\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{1st table}
Table containing the DGINN results for both Primates and bats. Conserve all genes.
\subsection{Primates}
\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{dginnT}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,}
\hlstr{"data/DGINN_202005281649summary_cleaned.csv"}\hlstd{),}
\hlkwc{fill}\hlstd{=T,} \hlkwc{h}\hlstd{=T,} \hlkwc{sep}\hlstd{=}\hlstr{","}\hlstd{)}
\hlkwd{dim}\hlstd{(dginnT)}
\end{alltt}
\begin{verbatim}
## [1] 412 27
\end{verbatim}
\begin{alltt}
\hlcom{#names(dginnT)}
\hlcom{# Rename the columns to include primate}
\hlkwd{names}\hlstd{(dginnT)}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"File"}\hlstd{,} \hlstr{"Name"}\hlstd{,} \hlstr{"Gene.name"}\hlstd{,} \hlstr{"GeneSize"}\hlstd{,}
\hlstr{"dginn-primate_NbSpecies"}\hlstd{,} \hlstr{"dginn-primate_omegaM0Bpp"}\hlstd{,}
\hlstr{"dginn-primate_omegaM0codeml"}\hlstd{,} \hlstr{"dginn-primate_BUSTED"}\hlstd{,}
\hlstr{"dginn-primate_BUSTED.p.value"}\hlstd{,} \hlstr{"dginn-primate_MEME.NbSites"}\hlstd{,}
\hlstr{"dginn-primate_MEME.PSS"}\hlstd{,} \hlstr{"dginn-primate_BppM1M2"}\hlstd{,}
\hlstr{"dginn-primate_BppM1M2.p.value"}\hlstd{,} \hlstr{"dginn-primate_BppM1M2.NbSites"}\hlstd{,}
\hlstr{"dginn-primate_BppM1M2.PSS"}\hlstd{,} \hlstr{"dginn-primate_BppM7M8"}\hlstd{,}
\hlstr{"dginn-primate_BppM7M8.p.value"}\hlstd{,} \hlstr{"dginn-primate_BppM7M8.NbSites"}\hlstd{,}
\hlstr{"dginn-primate_BppM7M8.PSS"}\hlstd{,} \hlstr{"dginn-primate_codemlM1M2"}\hlstd{,}
\hlstr{"dginn-primate_codemlM1M2.p.value"}\hlstd{,} \hlstr{"dginn-primate_codemlM1M2.NbSites"}\hlstd{,}
\hlstr{"dginn-primate_codemlM1M2.PSS"}\hlstd{,} \hlstr{"dginn-primate_codemlM7M8"}\hlstd{,}
\hlstr{"dginn-primate_codemlM7M8.p.value"}\hlstd{,} \hlstr{"dginn-primate_codemlM7M8.NbSites"}\hlstd{,}
\hlstr{"dginn-primate_codemlM7M8.PSS"}\hlstd{)}
\end{alltt}
\end{kframe}
\end{knitrout}
Add SELENOS
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{selenos}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,}
\hlstr{"data/resSELENOS.tab"}\hlstd{))}
\hlcom{# liste of colonne}
\hlstd{colonnes}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"File"}\hlstd{,} \hlstr{"Name"}\hlstd{,} \hlstr{"Gene"}\hlstd{,} \hlstr{"GeneSize"}\hlstd{,}
\hlstr{"NbSpecies"}\hlstd{,} \hlstr{"omegaM0Bpp"}\hlstd{,} \hlstr{"omegaM0codeml"}\hlstd{,} \hlstr{"BUSTED"}\hlstd{,}
\hlstr{"BUSTED_p.value"}\hlstd{,} \hlstr{"MEME_NbSites"}\hlstd{,} \hlstr{"MEME_PSS"}\hlstd{,} \hlstr{"BppM1M2"}\hlstd{,}
\hlstr{"BppM1M2_p.value"}\hlstd{,} \hlstr{"BppM1M2_NbSites"}\hlstd{,} \hlstr{"BppM1M2_PSS"}\hlstd{,} \hlstr{"BppM7M8"}\hlstd{,}
\hlstr{"BppM7M8_p.value"}\hlstd{,} \hlstr{"BppM7M8_NbSites"}\hlstd{,} \hlstr{"BppM7M8_PSS"}\hlstd{,}\hlstr{"codemlM1M2"}\hlstd{,}
\hlstr{"codemlM1M2_p.value"}\hlstd{,} \hlstr{"codemlM1M2_NbSites"}\hlstd{,} \hlstr{"codemlM1M2_PSS"}\hlstd{,} \hlstr{"codemlM7M8"}\hlstd{,}
\hlstr{"codemlM7M8_p.value"}\hlstd{,} \hlstr{"codemlM7M8_NbSites"}\hlstd{,} \hlstr{"codemlM7M8_PSS"}\hlstd{)}
\hlstd{selenos}\hlkwb{<-}\hlstd{selenos[,colonnes]}
\end{alltt}
\end{kframe}
\end{knitrout}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{names}\hlstd{(selenos)}\hlkwb{<-}\hlkwd{names}\hlstd{(dginnT)}
\hlstd{selenos[,}\hlnum{6}\hlstd{]}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(selenos[,}\hlnum{6}\hlstd{])}
\hlstd{selenos[,}\hlnum{9}\hlstd{]}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(selenos[,}\hlnum{9}\hlstd{])}
