Cacher is the code snippet organizer for pro developers

library(RISmed)
library(parallel)
library(ggplot2)

# Given two lists of terms, lets see how 'hot' they are together
set1 <- c("ebola","autoimmune","Diabetes","HIV","Glioblastoma","Asthma","Schizophrenia")
set2 <- c("C. elegans","D. Melanogaster","C. japonica", "M. Musculus","S. Cerevisiae")

# Generate all possible pairs
pairs <- expand.grid(set1, set2, stringsAsFactors=F)

# Search pubmed for each pair, and return the number of search results.
results <- mclapply(seq(nrow(pairs)),  function(x) {
res <- EUtilsSummary(sprintf("%s %s", pairs[x,]$Var1, pairs[x,]$Var2, type='esearch', db='pubmed'))
c(q1=pairs[x,]$Var1, q2=pairs[x,]$Var2, count=QueryCount(res))
})

# Do some data formatting on the results.
results <- as.data.frame(do.call("rbind", results), stringsAsFactors=F)
# Turn the number of search results into numeric form.
results$count <- as.numeric(results$count)

# Plot the results using geom_tile
ggplot(results) +
	geom_tile(aes(x=q1, y=q2, fill=count)) +
	geom_text(aes(x=q1, y=q2, label=count), color = "white") + 
	labs(title="Disease Publications by Organism", x="x", y="y")