Skip to content
Snippets Groups Projects

Compare revisions

Changes are shown as if the source revision was being merged into the target revision. Learn more about comparing revisions.

Source

Select target project
No results found

Target

Select target project
  • mcariou/2020_dginn_covid19
  • ciri/ps_sars-cov-2/2021_dginn_covid19
2 results
Show changes
Commits on Source (9)
Hide whitespace changes
Inline Side-by-side
Showing
with 2389 additions and 674 deletions
covid_comp_bats.Rnw
View file @ 77f559a1
......@@ -15,7 +15,7 @@
\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
\date{Mars 2021} % Activate to display a given date or no date
\begin{document}
\maketitle
......@@ -29,12 +29,13 @@
Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
<<>>=
workdir<-"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"
home<-"/home/adminmarie/Documents/"
workdir<-paste0(home,"CIRI_BIBS_projects/2020_05_Etienne_covid/")
tab<-read.delim(paste0(workdir,
"covid_comp/covid_comp_complete.txt"), h=T, sep="\t")
dim(tab)
tab$Gene.name<-as.character(tab$Gene.name)
tab$Gene.name<-as.character(tab$Gene.name.x)
tab$Gene.name[tab$PreyGene=="MTARC1"]<-"MTARC1"
@
......@@ -43,25 +44,38 @@ tab$Gene.name[tab$PreyGene=="MTARC1"]<-"MTARC1"
\subsection{Cooper-bats results VS DGINN-bats results}
<<omegaM7M8bats>>=
tab$bats_omegaM0codeml[tab$bats_omegaM0codeml=="na"]<-NA
plot(tab$cooper.batsAverage_dNdS, as.numeric(as.character(tab$bats_omegaM0codeml)),
xlab="Omega Cooper-bats", ylab="Omega DGINN-bats")
plot(tab$cooper.batsAverage_dNdS,
as.numeric(as.character(tab$bats_omegaM0codeml)),
xlab="Omega Cooper-bats",
ylab="Omega DGINN-bats")
abline(0,1)
abline(lm(as.numeric(as.character(tab$bats_omegaM0codeml))~tab$cooper.batsAverage_dNdS), col="red")
abline(lm(as.numeric(as.character(tab$bats_omegaM0codeml))~
tab$cooper.batsAverage_dNdS),
col="red")
outlier<-tab[tab$cooper.batsAverage_dNdS>0.35 &
as.numeric(as.character(tab$bats_omegaM0codeml))<0.3,]
text(x=outlier$cooper.batsAverage_dNdS,
y=as.numeric(as.character(outlier$bats_omegaM0codeml)),
outlier$Gene.name)
@
\subsection{Cooper-bats VS Hawkins-bats and DGINN-bats VS Hawkins-bats}
\textit{I don't think we have the omega values}
\section{Overlap}
\subsection{Data}
<<subbats>>=
tmp<-na.omit(tab[,c("Gene.name", "bats_codemlM7M8_p.value", "hawkins_Positive.Selection..M8vM8a.p.value", "cooper.batsM7.M8_p_value", "bats_BUSTED", "bats_BppM1M2", "bats_BppM7M8", "bats_codemlM1M2", "bats_codemlM7M8")])
tmp$bats_codemlM7M8_p.value<-as.numeric(as.character(tmp$bats_codemlM7M8_p.value))
tmp<-na.omit(tab[,c("Gene.name", "bats_codemlM7M8_p.value",
"hawkins_Positive.Selection..M8vM8a.p.value",
"cooper.batsM7.M8_p_value", "bats_BUSTED",
"bats_BppM1M2", "bats_BppM7M8", "bats_codemlM1M2",
"bats_codemlM7M8")])
tmp$bats_codemlM7M8_p.value[tmp$bats_codemlM7M8_p.value=="na"]<-NA
tmp$bats_codemlM7M8_p.value<-as.numeric(
as.character(tmp$bats_codemlM7M8_p.value))
dim(tmp)
@
......@@ -73,18 +87,25 @@ dim(tmp)
library(Mondrian)
monddata<-as.data.frame(tmp$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)
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$bats_BUSTED=="Y"))
dginntmp<-rowSums(cbind(tmp$bats_codemlM1M2=="Y",
tmp$bats_codemlM7M8=="Y",
tmp$bats_BppM1M2=="Y",
tmp$bats_BppM7M8=="Y",
tmp$bats_BUSTED=="Y"))
monddata$bats_dginn<-ifelse(dginntmp>=3, 1,0)
mondrian(monddata[,2:4], labels=c("DGINN >=3", "hawkins", "Cooper"))
mondrian(monddata[,2:4],
labels=c("DGINN >=3", "hawkins", "Cooper"))
monddata$bats_dginn<-ifelse(dginntmp>=4, 1,0)
mondrian(monddata[,2:4], labels=c("DGINN >=4", "hawkins", "Cooper"))
mondrian(monddata[,2:4],
labels=c("DGINN >=4", "hawkins", "Cooper"))
@
\subsection{subsetR}
......@@ -93,8 +114,10 @@ mondrian(monddata[,2:4], labels=c("DGINN >=4", "hawkins", "Cooper"))
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_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)
......@@ -117,23 +140,25 @@ df<-read.delim(paste0(workdir,
fill=T, h=T, sep=",")
names(df)
dftmp<-tab[,c("bats_File", "bats_Name", "Gene.name",
"bats_GeneSize", "bats_NbSpecies", "bats_omegaM0Bpp",
"bats_omegaM0codeml", "bats_BUSTED", "bats_BUSTED_p.value",
"bats_MEME_NbSites", "bats_MEME_PSS", "bats_BppM1M2",
"bats_BppM1M2_p.value", "bats_BppM1M2_NbSites", "bats_BppM1M2_PSS",
"bats_BppM7M8", "bats_BppM7M8_p.value", "bats_BppM7M8_NbSites",
"bats_BppM7M8_PSS", "bats_codemlM1M2", "bats_codemlM1M2_p.value",
"bats_codemlM1M2_NbSites","bats_codemlM1M2_PSS", "bats_codemlM7M8",
"bats_codemlM7M8_p.value", "bats_codemlM7M8_NbSites" , "bats_codemlM7M8_PSS")]
dftmp<-tab[,c("bats_File", "bats_Name",
"Gene.name", "bats_GeneSize",
"bats_NbSpecies", "bats_omegaM0Bpp",
"bats_omegaM0codeml", "bats_BUSTED",
"bats_BUSTED_p.value", "bats_MEME_NbSites",
"bats_MEME_PSS", "bats_BppM1M2",
"bats_BppM1M2_p.value", "bats_BppM1M2_NbSites",
"bats_BppM1M2_PSS", "bats_BppM7M8",
"bats_BppM7M8_p.value", "bats_BppM7M8_NbSites",
"bats_BppM7M8_PSS", "bats_codemlM1M2",
"bats_codemlM1M2_p.value", "bats_codemlM1M2_NbSites",
"bats_codemlM1M2_PSS", "bats_codemlM7M8",
"bats_codemlM7M8_p.value", "bats_codemlM7M8_NbSites" ,
"bats_codemlM7M8_PSS")]
names(dftmp)<-names(df)
makeFig1(dftmp)
@
\end{document}
......
covid_comp_bats.pdf
View file @ 77f559a1
No preview for this file type
covid_comp_bats.tex
View file @ 77f559a1
......@@ -65,7 +65,7 @@
\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
\date{Mars 2021} % Activate to display a given date or no date
\IfFileExists{upquote.sty}{\usepackage{upquote}}{}
\begin{document}
\maketitle
......@@ -81,17 +81,18 @@ 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{home}\hlkwb{<-}\hlstr{"/home/adminmarie/Documents/"}
\hlstd{workdir}\hlkwb{<-}\hlkwd{paste0}\hlstd{(home,}\hlstr{"CIRI_BIBS_projects/2020_05_Etienne_covid/"}\hlstd{)}
\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] 332 139
## [1] 332 141
\end{verbatim}
\begin{alltt}
\hlstd{tab}\hlopt{$}\hlstd{Gene.name}\hlkwb{<-}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{Gene.name)}
\hlstd{tab}\hlopt{$}\hlstd{Gene.name}\hlkwb{<-}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{Gene.name.x)}
\hlstd{tab}\hlopt{$}\hlstd{Gene.name[tab}\hlopt{$}\hlstd{PreyGene}\hlopt{==}\hlstr{"MTARC1"}\hlstd{]}\hlkwb{<-}\hlstr{"MTARC1"}
\end{alltt}
\end{kframe}
......@@ -104,26 +105,30 @@ 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}
\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}
\hlstd{tab}\hlopt{$}\hlstd{bats_omegaM0codeml[tab}\hlopt{$}\hlstd{bats_omegaM0codeml}\hlopt{==}\hlstr{"na"}\hlstd{]}\hlkwb{<-}\hlnum{NA}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning in xy.coords(x, y, xlabel, ylabel, log): NAs introduits lors de la conversion automatique}}\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{)}
\hlkwd{abline}\hlstd{(}\hlnum{0}\hlstd{,}\hlnum{1}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlkwd{lm}\hlstd{(}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{bats_omegaM0codeml))}\hlopt{~}\hlstd{tab}\hlopt{$}\hlstd{cooper.batsAverage_dNdS),} \hlkwc{col}\hlstd{=}\hlstr{"red"}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlkwd{lm}\hlstd{(}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{bats_omegaM0codeml))}\hlopt{~}
\hlstd{tab}\hlopt{$}\hlstd{cooper.batsAverage_dNdS),}
\hlkwc{col}\hlstd{=}\hlstr{"red"}\hlstd{)}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{cooper.batsAverage_dNdS}\hlopt{>}\hlnum{0.35} \hlopt{&}
\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{bats_omegaM0codeml))}\hlopt{<}\hlnum{0.3}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{cooper.batsAverage_dNdS,}
\hlkwc{y}\hlstd{=}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(outlier}\hlopt{$}\hlstd{bats_omegaM0codeml)),}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name)}
\end{alltt}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning in eval(predvars, data, env): NAs introduits lors de la conversion automatique}}\end{kframe}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/omegaM7M8bats-1}
\end{knitrout}
\subsection{Cooper-bats VS Hawkins-bats and DGINN-bats VS Hawkins-bats}
\textit{I don't think we have the omega values}
\section{Overlap}
\subsection{Data}
......@@ -131,17 +136,19 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tmp}\hlkwb{<-}\hlkwd{na.omit}\hlstd{(tab[,}\hlkwd{c}\hlstd{(}\hlstr{"Gene.name"}\hlstd{,} \hlstr{"bats_codemlM7M8_p.value"}\hlstd{,} \hlstr{"hawkins_Positive.Selection..M8vM8a.p.value"}\hlstd{,} \hlstr{"cooper.batsM7.M8_p_value"}\hlstd{,} \hlstr{"bats_BUSTED"}\hlstd{,} \hlstr{"bats_BppM1M2"}\hlstd{,} \hlstr{"bats_BppM7M8"}\hlstd{,} \hlstr{"bats_codemlM1M2"}\hlstd{,} \hlstr{"bats_codemlM7M8"}\hlstd{)])}
\hlstd{tmp}\hlopt{$}\hlstd{bats_codemlM7M8_p.value}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tmp}\hlopt{$}\hlstd{bats_codemlM7M8_p.value))}
\end{alltt}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning: NAs introduits lors de la conversion automatique}}\begin{alltt}
\hlstd{tmp}\hlkwb{<-}\hlkwd{na.omit}\hlstd{(tab[,}\hlkwd{c}\hlstd{(}\hlstr{"Gene.name"}\hlstd{,} \hlstr{"bats_codemlM7M8_p.value"}\hlstd{,}
\hlstr{"hawkins_Positive.Selection..M8vM8a.p.value"}\hlstd{,}
\hlstr{"cooper.batsM7.M8_p_value"}\hlstd{,} \hlstr{"bats_BUSTED"}\hlstd{,}
\hlstr{"bats_BppM1M2"}\hlstd{,} \hlstr{"bats_BppM7M8"}\hlstd{,} \hlstr{"bats_codemlM1M2"}\hlstd{,}
\hlstr{"bats_codemlM7M8"}\hlstd{)])}
\hlstd{tmp}\hlopt{$}\hlstd{bats_codemlM7M8_p.value[tmp}\hlopt{$}\hlstd{bats_codemlM7M8_p.value}\hlopt{==}\hlstr{"na"}\hlstd{]}\hlkwb{<-}\hlnum{NA}
\hlstd{tmp}\hlopt{$}\hlstd{bats_codemlM7M8_p.value}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}
\hlkwd{as.character}\hlstd{(tmp}\hlopt{$}\hlstd{bats_codemlM7M8_p.value))}
\hlkwd{dim}\hlstd{(tmp)}
\end{alltt}
\begin{verbatim}
## [1] 170 9
## [1] 174 9
\end{verbatim}
\end{kframe}
\end{knitrout}
......@@ -156,21 +163,28 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\hlkwd{library}\hlstd{(Mondrian)}
\hlstd{monddata}\hlkwb{<-}\hlkwd{as.data.frame}\hlstd{(tmp}\hlopt{$}\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{monddata}\hlopt{$}\hlstd{bats_hawkins}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(}
\hlstd{tmp}\hlopt{$}\hlstd{hawkins_Positive.Selection..M8vM8a.p.value}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{bats_cooper}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(}
\hlstd{tmp}\hlopt{$}\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{$}\hlstd{bats_BUSTED}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlstd{dginntmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tmp}\hlopt{$}\hlstd{bats_codemlM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstd{bats_codemlM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstd{bats_BppM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstd{bats_BppM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstd{bats_BUSTED}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlstd{monddata}\hlopt{$}\hlstd{bats_dginn}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginntmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlkwd{mondrian}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{],} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"DGINN >=3"}\hlstd{,} \hlstr{"hawkins"}\hlstd{,} \hlstr{"Cooper"}\hlstd{))}
\hlkwd{mondrian}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{],}
\hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"DGINN >=3"}\hlstd{,} \hlstr{"hawkins"}\hlstd{,} \hlstr{"Cooper"}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/mondrianbats-1}
\begin{kframe}\begin{alltt}
\hlstd{monddata}\hlopt{$}\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{))}
\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}
......@@ -185,8 +199,10 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\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_hawkins}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(}
\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{(}
\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{)}
......@@ -230,15 +246,20 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
## [25] "codemlM7M8.p.value" "codemlM7M8.NbSites" "codemlM7M8.PSS"
\end{verbatim}
\begin{alltt}
\hlstd{dftmp}\hlkwb{<-}\hlstd{tab[,}\hlkwd{c}\hlstd{(}\hlstr{"bats_File"}\hlstd{,} \hlstr{"bats_Name"}\hlstd{,} \hlstr{"Gene.name"}\hlstd{,}
\hlstr{"bats_GeneSize"}\hlstd{,} \hlstr{"bats_NbSpecies"}\hlstd{,} \hlstr{"bats_omegaM0Bpp"}\hlstd{,}
\hlstr{"bats_omegaM0codeml"}\hlstd{,} \hlstr{"bats_BUSTED"}\hlstd{,} \hlstr{"bats_BUSTED_p.value"}\hlstd{,}
\hlstr{"bats_MEME_NbSites"}\hlstd{,} \hlstr{"bats_MEME_PSS"}\hlstd{,} \hlstr{"bats_BppM1M2"}\hlstd{,}
\hlstr{"bats_BppM1M2_p.value"}\hlstd{,} \hlstr{"bats_BppM1M2_NbSites"}\hlstd{,} \hlstr{"bats_BppM1M2_PSS"}\hlstd{,}
\hlstr{"bats_BppM7M8"}\hlstd{,} \hlstr{"bats_BppM7M8_p.value"}\hlstd{,} \hlstr{"bats_BppM7M8_NbSites"}\hlstd{,}
\hlstr{"bats_BppM7M8_PSS"}\hlstd{,} \hlstr{"bats_codemlM1M2"}\hlstd{,} \hlstr{"bats_codemlM1M2_p.value"}\hlstd{,}
\hlstr{"bats_codemlM1M2_NbSites"}\hlstd{,}\hlstr{"bats_codemlM1M2_PSS"}\hlstd{,} \hlstr{"bats_codemlM7M8"}\hlstd{,}
\hlstr{"bats_codemlM7M8_p.value"}\hlstd{,} \hlstr{"bats_codemlM7M8_NbSites"} \hlstd{,} \hlstr{"bats_codemlM7M8_PSS"}\hlstd{)]}
\hlstd{dftmp}\hlkwb{<-}\hlstd{tab[,}\hlkwd{c}\hlstd{(}\hlstr{"bats_File"}\hlstd{,} \hlstr{"bats_Name"}\hlstd{,}
\hlstr{"Gene.name"}\hlstd{,} \hlstr{"bats_GeneSize"}\hlstd{,}
\hlstr{"bats_NbSpecies"}\hlstd{,} \hlstr{"bats_omegaM0Bpp"}\hlstd{,}
\hlstr{"bats_omegaM0codeml"}\hlstd{,} \hlstr{"bats_BUSTED"}\hlstd{,}
\hlstr{"bats_BUSTED_p.value"}\hlstd{,} \hlstr{"bats_MEME_NbSites"}\hlstd{,}
\hlstr{"bats_MEME_PSS"}\hlstd{,} \hlstr{"bats_BppM1M2"}\hlstd{,}
\hlstr{"bats_BppM1M2_p.value"}\hlstd{,} \hlstr{"bats_BppM1M2_NbSites"}\hlstd{,}
\hlstr{"bats_BppM1M2_PSS"}\hlstd{,} \hlstr{"bats_BppM7M8"}\hlstd{,}
\hlstr{"bats_BppM7M8_p.value"}\hlstd{,} \hlstr{"bats_BppM7M8_NbSites"}\hlstd{,}
\hlstr{"bats_BppM7M8_PSS"}\hlstd{,} \hlstr{"bats_codemlM1M2"}\hlstd{,}
\hlstr{"bats_codemlM1M2_p.value"}\hlstd{,} \hlstr{"bats_codemlM1M2_NbSites"}\hlstd{,}
\hlstr{"bats_codemlM1M2_PSS"}\hlstd{,} \hlstr{"bats_codemlM7M8"}\hlstd{,}
\hlstr{"bats_codemlM7M8_p.value"}\hlstd{,} \hlstr{"bats_codemlM7M8_NbSites"} \hlstd{,}
\hlstr{"bats_codemlM7M8_PSS"}\hlstd{)]}
\hlkwd{names}\hlstd{(dftmp)}\hlkwb{<-}\hlkwd{names}\hlstd{(df)}
\hlkwd{makeFig1}\hlstd{(dftmp)}
......