\hlstd{selenos[,}\hlnum{11}\hlstd{]}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(selenos[,}\hlnum{11}\hlstd{])}
\hlstd{selenos[,}\hlnum{13}\hlstd{]}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(selenos[,}\hlnum{13}\hlstd{])}
\hlstd{selenos[,}\hlnum{17}\hlstd{]}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(selenos[,}\hlnum{17}\hlstd{])}
\hlstd{selenos[,}\hlnum{21}\hlstd{]}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(selenos[,}\hlnum{21}\hlstd{])}
\hlstd{selenos[,}\hlnum{25}\hlstd{]}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(selenos[,}\hlnum{25}\hlstd{])}
\hlcom{## convertir les pvalues}
\hlstd{dginnT}\hlkwb{<-}\hlkwd{rbind}\hlstd{(dginnT, selenos)}
\end{alltt}
\end{kframe}
\end{knitrout}
\subsection{Bats}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlcom{# original table}
\hlstd{dginnbats}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,}
\hlstr{"data/DGINN_202005281339summary_cleaned-LE201108.txt"}\hlstd{),}
\hlkwc{fill}\hlstd{=T,} \hlkwc{h}\hlstd{=T)}
\hlcom{# rerun on corrected alignment}
\hlstd{dginnbatsnew}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,}
\hlstr{"data/DGINN_202011262248_hyphybpp-202012192053_codeml-summary.txt"}\hlstd{),}
\hlkwc{fill}\hlstd{=T,} \hlkwc{h}\hlstd{=T)}
\end{alltt}
\end{kframe}
\end{knitrout}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlcom{# Add both columns }
\hlstd{dginnbatsnew}\hlopt{$}\hlstd{Lucie.s.comments}\hlkwb{<-}\hlstr{""}
\hlstd{dginnbatsnew}\hlopt{$}\hlstd{Action.taken}\hlkwb{<-}\hlstr{""}
\hlcom{# Homogenize column names}
\hlstd{dginnbats}\hlopt{$}\hlstd{BUSTED_p.value}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{BUSTED.p.value}
\hlstd{dginnbats}\hlopt{$}\hlstd{MEME_NbSites}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{MEME.NbSites}
\hlstd{dginnbats}\hlopt{$}\hlstd{MEME_PSS}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{MEME.PSS}
\hlstd{dginnbats}\hlopt{$}\hlstd{BppM1M2_p.value}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{BppM1M2.p.value}
\hlstd{dginnbats}\hlopt{$}\hlstd{BppM1M2_NbSites}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{BppM1M2.NbSites}
\hlstd{dginnbats}\hlopt{$}\hlstd{BppM1M2_PSS}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{BppM1M2.PSS}
\hlstd{dginnbats}\hlopt{$}\hlstd{BppM7M8_p.value}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{BppM7M8.p.value}
\hlstd{dginnbats}\hlopt{$}\hlstd{BppM7M8_NbSites}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{BppM7M8.NbSites}
\hlstd{dginnbats}\hlopt{$}\hlstd{BppM7M8_PSS}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{BppM7M8.PSS}
\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM1M2_p.value}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM1M2.p.value}
\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM1M2_NbSites}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM1M2.NbSites}
\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM1M2_PSS}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM1M2.PSS}
\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM7M8_p.value}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM7M8.p.value}
\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM7M8_NbSites}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM7M8.NbSites}
\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM7M8_PSS}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{codemlM7M8.PSS}
\end{alltt}
\end{kframe}
\end{knitrout}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlcom{# Order columns in the same order in both tables}
