GSEA_Word_Cloud.R

library(readr)
library(dplyr)
library(tm)
library(wordcloud)
library(SnowballC)
library(RColorBrewer)

m <- read_csv("node_table.csv.gz") %>% 
  filter(EM1_fwer_qvalue_dataset1 < 0.5, EM1_gs_size_dataset1 > 95) 


terms <- Corpus(DataframeSource(data.frame(m$EM1_GS_DESCR)))
terms <- tm_map(terms, stripWhitespace)
terms <- tm_map(terms, removeWords, stopwords("english"))

skip_words <- c("cell", "protein", "organism", "single", "process", "negative", "regulation")
terms <- tm_map(terms, removeWords, skip_words)
# terms <- tm_map(terms, stemDocument, mc.cores = 1)

pdf("EM_wordcloud.pdf")
wordcloud(terms, 
          scale=c(4,0.8), 
          max.words=100, 
          min.freq=3,
          random.order=FALSE, 
          rot.per=0, 
          use.r.layout=FALSE, 
          colors=brewer.pal(8, "Dark2")
)
dev.off()