Skip to content
Snippets Groups Projects
Commit 4156bc21 authored by your name's avatar your name
Browse files

script for bats

parent 17105310
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
covid_comp_bats.Rnw 0 → 100644
+ 113
− 0
View file @ 4156bc21
\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{janvier 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.
<<>>=
workdir<-"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"
tab<-read.delim(paste0(workdir,
"covid_comp/covid_comp_complete.txt"), h=T, sep="\t")
dim(tab)
@
\section{Comparison Bats}
\subsection{Cooper-bats results VS DGINN-bats results}
<<omegaM7M8bats>>=
plot(tab$cooper.batsAverage_dNdS, as.numeric(as.character(tab$bats_omegaM0codeml)),
xlab="Omega Cooper-bats", ylab="Omega DGINN-bats")
abline(0,1)
@
\subsection{Cooper-bats VS Hawkins-bats and DGINN-bats VS Hawkins-bats}
\textit{I don't think we have the omega values}
\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$bats_codemlM7M8.p.value<-as.numeric(as.character(tmp$bats_codemlM7M8.p.value))
dim(tmp)
@
174 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")
@
\end{document}
covid_comp_bats.pdf 0 → 100644
+ 0
− 0
View file @ 4156bc21
File added
covid_comp_bats.tex 0 → 100644
+ 207
− 0
View file @ 4156bc21
\documentclass[11pt, oneside]{article}\usepackage[]{graphicx}\usepackage[]{color}
% maxwidth is the original width if it is less than linewidth
% otherwise use linewidth (to make sure the graphics do not exceed the margin)
\makeatletter
\def\maxwidth{ %
\ifdim\Gin@nat@width>\linewidth
\linewidth
\else
\Gin@nat@width
\fi
}
\makeatother
\definecolor{fgcolor}{rgb}{0.345, 0.345, 0.345}
\newcommand{\hlnum}[1]{\textcolor[rgb]{0.686,0.059,0.569}{#1}}%
\newcommand{\hlstr}[1]{\textcolor[rgb]{0.192,0.494,0.8}{#1}}%
\newcommand{\hlcom}[1]{\textcolor[rgb]{0.678,0.584,0.686}{\textit{#1}}}%
\newcommand{\hlopt}[1]{\textcolor[rgb]{0,0,0}{#1}}%
\newcommand{\hlstd}[1]{\textcolor[rgb]{0.345,0.345,0.345}{#1}}%
\newcommand{\hlkwa}[1]{\textcolor[rgb]{0.161,0.373,0.58}{\textbf{#1}}}%
\newcommand{\hlkwb}[1]{\textcolor[rgb]{0.69,0.353,0.396}{#1}}%
\newcommand{\hlkwc}[1]{\textcolor[rgb]{0.333,0.667,0.333}{#1}}%
\newcommand{\hlkwd}[1]{\textcolor[rgb]{0.737,0.353,0.396}{\textbf{#1}}}%
\let\hlipl\hlkwb
\usepackage{framed}
\makeatletter
\newenvironment{kframe}{%
\def\at@end@of@kframe{}%
\ifinner\ifhmode%
\def\at@end@of@kframe{\end{minipage}}%
\begin{minipage}{\columnwidth}%
\fi\fi%
\def\FrameCommand##1{\hskip\@totalleftmargin \hskip-\fboxsep
\colorbox{shadecolor}{##1}\hskip-\fboxsep
% There is no \\@totalrightmargin, so:
\hskip-\linewidth \hskip-\@totalleftmargin \hskip\columnwidth}%
\MakeFramed {\advance\hsize-\width
\@totalleftmargin\z@ \linewidth\hsize
\@setminipage}}%
{\par\unskip\endMakeFramed%
\at@end@of@kframe}
\makeatother
\definecolor{shadecolor}{rgb}{.97, .97, .97}
\definecolor{messagecolor}{rgb}{0, 0, 0}
\definecolor{warningcolor}{rgb}{1, 0, 1}
\definecolor{errorcolor}{rgb}{1, 0, 0}
\newenvironment{knitrout}{}{} % an empty environment to be redefined in TeX
\usepackage{alltt} % 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{janvier 2021} % Activate to display a given date or no date
\IfFileExists{upquote.sty}{\usepackage{upquote}}{}
\begin{document}
\maketitle
\tableofcontents
\newpage
\section{Data}
Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{workdir}\hlkwb{<-}\hlstr{"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"}
\hlstd{tab}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,}
\hlstr{"covid_comp/covid_comp_complete.txt"}\hlstd{),} \hlkwc{h}\hlstd{=T,} \hlkwc{sep}\hlstd{=}\hlstr{"\textbackslash{}t"}\hlstd{)}
\hlkwd{dim}\hlstd{(tab)}
\end{alltt}
\begin{verbatim}
## [1] 333 161
\end{verbatim}
\end{kframe}
\end{knitrout}
\section{Comparison Bats}
\subsection{Cooper-bats results VS DGINN-bats results}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{plot}\hlstd{(tab}\hlopt{$}\hlstd{cooper.batsAverage_dNdS,} \hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{bats_omegaM0codeml)),}
\hlkwc{xlab}\hlstd{=}\hlstr{"Omega Cooper-bats"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"Omega DGINN-bats"}\hlstd{)}
\end{alltt}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning in xy.coords(x, y, xlabel, ylabel, log): NAs introduits lors de la conversion automatique}}\begin{alltt}
\hlkwd{abline}\hlstd{(}\hlnum{0}\hlstd{,}\hlnum{1}\hlstd{)}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/omegaM7M8bats-1}
\end{knitrout}
\subsection{Cooper-bats VS Hawkins-bats and DGINN-bats VS Hawkins-bats}
\textit{I don't think we have the omega values}
