\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{Files manipulations}

\subsection{Read Janet Young's table}

\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{“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{(tab)} \end{alltt} \begin{verbatim}

[1] 332 84

\end{verbatim} \end{kframe} \end{knitrout}

\subsection{Read DGINN Young table}

\begin{knitrout} \definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} \begin{alltt} \hlstd{dginnY}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,} \hlstr{“data/summary_primate_young.res”}\hlstd{),} \hlkwc{fill}\hlstd{=T,} \hlkwc{h}\hlstd{=T)}

\hlkwd{dim}\hlstd{(dginnY)} \end{alltt} \begin{verbatim}

[1] 1992 7

\end{verbatim} \end{kframe} \end{knitrout}

\subsection{Joining Young and DGINN Young table}

\begin{knitrout} \definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} \begin{alltt} \hlcom{# correct gene names (MARC1)} \hlstd{val_remp}\hlkwb{=}\hlkwd{as.character}\hlstd{(}\hlkwd{unique}\hlstd{(dginnY}\hlopt{\(}\hlstd{Gene)[(}\hlkwd{unique}\hlstd{(dginnY}\hlopt{\)}\hlstd{Gene)} \hlopt{%in%} \hlstd{tab}\hlopt{\(}\hlstd{Gene.name)}\hlopt{==}\hlstd{F])} \hlstd{tab}\hlopt{\)}\hlstd{Gene.name}\hlkwb{<-}\hlkwd{as.character}\hlstd{(tab}\hlopt{\(}\hlstd{Gene.name)} \hlstd{tab}\hlopt{\)}\hlstd{Gene.name[}\hlnum{158}\hlstd{]}\hlkwb{<-}\hlstd{val_remp} \hlkwd{sum}\hlstd{(}\hlkwd{unique}\hlstd{(dginnY}\hlopt{\(}\hlstd{Gene)} \hlopt{%in%} \hlkwd{unique}\hlstd{(tab}\hlopt{\)}\hlstd{Gene.name))} \end{alltt} \begin{verbatim}

[1] 332

\end{verbatim} \end{kframe} \end{knitrout}

\begin{knitrout} \definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} \begin{alltt} \hlstd{add_col}\hlkwb{<-}\hlkwa{function}\hlstd{(}\hlkwc{method}\hlstd{=}\hlstr{“PamlM1M2”}\hlstd{){}

\hlstd{tmp}\hlkwb{<-}\hlstd{dginnY[dginnY}\hlopt{$}\hlstd{Method}\hlopt{==}\hlstd{method,} \hlkwd{c}\hlstd{(}\hlstr{“Gene”}\hlstd{,} \hlstr{“Omega”}\hlstd{,} \hlstr{“PosSel”}\hlstd{,} \hlstr{“PValue”}\hlstd{,} \hlstr{“NbSites”}\hlstd{,} \hlstr{“PSS”}\hlstd{)]}

\hlkwd{names}\hlstd{(tmp)}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{“Gene.name”}\hlstd{,} \hlkwd{paste0}\hlstd{(}\hlstr{“Omega”}\hlstd{, method),} \hlkwd{paste0}\hlstd{(}\hlstr{“PosSel”}\hlstd{, method),} \hlkwd{paste0}\hlstd{(}\hlstr{“PValue”}\hlstd{, method),} \hlkwd{paste0}\hlstd{(}\hlstr{“NbSites”}\hlstd{, method),} \hlkwd{paste0}\hlstd{(}\hlstr{“PSS_”}\hlstd{, method))}

\hlstd{tab}\hlkwb{<-}\hlkwd{merge}\hlstd{(tab, tmp,} \hlkwc{by}\hlstd{=}\hlstr{“Gene.name”}\hlstd{)}

\hlkwd{return}\hlstd{(tab)} \hlstd{}}

\hlstd{tab}\hlkwb{<-}\hlkwd{add_col}\hlstd{(}\hlstr{“PamlM1M2”}\hlstd{)} \hlstd{tab}\hlkwb{<-}\hlkwd{add_col}\hlstd{(}\hlstr{“PamlM7M8”}\hlstd{)} \hlstd{tab}\hlkwb{<-}\hlkwd{add_col}\hlstd{(}\hlstr{“BppM1M2”}\hlstd{)} \hlstd{tab}\hlkwb{<-}\hlkwd{add_col}\hlstd{(}\hlstr{“BppM7M8”}\hlstd{)}

\hlcom{# Manip pour la colonne BUSTED}

\hlstd{tmp}\hlkwb{<-}\hlstd{dginnY[dginnY}\hlopt{$}\hlstd{Method}\hlopt{==}\hlstr{“BUSTED”}\hlstd{,}\hlkwd{c}\hlstd{(}\hlstr{“Gene”}\hlstd{,} \hlstr{“Omega”}\hlstd{,} \hlstr{“PosSel”}\hlstd{,} \hlstr{“PValue”}\hlstd{)]} \hlkwd{names}\hlstd{(tmp)}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{“Gene.name”}\hlstd{,} \hlstr{“Omega_BUSTED”}\hlstd{,} \hlstr{“PosSel_BUSTED”}\hlstd{,} \hlstr{“PValue_BUSTED”}\hlstd{)} \hlstd{tab}\hlkwb{<-}\hlkwd{merge}\hlstd{(tab, tmp,} \hlkwc{by}\hlstd{=}\hlstr{“Gene.name”}\hlstd{)}

\hlstd{tmp}\hlkwb{<-}\hlstd{dginnY[dginnY}\hlopt{$}\hlstd{Method}\hlopt{==}\hlstr{“MEME”}\hlstd{,}\hlkwd{c}\hlstd{(}\hlstr{“Gene”}\hlstd{,} \hlstr{“NbSites”}\hlstd{,} \hlstr{“PSS”}\hlstd{)]} \hlkwd{names}\hlstd{(tmp)}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{“Gene.name”}\hlstd{,} \hlstr{“NbSites_MEME”}\hlstd{,} \hlstr{“PSS_MEME”}\hlstd{)} \hlstd{tab}\hlkwb{<-}\hlkwd{merge}\hlstd{(tab, tmp,} \hlkwc{by}\hlstd{=}\hlstr{“Gene.name”}\hlstd{)} \end{alltt} \end{kframe} \end{knitrout}

\subsection{Read DGINN Table}

\begin{knitrout} \definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} \begin{alltt} \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} \hlkwd{names}\hlstd{(dginnT)} \end{alltt} \begin{verbatim}

[1] “File”

[2] “Name”

[3] “Gene”

[4] “GeneSize”

[5] “NbSpecies”

[6] “omegaM0Bpp”

[7] “omegaM0codeml”

[8] “BUSTED”

[9] “BUSTED.p.value”

[10] “MEME.NbSites”

[11] “MEME.PSS”

[12] “BppM1M2”

[13] “BppM1M2.p.value”

[14] “BppM1M2.NbSites”

[15] “BppM1M2.PSS”

[16] “BppM7M8”

[17] “BppM7M8.p.value”

[18] “BppM7M8.NbSites”

[19] “BppM7M8.PSS”

[20] “codemlM1M2”

[21] “codemlM1M2.p.value”

[22] “codemlM1M2.NbSites”

[23] “codemlM1M2.PSS”

[24] “codemlM7M8”