\hlstd{dginnbats}\hlkwb{<-}\hlstd{dginnbats[,}\hlkwd{names}\hlstd{(dginnbatsnew)]}
\hlkwd{names}\hlstd{(dginnbatsnew)} \hlopt{%in%} \hlkwd{names}\hlstd{(dginnbats)}
\end{alltt}
\begin{verbatim}
## [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
## [27] TRUE TRUE TRUE
\end{verbatim}
\begin{alltt}
\hlkwd{names}\hlstd{(dginnbats)}\hlopt{==}\hlkwd{names}\hlstd{(dginnbatsnew)}
\end{alltt}
\begin{verbatim}
## [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
## [27] TRUE TRUE TRUE
\end{verbatim}
\begin{alltt}
\hlcom{# Put RIPK aside}
\hlstd{ripk1}\hlkwb{<-}\hlstd{dginnbatsnew[dginnbatsnew}\hlopt{$}\hlstd{Gene}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlnum{1}\hlopt{:}\hlnum{27}\hlstd{]}
\hlcom{# Add it to primate table}
\hlkwd{names}\hlstd{(ripk1)}\hlkwb{<-}\hlkwd{names}\hlstd{(dginnT)}
\hlstd{ripk1}\hlopt{$}\hlstd{`dginn-primate_omegaM0Bpp`}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(ripk1}\hlopt{$}\hlstd{`dginn-primate_omegaM0Bpp`)}
\hlstd{ripk1}\hlopt{$}\hlstd{`dginn-primate_BUSTED.p.value`}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(ripk1}\hlopt{$}\hlstd{`dginn-primate_BUSTED.p.value`)}
\hlstd{ripk1}\hlopt{$}\hlstd{`dginn-primate_BppM1M2.p.value`}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(ripk1}\hlopt{$}\hlstd{`dginn-primate_BppM1M2.p.value`)}
\hlstd{ripk1}\hlopt{$}\hlstd{`dginn-primate_BppM7M8.p.value`}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(ripk1}\hlopt{$}\hlstd{`dginn-primate_BppM7M8.p.value`)}
\hlstd{dginnT}\hlkwb{<-}\hlkwd{rbind}\hlstd{(dginnT, ripk1)}
\hlcom{## Remove it Ripk1 from bats}
\hlstd{dginnbatsnew}\hlkwb{<-}\hlstd{dginnbatsnew[dginnbatsnew}\hlopt{$}\hlstd{Gene}\hlopt{!=}\hlstr{"RIPK1"}\hlstd{,]}
\hlcom{## suppress redundant lines}
\hlstd{dginnbats}\hlkwb{<-}\hlstd{dginnbats[(dginnbats}\hlopt{$}\hlstd{Gene} \hlopt{%in%} \hlstd{dginnbatsnew}\hlopt{$}\hlstd{Gene)}\hlopt{==}\hlnum{FALSE}\hlstd{,]}
\hlkwd{names}\hlstd{(dginnbatsnew)}\hlkwb{<-}\hlkwd{names}\hlstd{(dginnbats)}
\hlcom{## replace by new data}
\hlstd{dginnbatsnew}\hlopt{$}\hlstd{omegaM0Bpp}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(dginnbatsnew}\hlopt{$}\hlstd{omegaM0Bpp)}
\hlstd{dginnbatsnew}\hlopt{$}\hlstd{BppM1M2_p.value}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(dginnbatsnew}\hlopt{$}\hlstd{BppM1M2_p.value)}
\hlstd{dginnbatsnew}\hlopt{$}\hlstd{BppM7M8_p.value}\hlkwb{<-}\hlkwd{as.factor}\hlstd{(dginnbatsnew}\hlopt{$}\hlstd{BppM7M8_p.value)}
\hlstd{dginnbats}\hlkwb{<-}\hlkwd{rbind}\hlstd{(dginnbats, dginnbatsnew)}
\hlkwd{names}\hlstd{(dginnbats)}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"bats_File"}\hlstd{,} \hlstr{"bats_Name"}\hlstd{,} \hlstr{"Gene.name"}\hlstd{,} \hlkwd{paste0}\hlstd{(}\hlstr{"bats_"}\hlstd{,}
\hlkwd{names}\hlstd{(dginnbats)[}\hlopt{-}\hlstd{(}\hlnum{1}\hlopt{:}\hlnum{3}\hlstd{)]))}
\hlkwd{names}\hlstd{(dginnbats)}
\end{alltt}
\begin{verbatim}
## [1] "bats_File" "bats_Name" "Gene.name" "bats_GeneSize" "bats_NbSpecies"
## [6] "bats_omegaM0Bpp" "bats_omegaM0codeml" "bats_BUSTED" "bats_BUSTED_p.value" "bats_MEME_NbSites"
## [11] "bats_MEME_PSS" "bats_BppM1M2" "bats_BppM1M2_p.value" "bats_BppM1M2_NbSites" "bats_BppM1M2_PSS"
## [16] "bats_BppM7M8" "bats_BppM7M8_p.value" "bats_BppM7M8_NbSites" "bats_BppM7M8_PSS" "bats_codemlM1M2"
## [21] "bats_codemlM1M2_p.value" "bats_codemlM1M2_NbSites" "bats_codemlM1M2_PSS" "bats_codemlM7M8" "bats_codemlM7M8_p.value"
## [26] "bats_codemlM7M8_NbSites" "bats_codemlM7M8_PSS" "bats_Lucie.s.comments" "bats_Action.taken"
\end{verbatim}