covid_comp_dataset.Rnw
View file @ 77f559a1
......@@ -15,7 +15,7 @@
\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
\date{March 2021} % Activate to display a given date or no date
\begin{document}
\maketitle
......@@ -28,19 +28,18 @@
Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
<<eval=FALSE>>=
workdir<-"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"
home<-"/home/adminmarie/Documents/"
workdir<-paste0(home, "CIRI_BIBS_projects/2020_05_Etienne_covid/")
tab<-read.delim(paste0(workdir,
"covid_comp/covid_comp_complete.txt"), h=T, sep="\t")
dim(tab)
@
<<>>=
workdir<-"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"
home<-"/home/adminmarie/Documents/"
workdir<-paste0(home, "CIRI_BIBS_projects/2020_05_Etienne_covid/")
tab<-read.delim(paste0(workdir,
"covid_comp/covid_comp_alldginn.txt"), h=T, sep="\t")
......@@ -52,31 +51,42 @@ dim(tab)
\subsection{Data}
<<data>>=
tmp<-na.omit(tab[,c("Gene.name", "bats_BUSTED", "bats_BppM1M2", "bats_BppM7M8",
"bats_codemlM1M2", "bats_codemlM7M8", "dginn.primate_codemlM1M2",
"dginn.primate_codemlM7M8", "dginn.primate_BppM1M2",
"dginn.primate_BppM7M8", "dginn.primate_BUSTED")])
col<-c("Gene.name", "bats_BUSTED", "bats_BppM1M2", "bats_BppM7M8",
"bats_codemlM1M2", "bats_codemlM7M8", "dginn.primate_codemlM1M2",
"dginn.primate_codemlM7M8", "dginn.primate_BppM1M2",
"dginn.primate_BppM7M8", "dginn.primate_BUSTED")
tmp<-na.omit(tab[,c("Gene.name", "bats_BUSTED", "bats_BppM1M2",
"bats_BppM7M8", "bats_codemlM1M2", "bats_codemlM7M8",
"dginn.primate_codemlM1M2", "dginn.primate_codemlM7M8",
"dginn.primate_BppM1M2", "dginn.primate_BppM7M8",
"dginn.primate_BUSTED")])
col<-c("Gene.name", "bats_BUSTED", "bats_BppM1M2",
"bats_BppM7M8", "bats_codemlM1M2", "bats_codemlM7M8",
"dginn.primate_codemlM1M2", "dginn.primate_codemlM7M8",
"dginn.primate_BppM1M2", "dginn.primate_BppM7M8",
"dginn.primate_BUSTED")
dim(tmp)
@
\subsection{Omega plot}
<<>>=
x=as.numeric(as.character(tab$dginn.primate_omegaM0Bpp[tab$status=="shared"]))
y=as.numeric(as.character(tab$bats_omegaM0Bpp[tab$status=="shared"]))
tab$dginn.primate_omegaM0Bpp[tab$dginn.primate_omegaM0Bpp=="na"]<-NA
x=as.numeric(as.character(
tab$dginn.primate_omegaM0Bpp[tab$status=="shared"]))
tab$bats_omegaM0Bpp[tab$bats_omegaM0Bpp=="na"]<-NA
y=as.numeric(as.character(
tab$bats_omegaM0Bpp[tab$status=="shared"]))
names(x)<-tab$Gene.name[tab$status=="shared"]
plot(x,y, xlab="bpp omega primate", ylab="bpp omega bats", cex=0.5)
abline(0,1)
abline(lm(y~x), col="red")
text(x[x>0.5 &y<0.4], (y[x>0.5 &y<0.4]+0.01), names(x)[x>0.5 &y<0.4], cex=0.7)
text(x[x<0.45 &y>0.45], (y[x<0.45 &y>0.45]+0.01), names(x)[x<0.45 &y>0.45], cex=0.7)
text(x[x>0.45 &y>0.4], (y[x>0.45 &y>0.4]+0.01), names(x)[x>0.45 &y>0.4], cex=0.7)
text(x[x>0.5 &y<0.4], (y[x>0.5 &y<0.4]+0.01),
names(x)[x>0.5 &y<0.4], cex=0.7)
text(x[x<0.45 &y>0.45], (y[x<0.45 &y>0.45]+0.01),
names(x)[x<0.45 &y>0.45], cex=0.7)
text(x[x>0.45 &y>0.4], (y[x>0.45 &y>0.4]+0.01),
names(x)[x>0.45 &y>0.4], cex=0.7)
@
......@@ -87,21 +97,28 @@ library(Mondrian)
monddata<-as.data.frame(tmp$Gene.name)
batstmp<-rowSums(cbind(tmp$bats_codemlM1M2=="Y", tmp$bats_codemlM7M8=="Y",
tmp$bats_BppM1M2=="Y", tmp$bats_BppM7M8=="Y", tmp$bats_BUSTED=="Y"))
primatetmp<-rowSums(cbind(tmp$"dginn.primate_codemlM1M2"=="Y",
tmp$"dginn.primate_codemlM7M8"=="Y", tmp$"dginn.primate_BppM1M2"=="Y",
tmp$"dginn.primate_BppM7M8"=="Y", tmp$"dginn.primate_BUSTED"=="Y"))
batstmp<-rowSums(cbind(tmp$bats_codemlM1M2=="Y",
tmp$bats_codemlM7M8=="Y",
tmp$bats_BppM1M2=="Y",
tmp$bats_BppM7M8=="Y",
tmp$bats_BUSTED=="Y"))
primatetmp<-rowSums(cbind(tmp$"dginn.primate_codemlM1M2"=="Y",
tmp$"dginn.primate_codemlM7M8"=="Y",
tmp$"dginn.primate_BppM1M2"=="Y",
tmp$"dginn.primate_BppM7M8"=="Y",
tmp$"dginn.primate_BUSTED"=="Y"))
monddata$bats_dginn3<-ifelse(batstmp>=3, 1,0)
monddata$primate_dginn3<-ifelse(primatetmp>=3, 1,0)
monddata$bats_dginn4<-ifelse(batstmp>=4, 1,0)
monddata$primate_dginn4<-ifelse(primatetmp>=4, 1,0)
mondrian(monddata[,2:3], labels=c("DGINN bats >3", "DGINN primate >3"))
mondrian(monddata[,2:3],
labels=c("DGINN bats >3", "DGINN primate >3"))
mondrian(monddata[,4:5], labels=c("DGINN bats >4", "DGINN primate >4"))
mondrian(monddata[,4:5],
labels=c("DGINN bats >4", "DGINN primate >4"))
@
......@@ -173,7 +190,11 @@ tablo<-as.data.frame(tmp$Gene.name)
tablo$nbats<-batstmp
tablo$nprimates<-primatetmp
plot(NULL, xlim=c(-0.5,5.5), ylim=c(-3,5.5), xlab="bats", ylab="primates", main="Genes supported by x,y methods in bats and primates", bty="n", xaxt="n", yaxt="n")
plot(NULL, xlim=c(-0.5,5.5), ylim=c(-3,5.5),
xlab="bats", ylab="primates",
main="Genes supported by x,y methods in bats and primates",
bty="n",
xaxt="n", yaxt="n")
text(x=rep(-0.6, 6), y=0:5, 0:5)
text(y=rep(-0.65, 6), x=0:5, 0:5)
......@@ -189,11 +210,14 @@ for (p in 0:5){
for (b in 0:5){
tmp<-tablo$`tmp$Gene.name`[tablo$nbats==b & tablo$nprimates==p]
if(length(tmp)>0 & length(tmp)<=8){
text(b,seq(from=(p-0.4), to=(p+0.4), length.out = length(tmp)), tmp, cex=0.4)
text(b,seq(from=(p-0.4), to=(p+0.4), length.out = length(tmp)),
tmp, cex=0.4)
}else if (length(tmp)>8 & length(tmp)<=16){
print(c(p, b))
text((b-0.3),seq(from=(p-0.4), to=(p+0.4), length.out = 8), tmp[1:8], cex=0.4)
text((b+0.3),seq(from=(p-0.4), to=(p+0.4), length.out = (length(tmp)-8)), tmp[9:length(tmp)], cex=0.4)
text((b-0.3),seq(from=(p-0.4), to=(p+0.4), length.out = 8),
tmp[1:8], cex=0.4)
text((b+0.3),seq(from=(p-0.4), to=(p+0.4), length.out = (length(tmp)-8)),
tmp[9:length(tmp)], cex=0.4)
}else if (length(tmp)>16){
text(b,p, paste0(length(tmp), " values"))
}
......@@ -203,13 +227,25 @@ for (p in 0:5){
tmp<-tablo$`tmp$Gene.name`[tablo$nbats==0 & tablo$nprimates==1]
text(-0.4,-1.2, "p=1/n=0", cex=0.6)
text(seq(from=0.1, to=5.5, length.out = 18),-1.1, tmp[1:18], cex=0.4)
text(seq(from=0.1, to=5.5, length.out = length(tmp)-18),-1.3, tmp[19:length(tmp)], cex=0.4)
text(seq(from=0.1, to=5.5, length.out = 19),
-1.1,
tmp[1:19],
cex=0.4)
text(seq(from=0.1, to=5.5, length.out = length(tmp)-19),
-1.3,
tmp[20:length(tmp)],
cex=0.4)
tmp<-tablo$`tmp$Gene.name`[tablo$nbats==1 & tablo$nprimates==1]
text(-0.4,-1.7, "p=1/n=1", cex=0.6)
text(seq(from=0.1, to=5.5, length.out = 18),-1.6, tmp[1:18], cex=0.4)
text(seq(from=0.1, to=4.5, length.out = length(tmp)-18),-1.8, tmp[19:length(tmp)], cex=0.4)
text(seq(from=0.1, to=5.5, length.out = 18),
-1.6,
tmp[1:18],
cex=0.4)
text(seq(from=0.1, to=4.5, length.out = length(tmp)-18),
-1.8,
tmp[19:length(tmp)],
cex=0.4)
tmp<-tablo$`tmp$Gene.name`[tablo$nbats==0 & tablo$nprimates==0]
......@@ -227,10 +263,16 @@ text(seq(from=0.1, to=1, length.out = length(tmp)-18),-3.0, tmp[19:length(tmp)],
@
<<>>=
write.csv(tablo[tablo$nbats>=3,"tmp$Gene.name"], "batssup3.csv", row.names=FALSE, quote=FALSE)
write.csv(tablo[tablo$nprimates>=3,"tmp$Gene.name"], "primatessup3.csv", row.names=FALSE, quote=FALSE)
write.csv(tablo, "primatesVbats.csv", row.names=FALSE, quote=FALSE)
write.csv(tablo[tablo$nbats>=3,"tmp$Gene.name"], "batssup3.csv",
row.names=FALSE,
quote=FALSE)
write.csv(tablo[tablo$nprimates>=3,"tmp$Gene.name"], "primatessup3.csv",
row.names=FALSE,
quote=FALSE)
write.csv(tablo, "primatesVbats.csv",
row.names=FALSE,
quote=FALSE)
@
Restreindre ce tableau aux gènes présent dans l'analyse de Krogan.
......@@ -271,7 +313,7 @@ write.csv(tabloK, "primatesVbats_onlykrogan.csv", row.names=FALSE, quote=FALSE)
\section{Tanglegram}
<<eval=FALSE>>=
<<eval=TRUE>>=
#install.packages('dendextend') # stable CRAN version
library(dendextend) # load the package
#install.packages("phytools") # stable CRAN version
......@@ -280,15 +322,13 @@ library(ggraph)
library(igraph)
library(tidyverse)
##
tmp<-tablo[(tablo$nbats!=0 | tablo$nprimates!=0),]
tmp<-head(tablo, 20)
#tmp<-head(tablo, 20)
#tmp<-rbind(as.matrix(tmp), c("outgroup", 50, 50))
tmp<-as.data.frame(tmp)
matbats<-hclust(dist(tmp$nbats))
matpri<-hclust(dist(tmp$nprimates))
tmp[order(tmp$nbats),]
dendpri<-as.dendrogram(matpri)
......@@ -305,14 +345,11 @@ tmp[order(tmp$nbats, decreasing=FALSE),]$'tmp$Gene.name'-> order
dendbats<-dendextend::rotate(dendbats, order=order)
#### Il faut swapper certains neud de l'arbrese
class(labels(dendpri))
dend12 <- dendlist(dendbats, dendpri)
?png
png("tanglegramm.png", width = 1800, height = 3000)
png("figure/tanglegramm.png", width = 1800, height = 3000)
tanglegram(dend12, columns_width=c(3, 3,3), axes=FALSE,
edge.lwd=0, margin_inner=6,
margin_top=2,
......@@ -325,12 +362,151 @@ tanglegram(dend12, columns_width=c(3, 3,3), axes=FALSE,
dev.off()
tmp
?tanglegram
@
<<eval=TRUE>>=
ace<-264
tmprss2<-75
znf318<-81
sepsecs<-228
tbk1<-273
ripk1<-224
col<-rep("grey", length(labels(dendpri)))
col[ace]<-"black"
col[tmprss2]<-"black"
col[znf318]<-"black"
col[sepsecs]<-"black"
col[tbk1]<-"black"
col[ripk1]<-"black"
font<-rep(1, length(labels(dendpri))*2)
#font[ace]<-1.3
#font[tmprss2]<-1.3
#font[length(labels(dendpri))+160]<-1.3
png("figure/tanglegramm.png", width = 1800, height = 3000)
tanglegram(dend12, columns_width=c(3, 3,3), axes=FALSE,
edge.lwd=0, margin_inner=6,
margin_top=2,
main_left=" bats",
main_right = "primates ",
lwd=0.5,
cex_main=1,
lab.cex=font,
k_labels=6,
color_lines=col)
dev.off()
@
<<>>=
tmp<-tablo[(tablo$nbats>=3 | tablo$nprimates>=3),]
dim(tmp)
tmp<-as.data.frame(tmp)
names(tmp)<-c("tmp.Gene.name", "nbats", "nprimates")
matbats<-hclust(dist(tmp$nbats))
matpri<-hclust(dist(tmp$nprimates))
#tmp[order(tmp$nbats),]
dendpri<-as.dendrogram(matpri)
dendbats<-as.dendrogram(matbats)
labels(dendpri)<-as.character(tmp$tmp.Gene.name[labels(dendpri)])
labels(dendbats)<-as.character(tmp$tmp.Gene.name[labels(dendbats)])
tmp[order(tmp$nprimates, decreasing=FALSE),]$tmp.Gene.name-> order
dendpri<-dendextend::rotate(dendpri, order=order)
tmp[order(tmp$nbats, decreasing=FALSE),]$tmp.Gene.name-> order
dendbats<-dendextend::rotate(dendbats, order=order)
#### Il faut swapper certains neuds de l'arbres
class(labels(dendpri))
dend12 <- dendlist(dendbats, dendpri)
ace<-97
tmprss2<-27
znf318<-31
sepsecs<-69
tbk1<-106
ripk1<-68
col<-rep("lightblue", length(labels(dendpri)))
plusplus<-tmp$tmp.Gene.name[tmp$nbats>=3 & tmp$nprimates>=3]
col[which(labels(dendbats) %in% plusplus)]<-"pink"
interest<-c("TMPRSS2","ZNF318", "SEPSECS","TBK1", "RIPK1")
col[which(labels(dendbats) %in% interest)]<-"blue"
interestpp<-c("ACE2")
col[which(labels(dendbats) %in% interestpp)]<-"red"
png("figure/tanglegrammsup3.png", width = 500, height = 1200)
tanglegram(dend12, columns_width=c(3, 3,3), axes=FALSE,
edge.lwd=0, margin_inner=6,
margin_top=3,
main_left=" bats",
main_right = "primates ",
lwd=0.5,
cex_main=2,
lab.cex=1,
k_labels=6,
color_lines=col)
dev.off()
### Changer couleurs des groupes
## changer couleurs des lines sel vs sel or sel vs non-sel
setEPS()
postscript("figure/tanglegramsup3.eps", height=15, width=5)
tanglegram(dend12, columns_width=c(3, 3,3), axes=FALSE,
edge.lwd=0, margin_inner=6,
margin_top=3,
main_left=" bats",
main_right = "primates ",
lwd=0.5,
cex_main=2,
lab.cex=1,
# k_labels=6,
color_lines=col)
dev.off()
labels_colors(dend12[[1]])<-rep(rainbow(15)[c(1:3, 9:11)], table(tmp$nbats))
labels_colors(dend12[[2]])<-rep(rainbow(15)[c(1:3, 9:11)], table(tmp$nprimates))
labels_colors(dend12[[1]])<-rep(viridis(10)[c(1:3, 7:9)], table(tmp$nbats))
labels_colors(dend12[[2]])<-rep(viridis(10)[c(1:3, 7:9)], table(tmp$nprimates))
setEPS()
postscript("figure/tanglegramsup3_V2.eps", height=15, width=5)
tanglegram(dend12, columns_width=c(3, 3,3), axes=FALSE,
edge.lwd=0, margin_inner=6,
margin_top=3,
main_left=" bats",
main_right = "primates ",
lwd=0.5,
cex_main=2,
lab.cex=1,
# k_labels=6,
color_lines=col)
dev.off()
@
\end{document}
......
covid_comp_dataset.log deleted 100644 → 0
View file @ 762975f5
This is pdfTeX, Version 3.14159265-2.6-1.40.18 (TeX Live 2017/Debian) (preloaded format=pdflatex 2021.2.23) 26 FEB 2021 17:33
entering extended mode
restricted \write18 enabled.
%&-line parsing enabled.
**covid_comp_dataset.tex
(./covid_comp_dataset.tex
LaTeX2e <2017-04-15>
Babel <3.18> and hyphenation patterns for 3 language(s) loaded.
(/usr/share/texlive/texmf-dist/tex/latex/base/article.cls
Document Class: article 2014/09/29 v1.4h Standard LaTeX document class
(/usr/share/texlive/texmf-dist/tex/latex/base/size11.clo
File: size11.clo 2014/09/29 v1.4h Standard LaTeX file (size option)
)
\c@part=\count79
\c@section=\count80
\c@subsection=\count81
\c@subsubsection=\count82
\c@paragraph=\count83
\c@subparagraph=\count84
\c@figure=\count85
\c@table=\count86
\abovecaptionskip=\skip41
\belowcaptionskip=\skip42
\bibindent=\dimen102
) (/usr/share/texlive/texmf-dist/tex/latex/graphics/graphicx.sty
Package: graphicx 2017/06/01 v1.1a Enhanced LaTeX Graphics (DPC,SPQR)
(/usr/share/texlive/texmf-dist/tex/latex/graphics/keyval.sty
Package: keyval 2014/10/28 v1.15 key=value parser (DPC)
\KV@toks@=\toks14
) (/usr/share/texlive/texmf-dist/tex/latex/graphics/graphics.sty
Package: graphics 2017/06/25 v1.2c Standard LaTeX Graphics (DPC,SPQR)
(/usr/share/texlive/texmf-dist/tex/latex/graphics/trig.sty
Package: trig 2016/01/03 v1.10 sin cos tan (DPC)
) (/usr/share/texlive/texmf-dist/tex/latex/graphics-cfg/graphics.cfg
File: graphics.cfg 2016/06/04 v1.11 sample graphics configuration
)
Package graphics Info: Driver file: pdftex.def on input line 99.
(/usr/share/texlive/texmf-dist/tex/latex/graphics-def/pdftex.def
File: pdftex.def 2018/01/08 v1.0l Graphics/color driver for pdftex
))
\Gin@req@height=\dimen103
\Gin@req@width=\dimen104
) (/usr/share/texlive/texmf-dist/tex/latex/graphics/color.sty
Package: color 2016/07/10 v1.1e Standard LaTeX Color (DPC)
(/usr/share/texlive/texmf-dist/tex/latex/graphics-cfg/color.cfg
File: color.cfg 2016/01/02 v1.6 sample color configuration
)
Package color Info: Driver file: pdftex.def on input line 147.
)
! LaTeX Error: File `framed.sty' not found.
Type X to quit or <RETURN> to proceed,
or enter new name. (Default extension: sty)
Enter file name:
! Emergency stop.