[25] “codemlM7M8.p.value”

[26] “codemlM7M8.NbSites”

[27] “codemlM7M8.PSS”

\end{verbatim} \begin{alltt} \hlcom{# Number of genes in dginn-primate output not present in the original table} \hlstd{dginnT[(dginnT}\hlopt{\(}\hlstd{Gene} \hlopt{%in%} \hlstd{tab}\hlopt{\)}\hlstd{Gene.name)}\hlopt{==}\hlstd{F,}\hlstr{“Gene”}\hlstd{]} \end{alltt} \begin{verbatim}

[1] ACE2

[2] ADAM9[0-3120]

[3] ADAM9[3119-3927]

[4] ATP5MGL

[5] C1H1ORF50

[6] CEP135[0-3264]

[7] CEP135[3263-3678]

[8] CEP43

[9] COQ8B

[10] COQ8A

[11] CSNK2A1

[12] CSNK2B[0-609]

[13] CSNK2B[608-2568]

[14] CYB5R1

[15] DDX21[0-717]

[16] DDX21[716-2538]

[17] DDX50

[18] DNAJC15

[19] DPH5[0-702]

[20] DPH5[701-1326]

[21] DPY19L2

[22] ELOC

[23] ERO1B

[24] EXOSC3[0-1446]

[25] EXOSC3[1445-1980]

[26] FBN3

[27] GNB4

[28] GNB2

[29] GNB3

[30] GOLGA7[0-312]

[31] GOLGA7[311-549]

[32] GPX1[0-1218]

[33] GPX1[1217-2946]

[34] HDAC1

[35] HS6ST3

[36] IMPDH1

[37] ITGB1[0-2328]

[38] ITGB1[2327-2844]

[39] LMAN2L

[40] MRPS5[0-1569]

[41] MRPS5[1568-3783]

[42] MARC2

[43] MGRN1

[44] NDFIP2[0-768]

[45] NDFIP2[767-1314]

[46] NDUFAF2[0-258]

[47] NDUFAF2[257-744]

[48] NSD2

[49] NUP58

[50] NUP58[0-1824]

[51] NUP58[1823-2367]

[52] PABPC3

[53] POTPABPC1

[54] PABPC4L

[55] PABPC5

[56] PCSK5

[57] PRIM2[0-1071]

[58] PRIM2[1070-1902]

[59] PRKACB

[60] PRKACG

[61] PTGES2[0-1587]

[62] PTGES2[1586-2202]

[63] RAB8B

[64] RAB13

[65] RAB18[0-855]

[66] RAB18[854-1815]

[67] RAB2B

[68] RAB5A

[69] RAB5B

[70] RAB15

[71] RALB

[72] EZR

[73] EZR[0-1458]

[74] EZR[1457-3771]

[75] MSN

[76] RETREG3

[77] RHOB

[78] RHOC

[79] SLC44A2[0-2577]

[80] SLC44A2[2576-3657]

[81] SPART

[82] SRP72[0-2604]

[83] SRP72[2603-3417]

[84] STOM[0-1047]

[85] STOM[1046-1800]

[86] STOML3

[87] TIMM29

[88] TLE4

[89] TLE2

[90] TLE2[0-1302]

[91] TLE2[1301-3987]

[92] TMPRSS2

[93] TOMM70

[94] TOR1B

[95] WASHC4

[96] WFS1[0-2346]

[97] WFS1[2345-3216]

[98] YIF1B

411 Levels: AAR2 AASS … ZYG11B

\end{verbatim} \begin{alltt} \hlcom{# This includes paralogs, recombinations found by DGINN and additionnal genes } \hlcom{# included on purpose}

\hlcom{# Number of genes from the original list not present in DGINN output} \hlstd{tab[(tab}\hlopt{\(}\hlstd{Gene.name} \hlopt{%in%} \hlstd{dginnT}\hlopt{\)}\hlstd{Gene)}\hlopt{==}\hlstd{F,}\hlstr{“Gene.name”}\hlstd{]} \end{alltt} \begin{verbatim}

[1] “ADCK4” “ARL6IP6”

[3] “ATP5L” “C19orf52”

[5] “C1orf50” “ERO1LB”

[7] “FAM134C” “FGFR1OP”

[9] “KIAA1033” “MFGE8”

[11] “NUPL1” “SIGMAR1”

[13] “SPG20” “TCEB1”

[15] “TCEB2” “TOMM70A”

[17] “USP13” “VIMP”

[19] “WHSC1”

\end{verbatim} \begin{alltt} \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}

\begin{knitrout} \definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} \begin{alltt} \hlkwd{table}\hlstd{(dginnT}\hlopt{\(}\hlstd{dginn-primate_BUSTED)} \hlkwd{table}\hlstd{(dginnT}\hlopt{\)}\hlstd{dginn-primate_codemlM1M2)} \hlkwd{table}\hlstd{(dginnT}\hlopt{\(}\hlstd{dginn-primate_codemlM7M8)} \hlkwd{table}\hlstd{(dginnT}\hlopt{\)}\hlstd{dginn-primate_BppM1M2)} \hlkwd{table}\hlstd{(dginnT}\hlopt{$}\hlstd{dginn-primate_BppM7M8)}

\hlkwd{table}\hlstd{(dginnT}\hlopt{\(}\hlstd{dginn-primate_BUSTED}\hlopt{==}\hlstr{“na”}\hlstd{,dginnT}\hlopt{\)}\hlstd{dginn-primate_codemlM1M2}\hlopt{==}\hlstr{“na”}\hlstd{, dginnT}\hlopt{\(}\hlstd{dginn-primate_codemlM7M8}\hlopt{==}\hlstr{“na”}\hlstd{,} \hlstd{dginnT}\hlopt{\)}\hlstd{dginn-primate_BppM1M2}\hlopt{==}\hlstr{“na”}\hlstd{, dginnT}\hlopt{$}\hlstd{dginn-primate_BppM7M8}\hlopt{==}\hlstr{“na”} \hlstd{)} \end{alltt} \end{kframe} \end{knitrout}

\subsection{Join Table and DGINN table}

\begin{knitrout} \definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} \begin{alltt} \hlstd{tab}\hlkwb{<-}\hlkwd{merge}\hlstd{(tab,dginnT,} \hlkwc{by}\hlstd{=}\hlstr{“Gene.name”}\hlstd{,} \hlkwc{all.x}\hlstd{=T)}

\hlkwd{table}\hlstd{(tab}\hlopt{$}\hlstd{dginn-primate_BUSTED)} \end{alltt} \begin{verbatim}

N na Y

155 12 147

\end{verbatim} \begin{alltt} \hlkwd{table}\hlstd{(tab}\hlopt{$}\hlstd{dginn-primate_codemlM1M2)} \end{alltt} \begin{verbatim}

N na Y

216 26 72

\end{verbatim} \begin{alltt} \hlkwd{table}\hlstd{(tab}\hlopt{$}\hlstd{dginn-primate_codemlM7M8)} \end{alltt} \begin{verbatim}

N na Y

161 40 113

\end{verbatim} \begin{alltt} \hlkwd{table}\hlstd{(tab}\hlopt{$}\hlstd{dginn-primate_BppM1M2)} \end{alltt} \begin{verbatim}

