--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/Dotplot_Release/Step2_data_filtering.R	Fri Jan 29 09:56:02 2016 -0500
@@ -0,0 +1,28 @@
+#!/usr/bin/env Rscript
+
+args <- commandArgs(trailingOnly = TRUE)
+
+d = read.delim(args[1], header=T, as.is=T)
+
+d2 = d
+d2s = d
+
+ss_cutoff <- as.numeric(args[2])
+### Here I'm only going to take the preys which appeared in at least 2 baits with >args[2] counts
+id = apply(d, 1, function(x) sum(x>ss_cutoff) >= 2)
+id2 = apply(d, 1, function(x) sum(x>ss_cutoff) < 2)
+d2 = d2[id, ]
+d2s = d2s[id2, 0]
+max.d2 = max(as.numeric(as.matrix(d2))) 
+d2 = d2 / max.d2 * 10
+
+d3 = data.frame(PROT = rownames(d2), d2)
+
+outfile <- paste(c(args[3]), "dat", sep=".")
+
+### The following file is the outcome of running this step.
+write.table(d3, outfile, sep="\t", quote=F, row.names=F)
+### This is the final input file for nested cluster algorithm
+
+write.table(d2s, "singletons.txt", quote=F)
+