<read *>
l.27 \makeatletter
^^M
Here is how much of TeX's memory you used:
648 strings out of 494923
8115 string characters out of 6180742
57123 words of memory out of 5000000
4029 multiletter control sequences out of 15000+600000
3940 words of font info for 15 fonts, out of 8000000 for 9000
14 hyphenation exceptions out of 8191
25i,0n,19p,276b,36s stack positions out of 5000i,500n,10000p,200000b,80000s
! ==> Fatal error occurred, no output PDF file produced!
covid_comp_dataset.pdf
View file @ 77f559a1
No preview for this file type
covid_comp_dataset.tex
View file @ 77f559a1
......@@ -65,7 +65,7 @@
\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
\date{March 2021} % Activate to display a given date or no date
\IfFileExists{upquote.sty}{\usepackage{upquote}}{}
\begin{document}
\maketitle
......@@ -78,11 +78,11 @@
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{home}\hlkwb{<-}\hlstr{"/home/adminmarie/Documents/"}
\hlstd{workdir}\hlkwb{<-}\hlkwd{paste0}\hlstd{(home,} \hlstr{"CIRI_BIBS_projects/2020_05_Etienne_covid/"}\hlstd{)}
\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{)}
......@@ -91,12 +91,11 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\end{kframe}
\end{knitrout}
\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{home}\hlkwb{<-}\hlstr{"/home/adminmarie/Documents/"}
\hlstd{workdir}\hlkwb{<-}\hlkwd{paste0}\hlstd{(home,} \hlstr{"CIRI_BIBS_projects/2020_05_Etienne_covid/"}\hlstd{)}
\hlstd{tab}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,}
\hlstr{"covid_comp/covid_comp_alldginn.txt"}\hlstd{),} \hlkwc{h}\hlstd{=T,} \hlkwc{sep}\hlstd{=}\hlstr{"\textbackslash{}t"}\hlstd{)}
......@@ -115,18 +114,20 @@ 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{tmp}\hlkwb{<-}\hlkwd{na.omit}\hlstd{(tab[,}\hlkwd{c}\hlstd{(}\hlstr{"Gene.name"}\hlstd{,} \hlstr{"bats_BUSTED"}\hlstd{,} \hlstr{"bats_BppM1M2"}\hlstd{,} \hlstr{"bats_BppM7M8"}\hlstd{,}
\hlstr{"bats_codemlM1M2"}\hlstd{,} \hlstr{"bats_codemlM7M8"}\hlstd{,} \hlstr{"dginn.primate_codemlM1M2"}\hlstd{,}
\hlstr{"dginn.primate_codemlM7M8"}\hlstd{,} \hlstr{"dginn.primate_BppM1M2"}\hlstd{,}
\hlstr{"dginn.primate_BppM7M8"}\hlstd{,} \hlstr{"dginn.primate_BUSTED"}\hlstd{)])}
\hlstd{col}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"Gene.name"}\hlstd{,} \hlstr{"bats_BUSTED"}\hlstd{,} \hlstr{"bats_BppM1M2"}\hlstd{,} \hlstr{"bats_BppM7M8"}\hlstd{,}
\hlstr{"bats_codemlM1M2"}\hlstd{,} \hlstr{"bats_codemlM7M8"}\hlstd{,} \hlstr{"dginn.primate_codemlM1M2"}\hlstd{,}
\hlstr{"dginn.primate_codemlM7M8"}\hlstd{,} \hlstr{"dginn.primate_BppM1M2"}\hlstd{,}
\hlstr{"dginn.primate_BppM7M8"}\hlstd{,} \hlstr{"dginn.primate_BUSTED"}\hlstd{)}
\hlstd{tmp}\hlkwb{<-}\hlkwd{na.omit}\hlstd{(tab[,}\hlkwd{c}\hlstd{(}\hlstr{"Gene.name"}\hlstd{,} \hlstr{"bats_BUSTED"}\hlstd{,} \hlstr{"bats_BppM1M2"}\hlstd{,}
\hlstr{"bats_BppM7M8"}\hlstd{,} \hlstr{"bats_codemlM1M2"}\hlstd{,} \hlstr{"bats_codemlM7M8"}\hlstd{,}
\hlstr{"dginn.primate_codemlM1M2"}\hlstd{,} \hlstr{"dginn.primate_codemlM7M8"}\hlstd{,}
\hlstr{"dginn.primate_BppM1M2"}\hlstd{,} \hlstr{"dginn.primate_BppM7M8"}\hlstd{,}
\hlstr{"dginn.primate_BUSTED"}\hlstd{)])}
\hlstd{col}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"Gene.name"}\hlstd{,} \hlstr{"bats_BUSTED"}\hlstd{,} \hlstr{"bats_BppM1M2"}\hlstd{,}
\hlstr{"bats_BppM7M8"}\hlstd{,} \hlstr{"bats_codemlM1M2"}\hlstd{,} \hlstr{"bats_codemlM7M8"}\hlstd{,}
\hlstr{"dginn.primate_codemlM1M2"}\hlstd{,} \hlstr{"dginn.primate_codemlM7M8"}\hlstd{,}
\hlstr{"dginn.primate_BppM1M2"}\hlstd{,} \hlstr{"dginn.primate_BppM7M8"}\hlstd{,}
\hlstr{"dginn.primate_BUSTED"}\hlstd{)}
\hlkwd{dim}\hlstd{(tmp)}
\end{alltt}
\begin{verbatim}
## [1] 323 11
## [1] 324 11
\end{verbatim}
\end{kframe}
\end{knitrout}
......@@ -136,25 +137,26 @@ 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{x}\hlkwb{=}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp[tab}\hlopt{$}\hlstd{status}\hlopt{==}\hlstr{"shared"}\hlstd{]))}
\end{alltt}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp[tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{==}\hlstr{"na"}\hlstd{]}\hlkwb{<-}\hlnum{NA}
\hlstd{x}\hlkwb{=}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp[tab}\hlopt{$}\hlstd{status}\hlopt{==}\hlstr{"shared"}\hlstd{]))}
\hlstd{tab}\hlopt{$}\hlstd{bats_omegaM0Bpp[tab}\hlopt{$}\hlstd{bats_omegaM0Bpp}\hlopt{==}\hlstr{"na"}\hlstd{]}\hlkwb{<-}\hlnum{NA}
\hlstd{y}\hlkwb{=}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(}
\hlstd{tab}\hlopt{$}\hlstd{bats_omegaM0Bpp[tab}\hlopt{$}\hlstd{status}\hlopt{==}\hlstr{"shared"}\hlstd{]))}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning: NAs introduits lors de la conversion automatique}}\begin{alltt}
\hlstd{y}\hlkwb{=}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{bats_omegaM0Bpp[tab}\hlopt{$}\hlstd{status}\hlopt{==}\hlstr{"shared"}\hlstd{]))}
\end{alltt}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning: NAs introduits lors de la conversion automatique}}\begin{alltt}
\hlkwd{names}\hlstd{(x)}\hlkwb{<-}\hlstd{tab}\hlopt{$}\hlstd{Gene.name[tab}\hlopt{$}\hlstd{status}\hlopt{==}\hlstr{"shared"}\hlstd{]}
\hlkwd{plot}\hlstd{(x,y,} \hlkwc{xlab}\hlstd{=}\hlstr{"bpp omega primate"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"bpp omega bats"}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.5}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlnum{0}\hlstd{,}\hlnum{1}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlkwd{lm}\hlstd{(y}\hlopt{~}\hlstd{x),} \hlkwc{col}\hlstd{=}\hlstr{"red"}\hlstd{)}
\hlkwd{text}\hlstd{(x[x}\hlopt{>}\hlnum{0.5} \hlopt{&}\hlstd{y}\hlopt{<}\hlnum{0.4}\hlstd{], (y[x}\hlopt{>}\hlnum{0.5} \hlopt{&}\hlstd{y}\hlopt{<}\hlnum{0.4}\hlstd{]}\hlopt{+}\hlnum{0.01}\hlstd{),} \hlkwd{names}\hlstd{(x)[x}\hlopt{>}\hlnum{0.5} \hlopt{&}\hlstd{y}\hlopt{<}\hlnum{0.4}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.7}\hlstd{)}
\hlkwd{text}\hlstd{(x[x}\hlopt{<}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.45}\hlstd{], (y[x}\hlopt{<}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.45}\hlstd{]}\hlopt{+}\hlnum{0.01}\hlstd{),} \hlkwd{names}\hlstd{(x)[x}\hlopt{<}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.45}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.7}\hlstd{)}
\hlkwd{text}\hlstd{(x[x}\hlopt{>}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.4}\hlstd{], (y[x}\hlopt{>}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.4}\hlstd{]}\hlopt{+}\hlnum{0.01}\hlstd{),} \hlkwd{names}\hlstd{(x)[x}\hlopt{>}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.4}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.7}\hlstd{)}
\hlkwd{text}\hlstd{(x[x}\hlopt{>}\hlnum{0.5} \hlopt{&}\hlstd{y}\hlopt{<}\hlnum{0.4}\hlstd{], (y[x}\hlopt{>}\hlnum{0.5} \hlopt{&}\hlstd{y}\hlopt{<}\hlnum{0.4}\hlstd{]}\hlopt{+}\hlnum{0.01}\hlstd{),}
\hlkwd{names}\hlstd{(x)[x}\hlopt{>}\hlnum{0.5} \hlopt{&}\hlstd{y}\hlopt{<}\hlnum{0.4}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.7}\hlstd{)}
\hlkwd{text}\hlstd{(x[x}\hlopt{<}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.45}\hlstd{], (y[x}\hlopt{<}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.45}\hlstd{]}\hlopt{+}\hlnum{0.01}\hlstd{),}
\hlkwd{names}\hlstd{(x)[x}\hlopt{<}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.45}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.7}\hlstd{)}
\hlkwd{text}\hlstd{(x[x}\hlopt{>}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.4}\hlstd{], (y[x}\hlopt{>}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.4}\hlstd{]}\hlopt{+}\hlnum{0.01}\hlstd{),}
\hlkwd{names}\hlstd{(x)[x}\hlopt{>}\hlnum{0.45} \hlopt{&}\hlstd{y}\hlopt{>}\hlnum{0.4}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.7}\hlstd{)}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/unnamed-chunk-3-1}
......@@ -170,24 +172,31 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\hlstd{monddata}\hlkwb{<-}\hlkwd{as.data.frame}\hlstd{(tmp}\hlopt{$}\hlstd{Gene.name)}
\hlstd{batstmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tmp}\hlopt{$}\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{batstmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tmp}\hlopt{$}\hlstd{bats_codemlM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstd{bats_codemlM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstd{bats_BppM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstd{bats_BppM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstd{bats_BUSTED}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlstd{primatetmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tmp}\hlopt{$}\hlstr{"dginn.primate_codemlM1M2"}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstr{"dginn.primate_codemlM7M8"}\hlopt{==}\hlstr{"Y"}\hlstd{, tmp}\hlopt{$}\hlstr{"dginn.primate_BppM1M2"}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstr{"dginn.primate_BppM7M8"}\hlopt{==}\hlstr{"Y"}\hlstd{, tmp}\hlopt{$}\hlstr{"dginn.primate_BUSTED"}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlstd{tmp}\hlopt{$}\hlstr{"dginn.primate_codemlM7M8"}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstr{"dginn.primate_BppM1M2"}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstr{"dginn.primate_BppM7M8"}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tmp}\hlopt{$}\hlstr{"dginn.primate_BUSTED"}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlstd{monddata}\hlopt{$}\hlstd{bats_dginn3}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(batstmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{primate_dginn3}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(primatetmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{bats_dginn4}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(batstmp}\hlopt{>=}\hlnum{4}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{primate_dginn4}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(primatetmp}\hlopt{>=}\hlnum{4}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlkwd{mondrian}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{3}\hlstd{],} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"DGINN bats >3"}\hlstd{,} \hlstr{"DGINN primate >3"}\hlstd{))}
\hlkwd{mondrian}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{3}\hlstd{],}
\hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"DGINN bats >3"}\hlstd{,} \hlstr{"DGINN primate >3"}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/mondrianbats-1}
\begin{kframe}\begin{alltt}
\hlkwd{mondrian}\hlstd{(monddata[,}\hlnum{4}\hlopt{:}\hlnum{5}\hlstd{],} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"DGINN bats >4"}\hlstd{,} \hlstr{"DGINN primate >4"}\hlstd{))}
\hlkwd{mondrian}\hlstd{(monddata[,}\hlnum{4}\hlopt{:}\hlnum{5}\hlstd{],}
\hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"DGINN bats >4"}\hlstd{,} \hlstr{"DGINN primate >4"}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/mondrianbats-2}
......@@ -233,18 +242,30 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn4}\hlopt{==}\hlnum{1} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn4}\hlopt{==}\hlnum{1}\hlstd{,]}
\end{alltt}
\begin{verbatim}
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4
## 6 ACADM 1 1 1 1
## 7 ACE2 1 1 1 1
## 109 GGH 1 1 1 1
## 117 GOLGA7 1 1 1 1
## 134 IDE 1 1 1 1
## 139 ITGB1 1 1 1 1
## 146 LMAN2 1 1 1 1
## 212 POLA1 1 1 1 1
## 263 SLC27A2 1 1 1 1
## 301 TOR1AIP1 1 1 1 1
## 314 VPS39 1 1 1 1
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4
## 6 ACADM 1 1 1
## 7 ACE2 1 1 1
## 109 GGH 1 1 1
## 117 GOLGA7 1 1 1
## 134 IDE 1 1 1
## 139 ITGB1 1 1 1
## 146 LMAN2 1 1 1
## 212 POLA1 1 1 1
## 264 SLC27A2 1 1 1
## 302 TOR1AIP1 1 1 1
## 315 VPS39 1 1 1
## primate_dginn4
## 6 1
## 7 1
## 109 1
## 117 1
## 134 1
## 139 1
## 146 1
## 212 1
## 264 1
## 302 1
## 315 1
\end{verbatim}
\end{kframe}
\end{knitrout}
......@@ -257,25 +278,44 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn3}\hlopt{==}\hlnum{1} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn3}\hlopt{==}\hlnum{1}\hlstd{,]}
\end{alltt}
\begin{verbatim}
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4
## 6 ACADM 1 1 1 1
## 7 ACE2 1 1 1 1
## 9 ADAM9 1 1 0 0
## 34 CDK5RAP2 1 1 0 1
## 71 EDEM3 1 1 1 0
## 109 GGH 1 1 1 1
## 117 GOLGA7 1 1 1 1
## 134 IDE 1 1 1 1
## 139 ITGB1 1 1 1 1
## 146 LMAN2 1 1 1 1
## 157 MIPOL1 1 1 0 1
## 159 MOV10 1 1 0 0
## 212 POLA1 1 1 1 1
## 239 RAP1GDS1 1 1 1 0
## 257 SCCPDH 1 1 0 0
## 263 SLC27A2 1 1 1 1
## 301 TOR1AIP1 1 1 1 1
## 314 VPS39 1 1 1 1
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4
## 6 ACADM 1 1 1
## 7 ACE2 1 1 1
## 9 ADAM9 1 1 0
## 34 CDK5RAP2 1 1 0
## 71 EDEM3 1 1 1
## 109 GGH 1 1 1
## 117 GOLGA7 1 1 1
## 134 IDE 1 1 1
## 139 ITGB1 1 1 1
## 146 LMAN2 1 1 1
## 157 MIPOL1 1 1 0
## 159 MOV10 1 1 0
## 212 POLA1 1 1 1
## 239 RAP1GDS1 1 1 1
## 257 SCCPDH 1 1 0
## 264 SLC27A2 1 1 1
## 302 TOR1AIP1 1 1 1
## 315 VPS39 1 1 1
## primate_dginn4
## 6 1
## 7 1
## 9 0
## 34 1
## 71 0
## 109 1
## 117 1
## 134 1
## 139 1
## 146 1
## 157 1
## 159 0
## 212 1
## 239 0
## 257 0
## 264 1
## 302 1
## 315 1
\end{verbatim}
\end{kframe}
\end{knitrout}
......@@ -291,47 +331,88 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn4}\hlopt{==}\hlnum{0} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn4}\hlopt{==}\hlnum{1}\hlstd{,]}
\end{alltt}
\begin{verbatim}
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4
## 31 BRD4 0 1 0 1
## 34 CDK5RAP2 1 1 0 1
## 37 CEP135 0 1 0 1
## 40 CEP68 0 1 0 1
## 47 CLIP4 0 1 0 1
## 67 DNMT1 0 1 0 1
## 68 DPH5 0 1 0 1
## 75 EMC1 0 1 0 1
## 80 ERO1B 0 1 0 1
## 101 FYCO1 0 1 0 1
## 105 GCC2 0 1 0 1
## 110 GHITM 0 1 0 1
## 111 GIGYF2 0 1 0 1
## 112 GLA 0 1 0 1
## 127 HECTD1 0 1 0 1
## 143 LARP1 0 1 0 1
## 144 LARP4B 0 1 0 1
## 150 MARK1 0 1 0 1
## 157 MIPOL1 1 1 0 1
## 160 MPHOSPH10 0 1 0 1
## 166 MYCBP2 0 1 0 1
## 171 NDUFAF2 0 1 0 1
## 172 NDUFB9 0 1 0 1
## 187 NUP58 0 1 0 1
## 195 PCNT 0 1 0 1
## 218 PRIM2 0 1 0 1
## 220 PRKAR2A 0 1 0 1
## 227 PVR 0 1 0 1
## 245 REEP6 0 1 0 1
## 248 RIPK1 0 1 0 1
## 253 SAAL1 0 1 0 1
## 259 SEPSECS 0 1 0 1
## 261 SIRT5 0 1 0 1
## 262 SLC25A21 0 1 0 1
## 296 TMEM39B 0 1 0 1
## 298 TMPRSS2 0 1 0 1
## 304 TUBGCP2 0 1 0 1
## 307 UBAP2 0 1 0 1
## 310 UGGT2 0 1 0 1
## 321 ZNF318 0 1 0 1
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4
## 31 BRD4 0 1 0
## 34 CDK5RAP2 1 1 0
## 37 CEP135 0 1 0
## 40 CEP68 0 1 0
## 47 CLIP4 0 1 0
## 67 DNMT1 0 1 0
## 68 DPH5 0 1 0
## 75 EMC1 0 1 0
## 80 ERO1B 0 1 0
## 101 FYCO1 0 1 0
## 105 GCC2 0 1 0
## 110 GHITM 0 1 0
## 111 GIGYF2 0 1 0
## 112 GLA 0 1 0
## 127 HECTD1 0 1 0
## 143 LARP1 0 1 0
## 144 LARP4B 0 1 0
## 150 MARK1 0 1 0
## 157 MIPOL1 1 1 0
## 160 MPHOSPH10 0 1 0
## 166 MYCBP2 0 1 0
## 171 NDUFAF2 0 1 0
## 172 NDUFB9 0 1 0
## 187 NUP58 0 1 0
## 195 PCNT 0 1 0
## 218 PRIM2 0 1 0
## 220 PRKAR2A 0 1 0
## 227 PVR 0 1 0
## 245 REEP6 0 1 0
## 248 RIPK1 0 1 0
## 253 SAAL1 0 1 0
## 260 SEPSECS 0 1 0
## 262 SIRT5 0 1 0
## 263 SLC25A21 0 1 0
## 297 TMEM39B 0 1 0
## 299 TMPRSS2 0 1 0
## 305 TUBGCP2 0 1 0
## 308 UBAP2 0 1 0
## 311 UGGT2 0 1 0
## 322 ZNF318 0 1 0
## primate_dginn4
## 31 1
## 34 1
## 37 1
## 40 1
## 47 1
## 67 1
## 68 1
## 75 1
## 80 1
## 101 1
## 105 1
## 110 1
## 111 1
## 112 1
## 127 1
## 143 1
## 144 1
## 150 1
## 157 1
## 160 1
## 166 1
## 171 1
## 172 1
## 187 1
## 195 1
## 218 1
## 220 1
## 227 1
## 245 1
## 248 1
## 253 1
## 260 1
## 262 1
## 263 1
## 297 1
## 299 1
## 305 1
## 308 1
## 311 1
## 322 1
\end{verbatim}