N na Y

252 21 41

\end{verbatim} \begin{alltt} \hlkwd{table}\hlstd{(tab}\hlopt{$}\hlstd{dginn-primate_BppM7M8)} \end{alltt} \begin{verbatim}

N na Y

173 22 119

\end{verbatim} \begin{alltt} \hlkwd{table}\hlstd{(tab}\hlopt{\(}\hlstd{dginn-primate_BUSTED}\hlopt{==}\hlstr{“na”} \hlopt{|} \hlstd{tab}\hlopt{\)}\hlstd{dginn-primate_codemlM1M2}\hlopt{==}\hlstr{“na”} \hlopt{|} \hlstd{tab}\hlopt{\(}\hlstd{dginn-primate_codemlM7M8}\hlopt{==}\hlstr{“na”} \hlopt{|} \hlstd{tab}\hlopt{\)}\hlstd{dginn-primate_BppM1M2}\hlopt{==}\hlstr{“na”}\hlopt{|} \hlstd{tab}\hlopt{$}\hlstd{dginn-primate_BppM7M8}\hlopt{==}\hlstr{“na”} \hlstd{)} \end{alltt} \begin{verbatim}

FALSE TRUE

274 40

\end{verbatim} \end{kframe} \end{knitrout}

\subsection{Add DGINN results on bat dataset}

DGINN results from different analysis.

\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.tab”}\hlstd{),} \hlkwc{fill}\hlstd{=T,} \hlkwc{h}\hlstd{=T)}

\hlcom{# rerun on corrected alignment} \hlstd{dginnbatsnew1}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,} \hlstr{“data/DGINN_202011262248_summary.tab”}\hlstd{),} \hlkwc{fill}\hlstd{=T,} \hlkwc{h}\hlstd{=T)} \hlstd{dginnbatsnew2}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,} \hlstr{“data/DGINN_202012192053_summary.tab”}\hlstd{),} \hlkwc{fill}\hlstd{=T,} \hlkwc{h}\hlstd{=T)}

\hlcom{# colomne choice, BUSTED and Bppml form first file, codeml from the other one} \hlstd{dginnbatsnew}\hlkwb{<-}\hlstd{dginnbatsnew1} \hlstd{dginnbatsnew}\hlopt{\(}\hlstd{omegaM0codeml}\hlkwb{<-}\hlstd{dginnbatsnew2}\hlopt{\)}\hlstd{omegaM0codeml}

\hlstd{dginnbatsnew}\hlopt{\(}\hlstd{codemlM1M2}\hlkwb{<-}\hlstd{dginnbatsnew2}\hlopt{\)}\hlstd{codemlM1M2} \hlstd{dginnbatsnew}\hlopt{\(}\hlstd{codemlM1M2_p.value}\hlkwb{<-}\hlstd{dginnbatsnew2}\hlopt{\)}\hlstd{codemlM1M2_p.value} \hlstd{dginnbatsnew}\hlopt{\(}\hlstd{codemlM1M2_NbSites}\hlkwb{<-}\hlstd{dginnbatsnew2}\hlopt{\)}\hlstd{codemlM1M2_NbSites} \hlstd{dginnbatsnew}\hlopt{\(}\hlstd{codemlM1M2_PSS}\hlkwb{<-}\hlstd{dginnbatsnew2}\hlopt{\)}\hlstd{codemlM1M2_PSS}

\hlstd{dginnbatsnew}\hlopt{\(}\hlstd{codemlM7M8}\hlkwb{<-}\hlstd{dginnbatsnew2}\hlopt{\)}\hlstd{codemlM7M8} \hlstd{dginnbatsnew}\hlopt{\(}\hlstd{codemlM7M8_p.value}\hlkwb{<-}\hlstd{dginnbatsnew2}\hlopt{\)}\hlstd{codemlM7M8_p.value} \hlstd{dginnbatsnew}\hlopt{\(}\hlstd{codemlM7M8_NbSites}\hlkwb{<-}\hlstd{dginnbatsnew2}\hlopt{\)}\hlstd{codemlM7M8_NbSites} \hlstd{dginnbatsnew}\hlopt{\(}\hlstd{codemlM7M8_PSS}\hlkwb{<-}\hlstd{dginnbatsnew2}\hlopt{\)}\hlstd{codemlM7M8_PSS}

\hlcom{####} \hlcom{## RIPK1 is actually a primat results} \hlcom{## 1. Take it and put it at the right place} \hlstd{ripk1}\hlkwb{<-}\hlkwd{as.vector}\hlstd{(dginnbatsnew[dginnbatsnew}\hlopt{\(}\hlstd{Gene}\hlopt{==}\hlstr{“RIPK1”}\hlstd{,])} \hlstd{tab}\hlopt{\)}\hlstd{dginn-primate_omegaM0Bpp}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{dginn-primate_omegaM0Bpp))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{tab}\hlopt{\(}\hlstd{dginn-primate_BUSTED.p.value}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{\)}\hlstd{dginn-primate_BUSTED.p.value))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{tab}\hlopt{\(}\hlstd{dginn-primate_BppM1M2.p.value}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{\)}\hlstd{dginn-primate_BppM1M2.p.value))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{tab}\hlopt{\(}\hlstd{dginn-primate_BppM7M8.p.value}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{\)}\hlstd{dginn-primate_BppM7M8.p.value))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{tab}\hlopt{\(}\hlstd{dginn-primate_BppM7M8.PSS}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{\)}\hlstd{dginn-primate_BppM7M8.PSS))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{tab}\hlopt{\(}\hlstd{dginn-primate_codemlM1M2.p.value}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{\)}\hlstd{dginn-primate_codemlM1M2.p.value))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{tab}\hlopt{\(}\hlstd{dginn-primate_codemlM1M2.PSS}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{\)}\hlstd{dginn-primate_codemlM1M2.PSS))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{tab}\hlopt{\(}\hlstd{dginn-primate_codemlM7M8.p.value}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{\)}\hlstd{dginn-primate_codemlM7M8.p.value))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{tab}\hlopt{\(}\hlstd{dginn-primate_codemlM7M8.PSS}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{\)}\hlstd{dginn-primate_codemlM7M8.PSS))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{“RIPK1”}\hlstd{,}\hlstr{“GeneSize”}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{GeneSize} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_NbSpecies"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{NbSpecies} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_omegaM0Bpp"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{omegaM0Bpp} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_omegaM0codeml"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{omegaM0codeml}

\hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{“RIPK1”}\hlstd{,}\hlstr{“dginn-primate_BUSTED”}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{BUSTED} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_BUSTED.p.value"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{BUSTED_p.value} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_MEME.NbSites"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{MEME_NbSites} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_MEME.PSS"}\hlstd{]}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(ripk1}\hlopt{\)}\hlstd{MEME_PSS))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{“RIPK1”}\hlstd{,}\hlstr{“dginn-primate_BppM1M2”}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{BppM1M2} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_BppM1M2.p.value"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{BppM1M2_p.value} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_BppM1M2.NbSites"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{BppM1M2_NbSites} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_BppM1M2.PSS"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{BppM1M2_PSS}

\hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{“RIPK1”}\hlstd{,}\hlstr{“dginn-primate_BppM7M8”}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{BppM7M8} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_BppM7M8.p.value"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{BppM7M8_p.value} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_BppM7M8.NbSites"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{BppM7M8_NbSites} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_BppM7M8.PSS"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{BppM7M8_PSS}

\hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{“RIPK1”}\hlstd{,}\hlstr{“dginn-primate_codemlM1M2”}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{codemlM1M2} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_codemlM1M2.p.value"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{codemlM1M2_p.value} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_codemlM1M2.NbSites"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{codemlM1M2_NbSites} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_codemlM1M2.PSS"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{codemlM1M2_PSS} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_codemlM7M8"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{codemlM7M8} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_codemlM7M8.p.value"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{codemlM7M8_p.value} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_codemlM7M8.NbSites"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{codemlM7M8_NbSites} \hlstd{tab[tab}\hlopt{\(}\hlstd{Gene.name}\hlopt{==}\hlstr{"RIPK1"}\hlstd{,}\hlstr{"dginn-primate_codemlM7M8.PSS"}\hlstd{]}\hlkwb{<-}\hlstd{ripk1}\hlopt{\)}\hlstd{codemlM7M8_PSS}

\hlcom{## 2. Remove it} \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{##############“} \hlstd{dginnbatsnew[,}\hlnum{4}\hlstd{]}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(dginnbatsnew[,}\hlnum{4}\hlstd{])} \hlstd{dginnbats[,}\hlnum{6}\hlstd{]}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(dginnbats[,}\hlnum{6}\hlstd{]))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{dginnbats[,}\hlnum{8}\hlstd{]}\hlkwb{<-}\hlkwd{as.character}\hlstd{(dginnbats[,}\hlnum{8}\hlstd{])} \hlstd{dginnbats[,}\hlnum{12}\hlstd{]}\hlkwb{<-}\hlkwd{as.character}\hlstd{(dginnbats[,}\hlnum{12}\hlstd{])} \hlstd{dginnbats[,}\hlnum{13}\hlstd{]}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(dginnbats[,}\hlnum{13}\hlstd{]))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlstd{dginnbats[,}\hlnum{16}\hlstd{]}\hlkwb{<-}\hlkwd{as.character}\hlstd{(dginnbats[,}\hlnum{16}\hlstd{])} \hlstd{dginnbats[,}\hlnum{17}\hlstd{]}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(dginnbats[,}\hlnum{17}\hlstd{]))} \end{alltt}

{\ttfamily\noindent\color{warningcolor}{## Warning: NAs introduits lors de la conversion automatique}}\begin{alltt} \hlcom{## replace by new data} \hlstd{dginnbats}\hlkwb{<-}\hlkwd{rbind}\hlstd{(dginnbats, dginnbatsnew)}

\hlkwd{names}\hlstd{(dginnbats)}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"File”}\hlstd{,} \hlstr{“batsName”}\hlstd{,} \hlstr{“cooper.batsGene”}\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] “File”

[2] “bats_Name”

[3] “cooper.batsGene”

[4] “bats_GeneSize”

[5] “bats_NbSpecies”

[6] “bats_omegaM0Bpp”

[7] “bats_omegaM0codeml”

[8] “bats_BUSTED”

[9] “bats_BUSTED.p.value”

[10] “bats_MEME.NbSites”

[11] “bats_MEME.PSS”

[12] “bats_BppM1M2”

[13] “bats_BppM1M2.p.value”

[14] “bats_BppM1M2.NbSites”

[15] “bats_BppM1M2.PSS”

[16] “bats_BppM7M8”

[17] “bats_BppM7M8.p.value”

[18] “bats_BppM7M8.NbSites”

[19] “bats_BppM7M8.PSS”

[20] “bats_codemlM1M2”

[21] “bats_codemlM1M2.p.value”

[22] “bats_codemlM1M2.NbSites”

[23] “bats_codemlM1M2.PSS”

[24] “bats_codemlM7M8”

[25] “bats_codemlM7M8.p.value”

[26] “bats_codemlM7M8.NbSites”

[27] “bats_codemlM7M8.PSS”

\end{verbatim} \begin{alltt} \hlstd{tab}\hlkwb{<-}\hlkwd{merge}\hlstd{(tab,dginnbats,} \hlkwc{by}\hlstd{=}\hlstr{“cooper.batsGene”}\hlstd{,} \hlkwc{all.x}\hlstd{=T)} \end{alltt} \end{kframe} \end{knitrout}

\subsection{Write the new table}

\begin{knitrout} \definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} \begin{alltt} \hlkwd{write.table}\hlstd{(tab,} \hlstr{“covid_comp_complete.txt”}\hlstd{,} \hlkwc{row.names}\hlstd{=}\hlnum{FALSE}\hlstd{,} \hlkwc{quote}\hlstd{=}\hlnum{FALSE}\hlstd{,} \hlkwc{sep}\hlstd{=}\hlstr{“\textbackslash{}t”}\hlstd{)} \end{alltt} \end{kframe} \end{knitrout}

\section{Second 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{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} \hlkwd{names}\hlstd{(dginnT)} \end{alltt} \begin{verbatim}

[1] “File”

[2] “Name”

[3] “Gene”

[4] “GeneSize”

[5] “NbSpecies”

[6] “omegaM0Bpp”

[7] “omegaM0codeml”

[8] “BUSTED”

[9] “BUSTED.p.value”

[10] “MEME.NbSites”

[11] “MEME.PSS”

[12] “BppM1M2”

[13] “BppM1M2.p.value”

[14] “BppM1M2.NbSites”

[15] “BppM1M2.PSS”

[16] “BppM7M8”

[17] “BppM7M8.p.value”

[18] “BppM7M8.NbSites”

[19] “BppM7M8.PSS”

[20] “codemlM1M2”

[21] “codemlM1M2.p.value”

[22] “codemlM1M2.NbSites”

[23] “codemlM1M2.PSS”

[24] “codemlM7M8”

[25] “codemlM7M8.p.value”

[26] “codemlM7M8.NbSites”

[27] “codemlM7M8.PSS”

\end{verbatim} \begin{alltt} \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}

\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

[6] TRUE TRUE TRUE TRUE TRUE

[11] TRUE TRUE TRUE TRUE TRUE

[16] TRUE TRUE TRUE TRUE TRUE

[21] TRUE TRUE TRUE TRUE TRUE

[26] TRUE 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

[6] TRUE TRUE TRUE TRUE TRUE

[11] TRUE TRUE TRUE TRUE TRUE

[16] TRUE TRUE TRUE TRUE TRUE

[21] TRUE TRUE TRUE TRUE TRUE

[26] TRUE 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{“batsFile”}\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”

[2] “bats_Name”

[3] “Gene.name”

[4] “bats_GeneSize”

[5] “bats_NbSpecies”

[6] “bats_omegaM0Bpp”

[7] “bats_omegaM0codeml”

[8] “bats_BUSTED”

[9] “bats_BUSTED_p.value”

[10] “bats_MEME_NbSites”

[11] “bats_MEME_PSS”

[12] “bats_BppM1M2”

[13] “bats_BppM1M2_p.value”

[14] “bats_BppM1M2_NbSites”

[15] “bats_BppM1M2_PSS”

[16] “bats_BppM7M8”

[17] “bats_BppM7M8_p.value”

[18] “bats_BppM7M8_NbSites”

[19] “bats_BppM7M8_PSS”

[20] “bats_codemlM1M2”

[21] “bats_codemlM1M2_p.value”