\section{Overlap}
\subsection{Data}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tmp}\hlkwb{<-}\hlkwd{na.omit}\hlstd{(tab[,}\hlkwd{c}\hlstd{(}\hlstr{"Gene.name"}\hlstd{,} \hlstr{"bats_codemlM7M8.p.value"}\hlstd{,} \hlstr{"hawkins_Positive.Selection..M8vM8a.p.value"}\hlstd{,} \hlstr{"cooper.batsM7.M8_p_value"}\hlstd{,} \hlstr{"bats_BUSTED"}\hlstd{,} \hlstr{"bats_BppM1M2"}\hlstd{,} \hlstr{"bats_BppM7M8"}\hlstd{,} \hlstr{"bats_codemlM1M2"}\hlstd{,} \hlstr{"bats_codemlM7M8"}\hlstd{)])}
\hlstd{tmp}\hlopt{$}\hlstd{bats_codemlM7M8.p.value}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tmp}\hlopt{$}\hlstd{bats_codemlM7M8.p.value))}
\end{alltt}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning: NAs introduits lors de la conversion automatique}}\begin{alltt}
\hlkwd{dim}\hlstd{(tmp)}
\end{alltt}
\begin{verbatim}
## [1] 174 9
\end{verbatim}
\end{kframe}
\end{knitrout}
174 genes (present in the 3 experiments)
\subsection{Mondrian}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{library}\hlstd{(Mondrian)}
\hlstd{monddata}\hlkwb{<-}\hlkwd{as.data.frame}\hlstd{(tmp}\hlopt{$}\hlstd{Gene.name)}
\hlstd{monddata}\hlopt{$}\hlstd{bats_hawkins}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(tmp}\hlopt{$}\hlstd{hawkins_Positive.Selection..M8vM8a.p.value}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{bats_cooper}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(tmp}\hlopt{$}\hlstd{cooper.batsM7.M8_p_value}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{dginntmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tmp}\hlopt{$}\hlstd{bats_codemlM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{, tmp}\hlopt{$}\hlstd{bats_codemlM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstd{bats_BppM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{, tmp}\hlopt{$}\hlstd{bats_BppM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{, tmp}\hlopt{$}\hlstd{bats_BUSTED}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlstd{monddata}\hlopt{$}\hlstd{bats_dginn}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginntmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlkwd{mondrian}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{],} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"DGINN >=3"}\hlstd{,} \hlstr{"hawkins"}\hlstd{,} \hlstr{"Cooper"}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/mondrianbats-1}
\begin{kframe}\begin{alltt}
\hlstd{monddata}\hlopt{$}\hlstd{bats_dginn}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginntmp}\hlopt{>=}\hlnum{4}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlkwd{mondrian}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{],} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"DGINN >=4"}\hlstd{,} \hlstr{"hawkins"}\hlstd{,} \hlstr{"Cooper"}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/mondrianbats-2}
\end{knitrout}
\subsection{subsetR}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{library}\hlstd{(UpSetR)}
\hlstd{upsetdata}\hlkwb{<-}\hlkwd{as.data.frame}\hlstd{(tmp}\hlopt{$}\hlstd{Gene.name)}
\hlstd{upsetdata}\hlopt{$}\hlstd{bats_hawkins}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(tmp}\hlopt{$}\hlstd{hawkins_Positive.Selection..M8vM8a.p.value}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{upsetdata}\hlopt{$}\hlstd{bats_cooper}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(tmp}\hlopt{$}\hlstd{cooper.batsM7.M8_p_value}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{upsetdata}\hlopt{$}\hlstd{bats_dginn}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginntmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlkwd{upset}\hlstd{(upsetdata,} \hlkwc{nsets} \hlstd{=} \hlnum{3}\hlstd{,} \hlkwc{matrix.color} \hlstd{=} \hlstr{"#DC267F"}\hlstd{,}
\hlkwc{main.bar.color} \hlstd{=} \hlstr{"#648FFF"}\hlstd{,} \hlkwc{sets.bar.color} \hlstd{=} \hlstr{"#FE6100"}\hlstd{)}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/subsetbats-1}
\begin{kframe}\begin{alltt}
\hlstd{upsetdata}\hlopt{$}\hlstd{bats_dginn}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginntmp}\hlopt{>=}\hlnum{4}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlkwd{upset}\hlstd{(upsetdata,} \hlkwc{nsets} \hlstd{=} \hlnum{3}\hlstd{,} \hlkwc{matrix.color} \hlstd{=} \hlstr{"#DC267F"}\hlstd{,}
\hlkwc{main.bar.color} \hlstd{=} \hlstr{"#648FFF"}\hlstd{,} \hlkwc{sets.bar.color} \hlstd{=} \hlstr{"#FE6100"}\hlstd{)}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/subsetbats-2}
\end{knitrout}
\end{document}
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment