\documentclass[11pt, oneside]{article}   	% use "amsart" instead of "article" for AMSLaTeX format
%\usepackage{geometry}                		% See geometry.pdf to learn the layout options. There are lots.
%\geometry{letterpaper}                   		% ... or a4paper or a5paper or ... 
%\geometry{landscape}                		% Activate for for rotated page geometry
%\usepackage[parfill]{parskip}    		% Activate to begin paragraphs with an empty line rather than an indent
%\usepackage{graphicx}				% Use pdf, png, jpg, or eps with pdflatex; use eps in DVI mode
								% TeX will automatically convert eps --> pdf in pdflatex		
%\usepackage{amssymb}

\usepackage[utf8]{inputenc}
%\usepackage[cyr]{aeguill}
%\usepackage[francais]{babel}
%\usepackage{hyperref}


\title{Positive selection on genes interacting with SARS-Cov2, comparison of different analysis}
\author{Marie Cariou}
\date{Mars 2021}							% Activate to display a given date or no date

\begin{document}
\maketitle

\tableofcontents

\newpage

\section{Data}

Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.

<<>>=
home<-"/home/adminmarie/Documents/"
workdir<-paste0(home,"CIRI_BIBS_projects/2020_05_Etienne_covid/")

tab<-read.delim(paste0(workdir, 
  "covid_comp/covid_comp_complete.txt"), h=T, sep="\t")
dim(tab)
tab$Gene.name<-as.character(tab$Gene.name.x)
tab$Gene.name[tab$PreyGene=="MTARC1"]<-"MTARC1"
@

\section{Comparison Bats}

\subsection{Cooper-bats results VS DGINN-bats results}

<<omegaM7M8bats>>=
tab$bats_omegaM0codeml[tab$bats_omegaM0codeml=="na"]<-NA

plot(tab$cooper.batsAverage_dNdS, 
     as.numeric(as.character(tab$bats_omegaM0codeml)), 
     xlab="Omega Cooper-bats", 
     ylab="Omega DGINN-bats")
abline(0,1)
abline(lm(as.numeric(as.character(tab$bats_omegaM0codeml))~
            tab$cooper.batsAverage_dNdS), 
       col="red")

outlier<-tab[tab$cooper.batsAverage_dNdS>0.35 & 
  as.numeric(as.character(tab$bats_omegaM0codeml))<0.3,]
text(x=outlier$cooper.batsAverage_dNdS,
y=as.numeric(as.character(outlier$bats_omegaM0codeml)),
outlier$Gene.name)
@

\section{Overlap}

\subsection{Data}

<<subbats>>=
tmp<-na.omit(tab[,c("Gene.name", "bats_codemlM7M8_p.value", 
                    "hawkins_Positive.Selection..M8vM8a.p.value", 
                    "cooper.batsM7.M8_p_value", "bats_BUSTED", 
                    "bats_BppM1M2", "bats_BppM7M8", "bats_codemlM1M2", 
                    "bats_codemlM7M8")])

tmp$bats_codemlM7M8_p.value[tmp$bats_codemlM7M8_p.value=="na"]<-NA
tmp$bats_codemlM7M8_p.value<-as.numeric(
  as.character(tmp$bats_codemlM7M8_p.value))
dim(tmp)
@

170 genes (present in the 3 experiments)

\subsection{Mondrian}

<<mondrianbats>>=
library(Mondrian)

monddata<-as.data.frame(tmp$Gene.name)
monddata$bats_hawkins<-ifelse(
  tmp$hawkins_Positive.Selection..M8vM8a.p.value<0.05, 1, 0)
monddata$bats_cooper<-ifelse(
  tmp$cooper.batsM7.M8_p_value<0.05, 1, 0)


dginntmp<-rowSums(cbind(tmp$bats_codemlM1M2=="Y", 
                        tmp$bats_codemlM7M8=="Y", 
                        tmp$bats_BppM1M2=="Y", 
                        tmp$bats_BppM7M8=="Y", 
                        tmp$bats_BUSTED=="Y")) 

monddata$bats_dginn<-ifelse(dginntmp>=3, 1,0)
mondrian(monddata[,2:4], 
         labels=c("DGINN >=3", "hawkins", "Cooper"))

monddata$bats_dginn<-ifelse(dginntmp>=4, 1,0)
mondrian(monddata[,2:4], 
         labels=c("DGINN >=4", "hawkins", "Cooper"))
@

\subsection{subsetR}

<<subsetbats>>=
library(UpSetR)
upsetdata<-as.data.frame(tmp$Gene.name)

upsetdata$bats_hawkins<-ifelse(
  tmp$hawkins_Positive.Selection..M8vM8a.p.value<0.05, 1, 0)
upsetdata$bats_cooper<-ifelse(
  tmp$cooper.batsM7.M8_p_value<0.05, 1, 0)

upsetdata$bats_dginn<-ifelse(dginntmp>=3, 1,0)

upset(upsetdata, nsets = 3, matrix.color = "#DC267F", 
main.bar.color = "#648FFF", sets.bar.color = "#FE6100")

upsetdata$bats_dginn<-ifelse(dginntmp>=4, 1,0)

upset(upsetdata, nsets = 3, matrix.color = "#DC267F", 
main.bar.color = "#648FFF", sets.bar.color = "#FE6100")

@

<<>>=
source("covid_comp_shiny.R")


df<-read.delim(paste0(workdir,
"/data/DGINN_202005281649summary_cleaned.csv"), 
      fill=T, h=T, sep=",")

names(df)
dftmp<-tab[,c("bats_File", "bats_Name", 
       "Gene.name", "bats_GeneSize", 
       "bats_NbSpecies", "bats_omegaM0Bpp",
       "bats_omegaM0codeml", "bats_BUSTED", 
       "bats_BUSTED_p.value", "bats_MEME_NbSites", 
       "bats_MEME_PSS", "bats_BppM1M2", 
       "bats_BppM1M2_p.value", "bats_BppM1M2_NbSites", 
       "bats_BppM1M2_PSS", "bats_BppM7M8", 
       "bats_BppM7M8_p.value", "bats_BppM7M8_NbSites", 
       "bats_BppM7M8_PSS", "bats_codemlM1M2", 
       "bats_codemlM1M2_p.value", "bats_codemlM1M2_NbSites",
       "bats_codemlM1M2_PSS", "bats_codemlM7M8",
       "bats_codemlM7M8_p.value", "bats_codemlM7M8_NbSites" , 
       "bats_codemlM7M8_PSS")]

names(dftmp)<-names(df)
makeFig1(dftmp)
@

\end{document}