[22] “bats_codemlM1M2_NbSites”

[23] “bats_codemlM1M2_PSS”

[24] “bats_codemlM7M8”

[25] “bats_codemlM7M8_p.value”

[26] “bats_codemlM7M8_NbSites”

[27] “bats_codemlM7M8_PSS”

[28] “bats_Lucie.s.comments”

[29] “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} \hlstd{tidy.opts} \hlkwb{=} \hlkwd{list}\hlstd{(}\hlkwc{width.cutoff} \hlstd{=} \hlnum{30}\hlstd{)} \hlkwd{dim}\hlstd{(dginnT)} \end{alltt} \begin{verbatim}

[1] 413 27

\end{verbatim} \begin{alltt} \hlstd{dginnT}\hlopt{$}\hlstd{Gene.name} \end{alltt} \begin{verbatim}

[1] AAR2

[2] AASS

[3] AATF

[4] ABCC1

[5] ACAD9

[6] ACADM

[7] ACE2

[8] ACSL3

[9] ADAM9

[10] ADAM9[0-3120]

[11] ADAM9[3119-3927]

[12] ADAMTS1

[13] AGPS

[14] AKAP8

[15] AKAP8L

[16] AKAP9

[17] ALG11

[18] ALG5

[19] ALG8

[20] ANO6

[21] AP2A2

[22] AP2M1

[23] AP3B1

[24] ARF6

[25] ATE1

[26] ATP13A3

[27] ATP1B1

[28] ATP5MGL

[29] ATP6AP1

[30] ATP6V1A

[31] BAG5

[32] BCKDK

[33] BCS1L

[34] BRD2

[35] BRD4

[36] BZW2

[37] C1H1ORF50

[38] CCDC86

[39] CDK5RAP2

[40] CENPF

[41] CEP112

[42] CEP135

[43] CEP135[0-3264]

[44] CEP135[3263-3678]

[45] CEP250

[46] CEP350

[47] CEP43

[48] CEP68

[49] CHMP2A

[50] CHPF

[51] CHPF2

[52] CISD3

[53] CIT

[54] CLCC1

[55] CLIP4

[56] CNTRL

[57] COL6A1

[58] COLGALT1

[59] COMT

[60] COQ8B

[61] COQ8A

[62] CRTC3

[63] CSDE1

[64] CSNK2A1

[65] CSNK2A2

[66] CSNK2B

[67] CSNK2B[0-609]

[68] CSNK2B[608-2568]

[69] CUL2

[70] CWC27

[71] CYB5B

[72] CYB5R3

[73] CYB5R1

[74] DCAF7

[75] DCAKD

[76] DCTPP1

[77] DDX10

[78] DDX21

[79] DDX21[0-717]

[80] DDX21[716-2538]

[81] DDX50

[82] DNAJC11

[83] DNAJC19

[84] DNAJC15

[85] DNMT1

[86] DPH5

[87] DPH5[0-702]

[88] DPH5[701-1326]

[89] DPY19L2

[90] DPY19L1

[91] ECSIT

[92] EDEM3

[93] EIF4E2

[94] EIF4H

[95] ELOC

[96] EMC1

[97] ERC1

[98] ERGIC1

[99] ERLEC1

[100] ERMP1

[101] ERO1B

[102] ERP44

[103] ETFA

[104] EXOSC2

[105] EXOSC3

[106] EXOSC3[0-1446]

[107] EXOSC3[1445-1980]

[108] EXOSC5

[109] EXOSC8

[110] F2RL1

[111] FAM162A

[112] FAM8A1

[113] FAM98A

[114] FAR2

[115] FASTKD5

[116] FBLN5

[117] FBN1

[118] FBN3

[119] FBN2

[120] FBXL12

[121] FKBP10

[122] FKBP15

[123] FKBP7

[124] FOXRED2

[125] FYCO1

[126] G3BP1

[127] G3BP2

[128] GCC1

[129] GCC2

[130] GDF15

[131] GFER

[132] GGCX

[133] GGH

[134] GHITM

[135] GIGYF2

[136] GLA

[137] GNB4

[138] GNB2

[139] GNB1

[140] GNB3

[141] GNG5

[142] GNG5

[143] GOLGA2

[144] GOLGA3

[145] GOLGA7

[146] GOLGA7[0-312]

[147] GOLGA7[311-549]

[148] GOLGB1

[149] GORASP1

[150] GPAA1

[151] GPX1

[152] GPX1[0-1218]

[153] GPX1[1217-2946]

[154] GRIPAP1

[155] GRPEL1

[156] GTF2F2

[157] HDAC2

[158] HDAC1

[159] HEATR3

[160] HECTD1

[161] HMOX1

[162] HOOK1

[163] HS2ST1

[164] HS6ST2

[165] HS6ST3

[166] HSBP1

[167] HYOU1

[168] IDE

[169] IL17RA

[170] IMPDH1

[171] IMPDH2

[172] INHBE

[173] INTS4

[174] ITGB1

[175] ITGB1[0-2328]

[176] ITGB1[2327-2844]

[177] JAKMIP1

[178] LARP1

[179] LARP4B

[180] LARP7

[181] LMAN2

[182] LMAN2L

[183] LOX

[184] MAP7D1

[185] MARK1

[186] MARK2

[187] MARK3

[188] MAT2B

[189] MDN1

[190] MEPCE

[191] MIB1

[192] MIPOL1

[193] MOGS

[194] MOV10

[195] MPHOSPH10

[196] MRPS2

[197] MRPS25

[198] MRPS27

[199] MRPS5

[200] MRPS5[0-1569]

[201] MRPS5[1568-3783]

[202] MARC1

[203] MARC2

[204] MTCH1

[205] MYCBP2

[206] MGRN1

[207] NARS2

[208] NAT14

[209] NDFIP2

[210] NDFIP2[0-768]

[211] NDFIP2[767-1314]

[212] NDUFAF1

[213] NDUFAF2

[214] NDUFAF2[0-258]

[215] NDUFAF2[257-744]

[216] NDUFB9

[217] NEK9

[218] NEU1

[219] NGDN

[220] NGLY1

[221] NIN

[222] NINL

[223] NLRX1

[224] NOL10

[225] NPC2

[226] NPTX1

[227] NSD2

[228] NUP210

[229] NUP214

[230] NUP54

[231] NUP58

[232] NUP58[0-1824]

[233] NUP58[1823-2367]

[234] NUP62

[235] NUP88

[236] NUP98

[237] NUTF2

[238] OS9

[239] PABPC3

[240] POTPABPC1

[241] PABPC1

[242] PABPC4

[243] PABPC4L

[244] PABPC5

[245] PCNT

[246] PCSK6

[247] PCSK5

[248] PDE4DIP

[249] PDZD11

[250] PIGO

[251] PIGS

[252] PITRM1

[253] PKP2

[254] PLAT

[255] PLD3

[256] PLEKHA5

[257] PLEKHF2

[258] PLOD2

[259] PMPCA

[260] PMPCB

[261] POFUT1

[262] KDELC1

[263] KDELC2

[264] POLA1

[265] POLA2

[266] POR

[267] PPIL3

[268] PPT1

[269] PRIM1

[270] PRIM2

[271] PRIM2[0-1071]

[272] PRIM2[1070-1902]