\end{kframe}
\end{knitrout}
\subsection{Merged table}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlcom{#tidy.opts = list(width.cutoff = 60)}
\hlkwd{dim}\hlstd{(dginnT)}
\end{alltt}
\begin{verbatim}
## [1] 414 27
\end{verbatim}
\begin{alltt}
\hlcom{#dginnT$Gene.name}
\hlkwd{dim}\hlstd{(dginnbats)}
\end{alltt}
\begin{verbatim}
## [1] 353 29
\end{verbatim}
\begin{alltt}
\hlcom{#dginnbats$Gene.name}
\end{alltt}
\end{kframe}
\end{knitrout}
Manual corrections:
TMPRSS2 in bats
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{dginnbats[dginnbats}\hlopt{$}\hlstd{Gene.name}\hlopt{==}\hlstr{"TMPRSS2"}\hlstd{,]}
\end{alltt}
\begin{verbatim}
## bats_File bats_Name Gene.name
## 2810 TMPRSS2_bat_same_mafft_prank TMPRSS2 TMPRSS2
## 2910 TMPRSS2_bat_select_cut_mafft_prank TMPRSS2 TMPRSS2
## bats_GeneSize bats_NbSpecies bats_omegaM0Bpp
## 2810 1174 12 0.140290584008726
## 2910 574 12 0.129489038364869
## bats_omegaM0codeml bats_BUSTED bats_BUSTED_p.value
## 2810 0.145 N 0.9333
## 2910 0.127 N 0.9358
## bats_MEME_NbSites
## 2810 12
## 2910 19
## bats_MEME_PSS
## 2810 630, 644, 649, 688, 775, 888, 921, 1003, 1051, 1055, 1066, 1173
## 2910 59, 73, 78, 108, 115, 117, 121, 133, 144, 241, 259, 288, 321, 403, 421, 451, 455, 466, 573
## bats_BppM1M2 bats_BppM1M2_p.value bats_BppM1M2_NbSites
## 2810 N 0.999999010422051 0
## 2910 N 0.999999906049202 0
## bats_BppM1M2_PSS bats_BppM7M8 bats_BppM7M8_p.value
## 2810 na N 0.621882294670985
## 2910 na N 0.334893426994811
## bats_BppM7M8_NbSites bats_BppM7M8_PSS bats_codemlM1M2
## 2810 0 na N
## 2910 0 na N
## bats_codemlM1M2_p.value bats_codemlM1M2_NbSites
## 2810 1.0 0
## 2910 1.0 0
## bats_codemlM1M2_PSS bats_codemlM7M8 bats_codemlM7M8_p.value
## 2810 na N 0.788991288016829
## 2910 na N 0.4210515526274131
## bats_codemlM7M8_NbSites bats_codemlM7M8_PSS
## 2810 0 na
## 2910 0 na
## bats_Lucie.s.comments bats_Action.taken
## 2810
## 2910
\end{verbatim}
\begin{alltt}
\hlcom{# keeping the uncut one}
\hlcom{# renaming the other one TMPRSS2_cut}
\hlstd{dginnbats}\hlopt{$}\hlstd{Gene.name}\hlkwb{<-}\hlkwd{as.character}\hlstd{(dginnbats}\hlopt{$}\hlstd{Gene.name)}
\hlstd{dginnbats[dginnbats}\hlopt{$}\hlstd{bats_File}\hlopt{==}\hlstr{"TMPRSS2_bat_select_cut_mafft_prank"}\hlstd{,}\hlstr{"Gene.name"}\hlstd{]}\hlkwb{<-}\hlstr{"TMPRSS2_cut"}
\end{alltt}
\end{kframe}
\end{knitrout}
RIPK1: ANcestral version kept, suppress it "RIPK1\_sequences\_filtered\_longestORFs\_mafft\_mincov\_prank"
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{dginnT}\hlkwb{<-}\hlstd{dginnT[dginnT}\hlopt{$}\hlstd{File}\hlopt{!=}\hlstr{"RIPK1_sequences_filtered_longestORFs_mafft_mincov_prank"}\hlstd{,]}
\end{alltt}
\end{kframe}
\end{knitrout}
REEP6 eA et B
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{dginnbats}\hlopt{$}\hlstd{Gene.name}\hlkwb{<-}\hlkwd{as.character}\hlstd{(dginnbats}\hlopt{$}\hlstd{Gene.name)}
\hlstd{dginnbats[dginnbats}\hlopt{$}\hlstd{bats_File}\hlopt{==}\hlstr{"REEP6_sequences_filtered_longestORFs_D210gp1_prank"}\hlstd{,} \hlstr{"Gene.name"}\hlstd{]}\hlkwb{<-}\hlstr{"REEP6_old"}
\hlstd{dginnbats[dginnbats}\hlopt{$}\hlstd{bats_File}\hlopt{==}\hlstr{"REEP6_LA_bat_select_mafft_prank"}\hlstd{,} \hlstr{"Gene.name"}\hlstd{]}\hlkwb{<-}\hlstr{"REEP6"}
\hlstd{dginnbats[dginnbats}\hlopt{$}\hlstd{bats_File}\hlopt{==}\hlstr{"REEP6_LB_bat_select_mafft_prank"}\hlstd{,} \hlstr{"Gene.name"}\hlstd{]}\hlkwb{<-}\hlstr{"REEP6_like"}
\end{alltt}
\end{kframe}
\end{knitrout}
GNG5
