09_boxplot.Rmd

---
title: "Boxplots"
author: "Florent Chuffart"
date: "`r Sys.Date()`"
output: 
  rmarkdown::html_document:
    toc: true
    toc_float: true
    toc_depth: 3
    number_sections: true
---



```{r, echo=FALSE, eval=TRUE}
knitr::opts_chunk$set(collapse=TRUE, comment = "#>", fig.width=9, fig.height=6, eval=TRUE, echo=FALSE, results="hide")
```

```{r}
hg_genes = c( 
  "ATAD2",
  "ASF1A", 
  "ASF1B", 
  "SUPT16H", 
  "SSRP1", 
  "MCM2", 
  "NASP", 
  "HJURP", 
  "DAXX", 
  "HIRA", 
  "CABIN1", 
  "UBN1", 
  "RBBP4", 
  "CHAF1A", 
  "CHAF1B"
)

homologene_tab = homologene::homologene(hg_genes, inTax=9606, outTax=10090)
homologene_tab
hg_genes %in% homologene_tab[,1]
mm_genes = homologene_tab[,2]

mm_genes = c(mm_genes, "Prm1", "Prm2", "Tnp1", "Tnp2", "H2afb1", "Nutm1")

table_file = "04_deseq2/tables/d20wtvsd20ko.complete.txt"
daresults = read.table(table_file, header=TRUE)
rownames(daresults) = daresults$Id

mm_genes %in% rownames(daresults)

"Tnp1" %in% rownames(daresults)


col_idx = colnames(daresults)[grep("norm", colnames(daresults))]

norm_data = as.matrix(log2(daresults[mm_genes,col_idx]+1))
colnames(norm_data)


day = substr(colnames(norm_data), 6,8)
day

line = substr(colnames(norm_data), 10,11)
line = factor(line, levels=rev(unique(line)))
line

d = cbind(data.frame(day=day, line=line), t(norm_data))

for (g in mm_genes) {
  print(g)
  par(mar=c(7.5, 4.1, 4.1, 2.1))
  layout(1, respect=1)
  model = paste0(g, "~line+day")
  boxplot(formula(model), d, main=model, las=2, xlab="", ylab="log2(norm_read_count + 1)", col=c(2,4))  
}
```


# Session Information

```{r, results="verbatim"}
sessionInfo()
```