[273] PRKACB

[274] PRKACG

[275] PRKACA

[276] PRKAR2A

[277] PRKAR2B

[278] PRRC2B

[279] PSMD8

[280] PTBP2

[281] PTGES2

[282] PTGES2[0-1587]

[283] PTGES2[1586-2202]

[284] PUSL1

[285] PVR

[286] QSOX2

[287] RAB10

[288] RAB8B

[289] RAB13

[290] RAB14

[291] RAB18

[292] RAB18[0-855]

[293] RAB18[854-1815]

[294] RAB1A

[295] RAB2B

[296] RAB2A

[297] RAB5C

[298] RAB5A

[299] RAB5B

[300] RAB7A

[301] RAB15

[302] RAB8A

[303] RAE1

[304] RALB

[305] RALA

[306] RAP1GDS1

[307] RBM28

[308] RBM41

[309] RBX1

[310] EZR

[311] EZR[0-1458]

[312] EZR[1457-3771]

[313] RDX

[314] MSN

[315] REEP5

[316] REEP6

[317] RETREG3

[318] RHOB

[319] RHOC

[320] RHOA

[321] RIPK1

[322] RNF41

[323] RPL36

[324] RRP9

[325] RTN4

[326] SAAL1

[327] SBNO1

[328] SCAP

[329] SCARB1

[330] SCCPDH

[331] SDF2

[332] SEPSECS

[333] SIL1

[334] SIRT5

[335] SLC25A21

[336] SLC27A2

[337] SLC30A6

[338] SLC30A7

[339] SLC30A9

[340] SLC44A2

[341] SLC44A2[0-2577]

[342] SLC44A2[2576-3657]

[343] SLC9A3R1

[344] SLU7

[345] SMOC1

[346] SNIP1

[347] SPART

[348] SRP19

[349] SRP54

[350] SRP72

[351] SRP72[0-2604]

[352] SRP72[2603-3417]

[353] STC2

[354] STOM

[355] STOM[0-1047]

[356] STOM[1046-1800]

[357] STOML3

[358] STOML2

[359] SUN2

[360] TAPT1

[361] TARS2

[362] TBCA

[363] TBK1

[364] TBKBP1

[365] TCF12

[366] THTPA

[367] TIMM10

[368] TIMM10B

[369] TIMM29

[370] TIMM8B

[371] TIMM9

[372] TLE1

[373] TLE3

[374] TLE4

[375] TLE2

[376] TLE2[0-1302]

[377] TLE2[1301-3987]

[378] AES

[379] TM2D3

[380] TMED5

[381] TMEM39B

[382] TMEM97

[383] TMPRSS2

[384] TOMM70

[385] TOR1A

[386] TOR1B

[387] TOR1AIP1

[388] TRIM59

[389] TRMT1

[390] TUBGCP2

[391] TUBGCP3

[392] TYSND1

[393] UBAP2

[394] UBAP2L

[395] UBXN8

[396] UGGT2

[397] UPF1

[398] USP54

[399] VPS11

[400] VPS39

[401] WASHC4

[402] WFS1

[403] WFS1[0-2346]

[404] WFS1[2345-3216]

[405] YIF1A

[406] YIF1B

[407] ZC3H18

[408] ZC3H7A

[409] ZDHHC5

[410] ZNF318

[411] ZNF503

[412] ZYG11B

[413] RIPK1

416 Levels: AAR2 AASS … SELENOS

\end{verbatim} \begin{alltt} \hlkwd{dim}\hlstd{(dginnbats)} \end{alltt} \begin{verbatim}

[1] 353 29

\end{verbatim} \begin{alltt} \hlstd{dginnbats}\hlopt{$}\hlstd{Gene.name} \end{alltt} \begin{verbatim}

[1] AAR2

[2] AASS

[3] AATF

[4] ABCC1

[5] ACAD9

[6] ACADM

[7] ACE2

[8] ACSL3

[9] ADAM9

[10] ADAM9[0-2769]

[11] ADAM9[2768-3030]

[12] ADAMTS1

[13] AGPS

[14] AKAP8

[15] AKAP8L

[16] AKAP9

[17] ALG11

[18] ALG5

[19] ALG8

[20] ANO6

[21] AP2A2

[22] AP2M1

[23] AP3B1

[24] ARF6

[25] ARL6IP6

[26] ATP13A3

[27] ATP1B1

[28] ATP5MG

[29] ATP6AP1

[30] ATP6V1A

[31] BAG5

[32] BCKDK

[33] BCS1

[34] BRD2

[35] BRD4

[36] BZW2

[37] CUNH1ORF50

[38] CCDC86

[39] CDK5RAP2

[40] CENPF

[41] CEP112

[42] CEP135

[43] CEP250

[44] CEP350

[45] CEP68

[46] CHMP2A

[47] CHPF

[48] CHPF2

[49] CISD3

[50] CIT

[51] CLCC1

[52] CLIP4

[53] CNTRL

[54] COLGALT1

[55] COMT

[56] CRTC3

[57] CSDE1

[58] CSNK2A2

[59] CSNK2B

[60] CUL2

[61] CWC27

[62] CYB5BR3

[63] DCAF7

[64] DCAKD

[65] DCTPP1

[66] DDX10

[67] DNAJC11

[68] DNAJC19

[69] DNMT1

[70] DPH5

[71] DPY19L1

[72] ECSIT

[73] EDEM3

[74] EIF4E2

[75] EIF4H

[76] ELOC

[77] EMC1

[78] ERC1

[79] ERGIC1

[80] ERLEC1

[81] ERMP1

[82] ERP44

[83] EXOSC2

[84] EXOSC3

[85] EXOSC5

[86] EXOSC8

[87] F2RL1

[88] FAM162A

[89] FAM8A1

[90] FAM98A

[91] FAR2

[92] FASTKD5

[93] FBLN5

[94] FBN1

[95] FBN2

[96] FBXL12

[97] FKBP10

[98] FKBP15

[99] FKBP7

[100] FOXRED2

[101] FYCO1

[102] G3BP1

[103] G3BP2

[104] GCC1

[105] GCC2

[106] GDF15

[107] GFER

[108] GGCX

[109] GGH

[110] GHITM

[111] GIGYF2

[112] GLA

[113] GNG5

[114] GOLGA2

[115] GOLGA3

[116] GOLGB1

[117] GORASP1

[118] GPAA1

[119] GPX1

[120] GRIPAP1

[121] GRPEL1

[122] GTF2F2

[123] HDAC2

[124] HEATR3

[125] HECTD1

[126] HMOX1

[127] HOOK1

[128] HS2ST1

[129] HS6ST2

[130] HYOU1

[131] IDE

[132] IDE[0-2343]

[133] IDE[2342-3240]

[134] IDE[3239-4911]