\end{kframe}
\end{knitrout}
......@@ -344,77 +425,148 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn3}\hlopt{==}\hlnum{0} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn3}\hlopt{==}\hlnum{1}\hlstd{,]}
\end{alltt}
\begin{verbatim}
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4
## 19 AP2A2 0 1 0 0
## 23 ATE1 0 1 0 0
## 31 BRD4 0 1 0 1
## 32 BZW2 0 1 0 0
## 37 CEP135 0 1 0 1
## 40 CEP68 0 1 0 1
## 47 CLIP4 0 1 0 1
## 48 CNTRL 0 1 0 0
## 67 DNMT1 0 1 0 1
## 68 DPH5 0 1 0 1
## 72 EIF4E2 0 1 0 0
## 75 EMC1 0 1 0 1
## 80 ERO1B 0 1 0 1
## 83 EXOSC2 0 1 0 0
## 101 FYCO1 0 1 0 1
## 105 GCC2 0 1 0 1
## 110 GHITM 0 1 0 1
## 111 GIGYF2 0 1 0 1
## 112 GLA 0 1 0 1
## 118 GOLGB1 0 1 0 0
## 119 GORASP1 0 1 0 0
## 125 HDAC2 0 1 0 0
## 127 HECTD1 0 1 0 1
## 131 HS6ST2 0 1 0 0
## 143 LARP1 0 1 0 1
## 144 LARP4B 0 1 0 1
## 145 LARP7 0 1 0 0
## 150 MARK1 0 1 0 1
## 154 MDN1 0 1 0 0
## 160 MPHOSPH10 0 1 0 1
## 164 MRPS5 0 1 0 0
## 166 MYCBP2 0 1 0 1
## 168 NAT14 0 1 0 0
## 171 NDUFAF2 0 1 0 1
## 172 NDUFB9 0 1 0 1
## 176 NGLY1 0 1 0 0
## 181 NPC2 0 1 0 0
## 187 NUP58 0 1 0 1
## 195 PCNT 0 1 0 1
## 202 PITRM1 0 1 0 0
## 204 PLAT 0 1 0 0
## 208 PLOD2 0 1 0 0
## 210 PMPCB 0 1 0 0
## 214 POR 0 1 0 0
## 218 PRIM2 0 1 0 1
## 220 PRKAR2A 0 1 0 1
## 224 PTBP2 0 1 0 0
## 227 PVR 0 1 0 1
## 230 RAB14 0 1 0 0
## 232 RAB1A 0 1 0 0
## 233 RAB2A 0 1 0 0
## 242 RBX1 0 1 0 0
## 245 REEP6 0 1 0 1
## 248 RIPK1 0 1 0 1
## 250 RPL36 0 1 0 0
## 253 SAAL1 0 1 0 1
## 259 SEPSECS 0 1 0 1
## 261 SIRT5 0 1 0 1
## 262 SLC25A21 0 1 0 1
## 277 STOM 0 1 0 0
## 290 TIMM8B 0 1 0 0
## 296 TMEM39B 0 1 0 1
## 298 TMPRSS2 0 1 0 1
## 302 TRIM59 0 1 0 0
## 303 TRMT1 0 1 0 0
## 304 TUBGCP2 0 1 0 1
## 307 UBAP2 0 1 0 1
## 310 UGGT2 0 1 0 1
## 312 USP54 0 1 0 0
## 321 ZNF318 0 1 0 1
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4
## 19 AP2A2 0 1 0
## 23 ATE1 0 1 0
## 31 BRD4 0 1 0
## 32 BZW2 0 1 0
## 37 CEP135 0 1 0
## 40 CEP68 0 1 0
## 47 CLIP4 0 1 0
## 48 CNTRL 0 1 0
## 67 DNMT1 0 1 0
## 68 DPH5 0 1 0
## 72 EIF4E2 0 1 0
## 75 EMC1 0 1 0
## 80 ERO1B 0 1 0
## 83 EXOSC2 0 1 0
## 101 FYCO1 0 1 0
## 105 GCC2 0 1 0
## 110 GHITM 0 1 0
## 111 GIGYF2 0 1 0
## 112 GLA 0 1 0
## 118 GOLGB1 0 1 0
## 119 GORASP1 0 1 0
## 125 HDAC2 0 1 0
## 127 HECTD1 0 1 0
## 131 HS6ST2 0 1 0
## 143 LARP1 0 1 0
## 144 LARP4B 0 1 0
## 145 LARP7 0 1 0
## 150 MARK1 0 1 0
## 154 MDN1 0 1 0
## 160 MPHOSPH10 0 1 0
## 164 MRPS5 0 1 0
## 166 MYCBP2 0 1 0
## 168 NAT14 0 1 0
## 171 NDUFAF2 0 1 0
## 172 NDUFB9 0 1 0
## 176 NGLY1 0 1 0
## 181 NPC2 0 1 0
## 187 NUP58 0 1 0
## 195 PCNT 0 1 0
## 202 PITRM1 0 1 0
## 204 PLAT 0 1 0
## 208 PLOD2 0 1 0
## 210 PMPCB 0 1 0
## 214 POR 0 1 0
## 218 PRIM2 0 1 0
## 220 PRKAR2A 0 1 0
## 224 PTBP2 0 1 0
## 227 PVR 0 1 0
## 230 RAB14 0 1 0
## 232 RAB1A 0 1 0
## 233 RAB2A 0 1 0
## 242 RBX1 0 1 0
## 245 REEP6 0 1 0
## 248 RIPK1 0 1 0
## 250 RPL36 0 1 0
## 253 SAAL1 0 1 0
## 260 SEPSECS 0 1 0
## 262 SIRT5 0 1 0
## 263 SLC25A21 0 1 0
## 278 STOM 0 1 0
## 291 TIMM8B 0 1 0
## 297 TMEM39B 0 1 0
## 299 TMPRSS2 0 1 0
## 303 TRIM59 0 1 0
## 304 TRMT1 0 1 0
## 305 TUBGCP2 0 1 0
## 308 UBAP2 0 1 0
## 311 UGGT2 0 1 0
## 313 USP54 0 1 0
## 322 ZNF318 0 1 0
## primate_dginn4
## 19 0
## 23 0
## 31 1
## 32 0
## 37 1
## 40 1
## 47 1
## 48 0
## 67 1
## 68 1
## 72 0
## 75 1
## 80 1
## 83 0
## 101 1
## 105 1
## 110 1
## 111 1
## 112 1
## 118 0
## 119 0
## 125 0
## 127 1
## 131 0
## 143 1
## 144 1
## 145 0
## 150 1
## 154 0
## 160 1
## 164 0
## 166 1
## 168 0
## 171 1
## 172 1
## 176 0
## 181 0
## 187 1
## 195 1
## 202 0
## 204 0
## 208 0
## 210 0
## 214 0
## 218 1
## 220 1
## 224 0
## 227 1
## 230 0
## 232 0
## 233 0
## 242 0
## 245 1
## 248 1
## 250 0
## 253 1
## 260 1
## 262 1
## 263 1
## 278 0
## 291 0
## 297 1
## 299 1
## 303 0
## 304 0
## 305 1
## 308 1
## 311 1
## 313 0
## 322 1
\end{verbatim}
\end{kframe}
\end{knitrout}
......@@ -430,18 +582,30 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn4}\hlopt{==}\hlnum{1} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn4}\hlopt{==}\hlnum{0}\hlstd{,]}
\end{alltt}
\begin{verbatim}
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4
## 14 AKAP9 1 0 1 0
## 26 ATP6AP1 1 0 1 0
## 44 CISD3 1 0 1 0
## 71 EDEM3 1 1 1 0
## 77 ERGIC1 1 0 1 0
## 136 IMPDH2 1 0 1 0
## 137 INHBE 1 0 1 0
## 231 RAB18 1 0 1 0
## 239 RAP1GDS1 1 1 1 0
## 267 SLC44A2 1 0 1 0
## 283 TBK1 1 0 1 0
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4
## 14 AKAP9 1 0 1
## 26 ATP6AP1 1 0 1
## 44 CISD3 1 0 1
## 71 EDEM3 1 1 1
## 77 ERGIC1 1 0 1
## 136 IMPDH2 1 0 1
## 137 INHBE 1 0 1
## 231 RAB18 1 0 1
## 239 RAP1GDS1 1 1 1
## 268 SLC44A2 1 0 1
## 284 TBK1 1 0 1
## primate_dginn4
## 14 0
## 26 0
## 44 0
## 71 0
## 77 0
## 136 0
## 137 0
## 231 0
## 239 0
## 268 0
## 284 0
\end{verbatim}
\end{kframe}
\end{knitrout}
......@@ -454,27 +618,48 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn3}\hlopt{==}\hlnum{1} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn3}\hlopt{==}\hlnum{0}\hlstd{,]}
\end{alltt}
\begin{verbatim}
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4
## 5 ACAD9 1 0 0 0
## 11 AGPS 1 0 0 0
## 14 AKAP9 1 0 1 0
## 26 ATP6AP1 1 0 1 0
## 44 CISD3 1 0 1 0
## 49 COL6A1 1 0 0 0
## 77 ERGIC1 1 0 1 0
## 122 GRIPAP1 1 0 0 0
## 123 GRPEL1 1 0 0 0
## 136 IMPDH2 1 0 1 0
## 137 INHBE 1 0 1 0
## 151 MARK2 1 0 0 0
## 185 NUP214 1 0 0 0
## 217 PRIM1 1 0 0 0
## 226 PUSL1 1 0 0 0
## 231 RAB18 1 0 1 0
## 266 SLC30A9 1 0 0 0
## 267 SLC44A2 1 0 1 0
## 268 SLC9A3R1 1 0 0 0
## 283 TBK1 1 0 1 0
## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4
## 5 ACAD9 1 0 0
## 11 AGPS 1 0 0
## 14 AKAP9 1 0 1
## 26 ATP6AP1 1 0 1
## 44 CISD3 1 0 1
## 49 COL6A1 1 0 0
## 77 ERGIC1 1 0 1
## 122 GRIPAP1 1 0 0
## 123 GRPEL1 1 0 0
## 136 IMPDH2 1 0 1
## 137 INHBE 1 0 1
## 151 MARK2 1 0 0
## 185 NUP214 1 0 0
## 217 PRIM1 1 0 0
## 226 PUSL1 1 0 0
## 231 RAB18 1 0 1
## 267 SLC30A9 1 0 0
## 268 SLC44A2 1 0 1
## 269 SLC9A3R1 1 0 0
## 284 TBK1 1 0 1
## primate_dginn4
## 5 0
## 11 0
## 14 0
## 26 0
## 44 0
## 49 0
## 77 0
## 122 0
## 123 0
## 136 0
## 137 0
## 151 0
## 185 0
## 217 0
## 226 0
## 231 0
## 267 0
## 268 0
## 269 0
## 284 0
\end{verbatim}
\end{kframe}
\end{knitrout}
......@@ -488,7 +673,11 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\hlstd{tablo}\hlopt{$}\hlstd{nbats}\hlkwb{<-}\hlstd{batstmp}
\hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlkwb{<-}\hlstd{primatetmp}
\hlkwd{plot}\hlstd{(}\hlkwa{NULL}\hlstd{,} \hlkwc{xlim}\hlstd{=}\hlkwd{c}\hlstd{(}\hlopt{-}\hlnum{0.5}\hlstd{,}\hlnum{5.5}\hlstd{),} \hlkwc{ylim}\hlstd{=}\hlkwd{c}\hlstd{(}\hlopt{-}\hlnum{3}\hlstd{,}\hlnum{5.5}\hlstd{),} \hlkwc{xlab}\hlstd{=}\hlstr{"bats"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"primates"}\hlstd{,} \hlkwc{main}\hlstd{=}\hlstr{"Genes supported by x,y methods in bats and primates"}\hlstd{,} \hlkwc{bty}\hlstd{=}\hlstr{"n"}\hlstd{,} \hlkwc{xaxt}\hlstd{=}\hlstr{"n"}\hlstd{,} \hlkwc{yaxt}\hlstd{=}\hlstr{"n"}\hlstd{)}
\hlkwd{plot}\hlstd{(}\hlkwa{NULL}\hlstd{,} \hlkwc{xlim}\hlstd{=}\hlkwd{c}\hlstd{(}\hlopt{-}\hlnum{0.5}\hlstd{,}\hlnum{5.5}\hlstd{),} \hlkwc{ylim}\hlstd{=}\hlkwd{c}\hlstd{(}\hlopt{-}\hlnum{3}\hlstd{,}\hlnum{5.5}\hlstd{),}
\hlkwc{xlab}\hlstd{=}\hlstr{"bats"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"primates"}\hlstd{,}
\hlkwc{main}\hlstd{=}\hlstr{"Genes supported by x,y methods in bats and primates"}\hlstd{,}
\hlkwc{bty}\hlstd{=}\hlstr{"n"}\hlstd{,}
\hlkwc{xaxt}\hlstd{=}\hlstr{"n"}\hlstd{,} \hlkwc{yaxt}\hlstd{=}\hlstr{"n"}\hlstd{)}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=}\hlkwd{rep}\hlstd{(}\hlopt{-}\hlnum{0.6}\hlstd{,} \hlnum{6}\hlstd{),} \hlkwc{y}\hlstd{=}\hlnum{0}\hlopt{:}\hlnum{5}\hlstd{,} \hlnum{0}\hlopt{:}\hlnum{5}\hlstd{)}
\hlkwd{text}\hlstd{(}\hlkwc{y}\hlstd{=}\hlkwd{rep}\hlstd{(}\hlopt{-}\hlnum{0.65}\hlstd{,} \hlnum{6}\hlstd{),} \hlkwc{x}\hlstd{=}\hlnum{0}\hlopt{:}\hlnum{5}\hlstd{,} \hlnum{0}\hlopt{:}\hlnum{5}\hlstd{)}
......@@ -550,11 +739,14 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\hlkwa{for} \hlstd{(b} \hlkwa{in} \hlnum{0}\hlopt{:}\hlnum{5}\hlstd{)\{}
\hlstd{tmp}\hlkwb{<-}\hlstd{tablo}\hlopt{$}\hlstd{`tmp$Gene.name`[tablo}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlstd{b} \hlopt{&} \hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlstd{p]}
\hlkwa{if}\hlstd{(}\hlkwd{length}\hlstd{(tmp)}\hlopt{>}\hlnum{0} \hlopt{&} \hlkwd{length}\hlstd{(tmp)}\hlopt{<=}\hlnum{8}\hlstd{)\{}
\hlkwd{text}\hlstd{(b,}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=(p}\hlopt{-}\hlnum{0.4}\hlstd{),} \hlkwc{to}\hlstd{=(p}\hlopt{+}\hlnum{0.4}\hlstd{),} \hlkwc{length.out} \hlstd{=} \hlkwd{length}\hlstd{(tmp)), tmp,} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlkwd{text}\hlstd{(b,}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=(p}\hlopt{-}\hlnum{0.4}\hlstd{),} \hlkwc{to}\hlstd{=(p}\hlopt{+}\hlnum{0.4}\hlstd{),} \hlkwc{length.out} \hlstd{=} \hlkwd{length}\hlstd{(tmp)),}
\hlstd{tmp,} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlstd{\}}\hlkwa{else if} \hlstd{(}\hlkwd{length}\hlstd{(tmp)}\hlopt{>}\hlnum{8} \hlopt{&} \hlkwd{length}\hlstd{(tmp)}\hlopt{<=}\hlnum{16}\hlstd{)\{}
\hlkwd{print}\hlstd{(}\hlkwd{c}\hlstd{(p, b))}
\hlkwd{text}\hlstd{((b}\hlopt{-}\hlnum{0.3}\hlstd{),}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=(p}\hlopt{-}\hlnum{0.4}\hlstd{),} \hlkwc{to}\hlstd{=(p}\hlopt{+}\hlnum{0.4}\hlstd{),} \hlkwc{length.out} \hlstd{=} \hlnum{8}\hlstd{), tmp[}\hlnum{1}\hlopt{:}\hlnum{8}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlkwd{text}\hlstd{((b}\hlopt{+}\hlnum{0.3}\hlstd{),}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=(p}\hlopt{-}\hlnum{0.4}\hlstd{),} \hlkwc{to}\hlstd{=(p}\hlopt{+}\hlnum{0.4}\hlstd{),} \hlkwc{length.out} \hlstd{= (}\hlkwd{length}\hlstd{(tmp)}\hlopt{-}\hlnum{8}\hlstd{)), tmp[}\hlnum{9}\hlopt{:}\hlkwd{length}\hlstd{(tmp)],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlkwd{text}\hlstd{((b}\hlopt{-}\hlnum{0.3}\hlstd{),}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=(p}\hlopt{-}\hlnum{0.4}\hlstd{),} \hlkwc{to}\hlstd{=(p}\hlopt{+}\hlnum{0.4}\hlstd{),} \hlkwc{length.out} \hlstd{=} \hlnum{8}\hlstd{),}
\hlstd{tmp[}\hlnum{1}\hlopt{:}\hlnum{8}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlkwd{text}\hlstd{((b}\hlopt{+}\hlnum{0.3}\hlstd{),}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=(p}\hlopt{-}\hlnum{0.4}\hlstd{),} \hlkwc{to}\hlstd{=(p}\hlopt{+}\hlnum{0.4}\hlstd{),} \hlkwc{length.out} \hlstd{= (}\hlkwd{length}\hlstd{(tmp)}\hlopt{-}\hlnum{8}\hlstd{)),}
\hlstd{tmp[}\hlnum{9}\hlopt{:}\hlkwd{length}\hlstd{(tmp)],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlstd{\}}\hlkwa{else if} \hlstd{(}\hlkwd{length}\hlstd{(tmp)}\hlopt{>}\hlnum{16}\hlstd{)\{}
\hlkwd{text}\hlstd{(b,p,} \hlkwd{paste0}\hlstd{(}\hlkwd{length}\hlstd{(tmp),} \hlstr{" values"}\hlstd{))}
\hlstd{\}}
......@@ -574,13 +766,25 @@ Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
\begin{alltt}
\hlstd{tmp}\hlkwb{<-}\hlstd{tablo}\hlopt{$}\hlstd{`tmp$Gene.name`[tablo}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{0} \hlopt{&} \hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{1}\hlstd{]}
\hlkwd{text}\hlstd{(}\hlopt{-}\hlnum{0.4}\hlstd{,}\hlopt{-}\hlnum{1.2}\hlstd{,} \hlstr{"p=1/n=0"}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.6}\hlstd{)}
\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlnum{18}\hlstd{),}\hlopt{-}\hlnum{1.1}\hlstd{, tmp[}\hlnum{1}\hlopt{:}\hlnum{18}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlkwd{length}\hlstd{(tmp)}\hlopt{-}\hlnum{18}\hlstd{),}\hlopt{-}\hlnum{1.3}\hlstd{, tmp[}\hlnum{19}\hlopt{:}\hlkwd{length}\hlstd{(tmp)],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlnum{19}\hlstd{),}
\hlopt{-}\hlnum{1.1}\hlstd{,}
\hlstd{tmp[}\hlnum{1}\hlopt{:}\hlnum{19}\hlstd{],}
\hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlkwd{length}\hlstd{(tmp)}\hlopt{-}\hlnum{19}\hlstd{),}
\hlopt{-}\hlnum{1.3}\hlstd{,}
\hlstd{tmp[}\hlnum{20}\hlopt{:}\hlkwd{length}\hlstd{(tmp)],}
\hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlstd{tmp}\hlkwb{<-}\hlstd{tablo}\hlopt{$}\hlstd{`tmp$Gene.name`[tablo}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{1} \hlopt{&} \hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{1}\hlstd{]}
\hlkwd{text}\hlstd{(}\hlopt{-}\hlnum{0.4}\hlstd{,}\hlopt{-}\hlnum{1.7}\hlstd{,} \hlstr{"p=1/n=1"}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.6}\hlstd{)}
\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlnum{18}\hlstd{),}\hlopt{-}\hlnum{1.6}\hlstd{, tmp[}\hlnum{1}\hlopt{:}\hlnum{18}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{4.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlkwd{length}\hlstd{(tmp)}\hlopt{-}\hlnum{18}\hlstd{),}\hlopt{-}\hlnum{1.8}\hlstd{, tmp[}\hlnum{19}\hlopt{:}\hlkwd{length}\hlstd{(tmp)],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlnum{18}\hlstd{),}
\hlopt{-}\hlnum{1.6}\hlstd{,}
\hlstd{tmp[}\hlnum{1}\hlopt{:}\hlnum{18}\hlstd{],}
\hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{4.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlkwd{length}\hlstd{(tmp)}\hlopt{-}\hlnum{18}\hlstd{),}
\hlopt{-}\hlnum{1.8}\hlstd{,}
\hlstd{tmp[}\hlnum{19}\hlopt{:}\hlkwd{length}\hlstd{(tmp)],}
\hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)}
\hlstd{tmp}\hlkwb{<-}\hlstd{tablo}\hlopt{$}\hlstd{`tmp$Gene.name`[tablo}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{0} \hlopt{&} \hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{0}\hlstd{]}
......@@ -603,10 +807,16 @@ 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}
\hlkwd{write.csv}\hlstd{(tablo[tablo}\hlopt{$}\hlstd{nbats}\hlopt{>=}\hlnum{3}\hlstd{,}\hlstr{"tmp$Gene.name"}\hlstd{],} \hlstr{"batssup3.csv"}\hlstd{,} \hlkwc{row.names}\hlstd{=}\hlnum{FALSE}\hlstd{,} \hlkwc{quote}\hlstd{=}\hlnum{FALSE}\hlstd{)}
\hlkwd{write.csv}\hlstd{(tablo[tablo}\hlopt{$}\hlstd{nprimates}\hlopt{>=}\hlnum{3}\hlstd{,}\hlstr{"tmp$Gene.name"}\hlstd{],} \hlstr{"primatessup3.csv"}\hlstd{,} \hlkwc{row.names}\hlstd{=}\hlnum{FALSE}\hlstd{,} \hlkwc{quote}\hlstd{=}\hlnum{FALSE}\hlstd{)}
\hlkwd{write.csv}\hlstd{(tablo,} \hlstr{"primatesVbats.csv"}\hlstd{,} \hlkwc{row.names}\hlstd{=}\hlnum{FALSE}\hlstd{,} \hlkwc{quote}\hlstd{=}\hlnum{FALSE}\hlstd{)}
\hlkwd{write.csv}\hlstd{(tablo[tablo}\hlopt{$}\hlstd{nbats}\hlopt{>=}\hlnum{3}\hlstd{,}\hlstr{"tmp$Gene.name"}\hlstd{],} \hlstr{"batssup3.csv"}\hlstd{,}
\hlkwc{row.names}\hlstd{=}\hlnum{FALSE}\hlstd{,}
\hlkwc{quote}\hlstd{=}\hlnum{FALSE}\hlstd{)}
\hlkwd{write.csv}\hlstd{(tablo[tablo}\hlopt{$}\hlstd{nprimates}\hlopt{>=}\hlnum{3}\hlstd{,}\hlstr{"tmp$Gene.name"}\hlstd{],} \hlstr{"primatessup3.csv"}\hlstd{,}
\hlkwc{row.names}\hlstd{=}\hlnum{FALSE}\hlstd{,}
\hlkwc{quote}\hlstd{=}\hlnum{FALSE}\hlstd{)}
\hlkwd{write.csv}\hlstd{(tablo,} \hlstr{"primatesVbats.csv"}\hlstd{,}
\hlkwc{row.names}\hlstd{=}\hlnum{FALSE}\hlstd{,}
\hlkwc{quote}\hlstd{=}\hlnum{FALSE}\hlstd{)}
\end{alltt}
\end{kframe}
\end{knitrout}
......@@ -715,13 +925,13 @@ Restreindre ce tableau aux gènes présent dans l'analyse de Krogan.