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{dginnT}\hlopt{$}\hlstd{Gene.name}\hlkwb{<-}\hlkwd{as.character}\hlstd{(dginnT}\hlopt{$}\hlstd{Gene.name)}
\hlstd{dginnT[dginnT}\hlopt{$}\hlstd{File}\hlopt{==}\hlstr{"GNG5_sequences_filtered_longestORFs_D189gp2_prank"}\hlstd{,} \hlstr{"Gene.name"}\hlstd{]}\hlkwb{<-}\hlstr{"GNG5_like"}
\end{alltt}
\end{kframe}
\end{knitrout}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{dim}\hlstd{(dginnbats)}
\end{alltt}
\begin{verbatim}
## [1] 353 29
\end{verbatim}
\begin{alltt}
\hlkwd{dim}\hlstd{(dginnT)}
\end{alltt}
\begin{verbatim}
## [1] 413 27
\end{verbatim}
\begin{alltt}
\hlcom{# genes in common}
\hlstd{common}\hlkwb{<-}\hlstd{dginnT}\hlopt{$}\hlstd{Gene.name[dginnT}\hlopt{$}\hlstd{Gene.name} \hlopt{%in%} \hlstd{dginnbats}\hlopt{$}\hlstd{Gene.name]}
\hlstd{common}
\end{alltt}
\begin{verbatim}
## [1] "AAR2" "AASS" "AATF" "ABCC1" "ACAD9"
## [6] "ACADM" "ACE2" "ACSL3" "ADAM9" "ADAMTS1"
## [11] "AGPS" "AKAP8" "AKAP8L" "AKAP9" "ALG11"
## [16] "ALG5" "ALG8" "ANO6" "AP2A2" "AP2M1"
## [21] "AP3B1" "ARF6" "ATE1" "ATP13A3" "ATP1B1"
## [26] "ATP6AP1" "ATP6V1A" "BAG5" "BCKDK" "BRD2"
## [31] "BRD4" "BZW2" "CCDC86" "CDK5RAP2" "CENPF"
## [36] "CEP112" "CEP135" "CEP250" "CEP350" "CEP68"
## [41] "CHMP2A" "CHPF" "CHPF2" "CISD3" "CIT"
## [46] "CLCC1" "CLIP4" "CNTRL" "COL6A1" "COLGALT1"
## [51] "COMT" "COQ8B" "CRTC3" "CSDE1" "CSNK2A2"
## [56] "CSNK2B" "CUL2" "CWC27" "CYB5B" "DCAF7"
## [61] "DCAKD" "DCTPP1" "DDX10" "DDX21" "DNAJC11"
## [66] "DNAJC19" "DNMT1" "DPH5" "DPY19L1" "ECSIT"
## [71] "EDEM3" "EIF4E2" "EIF4H" "ELOC" "EMC1"
## [76] "ERC1" "ERGIC1" "ERLEC1" "ERMP1" "ERO1B"
## [81] "ERP44" "ETFA" "EXOSC2" "EXOSC3" "EXOSC5"
## [86] "EXOSC8" "F2RL1" "FAM162A" "FAM8A1" "FAM98A"
## [91] "FAR2" "FASTKD5" "FBLN5" "FBN1" "FBN2"
## [96] "FBXL12" "FKBP10" "FKBP15" "FKBP7" "FOXRED2"
## [101] "FYCO1" "G3BP1" "G3BP2" "GCC1" "GCC2"
## [106] "GDF15" "GFER" "GGCX" "GGH" "GHITM"
## [111] "GIGYF2" "GLA" "GNB1" "GNG5" "GOLGA2"
## [116] "GOLGA3" "GOLGA7" "GOLGB1" "GORASP1" "GPAA1"
## [121] "GPX1" "GRIPAP1" "GRPEL1" "GTF2F2" "HDAC2"
## [126] "HEATR3" "HECTD1" "HMOX1" "HOOK1" "HS2ST1"
## [131] "HS6ST2" "HSBP1" "HYOU1" "IDE" "IL17RA"
## [136] "IMPDH2" "INHBE" "INTS4" "ITGB1" "JAKMIP1"
## [141] "LARP1" "LARP4B" "LARP7" "LMAN2" "LOX"
## [146] "MAP7D1" "MARK1" "MARK2" "MARK3" "MAT2B"
## [151] "MDN1" "MEPCE" "MIB1" "MIPOL1" "MOGS"
## [156] "MOV10" "MPHOSPH10" "MRPS2" "MRPS25" "MRPS27"
## [161] "MRPS5" "MARC1" "MTCH1" "MYCBP2" "NARS2"
## [166] "NAT14" "NDFIP2" "NDUFAF1" "NDUFAF2" "NDUFB9"
## [171] "NEK9" "NEU1" "NGDN" "NGLY1" "NIN"
## [176] "NINL" "NLRX1" "NOL10" "NPC2" "NPTX1"
## [181] "NSD2" "NUP210" "NUP214" "NUP54" "NUP58"
## [186] "NUP62" "NUP88" "NUP98" "NUTF2" "OS9"
## [191] "PABPC1" "PABPC4" "PCNT" "PCSK6" "PCSK5"
## [196] "PDE4DIP" "PDZD11" "PIGO" "PIGS" "PITRM1"
## [201] "PKP2" "PLAT" "PLD3" "PLEKHA5" "PLEKHF2"
## [206] "PLOD2" "PMPCA" "PMPCB" "POFUT1" "KDELC1"
## [211] "KDELC2" "POLA1" "POLA2" "POR" "PPIL3"
## [216] "PPT1" "PRIM1" "PRIM2" "PRKACA" "PRKAR2A"
## [221] "PRKAR2B" "PRRC2B" "PSMD8" "PTBP2" "PTGES2"
## [226] "PUSL1" "PVR" "QSOX2" "RAB10" "RAB14"
## [231] "RAB18" "RAB1A" "RAB2A" "RAB5C" "RAB7A"
## [236] "RAB8A" "RAE1" "RALA" "RAP1GDS1" "RBM28"
## [241] "RBM41" "RBX1" "RDX" "REEP5" "REEP6"
## [246] "RETREG3" "RHOA" "RNF41" "RPL36" "RRP9"
## [251] "RTN4" "SAAL1" "SBNO1" "SCAP" "SCARB1"
## [256] "SCCPDH" "SDF2" "SEPSECS" "SIL1" "SIRT5"
## [261] "SLC25A21" "SLC27A2" "SLC30A6" "SLC30A7" "SLC30A9"
## [266] "SLC44A2" "SLC9A3R1" "SLU7" "SMOC1" "SNIP1"