[135] IL17RA

[136] IMPDH2

[137] INHBE

[138] ITGB1

[139] JAKMIP1

[140] LARP1

[141] LARP4B

[142] LARP7

[143] LMAN2

[144] LOX

[145] MAP7D1

[146] MARK1

[147] MARK2

[148] MARK3

[149] MAT2B

[150] MDN1

[151] MEPCE

[152] MFGE8

[153] MIB1

[154] MIPOL1

[155] MOGS

[156] MPHOSPH10

[157] MRPS2

[158] MRPS25

[159] MRPS27

[160] MRPS5

[161] MTCH1

[162] MYCBP2

[163] NARS2

[164] NAT14

[165] NDFIP2

[166] NDUFAF1

[167] NDUFAF2

[168] NDUFB9

[169] NEK9

[170] NEU1

[171] NGDN

[172] NGLY1

[173] NIN

[174] NINL

[175] NLRX1

[176] NOL10

[177] NPC2

[178] NPTX1

[179] NSD2

[180] NUP210

[181] NUP214

[182] NUP54

[183] NUP58

[184] NUP62

[185] NUP88

[186] NUP98

[187] NUTF2

[188] OS9

[189] PABPC4

[190] PCNT

[191] PCSK5

[192] PDZD11

[193] PIGO

[194] PIGS

[195] PITRM1

[196] PKP2

[197] PLAT

[198] PLD3

[199] PLEKHA5

[200] PLEKHF2

[201] PLOD2

[202] PMPCA

[203] PMPCB

[204] POFUT1

[205] KDELC1

[206] KDELC2

[207] POLA1

[208] POLA2

[209] POR

[210] PPIL3

[211] PPT1

[212] PRIM1

[213] PRIM2

[214] PRKACA

[215] PRKAR2A

[216] PRKAR2B

[217] PRRC2B

[218] PSMD8

[219] PTBP2

[220] PTGES2

[221] PTGES2[0-513]

[222] PTGES2[512-2070]

[223] PUSL1

[224] PVR

[225] QSOX2

[226] RAB10

[227] RAB14

[228] RAB18

[229] RAB1A

[230] RAB2A

[231] RAB5C

[232] RAB7A

[233] RAB8A

[234] RAE1

[235] RALA

[236] RAP1GDS1

[237] RBM28

[238] RBM41

[239] RBX1

[240] REEP5

[241] REEP6

[242] RETREG3

[243] RHOA

[244] RIPK1

[245] RNF41

[246] RPL36

[247] RRP9

[248] RTN4

[249] SAAL1

[250] SBNO1

[251] SCAP

[252] SCARB1

[253] SCARB1[0-2004]

[254] SCARB1[2003-2289]

[255] SCCPDH

[256] SELENOS[0-927]

[257] SELENOS[926-1137]

[258] SEPSECS

[259] SIGMAR1

[260] SIL1

[261] SIRT5

[262] SLC25A21

[263] SLC27A2

[264] SLC30A6

[265] SLC30A7

[266] SLC30A9

[267] SLC44A2

[268] SLC44A2[0-2820]

[269] SLC44A2[2819-3792]

[270] SLC9A3R1

[271] SLU7

[272] SMOC1

[273] SNIP1

[274] SPART

[275] SRP19

[276] SRP54

[277] SRP72

[278] STC2

[279] STOM

[280] STOML2

[281] SUN2

[282] TAPT1

[283] TBK1

[284] TBKBP1

[285] TCF12

[286] THTPA

[287] TIMM10

[288] TIMM10B

[289] TIMM29

[290] TIMM8B

[291] TIMM9

[292] TLE1

[293] TLE3

[294] TLE5

[295] TM2D3

[296] TMED5

[297] TMEM97

[298] TOMM70

[299] TOR1A

[300] TOR1AIP1

[301] TRIM59

[302] TRMT1

[303] TUBGCP2

[304] TUBGCP3

[305] UBAP2

[306] UBAP2L

[307] UBXN8

[308] UGGT2

[309] UPF1

[310] USP13

[311] USP54

[312] VPS11

[313] VPS39

[314] WASHC4

[315] WFS1

[316] YIF1A

[317] ZC3H18

[318] ZC3H18[0-1101]

[319] ZC3H18[1100-3678]

[320] ZC3H7A

[321] ZDHHC5

[322] ZNF318

[323] ZNF503

[324] ZYG11B

[325] ATE1

[326] FGFR1OP

[327] COL6A1

[328] COQ8B

[329] CYB5B

[330] DDX21

[331] ELOB

[332] ERO1B

[333] ETFA

[334] GNB1

[335] GOLGA7

[336] HSBP1

[337] INTS4

[338] MOV10

[339] MARC1

[340] PABPC1

[341] PCSK6

[342] PDE4DIP

[343] RDX

[344] REEP6-A

[345] REEP6-B

[346] SDF2

[347] SELENOS

[348] TARS2

[349] TBCA

[350] TMEM39B

[351] TMPRSS2

[352] TMPRSS2

[353] TYSND1

352 Levels: AAR2 AASS … REEP6-B

\end{verbatim} \end{kframe} \end{knitrout}

\begin{knitrout} \definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} \begin{alltt} \hlcom{# genes in common} \hlstd{dginnT}\hlopt{\(}\hlstd{Gene.name[dginnT}\hlopt{\)}\hlstd{Gene.name} \hlopt{%in%} \hlstd{dginnbats}\hlopt{$}\hlstd{Gene.name]} \end{alltt} \begin{verbatim}

[1] AAR2 AASS

[3] AATF ABCC1

[5] ACAD9 ACADM

[7] ACE2 ACSL3

[9] ADAM9 ADAMTS1

[11] AGPS AKAP8

[13] AKAP8L AKAP9

[15] ALG11 ALG5

[17] ALG8 ANO6

[19] AP2A2 AP2M1

[21] AP3B1 ARF6

[23] ATE1 ATP13A3

[25] ATP1B1 ATP6AP1

[27] ATP6V1A BAG5

[29] BCKDK BRD2

[31] BRD4 BZW2

[33] CCDC86 CDK5RAP2

[35] CENPF CEP112

[37] CEP135 CEP250

[39] CEP350 CEP68

[41] CHMP2A CHPF

[43] CHPF2 CISD3

[45] CIT CLCC1

[47] CLIP4 CNTRL

[49] COL6A1 COLGALT1

[51] COMT COQ8B

[53] CRTC3 CSDE1

[55] CSNK2A2 CSNK2B

[57] CUL2 CWC27

[59] CYB5B DCAF7

[61] DCAKD DCTPP1

[63] DDX10 DDX21

[65] DNAJC11 DNAJC19

[67] DNMT1 DPH5

[69] DPY19L1 ECSIT

[71] EDEM3 EIF4E2

[73] EIF4H ELOC

[75] EMC1 ERC1

[77] ERGIC1 ERLEC1

[79] ERMP1 ERO1B

[81] ERP44 ETFA

[83] EXOSC2 EXOSC3

[85] EXOSC5 EXOSC8

[87] F2RL1 FAM162A

[89] FAM8A1 FAM98A

[91] FAR2 FASTKD5

[93] FBLN5 FBN1

[95] FBN2 FBXL12

[97] FKBP10 FKBP15

[99] FKBP7 FOXRED2

[101] FYCO1 G3BP1

[103] G3BP2 GCC1

[105] GCC2 GDF15

[107] GFER GGCX

[109] GGH GHITM

[111] GIGYF2 GLA

[113] GNB1 GNG5

[115] GNG5 GOLGA2

[117] GOLGA3 GOLGA7

[119] GOLGB1 GORASP1

[121] GPAA1 GPX1

[123] GRIPAP1 GRPEL1

[125] GTF2F2 HDAC2

[127] HEATR3 HECTD1

[129] HMOX1 HOOK1

[131] HS2ST1 HS6ST2

[133] HSBP1 HYOU1

[135] IDE IL17RA

[137] IMPDH2 INHBE

[139] INTS4 ITGB1

[141] JAKMIP1 LARP1

[143] LARP4B LARP7

[145] LMAN2 LOX

[147] MAP7D1 MARK1

[149] MARK2 MARK3

[151] MAT2B MDN1

[153] MEPCE MIB1

[155] MIPOL1 MOGS

[157] MOV10 MPHOSPH10

[159] MRPS2 MRPS25

[161] MRPS27 MRPS5

[163] MARC1 MTCH1

[165] MYCBP2 NARS2

[167] NAT14 NDFIP2

[169] NDUFAF1 NDUFAF2

[171] NDUFB9 NEK9

[173] NEU1 NGDN

[175] NGLY1 NIN

[177] NINL NLRX1

[179] NOL10 NPC2

[181] NPTX1 NSD2

[183] NUP210 NUP214

[185] NUP54 NUP58

[187] NUP62 NUP88

[189] NUP98 NUTF2

[191] OS9 PABPC1

[193] PABPC4 PCNT

[195] PCSK6 PCSK5

[197] PDE4DIP PDZD11

[199] PIGO PIGS

[201] PITRM1 PKP2

[203] PLAT PLD3

[205] PLEKHA5 PLEKHF2

[207] PLOD2 PMPCA

[209] PMPCB POFUT1

[211] KDELC1 KDELC2

[213] POLA1 POLA2

[215] POR PPIL3

[217] PPT1 PRIM1

[219] PRIM2 PRKACA

[221] PRKAR2A PRKAR2B

[223] PRRC2B PSMD8

[225] PTBP2 PTGES2

[227] PUSL1 PVR

[229] QSOX2 RAB10

[231] RAB14 RAB18

[233] RAB1A RAB2A

[235] RAB5C RAB7A

[237] RAB8A RAE1

[239] RALA RAP1GDS1

[241] RBM28 RBM41

[243] RBX1 RDX

[245] REEP5 REEP6

[247] RETREG3 RHOA

[249] RIPK1 RNF41

[251] RPL36 RRP9

[253] RTN4 SAAL1

[255] SBNO1 SCAP

[257] SCARB1 SCCPDH

[259] SDF2 SEPSECS

[261] SIL1 SIRT5

[263] SLC25A21 SLC27A2

[265] SLC30A6 SLC30A7

[267] SLC30A9 SLC44A2

[269] SLC9A3R1 SLU7

[271] SMOC1 SNIP1

[273] SPART SRP19

[275] SRP54 SRP72

[277] STC2 STOM

[279] STOML2 SUN2

[281] TAPT1 TARS2

[283] TBCA TBK1

[285] TBKBP1 TCF12

[287] THTPA TIMM10

[289] TIMM10B TIMM29

[291] TIMM8B TIMM9

[293] TLE1 TLE3

[295] TM2D3 TMED5

[297] TMEM39B TMEM97

[299] TMPRSS2 TOMM70

[301] TOR1A TOR1AIP1

[303] TRIM59 TRMT1

[305] TUBGCP2 TUBGCP3

[307] TYSND1 UBAP2

[309] UBAP2L UBXN8

[311] UGGT2 UPF1

[313] USP54 VPS11

[315] VPS39 WASHC4

[317] WFS1 YIF1A

[319] ZC3H18 ZC3H7A

[321] ZDHHC5 ZNF318

[323] ZNF503 ZYG11B

[325] RIPK1

416 Levels: AAR2 AASS … SELENOS

\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] 325

\end{verbatim} \begin{alltt} \hlcom{# genes only in primates} \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] ADAM9[0-3120]

[2] ADAM9[3119-3927]

[3] ATP5MGL

[4] BCS1L

[5] C1H1ORF50

[6] CEP135[0-3264]

[7] CEP135[3263-3678]

[8] CEP43

[9] COQ8A

[10] CSNK2A1

[11] CSNK2B[0-609]

[12] CSNK2B[608-2568]

[13] CYB5R3

[14] CYB5R1

[15] DDX21[0-717]

[16] DDX21[716-2538]

[17] DDX50

[18] DNAJC15

[19] DPH5[0-702]

[20] DPH5[701-1326]

[21] DPY19L2

[22] EXOSC3[0-1446]

[23] EXOSC3[1445-1980]

[24] FBN3

[25] GNB4

[26] GNB2

[27] GNB3

[28] GOLGA7[0-312]

[29] GOLGA7[311-549]

[30] GPX1[0-1218]

[31] GPX1[1217-2946]

[32] HDAC1

[33] HS6ST3

[34] IMPDH1

[35] ITGB1[0-2328]

[36] ITGB1[2327-2844]

[37] LMAN2L

[38] MRPS5[0-1569]

[39] MRPS5[1568-3783]

[40] MARC2

[41] MGRN1

[42] NDFIP2[0-768]

[43] NDFIP2[767-1314]

[44] NDUFAF2[0-258]

[45] NDUFAF2[257-744]

[46] NUP58[0-1824]

[47] NUP58[1823-2367]

[48] PABPC3

[49] POTPABPC1

[50] PABPC4L

[51] PABPC5

[52] PRIM2[0-1071]

[53] PRIM2[1070-1902]

[54] PRKACB

[55] PRKACG

[56] PTGES2[0-1587]

[57] PTGES2[1586-2202]

[58] RAB8B

[59] RAB13

[60] RAB18[0-855]

[61] RAB18[854-1815]

[62] RAB2B

[63] RAB5A

[64] RAB5B

[65] RAB15

[66] RALB

[67] EZR

[68] EZR[0-1458]

[69] EZR[1457-3771]

[70] MSN

[71] RHOB

[72] RHOC

[73] SLC44A2[0-2577]

[74] SLC44A2[2576-3657]

[75] SRP72[0-2604]

[76] SRP72[2603-3417]

[77] STOM[0-1047]

[78] STOM[1046-1800]

[79] STOML3

[80] TLE4

[81] TLE2

[82] TLE2[0-1302]

[83] TLE2[1301-3987]

[84] AES

[85] TOR1B

[86] WFS1[0-2346]

[87] WFS1[2345-3216]

[88] YIF1B

416 Levels: AAR2 AASS … SELENOS

\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] 88

\end{verbatim} \begin{alltt} \hlcom{# genes only in bats} \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] ADAM9[0-2769]

[2] ADAM9[2768-3030]

[3] ARL6IP6

[4] ATP5MG

[5] BCS1

[6] CUNH1ORF50

[7] CYB5BR3

[8] IDE[0-2343]

[9] IDE[2342-3240]

[10] IDE[3239-4911]

[11] MFGE8

[12] PTGES2[0-513]

[13] PTGES2[512-2070]

[14] SCARB1[0-2004]

[15] SCARB1[2003-2289]

[16] SELENOS[0-927]

[17] SELENOS[926-1137]

[18] SIGMAR1

[19] SLC44A2[0-2820]

[20] SLC44A2[2819-3792]

[21] TLE5

[22] USP13

[23] ZC3H18[0-1101]

[24] ZC3H18[1100-3678]

[25] FGFR1OP

[26] ELOB

[27] REEP6-A

[28] REEP6-B

[29] SELENOS

352 Levels: AAR2 AASS … REEP6-B

\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}

\end{document}