gene lists provided
GL <-x$Gene.lists.provided
res <- table(GL)
res## GL
## No Yes
## 1040 587sum(res[which(names(res)!="Yes")])/sum(res)*100## [1] 63.92133par(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))
text(y = (1:length(res)*1.2) - 0.6 , x = res-70, label = res, pos = 3, cex = 1, col = "black")
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"png("images/genelists1.png",width = 260, height = 260)
par(mar=c(5,7,3,1))
barplot(tail(res,20),horiz=TRUE,las=1,cex.names = 1, xlab="no. analyses",
main = "Gene lists provided", xlim=c(0,1200))
text(y = (1:length(res)*1.2) - 0.6 , x = res-120, label = res, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2Assumptions violated
ok <- nrow(subset(x,Assumptions.violated=="No"))
ok## [1] 171bad <- nrow(subset(x,Assumptions.violated!="No"))
bad## [1] 1459ok/sum(bad,ok)*100## [1] 10.4908ass <-x$Assumptions.violated
ass <- strsplit(ass,", ")
ass <- unlist(ass)
res <- table(ass)
res <- res[order(res)]
res## ass
## Misinterpreted FDR values No data shown Inference without test
## 2 42 58
## No FDR Background
## 171 761 1356par(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(0,1500))
text(y = (1:length(res)*1.2)-0.75 , x = res+60, label = res, pos = 3, cex = 1, col = "black")
grid()
png("images/assumptions1.png")
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(0,1500))
text(y = (1:length(res)*1.2)-0.75 , x = res+80, label = res, pos = 3, cex = 1, col = "black")
grid()
dev.off()## png
## 2Score
Here I am proposing a scoring scheme. If there is information missing from the article, or basic mistakes are made, then a point is deducted. If the article goes over and above the basic reproducibility, then they are awarded a point.
Gene set library origin not stated = -1
Gene set library version not stated = -1
Stat test not stated = -1
No stat test conducted = -1
No FDR correction conducted = -1
App used not stated = -1
App version not stated = -1
Background list not defined = -1
Inappropriate background list used = -1
Code availability = +1
Gene lists provided = +1
score <- function(r){
r[is.na(r)] <- 0
SCORE=0
# gene set lib
if(r["Gene.set.library"]=="Not stated"){
SCORE=SCORE-1
}
# GS version
if(r["GS.version"]=="No"){
SCORE=SCORE-1
}
# stat test
if(r["Statistical.test.used"]=="No test"){
SCORE=SCORE-1
}
if(r["Statistical.test.used"]=="Not stated"){
SCORE=SCORE-1
}
# FDR
if(r["FDR.Correction"]!="Yes"){
SCORE=SCORE-1
}
# app used
if(r["App.used"]=="Not stated"){
SCORE=SCORE-1
}
# App version
if(r["App.Version"]=="No"){
SCORE=SCORE-1
}
# Code availability
if(r["Code.availability"]=="Yes"){
SCORE=SCORE+1
}
# Background
if(r["Background.gene.set"]=="Not stated"){
SCORE=SCORE-1
}
if(r["Background.gene.set"]=="No"){
SCORE=SCORE-1
}
if(r["Background.gene.set"]=="Stated, but incorrect"){
SCORE=SCORE-1
}
# gene list
if(r["Gene.lists.provided"]=="Yes"){
SCORE=SCORE+1
}
return(SCORE)
}
scores <- apply(X = x,MARGIN = 1, FUN = score)
barplot(table(scores), xlab="analysis score",ylab="frequency")
x$scores <- scores
length(which(scores>0))## [1] 2mean(x$scores)## [1] -3.529448sd(x$scores)## [1] 1.361599median(x$scores)## [1] -4length(scores)## [1] 1630which(scores>0)## 349 5910
## 278 1450png("images/hist1.png",width=300,height=200)
par(mar=c(5,5,3,1))
barplot(table(scores), xlab="analysis score",ylab="frequency")
dev.off()## png
## 2pdf("images/hist1.pdf",width=4,height=3)
par(mar=c(5,5,3,1))
barplot(table(scores), xlab="analysis score",ylab="frequency")
dev.off()## png
## 2Journal rank
jmetrics <- read.table("scimagojr_2020.csv",sep=";",header=TRUE,dec = ",")
jmetrics$Title <- toupper(jmetrics$Title)
head(jmetrics,3)## Rank Sourceid Title Type
## 1 1 28773 CA-A CANCER JOURNAL FOR CLINICIANS journal
## 2 2 19434 MMWR RECOMMENDATIONS AND REPORTS journal
## 3 3 20315 NATURE REVIEWS MOLECULAR CELL BIOLOGY journal
## Issn SJR SJR.Best.Quartile H.index Total.Docs...2020.
## 1 15424863, 00079235 62.937 Q1 168 47
## 2 10575987, 15458601 40.949 Q1 143 10
## 3 14710072, 14710080 37.461 Q1 431 115
## Total.Docs...3years. Total.Refs. Total.Cites..3years. Citable.Docs...3years.
## 1 119 3452 15499 80
## 2 9 1292 492 9
## 3 338 8439 10844 167
## Cites...Doc...2years. Ref....Doc. Country Region
## 1 126.34 73.45 United States Northern America
## 2 50.00 129.20 United States Northern America
## 3 32.83 73.38 United Kingdom Western Europe
## Publisher Coverage
## 1 Wiley-Blackwell 1950-2020
## 2 Centers for Disease Control and Prevention (CDC) 1990-2020
## 3 Nature Publishing Group 2000-2020
## Categories
## 1 Hematology (Q1); Oncology (Q1)
## 2 Epidemiology (Q1); Health Information Management (Q1); Health (social science) (Q1); Health, Toxicology and Mutagenesis (Q1); Medicine (miscellaneous) (Q1)
## 3 Cell Biology (Q1); Molecular Biology (Q1)dim(jmetrics)## [1] 32952 20nlmcat <- readLines("nlmcatalog_result.txt")
journaltitle <- nlmcat[grep("Title\\(s\\):",nlmcat)]
journaltitle <- gsub("Title\\(s\\): ","",journaltitle)
journaltitle <- gsub("\\.$","",journaltitle)
journaltitle <- toupper(journaltitle)
journalabbrev <- nlmcat[grep("Title Abbreviation:",nlmcat)]
journalabbrev <- sapply(strsplit(journalabbrev,":"),"[[",2)
journalabbrev <- gsub(" $","",journalabbrev)
journalabbrev <- gsub("^ ","",journalabbrev)
jdf <- data.frame(journalabbrev,journaltitle)
mjdf <- merge(jdf,jmetrics,by.x="journaltitle",by.y="Title")
xm <- merge(x,mjdf,by.x="Journal",by.y="journalabbrev",all.x = TRUE)Analysis scores vs Journal rank
tail(xm$Journal)## [1] "World J Gastroenterol" "World J Gastrointest Oncol"
## [3] "World J Gastrointest Oncol" "World J Surg Oncol"
## [5] "World J Surg Oncol" "World J Surg Oncol"hist(xm$SJR,xlab="SJR",main="SJR distribution")
mylm1 <- lm (xm$scores ~ xm$SJR)
plot(xm$SJR,xm$scores, col = rgb(red=0,blue=0,green=0,alpha=0.2), pch=19, bty="n",
xlab="SJR",ylab="score",main="Analysis scores vs. journal metrics")
abline(mylm1,col="red")
cor.test(xm$scores,xm$SJR,method="pearson")##
## Pearson's product-moment correlation
##
## data: xm$scores and xm$SJR
## t = 1.335, df = 1196, p-value = 0.1821
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.01810308 0.09500263
## sample estimates:
## cor
## 0.03857333cor.test(xm$scores,xm$SJR,method="spearman")## Warning in cor.test.default(xm$scores, xm$SJR, method = "spearman"): Cannot
## compute exact p-value with ties##
## Spearman's rank correlation rho
##
## data: xm$scores and xm$SJR
## S = 278554962, p-value = 0.3339
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## 0.0279424png("images/score_sjr1.png",width=350,height=300)
par(mar=c(5,5,3,1))
plot(xm$SJR,xm$scores, col = rgb(red=0,blue=0,green=0,alpha=0.2), pch=19,bty="n",
xlab="SJR",ylab="score",main="Analysis scores vs. journal metrics")
abline(mylm1,col="red")
grid()
dev.off()## png
## 2pdf("images/score_sjr1.pdf",width=4,height=3)
par(mar=c(4,4,3,2))
plot(xm$SJR,xm$scores, col = rgb(red=0,blue=0,green=0,alpha=0.2), pch=19,bty="n",
xlab="SJR",ylab="score",main="Analysis scores vs. journal metrics")
abline(mylm1,col="red")
grid()
dev.off()## png
## 2Best and worst journals
Minimum of 5 analyses.
xmm <-xm[,c("Journal","scores")]
tab <- table(xmm$Journal)
tab <- tab[which(tab>=5)]
xmm <- xmm[which(xmm$Journal %in% names(tab)),]
dim(xmm)## [1] 1236 2jres <- aggregate(. ~ Journal, xmm ,mean)
jsd <- aggregate(. ~ Journal, xmm ,sd)
jres$sd <- jsd$scores
jres <- jres[order(jres$scores),]
dim(jres)## [1] 70 3head(jres)## Journal scores sd
## 65 RNA Biol -5.000000 1.0954451
## 53 Mol Med Rep -4.275000 0.9867715
## 15 Cancer Med -4.272727 0.9045340
## 70 World J Gastroenterol -4.250000 1.3887301
## 18 Cell Death Discov -4.200000 1.3038405
## 39 Int J Med Sci -4.200000 1.3038405par(mar=c(5,12,3,1))
barplot(tail(jres$scores,20),names.arg = tail(jres$Journal,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="mean score",
main = "Highest scoring",xlim=c(-4,0))
grid()
png("images/score_highest1.png",width=300,height=350)
par(mar=c(5,12,3,1))
barplot(tail(jres$scores,20),names.arg = tail(jres$Journal,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="mean score",
main = "Highest scoring",xlim=c(-4,0))
grid()
dev.off()## png
## 2par(mar=c(5,12,3,1))
barplot(head(jres$scores,20),names.arg = head(jres$Journal,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="mean score",
main = "Lowest scoring journals",xlim=c(-5,0))
grid()
png("images/score_lowest1.png",width=300,height=350)
par(mar=c(5,12,3,1))
barplot(head(jres$scores,20),names.arg = head(jres$Journal,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="mean score",
main = "Lowest scoring",xlim=c(-5,0))
grid()
dev.off()## png
## 2pdf("images/score_highest1.pdf",width=3,height=4.5)
par(mar=c(5,8,3,1))
barplot(tail(jres$scores,20),names.arg = tail(jres$Journal,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="mean score",
main = "Highest scoring",xlim=c(-4,0))
grid()
dev.off()## png
## 2pdf("images/score_lowest1.pdf",width=3,height=4.5)
par(mar=c(5,8,3,1))
barplot(head(jres$scores,20),names.arg = head(jres$Journal,20),horiz=TRUE,las=1,cex.names = 0.7, xlab="mean score",
main = "Lowest scoring",xlim=c(-5,0))
grid()
dev.off()## png
## 2j <- unique(xmm$Journal)
jscores <- sapply(j,function(jj) {
xmm[which(xmm$Journal == jj ),2]
})
jscores <- jscores[order(unlist(lapply(jscores,mean)))]
par(mar=c(5,12,3,1))
vioplot(tail(jscores,20),horizontal = TRUE,las=1,cex.axis=0.75,main="Highest scoring journals")
par(mar=c(5,12,3,1))
vioplot(head(jscores,20),horizontal = TRUE,las=1,cex.axis=0.75,main="Lowest scoring journals")
Mean analysis scores vs Journal rank
jjres <- merge(jres,mjdf,by.x="Journal",by.y="journalabbrev",all.x = TRUE)
mylm2 <- lm (jjres$scores ~ jjres$SJR)
plot(jjres$SJR,jjres$scores,col = rgb(red=0,blue=0,green=0,alpha=0.2) , pch=19,bty="n",
xlab="SJR",ylab="mean score",main="Mean analysis score vs. journal metrics")
abline(mylm2,col="red")
png("images/mean_sjr1.png",width=350,height=300)
par(mar=c(5,5,3,1))
plot(jjres$SJR,jjres$scores, col = rgb(red=0,blue=0,green=0,alpha=0.2) , pch=19,bty="n",
xlab="SJR",ylab="mean score",main="Mean analysis score vs. journal metrics")
abline(mylm2,col="red")
dev.off()## png
## 2cor.test(jjres$scores,jjres$SJR,method="pearson")##
## Pearson's product-moment correlation
##
## data: jjres$scores and jjres$SJR
## t = -0.051925, df = 54, p-value = 0.9588
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2694658 0.2563108
## sample estimates:
## cor
## -0.007065863cor.test(jjres$scores,jjres$SJR,method="spearman")## Warning in cor.test.default(jjres$scores, jjres$SJR, method = "spearman"):
## Cannot compute exact p-value with ties##
## Spearman's rank correlation rho
##
## data: jjres$scores and jjres$SJR
## S = 31981, p-value = 0.4954
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## -0.09299186pdf("images/mean_sjr1.pdf",width=3.5,height=3)
par(mar=c(5,5,3,1))
plot(jjres$SJR,jjres$scores, col = rgb(red=0,blue=0,green=0,alpha=0.2) , pch=19,bty="n",
xlab="SJR",ylab="mean score",main="Mean analysis score vs. journal metrics")
abline(mylm2,col="red")
dev.off()## png
## 2Article citations
Get the number of citations per article.
if (file.exists("cites_data.rds") ) {
cites <- readRDS("cites_data.rds")
} else {
PMCIDS <- as.numeric(gsub("PMC","",x$Pubmed.Central.ID ))
mylink <- elink(uid=PMCIDS , dbFrom="pmc", dbTo = "pubmed")
PMID <- mylink[1]
#writeLines(PMID,"pubmedids.txt")
res <- sapply(X=PMID,FUN=function(x){
Sys.sleep(1)
CITES <- elink(uid = x , dbFrom = "pubmed" , linkname = "pubmed_pubmed_citedin" )
CITES=length(CITES[1])
return(CITES)
})
mylink2 <- elink(uid=PMID , dbFrom="pubmed", dbTo = "pmc")
cites <- data.frame(mylink2[1],PMID,res)
colnames(cites) <- c("PMCID","PMID","cites")
saveRDS(cites,file="cites_data.rds")
}
cites$PMCID <- gsub("^","PMC",cites$PMCID)
cites$PMID <- gsub("^","PMID",cites$PMID)
xm <- merge(x,cites,by.x="Pubmed.Central.ID",by.y="PMCID")
dim(xm)## [1] 1627 19Plot the number of citations against analysis scores
mylm2 <- lm (xm$scores ~ xm$cites)
plot(xm$cites,xm$scores, col = rgb(red=0,blue=0,green=0,alpha=0.2) , pch=19,bty="n",
xlab="Num cites",ylab="score",main="Association of analysis scores with number of citations")
abline(mylm2,col="red")
cor.test(xm$scores , xm$cites, method="pearson")##
## Pearson's product-moment correlation
##
## data: xm$scores and xm$cites
## t = -0.061871, df = 1625, p-value = 0.9507
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.05012847 0.04706605
## sample estimates:
## cor
## -0.001534836cor.test(xm$scores , xm$cites, method="spearman")## Warning in cor.test.default(xm$scores, xm$cites, method = "spearman"): Cannot
## compute exact p-value with ties##
## Spearman's rank correlation rho
##
## data: xm$scores and xm$cites
## S = 732512662, p-value = 0.4091
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## -0.02047858mylm2 <- lm (xm$scores ~ log2(xm$cites))
plot(log2(xm$cites),xm$scores, col = rgb(red=0,blue=0,green=0,alpha=0.2) , pch=19,bty="n",
xlab="log2(citations)",ylab="score",main="Analysis scores vs. log2(citations)")
abline(mylm2,col="red")
png("images/cites1.png",width=350,height=300)
par(mar=c(5,5,3,1))
plot(log2(xm$cites),xm$scores,col = rgb(red=0,blue=0,green=0,alpha=0.2) , pch=19,bty="n",
xlab="log2(citations)",ylab="score",main="Analysis scores vs. log2(citations)")
abline(mylm2,col="red")
dev.off()## png
## 2cor.test(xm$scores , xm$cites, method="pearson")##
## Pearson's product-moment correlation
##
## data: xm$scores and xm$cites
## t = -0.061871, df = 1625, p-value = 0.9507
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.05012847 0.04706605
## sample estimates:
## cor
## -0.001534836cor.test(xm$scores , xm$cites, method="spearman")## Warning in cor.test.default(xm$scores, xm$cites, method = "spearman"): Cannot
## compute exact p-value with ties##
## Spearman's rank correlation rho
##
## data: xm$scores and xm$cites
## S = 732512662, p-value = 0.4091
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## -0.02047858pdf("images/cites1.pdf",width=3.5,height=3)
par(mar=c(5,5,3,1))
plot(log2(xm$cites),xm$scores,col = rgb(red=0,blue=0,green=0,alpha=0.2) , pch=19,bty="n",
xlab="log2(citations)",ylab="score",main="Analysis scores vs. log2(citations)")
abline(mylm2,col="red")
dev.off()## png
## 2Session 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] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] vioplot_0.3.7 zoo_1.8-9 sm_2.2-5.6 kableExtra_1.3.4
## [5] XML_3.99-0.6 reutils_0.2.3 wordcloud2_0.2.1 wordcloud_2.6
## [9] 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 fastmap_1.1.0 stringr_1.4.0 httr_1.4.2
## [21] knitr_1.33 xml2_1.3.2 systemfonts_1.0.2 htmlwidgets_1.5.3
## [25] sass_0.4.0 grid_4.1.0 webshot_0.5.2 svglite_2.0.0
## [29] glue_1.4.2 R6_2.5.1 tcltk_4.1.0 rmarkdown_2.10
## [33] magrittr_2.0.1 scales_1.1.1 htmltools_0.5.2 rvest_1.0.1
## [37] colorspace_2.0-2 stringi_1.7.4 RCurl_1.98-1.3 munsell_0.5.0