## [271] "SPART" "SRP19" "SRP54" "SRP72" "STC2"
## [276] "STOM" "STOML2" "SUN2" "TAPT1" "TARS2"
## [281] "TBCA" "TBK1" "TBKBP1" "TCF12" "THTPA"
## [286] "TIMM10" "TIMM10B" "TIMM29" "TIMM8B" "TIMM9"
## [291] "TLE1" "TLE3" "TM2D3" "TMED5" "TMEM39B"
## [296] "TMEM97" "TMPRSS2" "TOMM70" "TOR1A" "TOR1AIP1"
## [301] "TRIM59" "TRMT1" "TUBGCP2" "TUBGCP3" "TYSND1"
## [306] "UBAP2" "UBAP2L" "UBXN8" "UGGT2" "UPF1"
## [311] "USP54" "VPS11" "VPS39" "WASHC4" "WFS1"
## [316] "YIF1A" "ZC3H18" "ZC3H7A" "ZDHHC5" "ZNF318"
## [321] "ZNF503" "ZYG11B" "SELENOS" "RIPK1"
\end{verbatim}
\begin{alltt}
\hlkwd{length}\hlstd{(dginnT}\hlopt{$}\hlstd{Gene.name[dginnT}\hlopt{$}\hlstd{Gene.name} \hlopt{%in%} \hlstd{dginnbats}\hlopt{$}\hlstd{Gene.name])}
\end{alltt}
\begin{verbatim}
## [1] 324
\end{verbatim}
\begin{alltt}
\hlcom{# genes only in primates}
\hlstd{onlyprimates}\hlkwb{<-}\hlstd{dginnT}\hlopt{$}\hlstd{Gene.name[(dginnT}\hlopt{$}\hlstd{Gene.name} \hlopt{%in%} \hlstd{dginnbats}\hlopt{$}\hlstd{Gene.name)}\hlopt{==}\hlnum{FALSE}\hlstd{]}
\hlstd{onlyprimates}
\end{alltt}
\begin{verbatim}
## [1] "ADAM9[0-3120]" "ADAM9[3119-3927]" "ATP5MGL"
## [4] "BCS1L" "C1H1ORF50" "CEP135[0-3264]"
## [7] "CEP135[3263-3678]" "CEP43" "COQ8A"
## [10] "CSNK2A1" "CSNK2B[0-609]" "CSNK2B[608-2568]"
## [13] "CYB5R3" "CYB5R1" "DDX21[0-717]"
## [16] "DDX21[716-2538]" "DDX50" "DNAJC15"
## [19] "DPH5[0-702]" "DPH5[701-1326]" "DPY19L2"
## [22] "EXOSC3[0-1446]" "EXOSC3[1445-1980]" "FBN3"
## [25] "GNB4" "GNB2" "GNB3"
## [28] "GNG5_like" "GOLGA7[0-312]" "GOLGA7[311-549]"
## [31] "GPX1[0-1218]" "GPX1[1217-2946]" "HDAC1"
## [34] "HS6ST3" "IMPDH1" "ITGB1[0-2328]"
## [37] "ITGB1[2327-2844]" "LMAN2L" "MRPS5[0-1569]"
## [40] "MRPS5[1568-3783]" "MARC2" "MGRN1"
## [43] "NDFIP2[0-768]" "NDFIP2[767-1314]" "NDUFAF2[0-258]"
## [46] "NDUFAF2[257-744]" "NUP58[0-1824]" "NUP58[1823-2367]"
## [49] "PABPC3" "POTPABPC1" "PABPC4L"
## [52] "PABPC5" "PRIM2[0-1071]" "PRIM2[1070-1902]"
## [55] "PRKACB" "PRKACG" "PTGES2[0-1587]"
## [58] "PTGES2[1586-2202]" "RAB8B" "RAB13"
## [61] "RAB18[0-855]" "RAB18[854-1815]" "RAB2B"
## [64] "RAB5A" "RAB5B" "RAB15"
## [67] "RALB" "EZR" "EZR[0-1458]"
## [70] "EZR[1457-3771]" "MSN" "RHOB"
## [73] "RHOC" "SLC44A2[0-2577]" "SLC44A2[2576-3657]"
## [76] "SRP72[0-2604]" "SRP72[2603-3417]" "STOM[0-1047]"
## [79] "STOM[1046-1800]" "STOML3" "TLE4"
## [82] "TLE2" "TLE2[0-1302]" "TLE2[1301-3987]"
## [85] "AES" "TOR1B" "WFS1[0-2346]"
## [88] "WFS1[2345-3216]" "YIF1B"
\end{verbatim}
\begin{alltt}
\hlkwd{length}\hlstd{(dginnT}\hlopt{$}\hlstd{Gene.name[(dginnT}\hlopt{$}\hlstd{Gene.name} \hlopt{%in%} \hlstd{dginnbats}\hlopt{$}\hlstd{Gene.name)}\hlopt{==}\hlnum{FALSE}\hlstd{])}
\end{alltt}
\begin{verbatim}
## [1] 89
\end{verbatim}
\begin{alltt}
\hlcom{# genes only in bats}
\hlstd{onlybats}\hlkwb{<-}\hlstd{dginnbats}\hlopt{$}\hlstd{Gene.name[(dginnbats}\hlopt{$}\hlstd{Gene.name} \hlopt{%in%} \hlstd{dginnT}\hlopt{$}\hlstd{Gene.name)}\hlopt{==}\hlnum{FALSE}\hlstd{]}
\hlstd{onlybats}
\end{alltt}
\begin{verbatim}
## [1] "ADAM9[0-2769]" "ADAM9[2768-3030]" "ARL6IP6"
## [4] "ATP5MG" "BCS1" "CUNH1ORF50"
## [7] "CYB5BR3" "IDE[0-2343]" "IDE[2342-3240]"
## [10] "IDE[3239-4911]" "MFGE8" "PTGES2[0-513]"
## [13] "PTGES2[512-2070]" "REEP6_old" "SCARB1[0-2004]"
## [16] "SCARB1[2003-2289]" "SELENOS[0-927]" "SELENOS[926-1137]"
## [19] "SIGMAR1" "SLC44A2[0-2820]" "SLC44A2[2819-3792]"
## [22] "TLE5" "USP13" "ZC3H18[0-1101]"
## [25] "ZC3H18[1100-3678]" "FGFR1OP" "ELOB"
## [28] "REEP6_like" "TMPRSS2_cut"
\end{verbatim}
\begin{alltt}
\hlkwd{length}\hlstd{(dginnbats}\hlopt{$}\hlstd{Gene.name[(dginnbats}\hlopt{$}\hlstd{Gene.name} \hlopt{%in%} \hlstd{dginnT}\hlopt{$}\hlstd{Gene.name)}\hlopt{==}\hlnum{FALSE}\hlstd{])}
\end{alltt}
\begin{verbatim}
## [1] 29
\end{verbatim}
\end{kframe}
\end{knitrout}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tab}\hlkwb{<-}\hlkwd{merge}\hlstd{(dginnT, dginnbats,} \hlkwc{by}\hlstd{=}\hlstr{"Gene.name"}\hlstd{,} \hlkwc{all.x}\hlstd{=T,} \hlkwc{all.y}\hlstd{=T)}
\hlkwd{dim}\hlstd{(tab)}
\end{alltt}
\begin{verbatim}
## [1] 442 55
\end{verbatim}
\begin{alltt}
\hlcom{# add column "shared"/"only bats"/"only primates"}
\hlstd{tab}\hlopt{$}\hlstd{status}\hlkwb{<-}\hlstr{""}
\hlstd{tab}\hlopt{$}\hlstd{status[tab}\hlopt{$}\hlstd{Gene.name} \hlopt{%in%} \hlstd{common]}\hlkwb{<-}\hlstr{"shared"}
\hlstd{tab}\hlopt{$}\hlstd{status[tab}\hlopt{$}\hlstd{Gene.name} \hlopt{%in%} \hlstd{onlyprimates]}\hlkwb{<-}\hlstr{"onlyprimates"}
\hlstd{tab}\hlopt{$}\hlstd{status[tab}\hlopt{$}\hlstd{Gene.name} \hlopt{%in%} \hlstd{onlybats]}\hlkwb{<-}\hlstr{"onlybats"}
\hlkwd{table}\hlstd{(tab}\hlopt{$}\hlstd{status)}
\end{alltt}
\begin{verbatim}
##
## onlybats onlyprimates shared
## 29 89 324
\end{verbatim}
\begin{alltt}
\hlkwd{write.table}\hlstd{(tab,} \hlstr{"covid_comp_alldginn.txt"}\hlstd{,} \hlkwc{sep}\hlstd{=}\hlstr{"\textbackslash{}t"}\hlstd{)}
\end{alltt}
\end{kframe}
\end{knitrout}
\section{Complete data}
Merge the previous tab with J Young's original table.
\subsection{Read the original Young table}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{young}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,}
\hlstr{"data/COVID_PAMLresults_332hits_plusBatScreens_2020_Apr14.csv"}\hlstd{),}
\hlkwc{fill}\hlstd{=T,} \hlkwc{h}\hlstd{=T,} \hlkwc{dec}\hlstd{=}\hlstr{","}\hlstd{)}
\hlkwd{dim}\hlstd{(young)}
\end{alltt}
\begin{verbatim}
## [1] 332 84
\end{verbatim}
\begin{alltt}
\hlstd{young}\hlopt{$}\hlstd{PreyGene}\hlkwb{<-}\hlkwd{as.character}\hlstd{(young}\hlopt{$}\hlstd{PreyGene)}
\hlstd{young}\hlopt{$}\hlstd{PreyGene[young}\hlopt{$}\hlstd{PreyGene}\hlopt{==}\hlstr{"MTARC1"}\hlstd{]}\hlkwb{<-}\hlstr{"MARC1"}
\end{alltt}
\end{kframe}
\end{knitrout}
\subsection{Read the gene names conversion table}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{usthem}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,}
\hlstr{"/data/table_gene_name_correspondence.csv"}\hlstd{),}
\hlkwc{h}\hlstd{=T,} \hlkwc{sep}\hlstd{=}\hlstr{";"}\hlstd{)}
\hlstd{young[young}\hlopt{$}\hlstd{PreyGene} \hlopt{%in%} \hlstd{usthem}\hlopt{$}\hlstd{Us,} \hlkwd{c}\hlstd{(}\hlstr{"PreyGene"}\hlstd{,} \hlstr{"Gene.name"}\hlstd{)]}
\end{alltt}
\begin{verbatim}
## PreyGene Gene.name
## 57 TIMM29 C19orf52
## 107 ERO1B ERO1LB
## 111 NUP58 NUPL1
## 115 COQ8B ADCK4
## 118 SPART SPG20
## 131 NSD2 WHSC1
## 149 RETREG3 FAM134C
## 158 MARC1 01/03/2020
## 197 ELOC TCEB1
## 268 TOMM70 TOMM70A
## 269 WASHC4 KIAA1033
\end{verbatim}
\begin{alltt}
\hlstd{usthem[}\hlkwd{order}\hlstd{(usthem}\hlopt{$}\hlstd{Us),]}
\end{alltt}
\begin{verbatim}
## Us Else
## 1 COQ8B ADCK4
## 2 ELOC TCEB1
## 3 ERO1B ERO1LB
## 4 MARC1 MTARC1
## 5 NSD2 WHSC1
## 6 NUP58 NUPL1
## 7 PCSK5
## 8 RETREG3 FAM134C
## 9 SPART SPG20
## 10 TIMM29 C19orf52
## 11 TOMM70 TOMM70A
## 12 WASHC4 KIAA1033
\end{verbatim}
\end{kframe}
\end{knitrout}
\subsection{Merge Young and DGINN table}
\textbf{Based on which column?}
How many genes in the Young table are not in the DGINN table. And who are they?
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{table}\hlstd{(young}\hlopt{$}\hlstd{PreyGene} \hlopt{%in%} \hlstd{tab}\hlopt{$}\hlstd{Gene.name)}
\end{alltt}
\begin{verbatim}
##
## FALSE TRUE
## 3 329
\end{verbatim}
\begin{alltt}
\hlstd{young[(young}\hlopt{$}\hlstd{PreyGene} \hlopt{%in%} \hlstd{tab}\hlopt{$}\hlstd{Gene.name)}\hlopt{==}\hlnum{FALSE}\hlstd{,} \hlstr{"PreyGene"}\hlstd{]}
\end{alltt}
\begin{verbatim}
## [1] "POGLUT3" "POGLUT2" "C1orf50"
\end{verbatim}
\begin{alltt}
\hlstd{tab[(tab}\hlopt{$}\hlstd{Gene.name} \hlopt{%in%} \hlstd{young}\hlopt{$}\hlstd{PreyGene)}\hlopt{==}\hlnum{FALSE}\hlstd{,} \hlstr{"Gene.name"}\hlstd{]}
\end{alltt}
\begin{verbatim}
## [1] "ACE2" "ADAM9[0-2769]" "ADAM9[0-3120]"
## [4] "ADAM9[2768-3030]" "ADAM9[3119-3927]" "AES"
## [7] "ATP5MGL" "BCS1" "C1H1ORF50"
## [10] "CEP135[0-3264]" "CEP135[3263-3678]" "COQ8A"
## [13] "CSNK2A1" "CSNK2B[0-609]" "CSNK2B[608-2568]"
## [16] "CUNH1ORF50" "CYB5BR3" "CYB5R1"
## [19] "DDX21[0-717]" "DDX21[716-2538]" "DDX50"
## [22] "DNAJC15" "DPH5[0-702]" "DPH5[701-1326]"
## [25] "DPY19L2" "EXOSC3[0-1446]" "EXOSC3[1445-1980]"
## [28] "EZR" "EZR[0-1458]" "EZR[1457-3771]"
## [31] "FBN3" "FGFR1OP" "GNB2"
## [34] "GNB3" "GNB4" "GNG5_like"
## [37] "GOLGA7[0-312]" "GOLGA7[311-549]" "GPX1[0-1218]"
## [40] "GPX1[1217-2946]" "HDAC1" "HS6ST3"
## [43] "IDE[0-2343]" "IDE[2342-3240]" "IDE[3239-4911]"
## [46] "IMPDH1" "ITGB1[0-2328]" "ITGB1[2327-2844]"
## [49] "KDELC1" "KDELC2" "LMAN2L"
## [52] "MARC2" "MGRN1" "MRPS5[0-1569]"
## [55] "MRPS5[1568-3783]" "MSN" "NDFIP2[0-768]"
## [58] "NDFIP2[767-1314]" "NDUFAF2[0-258]" "NDUFAF2[257-744]"
## [61] "NUP58[0-1824]" "NUP58[1823-2367]" "PABPC3"
## [64] "PABPC4L" "PABPC5" "PCSK5"
## [67] "POTPABPC1" "PRIM2[0-1071]" "PRIM2[1070-1902]"
## [70] "PRKACB" "PRKACG" "PTGES2[0-1587]"
## [73] "PTGES2[0-513]" "PTGES2[1586-2202]" "PTGES2[512-2070]"
## [76] "RAB13" "RAB15" "RAB18[0-855]"
## [79] "RAB18[854-1815]" "RAB2B" "RAB5A"
## [82] "RAB5B" "RAB8B" "RALB"
## [85] "REEP6_like" "REEP6_old" "RHOB"
## [88] "RHOC" "SCARB1[0-2004]" "SCARB1[2003-2289]"
## [91] "SELENOS[0-927]" "SELENOS[926-1137]" "SLC44A2[0-2577]"
## [94] "SLC44A2[0-2820]" "SLC44A2[2576-3657]" "SLC44A2[2819-3792]"
## [97] "SRP72[0-2604]" "SRP72[2603-3417]" "STOM[0-1047]"
## [100] "STOM[1046-1800]" "STOML3" "TLE2"
## [103] "TLE2[0-1302]" "TLE2[1301-3987]" "TLE4"
## [106] "TMPRSS2" "TMPRSS2_cut" "TOR1B"
## [109] "WFS1[0-2346]" "WFS1[2345-3216]" "YIF1B"
## [112] "ZC3H18[0-1101]" "ZC3H18[1100-3678]"
\end{verbatim}
\end{kframe}
\end{knitrout}
Merge them and keep only the krogan genes
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlcom{# creation of a dedicated column}
\hlstd{young}\hlopt{$}\hlstd{merge.Gene}\hlkwb{<-}\hlstd{young}\hlopt{$}\hlstd{PreyGene}
\hlstd{tab}\hlopt{$}\hlstd{merge.Gene}\hlkwb{<-}\hlstd{tab}\hlopt{$}\hlstd{Gene.name}
\hlstd{tablo}\hlkwb{<-}\hlkwd{merge}\hlstd{(young, tab,} \hlkwc{by}\hlstd{=}\hlstr{"merge.Gene"}\hlstd{,} \hlkwc{all.x}\hlstd{=}\hlnum{TRUE}\hlstd{)}
\hlkwd{write.table}\hlstd{(tablo,} \hlstr{"covid_comp_complete.txt"}\hlstd{,} \hlkwc{row.names}\hlstd{=}\hlnum{FALSE}\hlstd{,} \hlkwc{quote}\hlstd{=}\hlnum{TRUE}\hlstd{,} \hlkwc{sep}\hlstd{=}\hlstr{"\textbackslash{}t"}\hlstd{)}
\end{alltt}
\end{kframe}
\end{knitrout}
\end{document}