Select ORF rls

# 9.ken/_explore.20140705

rm(list=ls())
setwd("~/projects/0.network.aging.prj/9.ken")

list.files()

tb = read.csv('conditionsWeibRedo_qin.csv')
tb$genotype = toupper( as.character(tb$genotype))
tb$media = as.character(tb$media)
str(tb)

tb[grep("ctf", tb$genotype, ignore.case=T), ]


tb2 = read.csv("SceORF_name.csv", header=F, colClass=c("character", "character"))
names(tb2) = c('ORF','name')
length(unique(tb$genotype))

table( tb$genotype %in% tb2$name )
table( tb2$name %in% tb$genotype )

tb$flag = tb$genotype %in% tb2$name
sub = tb[tb$flag, ]
sub$ORF = tb2$ORF[match(sub$genotype, tb2$name)]

length(unique(sub$genotype))
x = table(sub$media)
x[grep("YPD",names(x))]
tb$media[grep("% D", tb$media, ignore.case=T)]

write.csv(sub, "ken-RLS-byORF.csv", row.names=F, quote=F)

x = sub[sub$n>30, ]
hist(log10(x$n)/log10(3))
summary(sub)
tb[tb$n>1000,]