NAs_per_strain.Rmd

---
output: pdf_document
geometry: margin=1in
mainfont: Times New Roman
---

```{r,fig.width=7.5, fig.height=4,warning=F, message=F, echo=F,comment="K",results='asis'}
#!/usr/bin/R
# this script plots a histogram of percentage of NAs in a strain for each TE family

library(dplyr)
library(tidyr)
library(ggplot2)


setwd("/Users/kristen/Documents/transposon_figure_data/data")
nas<-read.table("T_kin_C_matrix_NAs_reduced.txt",header=TRUE,stringsAsFactors=F)
nas<-filter(nas,grepl('ONE_new',trait))
nas<-mutate(nas,total=AB1)
nas<-mutate(nas,total=gsub(".*\\(.*/", "",total))
nas<-mutate(nas,total=gsub(")", "",total))
nas<-mutate(nas,trait=paste(trait,total, sep =":"))
nas<-select(nas,-total)
nas <- as.data.frame(sapply(nas,gsub,pattern="\\(.*\\)",replacement=""),stringsAsFactors=F)


i="ONE_new_TRANS_CELE14B_NA:1"
trait_list<-list(nas$trait)

for (i in unique(nas$trait)){

data<-filter(nas, trait==i)
col_length=length(data)
data[, c(2:col_length)] <- sapply(data[, c(2:col_length)], as.numeric)
data<-data %>% gather(strain,value, AB1:WN2002)
data<-mutate(data, value=as.numeric(value))
#m <- geom_histogram(data)
m <- ggplot(data, aes(x=value))
m <- m + geom_histogram(binwidth=.05) +ggtitle(i)
m <- m +theme(panel.background = element_rect(fill = "white"),
              strip.background = element_rect(fill="white"),
              axis.ticks = element_line(colour = "black"),
              axis.text.y = element_text(colour = "black",size=9),
              axis.text.x = element_text(colour = "black",size=9),
              axis.line=element_line(linetype="solid"),
              axis.title=element_text(size=9,face="bold"))
plot(m)
#cat("\n\n\\pagebreak\n")
}