\hlkwd{dim}\hlstd{(tablo)}
\end{alltt}
\begin{verbatim}
## [1] 323 3
## [1] 324 3
\end{verbatim}
\begin{alltt}
\hlkwd{dim}\hlstd{(tabloK)}
\end{alltt}
\begin{verbatim}
## [1] 320 3
## [1] 321 3
\end{verbatim}
\begin{alltt}
\hlcom{# Les gènes perdus (dans le tableau mais pas dans la liste de Krogan)}
......@@ -737,8 +947,8 @@ Restreindre ce tableau aux gènes présent dans l'analyse de Krogan.
\end{alltt}
\begin{verbatim}
## [1] "ARL6IP6" "ATP5MG" "BCS1L" "C1orf50" "CEP43" "CYB5R3"
## [7] "ELOB" "MFGE8" "POGLUT2" "POGLUT3" "SELENOS" "SIGMAR1"
## [13] "TLE5" "USP13"
## [7] "ELOB" "MFGE8" "POGLUT2" "POGLUT3" "SIGMAR1" "TLE5"
## [13] "USP13"
\end{verbatim}
\begin{alltt}
\hlkwd{write.csv}\hlstd{(tabloK,} \hlstr{"primatesVbats_onlykrogan.csv"}\hlstd{,} \hlkwc{row.names}\hlstd{=}\hlnum{FALSE}\hlstd{,} \hlkwc{quote}\hlstd{=}\hlnum{FALSE}\hlstd{)}
......@@ -759,32 +969,317 @@ Restreindre ce tableau aux gènes présent dans l'analyse de Krogan.
\hlkwd{library}\hlstd{(igraph)}
\hlkwd{library}\hlstd{(tidyverse)}
\hlcom{##}
\hlstd{tmp}\hlkwb{<-}\hlstd{tablo[(tablo}\hlopt{$}\hlstd{nbats}\hlopt{!=}\hlnum{0} \hlopt{|} \hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlopt{!=}\hlnum{0}\hlstd{),]}
\hlstd{tmp}\hlkwb{<-}\hlkwd{head}\hlstd{(tablo,} \hlnum{20}\hlstd{)}
\hlcom{#tmp<-head(tablo, 20)}
\hlcom{#tmp<-rbind(as.matrix(tmp), c("outgroup", 50, 50))}
\hlstd{tmp}\hlkwb{<-}\hlkwd{as.data.frame}\hlstd{(tmp)}
\hlstd{matbats}\hlkwb{<-}\hlkwd{hclust}\hlstd{(}\hlkwd{dist}\hlstd{(tmp}\hlopt{$}\hlstd{nbats))}
\hlstd{matpri}\hlkwb{<-}\hlkwd{hclust}\hlstd{(}\hlkwd{dist}\hlstd{(tmp}\hlopt{$}\hlstd{nprimates))}
\hlstd{tmp[}\hlkwd{order}\hlstd{(tmp}\hlopt{$}\hlstd{nbats),]}
\hlstd{dendpri}\hlkwb{<-}\hlstd{dendextend}\hlopt{::}\hlkwd{rotate}\hlstd{(}\hlkwd{as.dendrogram}\hlstd{(matpri),} \hlkwc{order}\hlstd{=}\hlkwd{nrow}\hlstd{(tmp)}\hlopt{:}\hlnum{1}\hlstd{)}
\hlstd{dendbats}\hlkwb{<-}\hlstd{dendextend}\hlopt{::}\hlkwd{rotate}\hlstd{(}\hlkwd{as.dendrogram}\hlstd{(matbats),} \hlkwc{order}\hlstd{=}\hlkwd{nrow}\hlstd{(tmp)}\hlopt{:}\hlnum{1}\hlstd{)}
\end{alltt}
\begin{verbatim}
## tmp$Gene.name nbats nprimates
## 3 AATF 0 1
## 8 ACSL3 0 1
## 13 AKAP8L 0 1
## 16 ALG5 0 2
## 20 AP2M1 0 1
## 23 ATE1 0 3
## 24 ATP13A3 0 2
## 29 BCKDK 0 1
## 32 BZW2 0 3
## 37 CEP135 0 4
## 39 CEP350 0 2
## 42 CHPF 0 2
## 46 CLCC1 0 1
## 54 CSDE1 0 1
## 56 CSNK2B 0 1
## 60 DCAF7 0 1
## 68 DPH5 0 4
## 78 ERLEC1 0 2
## 80 ERO1B 0 4
## 83 EXOSC2 0 3
## 96 FBXL12 0 2
## 99 FKBP7 0 2
## 105 GCC2 0 4
## 107 GFER 0 1
## 110 GHITM 0 4
## 113 GNB1 0 1
## 114 GNG5 0 1
## 116 GOLGA3 0 1
## 119 GORASP1 0 3
## 121 GPX1 0 1
## 125 HDAC2 0 3
## 131 HS6ST2 0 3
## 132 HSBP1 0 1
## 144 LARP4B 0 4
## 145 LARP7 0 3
## 148 MAP7D1 0 1
## 161 MRPS2 0 1
## 168 NAT14 0 3
## 169 NDFIP2 0 1
## 170 NDUFAF1 0 2
## 171 NDUFAF2 0 5
## 172 NDUFB9 0 4
## 178 NINL 0 2
## 181 NPC2 0 3
## 190 NUP98 0 1
## 191 NUTF2 0 1
## 198 PDE4DIP 0 1
## 199 PDZD11 0 1
## 200 PIGO 0 1
## 203 PKP2 0 1
## 205 PLD3 0 1
## 209 PMPCA 0 2
## 215 PPIL3 0 1
## 218 PRIM2 0 5
## 224 PTBP2 0 3
## 230 RAB14 0 3
## 232 RAB1A 0 3
## 233 RAB2A 0 3
## 234 RAB5C 0 2
## 235 RAB7A 0 1
## 241 RBM41 0 2
## 242 RBX1 0 3
## 245 REEP6 0 5
## 246 RETREG3 0 1
## 259 SELENOS 0 1
## 263 SLC25A21 0 4
## 271 SMOC1 0 2
## 274 SRP19 0 1
## 282 TARS2 0 1
## 285 TBKBP1 0 2
## 286 TCF12 0 1
## 291 TIMM8B 0 3
## 294 TLE3 0 1
## 298 TMEM97 0 1
## 299 TMPRSS2 0 4
## 300 TOMM70 0 1
## 303 TRIM59 0 3
## 305 TUBGCP2 0 4
## 308 UBAP2 0 4
## 310 UBXN8 0 1
## 322 ZNF318 0 5
## 323 ZNF503 0 1
## 324 ZYG11B 0 2
## 4 ABCC1 1 2
## 15 ALG11 1 0
## 17 ALG8 1 1
## 19 AP2A2 1 3
## 21 AP3B1 1 1
## 27 ATP6V1A 1 1
## 30 BRD2 1 0
## 35 CENPF 1 2
## 36 CEP112 1 1
## 38 CEP250 1 2
## 40 CEP68 1 5
## 43 CHPF2 1 1
## 45 CIT 1 2
## 48 CNTRL 1 3
## 52 COQ8B 1 0
## 53 CRTC3 1 2
## 58 CWC27 1 2
## 59 CYB5B 1 0
## 64 DDX21 1 1
## 65 DNAJC11 1 0
## 67 DNMT1 1 5
## 72 EIF4E2 1 3
## 76 ERC1 1 1
## 81 ERP44 1 0
## 84 EXOSC3 1 0
## 87 F2RL1 1 0
## 89 FAM8A1 1 1
## 93 FBLN5 1 1
## 97 FKBP10 1 0
## 102 G3BP1 1 1
## 103 G3BP2 1 0
## 104 GCC1 1 0
## 108 GGCX 1 0
## 111 GIGYF2 1 4
## 112 GLA 1 4
## 126 HEATR3 1 0
## 128 HMOX1 1 1
## 135 IL17RA 1 0
## 138 INTS4 1 0
## 141 KDELC1 1 1
## 143 LARP1 1 4
## 147 LOX 1 1
## 150 MARK1 1 4
## 160 MPHOSPH10 1 4
## 162 MRPS25 1 0
## 163 MRPS27 1 2
## 165 MTCH1 1 0
## 167 NARS2 1 1
## 176 NGLY1 1 3
## 177 NIN 1 0
## 179 NLRX1 1 2
## 180 NOL10 1 1
## 182 NPTX1 1 0
## 187 NUP58 1 5
## 188 NUP62 1 1
## 194 PABPC4 1 2
## 196 PCSK5 1 0
## 202 PITRM1 1 3
## 204 PLAT 1 3
## 208 PLOD2 1 3
## 213 POLA2 1 0
## 216 PPT1 1 0
## 219 PRKACA 1 0
## 220 PRKAR2A 1 4
## 221 PRKAR2B 1 2
## 222 PRRC2B 1 0
## 228 QSOX2 1 1
## 236 RAB8A 1 0
## 237 RAE1 1 1
## 250 RPL36 1 3
## 252 RTN4 1 2
## 253 SAAL1 1 4
## 255 SCAP 1 2
## 261 SIL1 1 0
## 262 SIRT5 1 4
## 266 SLC30A7 1 1
## 270 SLU7 1 2
## 273 SPART 1 0
## 276 SRP72 1 1
## 278 STOM 1 3
## 281 TAPT1 1 2
## 288 TIMM10 1 0
## 290 TIMM29 1 1
## 295 TM2D3 1 1
## 301 TOR1A 1 1
## 304 TRMT1 1 3
## 309 UBAP2L 1 1
## 311 UGGT2 1 4
## 313 USP54 1 3
## 314 VPS11 1 1
## 319 ZC3H18 1 1
## 320 ZC3H7A 1 1
## 321 ZDHHC5 1 2
## 2 AASS 2 0
## 18 ANO6 2 2
## 25 ATP1B1 2 0
## 31 BRD4 2 4
## 41 CHMP2A 2 1
## 47 CLIP4 2 4
## 50 COLGALT1 2 1
## 51 COMT 2 0
## 57 CUL2 2 0
## 63 DDX10 2 0
## 74 ELOC 2 0
## 75 EMC1 2 5
## 79 ERMP1 2 0
## 91 FAR2 2 2
## 94 FBN1 2 2
## 95 FBN2 2 2
## 100 FOXRED2 2 0
## 101 FYCO1 2 5
## 106 GDF15 2 1
## 115 GOLGA2 2 2
## 118 GOLGB1 2 3
## 120 GPAA1 2 0
## 127 HECTD1 2 5
## 130 HS2ST1 2 0
## 133 HYOU1 2 1
## 140 JAKMIP1 2 0
## 152 MARK3 2 1
## 154 MDN1 2 3
## 155 MEPCE 2 0
## 156 MIB1 2 0
## 164 MRPS5 2 3
## 166 MYCBP2 2 5
## 173 NEK9 2 0
## 174 NEU1 2 0
## 183 NSD2 2 1
## 184 NUP210 2 2
## 195 PCNT 2 4
## 197 PCSK6 2 0
## 207 PLEKHF2 2 0
## 210 PMPCB 2 3
## 211 POFUT1 2 1
## 214 POR 2 3
## 223 PSMD8 2 1
## 225 PTGES2 2 1
## 227 PVR 2 5
## 240 RBM28 2 0
## 243 RDX 2 0
## 248 RIPK1 2 4
## 251 RRP9 2 1
## 254 SBNO1 2 2
## 256 SCARB1 2 2
## 260 SEPSECS 2 5
## 280 SUN2 2 0
## 283 TBCA 2 1
## 293 TLE1 2 1
## 296 TMED5 2 0
## 297 TMEM39B 2 4
## 306 TUBGCP3 2 1
## 307 TYSND1 2 0
## 316 WASHC4 2 2
## 317 WFS1 2 2
## 5 ACAD9 3 1
## 9 ADAM9 3 3
## 11 AGPS 3 1
## 34 CDK5RAP2 3 5
## 49 COL6A1 3 2
## 122 GRIPAP1 3 1
## 123 GRPEL1 3 0
## 151 MARK2 3 0
## 157 MIPOL1 3 4
## 159 MOV10 3 3
## 185 NUP214 3 2
## 217 PRIM1 3 2
## 226 PUSL1 3 1
## 257 SCCPDH 3 3
## 267 SLC30A9 3 0
## 269 SLC9A3R1 3 0
## 6 ACADM 4 5
## 14 AKAP9 4 2
## 26 ATP6AP1 4 1
## 44 CISD3 4 1
## 77 ERGIC1 4 0
## 134 IDE 4 4
## 136 IMPDH2 4 1
## 139 ITGB1 4 5
## 146 LMAN2 4 4
## 212 POLA1 4 4
## 7 ACE2 5 5
## 71 EDEM3 5 3
## 109 GGH 5 5
## 117 GOLGA7 5 5
## 137 INHBE 5 0
## 231 RAB18 5 1
## 239 RAP1GDS1 5 3
## 264 SLC27A2 5 4
## 268 SLC44A2 5 0
## 284 TBK1 5 2
## 302 TOR1AIP1 5 5
## 315 VPS39 5 5
\end{verbatim}
\begin{alltt}
\hlstd{dendpri}\hlkwb{<-}\hlkwd{as.dendrogram}\hlstd{(matpri)}
\hlstd{dendbats}\hlkwb{<-}\hlkwd{as.dendrogram}\hlstd{(matbats)}
\hlkwd{labels}\hlstd{(dendpri)}\hlkwb{<-}\hlkwd{as.character}\hlstd{(tmp}\hlopt{$}\hlstd{`tmp$Gene.name`[}\hlkwd{labels}\hlstd{(dendpri)])}
\hlkwd{labels}\hlstd{(dendbats)}\hlkwb{<-}\hlkwd{as.character}\hlstd{(tmp}\hlopt{$}\hlstd{`tmp$Gene.name`[}\hlkwd{labels}\hlstd{(dendbats)])}
\hlcom{#### Il faut swapper certains neud de l'arbre}
\hlstd{tmp[}\hlkwd{order}\hlstd{(tmp}\hlopt{$}\hlstd{nprimates,} \hlkwc{decreasing}\hlstd{=}\hlnum{FALSE}\hlstd{),]}\hlopt{$}\hlstr{'tmp$Gene.name'}\hlkwb{->} \hlstd{order}
\hlstd{dendpri}\hlkwb{<-}\hlstd{dendextend}\hlopt{::}\hlkwd{rotate}\hlstd{(dendpri,} \hlkwc{order}\hlstd{=order)}
\hlkwd{class}\hlstd{(}\hlkwd{labels}\hlstd{(dendpri))}
\hlstd{tmp[}\hlkwd{order}\hlstd{(tmp}\hlopt{$}\hlstd{nbats,} \hlkwc{decreasing}\hlstd{=}\hlnum{FALSE}\hlstd{),]}\hlopt{$}\hlstr{'tmp$Gene.name'}\hlkwb{->} \hlstd{order}
\hlstd{dendbats}\hlkwb{<-}\hlstd{dendextend}\hlopt{::}\hlkwd{rotate}\hlstd{(dendbats,} \hlkwc{order}\hlstd{=order)}
\hlcom{#### Il faut swapper certains neud de l'arbrese}
\hlkwd{class}\hlstd{(}\hlkwd{labels}\hlstd{(dendpri))}
\end{alltt}
\begin{verbatim}
## [1] "character"
\end{verbatim}
\begin{alltt}
\hlstd{dend12} \hlkwb{<-} \hlkwd{dendlist}\hlstd{(dendbats, dendpri)}
\hlopt{?}\hlstd{png}
\hlkwd{png}\hlstd{(}\hlstr{"tanglegramm.png"}\hlstd{,} \hlkwc{width} \hlstd{=} \hlnum{1800}\hlstd{,} \hlkwc{height} \hlstd{=} \hlnum{3000}\hlstd{)}
\hlkwd{png}\hlstd{(}\hlstr{"figure/tanglegramm.png"}\hlstd{,} \hlkwc{width} \hlstd{=} \hlnum{1800}\hlstd{,} \hlkwc{height} \hlstd{=} \hlnum{3000}\hlstd{)}
\hlkwd{tanglegram}\hlstd{(dend12,} \hlkwc{columns_width}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{3}\hlstd{,} \hlnum{3}\hlstd{,}\hlnum{3}\hlstd{),} \hlkwc{axes}\hlstd{=}\hlnum{FALSE}\hlstd{,}
\hlkwc{edge.lwd}\hlstd{=}\hlnum{0}\hlstd{,} \hlkwc{margin_inner}\hlstd{=}\hlnum{6}\hlstd{,}
\hlkwc{margin_top}\hlstd{=}\hlnum{2}\hlstd{,}
......@@ -796,14 +1291,201 @@ Restreindre ce tableau aux gènes présent dans l'analyse de Krogan.
\hlkwc{k_labels}\hlstd{=}\hlnum{6}\hlstd{)}
\hlkwd{dev.off}\hlstd{()}
\end{alltt}
\begin{verbatim}
## RStudioGD
## 2
\end{verbatim}
\end{kframe}
\end{knitrout}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{ace}\hlkwb{<-}\hlnum{264}
\hlstd{tmprss2}\hlkwb{<-}\hlnum{75}
\hlstd{znf318}\hlkwb{<-}\hlnum{81}
\hlstd{sepsecs}\hlkwb{<-}\hlnum{228}
\hlstd{tbk1}\hlkwb{<-}\hlnum{273}
\hlstd{ripk1}\hlkwb{<-}\hlnum{224}
\hlstd{col}\hlkwb{<-}\hlkwd{rep}\hlstd{(}\hlstr{"grey"}\hlstd{,} \hlkwd{length}\hlstd{(}\hlkwd{labels}\hlstd{(dendpri)))}
\hlstd{col[ace]}\hlkwb{<-}\hlstr{"black"}
\hlstd{col[tmprss2]}\hlkwb{<-}\hlstr{"black"}
\hlstd{col[znf318]}\hlkwb{<-}\hlstr{"black"}
\hlstd{col[sepsecs]}\hlkwb{<-}\hlstr{"black"}
\hlstd{col[tbk1]}\hlkwb{<-}\hlstr{"black"}
\hlstd{col[ripk1]}\hlkwb{<-}\hlstr{"black"}
\hlstd{font}\hlkwb{<-}\hlkwd{rep}\hlstd{(}\hlnum{1}\hlstd{,} \hlkwd{length}\hlstd{(}\hlkwd{labels}\hlstd{(dendpri))}\hlopt{*}\hlnum{2}\hlstd{)}
\hlcom{#font[ace]<-1.3}
\hlcom{#font[tmprss2]<-1.3}
\hlcom{#font[length(labels(dendpri))+160]<-1.3}
\hlkwd{png}\hlstd{(}\hlstr{"figure/tanglegramm.png"}\hlstd{,} \hlkwc{width} \hlstd{=} \hlnum{1800}\hlstd{,} \hlkwc{height} \hlstd{=} \hlnum{3000}\hlstd{)}
\hlkwd{tanglegram}\hlstd{(dend12,} \hlkwc{columns_width}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{3}\hlstd{,} \hlnum{3}\hlstd{,}\hlnum{3}\hlstd{),} \hlkwc{axes}\hlstd{=}\hlnum{FALSE}\hlstd{,}
\hlkwc{edge.lwd}\hlstd{=}\hlnum{0}\hlstd{,} \hlkwc{margin_inner}\hlstd{=}\hlnum{6}\hlstd{,}
\hlkwc{margin_top}\hlstd{=}\hlnum{2}\hlstd{,}
\hlkwc{main_left}\hlstd{=}\hlstr{" bats"}\hlstd{,}
\hlkwc{main_right} \hlstd{=} \hlstr{"primates "}\hlstd{,}
\hlkwc{lwd}\hlstd{=}\hlnum{0.5}\hlstd{,}
\hlkwc{cex_main}\hlstd{=}\hlnum{1}\hlstd{,}
\hlkwc{lab.cex}\hlstd{=font,}
\hlkwc{k_labels}\hlstd{=}\hlnum{6}\hlstd{,}
\hlkwc{color_lines}\hlstd{=col)}
\hlkwd{dev.off}\hlstd{()}
\end{alltt}
\begin{verbatim}
## RStudioGD
## 2
\end{verbatim}
\end{kframe}
\end{knitrout}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tmp}\hlkwb{<-}\hlstd{tablo[(tablo}\hlopt{$}\hlstd{nbats}\hlopt{>=}\hlnum{3} \hlopt{|} \hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlopt{>=}\hlnum{3}\hlstd{),]}
\hlkwd{dim}\hlstd{(tmp)}
\end{alltt}
\begin{verbatim}
## [1] 108 3
\end{verbatim}
\begin{alltt}
\hlstd{tmp}\hlkwb{<-}\hlkwd{as.data.frame}\hlstd{(tmp)}
\hlkwd{names}\hlstd{(tmp)}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"tmp.Gene.name"}\hlstd{,} \hlstr{"nbats"}\hlstd{,} \hlstr{"nprimates"}\hlstd{)}
\hlstd{matbats}\hlkwb{<-}\hlkwd{hclust}\hlstd{(}\hlkwd{dist}\hlstd{(tmp}\hlopt{$}\hlstd{nbats))}
\hlstd{matpri}\hlkwb{<-}\hlkwd{hclust}\hlstd{(}\hlkwd{dist}\hlstd{(tmp}\hlopt{$}\hlstd{nprimates))}
\hlcom{#tmp[order(tmp$nbats),]}
\hlstd{dendpri}\hlkwb{<-}\hlkwd{as.dendrogram}\hlstd{(matpri)}
\hlstd{dendbats}\hlkwb{<-}\hlkwd{as.dendrogram}\hlstd{(matbats)}
\hlkwd{labels}\hlstd{(dendpri)}\hlkwb{<-}\hlkwd{as.character}\hlstd{(tmp}\hlopt{$}\hlstd{tmp.Gene.name[}\hlkwd{labels}\hlstd{(dendpri)])}
\hlkwd{labels}\hlstd{(dendbats)}\hlkwb{<-}\hlkwd{as.character}\hlstd{(tmp}\hlopt{$}\hlstd{tmp.Gene.name[}\hlkwd{labels}\hlstd{(dendbats)])}
\hlstd{tmp[}\hlkwd{order}\hlstd{(tmp}\hlopt{$}\hlstd{nprimates,} \hlkwc{decreasing}\hlstd{=}\hlnum{FALSE}\hlstd{),]}\hlopt{$}\hlstd{tmp.Gene.name}\hlkwb{->} \hlstd{order}
\hlstd{dendpri}\hlkwb{<-}\hlstd{dendextend}\hlopt{::}\hlkwd{rotate}\hlstd{(dendpri,} \hlkwc{order}\hlstd{=order)}
\hlstd{tmp[}\hlkwd{order}\hlstd{(tmp}\hlopt{$}\hlstd{nbats,} \hlkwc{decreasing}\hlstd{=}\hlnum{FALSE}\hlstd{),]}\hlopt{$}\hlstd{tmp.Gene.name}\hlkwb{->} \hlstd{order}
\hlstd{dendbats}\hlkwb{<-}\hlstd{dendextend}\hlopt{::}\hlkwd{rotate}\hlstd{(dendbats,} \hlkwc{order}\hlstd{=order)}
\hlcom{#### Il faut swapper certains neuds de l'arbres}
\hlkwd{class}\hlstd{(}\hlkwd{labels}\hlstd{(dendpri))}
\end{alltt}
\begin{verbatim}
## [1] "character"
\end{verbatim}
\begin{alltt}
\hlstd{dend12} \hlkwb{<-} \hlkwd{dendlist}\hlstd{(dendbats, dendpri)}
\hlstd{ace}\hlkwb{<-}\hlnum{97}
\hlstd{tmprss2}\hlkwb{<-}\hlnum{27}
\hlstd{znf318}\hlkwb{<-}\hlnum{31}
\hlstd{sepsecs}\hlkwb{<-}\hlnum{69}
\hlstd{tbk1}\hlkwb{<-}\hlnum{106}
\hlstd{ripk1}\hlkwb{<-}\hlnum{68}
\hlstd{col}\hlkwb{<-}\hlkwd{rep}\hlstd{(}\hlstr{"lightblue"}\hlstd{,} \hlkwd{length}\hlstd{(}\hlkwd{labels}\hlstd{(dendpri)))}
\hlstd{plusplus}\hlkwb{<-}\hlstd{tmp}\hlopt{$}\hlstd{tmp.Gene.name[tmp}\hlopt{$}\hlstd{nbats}\hlopt{>=}\hlnum{3} \hlopt{&} \hlstd{tmp}\hlopt{$}\hlstd{nprimates}\hlopt{>=}\hlnum{3}\hlstd{]}
\hlstd{col[}\hlkwd{which}\hlstd{(}\hlkwd{labels}\hlstd{(dendbats)} \hlopt{%in%} \hlstd{plusplus)]}\hlkwb{<-}\hlstr{"pink"}
\hlstd{interest}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"TMPRSS2"}\hlstd{,}\hlstr{"ZNF318"}\hlstd{,} \hlstr{"SEPSECS"}\hlstd{,}\hlstr{"TBK1"}\hlstd{,} \hlstr{"RIPK1"}\hlstd{)}
\hlstd{col[}\hlkwd{which}\hlstd{(}\hlkwd{labels}\hlstd{(dendbats)} \hlopt{%in%} \hlstd{interest)]}\hlkwb{<-}\hlstr{"blue"}
\hlstd{interestpp}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"ACE2"}\hlstd{)}
\hlstd{col[}\hlkwd{which}\hlstd{(}\hlkwd{labels}\hlstd{(dendbats)} \hlopt{%in%} \hlstd{interestpp)]}\hlkwb{<-}\hlstr{"red"}
\hlkwd{png}\hlstd{(}\hlstr{"figure/tanglegrammsup3.png"}\hlstd{,} \hlkwc{width} \hlstd{=} \hlnum{500}\hlstd{,} \hlkwc{height} \hlstd{=} \hlnum{1200}\hlstd{)}
\hlkwd{tanglegram}\hlstd{(dend12,} \hlkwc{columns_width}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{3}\hlstd{,} \hlnum{3}\hlstd{,}\hlnum{3}\hlstd{),} \hlkwc{axes}\hlstd{=}\hlnum{FALSE}\hlstd{,}
\hlkwc{edge.lwd}\hlstd{=}\hlnum{0}\hlstd{,} \hlkwc{margin_inner}\hlstd{=}\hlnum{6}\hlstd{,}
\hlkwc{margin_top}\hlstd{=}\hlnum{3}\hlstd{,}
\hlkwc{main_left}\hlstd{=}\hlstr{" bats"}\hlstd{,}
\hlkwc{main_right} \hlstd{=} \hlstr{"primates "}\hlstd{,}
\hlkwc{lwd}\hlstd{=}\hlnum{0.5}\hlstd{,}
\hlkwc{cex_main}\hlstd{=}\hlnum{2}\hlstd{,}
\hlkwc{lab.cex}\hlstd{=}\hlnum{1}\hlstd{,}
\hlkwc{k_labels}\hlstd{=}\hlnum{6}\hlstd{,}
\hlkwc{color_lines}\hlstd{=col)}
\hlkwd{dev.off}\hlstd{()}
\end{alltt}
\begin{verbatim}
## RStudioGD
## 2
\end{verbatim}
\begin{alltt}
\hlcom{### Changer couleurs des groupes}
\hlcom{## changer couleurs des lines sel vs sel or sel vs non-sel}
\hlkwd{setEPS}\hlstd{()}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/unnamed-chunk-13-1}
\begin{kframe}\begin{alltt}
\hlkwd{postscript}\hlstd{(}\hlstr{"figure/tanglegramsup3.eps"}\hlstd{,} \hlkwc{height}\hlstd{=}\hlnum{15}\hlstd{,} \hlkwc{width}\hlstd{=}\hlnum{5}\hlstd{)}
\hlkwd{tanglegram}\hlstd{(dend12,} \hlkwc{columns_width}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{3}\hlstd{,} \hlnum{3}\hlstd{,}\hlnum{3}\hlstd{),} \hlkwc{axes}\hlstd{=}\hlnum{FALSE}\hlstd{,}
\hlkwc{edge.lwd}\hlstd{=}\hlnum{0}\hlstd{,} \hlkwc{margin_inner}\hlstd{=}\hlnum{6}\hlstd{,}
\hlkwc{margin_top}\hlstd{=}\hlnum{3}\hlstd{,}
\hlkwc{main_left}\hlstd{=}\hlstr{" bats"}\hlstd{,}
\hlkwc{main_right} \hlstd{=} \hlstr{"primates "}\hlstd{,}
\hlkwc{lwd}\hlstd{=}\hlnum{0.5}\hlstd{,}
\hlkwc{cex_main}\hlstd{=}\hlnum{2}\hlstd{,}
\hlkwc{lab.cex}\hlstd{=}\hlnum{1}\hlstd{,}
\hlcom{# k_labels=6,}
\hlkwc{color_lines}\hlstd{=col)}
\hlkwd{dev.off}\hlstd{()}
\end{alltt}
\begin{verbatim}
## RStudioGD
## 2
\end{verbatim}
\begin{alltt}
\hlkwd{labels_colors}\hlstd{(dend12[[}\hlnum{1}\hlstd{]])}\hlkwb{<-}\hlkwd{rep}\hlstd{(}\hlkwd{rainbow}\hlstd{(}\hlnum{15}\hlstd{)[}\hlkwd{c}\hlstd{(}\hlnum{1}\hlopt{:}\hlnum{3}\hlstd{,} \hlnum{9}\hlopt{:}\hlnum{11}\hlstd{)],} \hlkwd{table}\hlstd{(tmp}\hlopt{$}\hlstd{nbats))}
\hlkwd{labels_colors}\hlstd{(dend12[[}\hlnum{2}\hlstd{]])}\hlkwb{<-}\hlkwd{rep}\hlstd{(}\hlkwd{rainbow}\hlstd{(}\hlnum{15}\hlstd{)[}\hlkwd{c}\hlstd{(}\hlnum{1}\hlopt{:}\hlnum{3}\hlstd{,} \hlnum{9}\hlopt{:}\hlnum{11}\hlstd{)],} \hlkwd{table}\hlstd{(tmp}\hlopt{$}\hlstd{nprimates))}
\hlstd{tmp}
\hlopt{?}\hlstd{tanglegram}
\hlkwd{labels_colors}\hlstd{(dend12[[}\hlnum{1}\hlstd{]])}\hlkwb{<-}\hlkwd{rep}\hlstd{(}\hlkwd{viridis}\hlstd{(}\hlnum{10}\hlstd{)[}\hlkwd{c}\hlstd{(}\hlnum{1}\hlopt{:}\hlnum{3}\hlstd{,} \hlnum{7}\hlopt{:}\hlnum{9}\hlstd{)],} \hlkwd{table}\hlstd{(tmp}\hlopt{$}\hlstd{nbats))}
\end{alltt}
{\ttfamily\noindent\bfseries\color{errorcolor}{\#\# Error in viridis(10): impossible de trouver la fonction "{}viridis"{}}}\begin{alltt}
\hlkwd{labels_colors}\hlstd{(dend12[[}\hlnum{2}\hlstd{]])}\hlkwb{<-}\hlkwd{rep}\hlstd{(}\hlkwd{viridis}\hlstd{(}\hlnum{10}\hlstd{)[}\hlkwd{c}\hlstd{(}\hlnum{1}\hlopt{:}\hlnum{3}\hlstd{,} \hlnum{7}\hlopt{:}\hlnum{9}\hlstd{)],} \hlkwd{table}\hlstd{(tmp}\hlopt{$}\hlstd{nprimates))}
\end{alltt}
{\ttfamily\noindent\bfseries\color{errorcolor}{\#\# Error in viridis(10): impossible de trouver la fonction "{}viridis"{}}}\begin{alltt}
\hlkwd{setEPS}\hlstd{()}
\hlkwd{postscript}\hlstd{(}\hlstr{"figure/tanglegramsup3_V2.eps"}\hlstd{,} \hlkwc{height}\hlstd{=}\hlnum{15}\hlstd{,} \hlkwc{width}\hlstd{=}\hlnum{5}\hlstd{)}
\hlkwd{tanglegram}\hlstd{(dend12,} \hlkwc{columns_width}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{3}\hlstd{,} \hlnum{3}\hlstd{,}\hlnum{3}\hlstd{),} \hlkwc{axes}\hlstd{=}\hlnum{FALSE}\hlstd{,}
\hlkwc{edge.lwd}\hlstd{=}\hlnum{0}\hlstd{,} \hlkwc{margin_inner}\hlstd{=}\hlnum{6}\hlstd{,}
\hlkwc{margin_top}\hlstd{=}\hlnum{3}\hlstd{,}
\hlkwc{main_left}\hlstd{=}\hlstr{" bats"}\hlstd{,}
\hlkwc{main_right} \hlstd{=} \hlstr{"primates "}\hlstd{,}
\hlkwc{lwd}\hlstd{=}\hlnum{0.5}\hlstd{,}
\hlkwc{cex_main}\hlstd{=}\hlnum{2}\hlstd{,}
\hlkwc{lab.cex}\hlstd{=}\hlnum{1}\hlstd{,}
\hlcom{# k_labels=6,}
\hlkwc{color_lines}\hlstd{=col)}
\hlkwd{dev.off}\hlstd{()}
\end{alltt}
\begin{verbatim}
## RStudioGD
## 2
\end{verbatim}
\end{kframe}
\end{knitrout}
\end{document}
......
covid_comp_maic-pancorona.Rnw 0 → 100644
View file @ 77f559a1
\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, maic}
\author{Marie Cariou}
\date{March 2021} % Activate to display a given date or no date
\begin{document}
\maketitle
\tableofcontents
\newpage
\section{Data}
output from covid\_comp\_dataset.
<<>>=
tablo<-read.table("primatesVbats.csv",
h=T, sep=",")
@
Output MAIC formatted by Léa. This table includes the DGINN "score".
<<>>=
home<-"/home/adminmarie/Documents/"
workdir<-paste0(home, "CIRI_BIBS_projects/2020_05_Etienne_covid/")
maic<-read.table(paste0(workdir, "data/covid_comp_maic.txt"),
h=T)
@
\section{MAIC}
\subsection{Boxplot}
<<boxplot, fig.height=12>>=
par(mfrow=c(2,1))
boxplot(maic$rank~maic$nbats, notch=TRUE, varwidth=TRUE, xlab="score DGINN", ylab="rank MAIC", main="Bats")
stripchart(maic$rank~maic$nbats, method="jitter", vertical=TRUE, pch=1, cex=0.3, add=TRUE)
boxplot(maic$rank~maic$nprimates, notch=TRUE, xlab="score DGINN", ylab="rank MAIC", main="Primates")
stripchart(maic$rank~maic$nprimates, method="jitter", vertical=TRUE, pch=1, cex=0.3, add=TRUE)
@
\subsection{Dotchart}
<<dotbats, fig.height=8>>=
tmp<-maic[maic$nbats>=3, c("gene", "rank", "nbats")]
tmp<-tmp[order(tmp$rank, decreasing = TRUE),]
tmp$col<-"black"
tmp$col[tmp$gene=="ACE2"]<-"red"
tmp$col[tmp$gene=="TMPRSS2"]<-"red"
tmp$pch[tmp$nbats==5]<-1
tmp$pch[tmp$nbats==4]<-20
tmp$pch[tmp$nbats==3]<-4
dotchart(tmp$rank, main="Bats DGINN >=3", xlab="rank MAIC", labels=tmp$gene, pch=tmp$pch, col=tmp$col)
legend("topright", c("5 (score DGINN)", "4", "3"), pch=c(1,20,4))
@
<<dotprimates, fig.height=12>>=
tmp<-maic[maic$nprimates>=3, c("gene", "rank", "nprimates")]
tmp<-tmp[order(tmp$rank, decreasing = TRUE),]
tmp$pch[tmp$nprimates==5]<-1
tmp$pch[tmp$nprimates==4]<-20
tmp$pch[tmp$nprimates==3]<-4
tmp$col<-"black"
tmp$col[tmp$gene=="ACE2"]<-"red"
tmp$col[tmp$gene=="TMPRSS2"]<-"red"
dotchart(tmp$rank, main="Primates DGINN >=3", xlab="rank MAIC", labels=tmp$gene, pch=tmp$pch, cex=0.8, col=tmp$col)
legend("topright", c("5 (score DGINN)", "4", "3"), pch=c(1,20,4))
@
\section{Pan Corona}
<<>>=
pancorona<-read.table(paste0(workdir, "data/pancorona_S5.csv"),
h=T, fill = TRUE, sep="\t")
names(pancorona)<-c("tmp.Gene.name", names(pancorona)[-1])
# Genes en commun
pancorona$tmp.Gene.name[pancorona$tmp.Gene.name %in% tablo$tmp.Gene.name]
# Uniquement dans le tableau pancorona
sort(pancorona$tmp.Gene.name[(pancorona$tmp.Gene.name %in% tablo$tmp.Gene.name)==FALSE])
## Uniquement dans tableau
sort(tablo$tmp.Gene.name[(tablo$tmp.Gene.name %in% pancorona$tmp.Gene.name)==FALSE])
@
<<pancorona, fig.height=8>>=
pancorona<-pancorona[,c("tmp.Gene.name", "TOTAL")]
pandginn<-na.omit(merge(pancorona, tablo, by="tmp.Gene.name", all.x=TRUE))
pandginn<-pandginn[order(pandginn$nprimates),]
pandginn<-pandginn[order(pandginn$TOTAL),]
dotchart(as.matrix(pandginn[,2]), labels = pandginn$tmp.Gene.name, xlim=c(0,5))
points(pandginn[,4], 1:nrow(pandginn), col="blue", pch=20, cex=0.7)
points(pandginn[,3], 1:nrow(pandginn), col="blue", pch=4)
legend("bottomright", c("pancorona score", "dginn primate score", "dginn bats score"), pch=c(1,20,4), col=c("black", "blue", "blue"))
@
A-t-on un enrichissement en Pan-corona dans nos gènes sous PS?
<<>>=
pandginnall<-merge(pancorona, tablo, by="tmp.Gene.name", all.x=FALSE,all.y=TRUE)
dim(pandginnall)
# test indépendance: under PS / in the pancorona list
table(is.na(pandginnall$TOTAL)==FALSE)
table(pandginnall$nbats>=3)
chi<-table(is.na(pandginnall$TOTAL)==FALSE,pandginnall$nbats>=3)
chi
chisq.test(chi)
table(is.na(pandginnall$TOTAL)==FALSE)
table(pandginnall$nprimates>=3)
chi<-table(is.na(pandginnall$TOTAL)==FALSE,pandginnall$nprimates>=3)
chi
chisq.test(chi)
@
No enrichment in PanCORONA in our genes under PS.
\end{document}
covid_comp_maic-pancorona.pdf 0 → 100644
View file @ 77f559a1
File added
covid_comp_maic-pancorona.tex 0 → 100644
View file @ 77f559a1
\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, maic}
\author{Marie Cariou}
\date{March 2021} % Activate to display a given date or no date
\IfFileExists{upquote.sty}{\usepackage{upquote}}{}
\begin{document}
\maketitle
\tableofcontents
\newpage
\section{Data}
output from covid\_comp\_dataset.
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tablo}\hlkwb{<-}\hlkwd{read.table}\hlstd{(}\hlstr{"primatesVbats.csv"}\hlstd{,}
\hlkwc{h}\hlstd{=T,} \hlkwc{sep}\hlstd{=}\hlstr{","}\hlstd{)}
\end{alltt}
\end{kframe}
\end{knitrout}
Output MAIC formatted by Léa. This table includes the DGINN "score".
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{home}\hlkwb{<-}\hlstr{"/home/adminmarie/Documents/"}
\hlstd{workdir}\hlkwb{<-}\hlkwd{paste0}\hlstd{(home,} \hlstr{"CIRI_BIBS_projects/2020_05_Etienne_covid/"}\hlstd{)}
\hlstd{maic}\hlkwb{<-}\hlkwd{read.table}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,} \hlstr{"data/covid_comp_maic.txt"}\hlstd{),}
\hlkwc{h}\hlstd{=T)}
\end{alltt}
\end{kframe}
\end{knitrout}
\section{MAIC}
\subsection{Boxplot}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{par}\hlstd{(}\hlkwc{mfrow}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{2}\hlstd{,}\hlnum{1}\hlstd{))}
\hlkwd{boxplot}\hlstd{(maic}\hlopt{$}\hlstd{rank}\hlopt{~}\hlstd{maic}\hlopt{$}\hlstd{nbats,} \hlkwc{notch}\hlstd{=}\hlnum{TRUE}\hlstd{,} \hlkwc{varwidth}\hlstd{=}\hlnum{TRUE}\hlstd{,} \hlkwc{xlab}\hlstd{=}\hlstr{"score DGINN"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"rank MAIC"}\hlstd{,} \hlkwc{main}\hlstd{=}\hlstr{"Bats"}\hlstd{)}
\end{alltt}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning in bxp(list(stats = structure(c(21, 825, 1664, 2860, 5392, 15, 625.5, : some notches went outside hinges ('box'): maybe set notch=FALSE}}\begin{alltt}
\hlkwd{stripchart}\hlstd{(maic}\hlopt{$}\hlstd{rank}\hlopt{~}\hlstd{maic}\hlopt{$}\hlstd{nbats,} \hlkwc{method}\hlstd{=}\hlstr{"jitter"}\hlstd{,} \hlkwc{vertical}\hlstd{=}\hlnum{TRUE}\hlstd{,} \hlkwc{pch}\hlstd{=}\hlnum{1}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.3}\hlstd{,} \hlkwc{add}\hlstd{=}\hlnum{TRUE}\hlstd{)}
\hlkwd{boxplot}\hlstd{(maic}\hlopt{$}\hlstd{rank}\hlopt{~}\hlstd{maic}\hlopt{$}\hlstd{nprimates,} \hlkwc{notch}\hlstd{=}\hlnum{TRUE}\hlstd{,} \hlkwc{xlab}\hlstd{=}\hlstr{"score DGINN"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"rank MAIC"}\hlstd{,} \hlkwc{main}\hlstd{=}\hlstr{"Primates"}\hlstd{)}
\hlkwd{stripchart}\hlstd{(maic}\hlopt{$}\hlstd{rank}\hlopt{~}\hlstd{maic}\hlopt{$}\hlstd{nprimates,} \hlkwc{method}\hlstd{=}\hlstr{"jitter"}\hlstd{,} \hlkwc{vertical}\hlstd{=}\hlnum{TRUE}\hlstd{,} \hlkwc{pch}\hlstd{=}\hlnum{1}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.3}\hlstd{,} \hlkwc{add}\hlstd{=}\hlnum{TRUE}\hlstd{)}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/boxplot-1}
\end{knitrout}
\subsection{Dotchart}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tmp}\hlkwb{<-}\hlstd{maic[maic}\hlopt{$}\hlstd{nbats}\hlopt{>=}\hlnum{3}\hlstd{,} \hlkwd{c}\hlstd{(}\hlstr{"gene"}\hlstd{,} \hlstr{"rank"}\hlstd{,} \hlstr{"nbats"}\hlstd{)]}
\hlstd{tmp}\hlkwb{<-}\hlstd{tmp[}\hlkwd{order}\hlstd{(tmp}\hlopt{$}\hlstd{rank,} \hlkwc{decreasing} \hlstd{=} \hlnum{TRUE}\hlstd{),]}
\hlstd{tmp}\hlopt{$}\hlstd{col}\hlkwb{<-}\hlstr{"black"}
\hlstd{tmp}\hlopt{$}\hlstd{col[tmp}\hlopt{$}\hlstd{gene}\hlopt{==}\hlstr{"ACE2"}\hlstd{]}\hlkwb{<-}\hlstr{"red"}
\hlstd{tmp}\hlopt{$}\hlstd{col[tmp}\hlopt{$}\hlstd{gene}\hlopt{==}\hlstr{"TMPRSS2"}\hlstd{]}\hlkwb{<-}\hlstr{"red"}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{5}\hlstd{]}\hlkwb{<-}\hlnum{1}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{4}\hlstd{]}\hlkwb{<-}\hlnum{20}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{3}\hlstd{]}\hlkwb{<-}\hlnum{4}
\hlkwd{dotchart}\hlstd{(tmp}\hlopt{$}\hlstd{rank,} \hlkwc{main}\hlstd{=}\hlstr{"Bats DGINN >=3"}\hlstd{,} \hlkwc{xlab}\hlstd{=}\hlstr{"rank MAIC"}\hlstd{,} \hlkwc{labels}\hlstd{=tmp}\hlopt{$}\hlstd{gene,} \hlkwc{pch}\hlstd{=tmp}\hlopt{$}\hlstd{pch,} \hlkwc{col}\hlstd{=tmp}\hlopt{$}\hlstd{col)}
\hlkwd{legend}\hlstd{(}\hlstr{"topright"}\hlstd{,} \hlkwd{c}\hlstd{(}\hlstr{"5 (score DGINN)"}\hlstd{,} \hlstr{"4"}\hlstd{,} \hlstr{"3"}\hlstd{),} \hlkwc{pch}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{1}\hlstd{,}\hlnum{20}\hlstd{,}\hlnum{4}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/dotbats-1}
\end{knitrout}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tmp}\hlkwb{<-}\hlstd{maic[maic}\hlopt{$}\hlstd{nprimates}\hlopt{>=}\hlnum{3}\hlstd{,} \hlkwd{c}\hlstd{(}\hlstr{"gene"}\hlstd{,} \hlstr{"rank"}\hlstd{,} \hlstr{"nprimates"}\hlstd{)]}
\hlstd{tmp}\hlkwb{<-}\hlstd{tmp[}\hlkwd{order}\hlstd{(tmp}\hlopt{$}\hlstd{rank,} \hlkwc{decreasing} \hlstd{=} \hlnum{TRUE}\hlstd{),]}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{5}\hlstd{]}\hlkwb{<-}\hlnum{1}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{4}\hlstd{]}\hlkwb{<-}\hlnum{20}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{3}\hlstd{]}\hlkwb{<-}\hlnum{4}
\hlstd{tmp}\hlopt{$}\hlstd{col}\hlkwb{<-}\hlstr{"black"}
\hlstd{tmp}\hlopt{$}\hlstd{col[tmp}\hlopt{$}\hlstd{gene}\hlopt{==}\hlstr{"ACE2"}\hlstd{]}\hlkwb{<-}\hlstr{"red"}
\hlstd{tmp}\hlopt{$}\hlstd{col[tmp}\hlopt{$}\hlstd{gene}\hlopt{==}\hlstr{"TMPRSS2"}\hlstd{]}\hlkwb{<-}\hlstr{"red"}
\hlkwd{dotchart}\hlstd{(tmp}\hlopt{$}\hlstd{rank,} \hlkwc{main}\hlstd{=}\hlstr{"Primates DGINN >=3"}\hlstd{,} \hlkwc{xlab}\hlstd{=}\hlstr{"rank MAIC"}\hlstd{,} \hlkwc{labels}\hlstd{=tmp}\hlopt{$}\hlstd{gene,} \hlkwc{pch}\hlstd{=tmp}\hlopt{$}\hlstd{pch,} \hlkwc{cex}\hlstd{=}\hlnum{0.8}\hlstd{,} \hlkwc{col}\hlstd{=tmp}\hlopt{$}\hlstd{col)}
\hlkwd{legend}\hlstd{(}\hlstr{"topright"}\hlstd{,} \hlkwd{c}\hlstd{(}\hlstr{"5 (score DGINN)"}\hlstd{,} \hlstr{"4"}\hlstd{,} \hlstr{"3"}\hlstd{),} \hlkwc{pch}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{1}\hlstd{,}\hlnum{20}\hlstd{,}\hlnum{4}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/dotprimates-1}
\end{knitrout}
\section{Pan Corona}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{pancorona}\hlkwb{<-}\hlkwd{read.table}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,} \hlstr{"data/pancorona_S5.csv"}\hlstd{),}
\hlkwc{h}\hlstd{=T,} \hlkwc{fill} \hlstd{=} \hlnum{TRUE}\hlstd{,} \hlkwc{sep}\hlstd{=}\hlstr{"\textbackslash{}t"}\hlstd{)}
\hlkwd{names}\hlstd{(pancorona)}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"tmp.Gene.name"}\hlstd{,} \hlkwd{names}\hlstd{(pancorona)[}\hlopt{-}\hlnum{1}\hlstd{])}
\hlcom{# Genes en commun}
\hlstd{pancorona}\hlopt{$}\hlstd{tmp.Gene.name[pancorona}\hlopt{$}\hlstd{tmp.Gene.name} \hlopt{%in%} \hlstd{tablo}\hlopt{$}\hlstd{tmp.Gene.name]}
\end{alltt}
\begin{verbatim}
## [1] TBK1 MARK3 GIGYF2 MARK2 G3BP1 LARP1 ACE2 PABPC1
## [9] TMPRSS2 AP3B1 CLCC1 CSDE1 HECTD1 MARK1 MEPCE PDE4DIP
## [17] POR PRKAR2B RAB5C RTN4 SRP54 UBAP2 UBAP2L UBXN8
## [25] SPART BZW2 EIF4E2 SMOC1 STOML2 DDX21 FAM98A G3BP2
## [33] MOV10 PABPC4 UPF1
## 105 Levels: ACE2 ANPEP AP3B1 ATXN2L BTF3 BZW2 CKAP5 CLCC1 ... YTHDF2
\end{verbatim}
\begin{alltt}
\hlcom{# Uniquement dans le tableau pancorona}
\hlkwd{sort}\hlstd{(pancorona}\hlopt{$}\hlstd{tmp.Gene.name[(pancorona}\hlopt{$}\hlstd{tmp.Gene.name} \hlopt{%in%} \hlstd{tablo}\hlopt{$}\hlstd{tmp.Gene.name)}\hlopt{==}\hlnum{FALSE}\hlstd{])}
\end{alltt}
\begin{verbatim}
## [1] ANPEP ATXN2L BTF3 CKAP5 CTSB CTSL
## [7] CYB5R3 DDX1 DDX5 DDX58 DHX9 DNM1L
## [13] EEF1A1 EIF2A EIF3F EIF4B EZR FLNA
## [19] FURIN FUS GSK3A GSK3B HDLBP HNRNPA1
## [25] HNRNPD HNRNPF HNRNPU IFIH1 IGF2BP1 IKBKB
## [31] IKBKE IRF3 ISG15 KPNA3 KPNB1 MYH9
## [37] NCL POLD1 POLR2B PRKRA RBM14 RCHY1
## [43] RPL13A RPL26 RPS13 RPS17 RPS19 RPS9
## [49] SDCBP SERBP1 SGTA SLC1A5 SNAP47 SSB
## [55] STING1 SYNCRIP TANC1 TBCB TMPRSS11D TRAF3
## [61] TUBA4A TUBB2A TUBB4A TUBB6 USP10 VPS36
## [67] XRCC5 XRCC6 YBX1 YTHDF2
## 105 Levels: ACE2 ANPEP AP3B1 ATXN2L BTF3 BZW2 CKAP5 CLCC1 ... YTHDF2
\end{verbatim}
\begin{alltt}
\hlcom{## Uniquement dans tableau }
\hlkwd{sort}\hlstd{(tablo}\hlopt{$}\hlstd{tmp.Gene.name[(tablo}\hlopt{$}\hlstd{tmp.Gene.name} \hlopt{%in%} \hlstd{pancorona}\hlopt{$}\hlstd{tmp.Gene.name)}\hlopt{==}\hlnum{FALSE}\hlstd{])}
\end{alltt}
\begin{verbatim}
## [1] AAR2 AASS AATF ABCC1 ACAD9 ACADM
## [7] ACSL3 ADAM9 ADAMTS1 AGPS AKAP8 AKAP8L
## [13] AKAP9 ALG11 ALG5 ALG8 ANO6 AP2A2
## [19] AP2M1 ARF6 ATE1 ATP13A3 ATP1B1 ATP6AP1
## [25] ATP6V1A BAG5 BCKDK BRD2 BRD4 CCDC86
## [31] CDK5RAP2 CENPF CEP112 CEP135 CEP250 CEP350
## [37] CEP68 CHMP2A CHPF CHPF2 CISD3 CIT
## [43] CLIP4 CNTRL COL6A1 COLGALT1 COMT COQ8B
## [49] CRTC3 CSNK2A2 CSNK2B CUL2 CWC27 CYB5B
## [55] DCAF7 DCAKD DCTPP1 DDX10 DNAJC11 DNAJC19
## [61] DNMT1 DPH5 DPY19L1 ECSIT EDEM3 EIF4H
## [67] ELOC EMC1 ERC1 ERGIC1 ERLEC1 ERMP1
## [73] ERO1B ERP44 ETFA EXOSC2 EXOSC3 EXOSC5
## [79] EXOSC8 F2RL1 FAM162A FAM8A1 FAR2 FASTKD5
## [85] FBLN5 FBN1 FBN2 FBXL12 FKBP10 FKBP15
## [91] FKBP7 FOXRED2 FYCO1 GCC1 GCC2 GDF15
## [97] GFER GGCX GGH GHITM GLA GNB1
## [103] GNG5 GOLGA2 GOLGA3 GOLGA7 GOLGB1 GORASP1
## [109] GPAA1 GPX1 GRIPAP1 GRPEL1 GTF2F2 HDAC2
## [115] HEATR3 HMOX1 HOOK1 HS2ST1 HS6ST2 HSBP1
## [121] HYOU1 IDE IL17RA IMPDH2 INHBE INTS4
## [127] ITGB1 JAKMIP1 KDELC1 KDELC2 LARP4B LARP7
## [133] LMAN2 LOX MAP7D1 MARC1 MAT2B MDN1
## [139] MIB1 MIPOL1 MOGS MPHOSPH10 MRPS2 MRPS25
## [145] MRPS27 MRPS5 MTCH1 MYCBP2 NARS2 NAT14
## [151] NDFIP2 NDUFAF1 NDUFAF2 NDUFB9 NEK9 NEU1
## [157] NGDN NGLY1 NIN NINL NLRX1 NOL10
## [163] NPC2 NPTX1 NSD2 NUP210 NUP214 NUP54
## [169] NUP58 NUP62 NUP88 NUP98 NUTF2 OS9
## [175] PCNT PCSK5 PCSK6 PDZD11 PIGO PIGS
## [181] PITRM1 PKP2 PLAT PLD3 PLEKHA5 PLEKHF2
## [187] PLOD2 PMPCA PMPCB POFUT1 POLA1 POLA2
## [193] PPIL3 PPT1 PRIM1 PRIM2 PRKACA PRKAR2A
## [199] PRRC2B PSMD8 PTBP2 PTGES2 PUSL1 PVR
## [205] QSOX2 RAB10 RAB14 RAB18 RAB1A RAB2A
## [211] RAB7A RAB8A RAE1 RALA RAP1GDS1 RBM28
## [217] RBM41 RBX1 RDX REEP5 REEP6 RETREG3
## [223] RHOA RIPK1 RNF41 RPL36 RRP9 SAAL1
## [229] SBNO1 SCAP SCARB1 SCCPDH SDF2 SELENOS
## [235] SEPSECS SIL1 SIRT5 SLC25A21 SLC27A2 SLC30A6
## [241] SLC30A7 SLC30A9 SLC44A2 SLC9A3R1 SLU7 SNIP1
## [247] SRP19 SRP72 STC2 STOM SUN2 TAPT1
## [253] TARS2 TBCA TBKBP1 TCF12 THTPA TIMM10
## [259] TIMM10B TIMM29 TIMM8B TIMM9 TLE1 TLE3
## [265] TM2D3 TMED5 TMEM39B TMEM97 TOMM70 TOR1A
## [271] TOR1AIP1 TRIM59 TRMT1 TUBGCP2 TUBGCP3 TYSND1
## [277] UGGT2 USP54 VPS11 VPS39 WASHC4 WFS1
## [283] YIF1A ZC3H18 ZC3H7A ZDHHC5 ZNF318 ZNF503
## [289] ZYG11B
## 324 Levels: AAR2 AASS AATF ABCC1 ACAD9 ACADM ACE2 ACSL3 ... ZYG11B
\end{verbatim}
\end{kframe}
\end{knitrout}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{pancorona}\hlkwb{<-}\hlstd{pancorona[,}\hlkwd{c}\hlstd{(}\hlstr{"tmp.Gene.name"}\hlstd{,} \hlstr{"TOTAL"}\hlstd{)]}
\hlstd{pandginn}\hlkwb{<-}\hlkwd{na.omit}\hlstd{(}\hlkwd{merge}\hlstd{(pancorona, tablo,} \hlkwc{by}\hlstd{=}\hlstr{"tmp.Gene.name"}\hlstd{,} \hlkwc{all.x}\hlstd{=}\hlnum{TRUE}\hlstd{))}
\hlstd{pandginn}\hlkwb{<-}\hlstd{pandginn[}\hlkwd{order}\hlstd{(pandginn}\hlopt{$}\hlstd{nprimates),]}
\hlstd{pandginn}\hlkwb{<-}\hlstd{pandginn[}\hlkwd{order}\hlstd{(pandginn}\hlopt{$}\hlstd{TOTAL),]}
\hlkwd{dotchart}\hlstd{(}\hlkwd{as.matrix}\hlstd{(pandginn[,}\hlnum{2}\hlstd{]),} \hlkwc{labels} \hlstd{= pandginn}\hlopt{$}\hlstd{tmp.Gene.name,} \hlkwc{xlim}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{0}\hlstd{,}\hlnum{5}\hlstd{))}
\hlkwd{points}\hlstd{(pandginn[,}\hlnum{4}\hlstd{],} \hlnum{1}\hlopt{:}\hlkwd{nrow}\hlstd{(pandginn),} \hlkwc{col}\hlstd{=}\hlstr{"blue"}\hlstd{,} \hlkwc{pch}\hlstd{=}\hlnum{20}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.7}\hlstd{)}
\hlkwd{points}\hlstd{(pandginn[,}\hlnum{3}\hlstd{],} \hlnum{1}\hlopt{:}\hlkwd{nrow}\hlstd{(pandginn),} \hlkwc{col}\hlstd{=}\hlstr{"blue"}\hlstd{,} \hlkwc{pch}\hlstd{=}\hlnum{4}\hlstd{)}
\hlkwd{legend}\hlstd{(}\hlstr{"bottomright"}\hlstd{,} \hlkwd{c}\hlstd{(}\hlstr{"pancorona score"}\hlstd{,} \hlstr{"dginn primate score"}\hlstd{,} \hlstr{"dginn bats score"}\hlstd{),} \hlkwc{pch}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{1}\hlstd{,}\hlnum{20}\hlstd{,}\hlnum{4}\hlstd{),} \hlkwc{col}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"black"}\hlstd{,} \hlstr{"blue"}\hlstd{,} \hlstr{"blue"}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/pancorona-1}
\end{knitrout}
A-t-on un enrichissement en Pan-corona dans nos gènes sous PS?
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{pandginnall}\hlkwb{<-}\hlkwd{merge}\hlstd{(pancorona, tablo,} \hlkwc{by}\hlstd{=}\hlstr{"tmp.Gene.name"}\hlstd{,} \hlkwc{all.x}\hlstd{=}\hlnum{FALSE}\hlstd{,}\hlkwc{all.y}\hlstd{=}\hlnum{TRUE}\hlstd{)}
\hlkwd{dim}\hlstd{(pandginnall)}
\end{alltt}
\begin{verbatim}
## [1] 324 4
\end{verbatim}
\begin{alltt}
\hlcom{# test indépendance: under PS / in the pancorona list}
\hlkwd{table}\hlstd{(}\hlkwd{is.na}\hlstd{(pandginnall}\hlopt{$}\hlstd{TOTAL)}\hlopt{==}\hlnum{FALSE}\hlstd{)}
\end{alltt}
\begin{verbatim}
##
## FALSE TRUE
## 289 35
\end{verbatim}
\begin{alltt}
\hlkwd{table}\hlstd{(pandginnall}\hlopt{$}\hlstd{nbats}\hlopt{>=}\hlnum{3}\hlstd{)}
\end{alltt}
\begin{verbatim}
##
## FALSE TRUE
## 286 38
\end{verbatim}
\begin{alltt}
\hlstd{chi}\hlkwb{<-}\hlkwd{table}\hlstd{(}\hlkwd{is.na}\hlstd{(pandginnall}\hlopt{$}\hlstd{TOTAL)}\hlopt{==}\hlnum{FALSE}\hlstd{,pandginnall}\hlopt{$}\hlstd{nbats}\hlopt{>=}\hlnum{3}\hlstd{)}
\hlstd{chi}
\end{alltt}
\begin{verbatim}
##
## FALSE TRUE
## FALSE 255 34
## TRUE 31 4
\end{verbatim}
\begin{alltt}
\hlkwd{chisq.test}\hlstd{(chi)}
\end{alltt}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning in chisq.test(chi): Chi-squared approximation may be incorrect}}\begin{verbatim}
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: chi
## X-squared = 7.6869e-31, df = 1, p-value = 1
\end{verbatim}
\begin{alltt}
\hlkwd{table}\hlstd{(}\hlkwd{is.na}\hlstd{(pandginnall}\hlopt{$}\hlstd{TOTAL)}\hlopt{==}\hlnum{FALSE}\hlstd{)}
\end{alltt}
\begin{verbatim}
##
## FALSE TRUE
## 289 35
\end{verbatim}
\begin{alltt}
\hlkwd{table}\hlstd{(pandginnall}\hlopt{$}\hlstd{nprimates}\hlopt{>=}\hlnum{3}\hlstd{)}
\end{alltt}
\begin{verbatim}
##
## FALSE TRUE
## 236 88
\end{verbatim}
\begin{alltt}
\hlstd{chi}\hlkwb{<-}\hlkwd{table}\hlstd{(}\hlkwd{is.na}\hlstd{(pandginnall}\hlopt{$}\hlstd{TOTAL)}\hlopt{==}\hlnum{FALSE}\hlstd{,pandginnall}\hlopt{$}\hlstd{nprimates}\hlopt{>=}\hlnum{3}\hlstd{)}
\hlstd{chi}
\end{alltt}
\begin{verbatim}
##
## FALSE TRUE
## FALSE 212 77
## TRUE 24 11
\end{verbatim}
\begin{alltt}
\hlkwd{chisq.test}\hlstd{(chi)}
\end{alltt}
\begin{verbatim}
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: chi
## X-squared = 0.15992, df = 1, p-value = 0.6892
\end{verbatim}
\end{kframe}
\end{knitrout}
No enrichment in PanCORONA in our genes under PS.
\end{document}
covid_comp_maic.pdf 0 → 100644
View file @ 77f559a1
File added
covid_comp_maic.tex 0 → 100644
View file @ 77f559a1
\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, maic}
\author{Marie Cariou}
\date{March 2021} % Activate to display a given date or no date
\IfFileExists{upquote.sty}{\usepackage{upquote}}{}
\begin{document}
\maketitle
\tableofcontents
\newpage
\section{Data}
output from covid\_comp\_dataset.
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tablo}\hlkwb{<-}\hlkwd{read.table}\hlstd{(}\hlstr{"primatesVbats.csv"}\hlstd{,}
\hlkwc{h}\hlstd{=T,} \hlkwc{sep}\hlstd{=}\hlstr{","}\hlstd{)}
\end{alltt}
\end{kframe}
\end{knitrout}
Output MAIC formatted by Léa. This table includes the DGINN "score".
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{home}\hlkwb{<-}\hlstr{"/home/adminmarie/Documents/"}
\hlstd{workdir}\hlkwb{<-}\hlkwd{paste0}\hlstd{(home,} \hlstr{"CIRI_BIBS_projects/2020_05_Etienne_covid/"}\hlstd{)}
\hlstd{maic}\hlkwb{<-}\hlkwd{read.table}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,} \hlstr{"data/covid_comp_maic.txt"}\hlstd{),}
\hlkwc{h}\hlstd{=T)}
\end{alltt}
\end{kframe}
\end{knitrout}
\section{MAIC}
\subsection{Boxplot}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{par}\hlstd{(}\hlkwc{mfrow}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{2}\hlstd{,}\hlnum{1}\hlstd{))}
\hlkwd{boxplot}\hlstd{(maic}\hlopt{$}\hlstd{rank}\hlopt{~}\hlstd{maic}\hlopt{$}\hlstd{nbats,} \hlkwc{notch}\hlstd{=}\hlnum{TRUE}\hlstd{,} \hlkwc{varwidth}\hlstd{=}\hlnum{TRUE}\hlstd{,} \hlkwc{xlab}\hlstd{=}\hlstr{"score DGINN"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"rank MAIC"}\hlstd{,} \hlkwc{main}\hlstd{=}\hlstr{"Bats"}\hlstd{)}
\end{alltt}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning in bxp(list(stats = structure(c(21, 825, 1664, 2860, 5392, 15, 625.5, : some notches went outside hinges ('box'): maybe set notch=FALSE}}\begin{alltt}
\hlkwd{stripchart}\hlstd{(maic}\hlopt{$}\hlstd{rank}\hlopt{~}\hlstd{maic}\hlopt{$}\hlstd{nbats,} \hlkwc{method}\hlstd{=}\hlstr{"jitter"}\hlstd{,} \hlkwc{vertical}\hlstd{=}\hlnum{TRUE}\hlstd{,} \hlkwc{pch}\hlstd{=}\hlnum{1}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.3}\hlstd{,} \hlkwc{add}\hlstd{=}\hlnum{TRUE}\hlstd{)}
\hlkwd{boxplot}\hlstd{(maic}\hlopt{$}\hlstd{rank}\hlopt{~}\hlstd{maic}\hlopt{$}\hlstd{nprimates,} \hlkwc{notch}\hlstd{=}\hlnum{TRUE}\hlstd{,} \hlkwc{xlab}\hlstd{=}\hlstr{"score DGINN"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"rank MAIC"}\hlstd{,} \hlkwc{main}\hlstd{=}\hlstr{"Primates"}\hlstd{)}
\hlkwd{stripchart}\hlstd{(maic}\hlopt{$}\hlstd{rank}\hlopt{~}\hlstd{maic}\hlopt{$}\hlstd{nprimates,} \hlkwc{method}\hlstd{=}\hlstr{"jitter"}\hlstd{,} \hlkwc{vertical}\hlstd{=}\hlnum{TRUE}\hlstd{,} \hlkwc{pch}\hlstd{=}\hlnum{1}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.3}\hlstd{,} \hlkwc{add}\hlstd{=}\hlnum{TRUE}\hlstd{)}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/boxplot-1}
\end{knitrout}
\subsection{Dotchart}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tmp}\hlkwb{<-}\hlstd{maic[maic}\hlopt{$}\hlstd{nbats}\hlopt{>=}\hlnum{3}\hlstd{,} \hlkwd{c}\hlstd{(}\hlstr{"gene"}\hlstd{,} \hlstr{"rank"}\hlstd{,} \hlstr{"nbats"}\hlstd{)]}
\hlstd{tmp}\hlkwb{<-}\hlstd{tmp[}\hlkwd{order}\hlstd{(tmp}\hlopt{$}\hlstd{rank,} \hlkwc{decreasing} \hlstd{=} \hlnum{TRUE}\hlstd{),]}
\hlstd{tmp}\hlopt{$}\hlstd{col}\hlkwb{<-}\hlstr{"black"}
\hlstd{tmp}\hlopt{$}\hlstd{col[tmp}\hlopt{$}\hlstd{gene}\hlopt{==}\hlstr{"ACE2"}\hlstd{]}\hlkwb{<-}\hlstr{"red"}
\hlstd{tmp}\hlopt{$}\hlstd{col[tmp}\hlopt{$}\hlstd{gene}\hlopt{==}\hlstr{"TMPRSS2"}\hlstd{]}\hlkwb{<-}\hlstr{"red"}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{5}\hlstd{]}\hlkwb{<-}\hlnum{1}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{4}\hlstd{]}\hlkwb{<-}\hlnum{20}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{3}\hlstd{]}\hlkwb{<-}\hlnum{4}
\hlkwd{dotchart}\hlstd{(tmp}\hlopt{$}\hlstd{rank,} \hlkwc{main}\hlstd{=}\hlstr{"Bats DGINN >=3"}\hlstd{,} \hlkwc{xlab}\hlstd{=}\hlstr{"rank MAIC"}\hlstd{,} \hlkwc{labels}\hlstd{=tmp}\hlopt{$}\hlstd{gene,} \hlkwc{pch}\hlstd{=tmp}\hlopt{$}\hlstd{pch,} \hlkwc{col}\hlstd{=tmp}\hlopt{$}\hlstd{col)}
\hlkwd{legend}\hlstd{(}\hlstr{"topright"}\hlstd{,} \hlkwd{c}\hlstd{(}\hlstr{"5 (score DGINN)"}\hlstd{,} \hlstr{"4"}\hlstd{,} \hlstr{"3"}\hlstd{),} \hlkwc{pch}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{1}\hlstd{,}\hlnum{20}\hlstd{,}\hlnum{4}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/dotbats-1}
\end{knitrout}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tmp}\hlkwb{<-}\hlstd{maic[maic}\hlopt{$}\hlstd{nprimates}\hlopt{>=}\hlnum{3}\hlstd{,} \hlkwd{c}\hlstd{(}\hlstr{"gene"}\hlstd{,} \hlstr{"rank"}\hlstd{,} \hlstr{"nprimates"}\hlstd{)]}
\hlstd{tmp}\hlkwb{<-}\hlstd{tmp[}\hlkwd{order}\hlstd{(tmp}\hlopt{$}\hlstd{rank,} \hlkwc{decreasing} \hlstd{=} \hlnum{TRUE}\hlstd{),]}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{5}\hlstd{]}\hlkwb{<-}\hlnum{1}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{4}\hlstd{]}\hlkwb{<-}\hlnum{20}
\hlstd{tmp}\hlopt{$}\hlstd{pch[tmp}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{3}\hlstd{]}\hlkwb{<-}\hlnum{4}
\hlstd{tmp}\hlopt{$}\hlstd{col}\hlkwb{<-}\hlstr{"black"}
\hlstd{tmp}\hlopt{$}\hlstd{col[tmp}\hlopt{$}\hlstd{gene}\hlopt{==}\hlstr{"ACE2"}\hlstd{]}\hlkwb{<-}\hlstr{"red"}
\hlstd{tmp}\hlopt{$}\hlstd{col[tmp}\hlopt{$}\hlstd{gene}\hlopt{==}\hlstr{"TMPRSS2"}\hlstd{]}\hlkwb{<-}\hlstr{"red"}
\hlkwd{dotchart}\hlstd{(tmp}\hlopt{$}\hlstd{rank,} \hlkwc{main}\hlstd{=}\hlstr{"Primates DGINN >=3"}\hlstd{,} \hlkwc{xlab}\hlstd{=}\hlstr{"rank MAIC"}\hlstd{,} \hlkwc{labels}\hlstd{=tmp}\hlopt{$}\hlstd{gene,} \hlkwc{pch}\hlstd{=tmp}\hlopt{$}\hlstd{pch,} \hlkwc{cex}\hlstd{=}\hlnum{0.8}\hlstd{,} \hlkwc{col}\hlstd{=tmp}\hlopt{$}\hlstd{col)}
\hlkwd{legend}\hlstd{(}\hlstr{"topright"}\hlstd{,} \hlkwd{c}\hlstd{(}\hlstr{"5 (score DGINN)"}\hlstd{,} \hlstr{"4"}\hlstd{,} \hlstr{"3"}\hlstd{),} \hlkwc{pch}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{1}\hlstd{,}\hlnum{20}\hlstd{,}\hlnum{4}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/dotprimates-1}
\end{knitrout}
\section{Pan Corona}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{pancorona}\hlkwb{<-}\hlkwd{read.table}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,} \hlstr{"data/pancorona_S5.csv"}\hlstd{),}
\hlkwc{h}\hlstd{=T,} \hlkwc{fill} \hlstd{=} \hlnum{TRUE}\hlstd{,} \hlkwc{sep}\hlstd{=}\hlstr{"\textbackslash{}t"}\hlstd{)}
\hlkwd{names}\hlstd{(pancorona)}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"tmp.Gene.name"}\hlstd{,} \hlkwd{names}\hlstd{(pancorona)[}\hlopt{-}\hlnum{1}\hlstd{])}
\hlcom{# Genes en commun}
\hlstd{pancorona}\hlopt{$}\hlstd{tmp.Gene.name[pancorona}\hlopt{$}\hlstd{tmp.Gene.name} \hlopt{%in%} \hlstd{tablo}\hlopt{$}\hlstd{tmp.Gene.name]}
\end{alltt}
\begin{verbatim}
## [1] TBK1 MARK3 GIGYF2 MARK2 G3BP1 LARP1 ACE2 PABPC1
## [9] TMPRSS2 AP3B1 CLCC1 CSDE1 HECTD1 MARK1 MEPCE PDE4DIP
## [17] POR PRKAR2B RAB5C RTN4 SRP54 UBAP2 UBAP2L UBXN8
## [25] SPART BZW2 EIF4E2 SMOC1 STOML2 DDX21 FAM98A G3BP2
## [33] MOV10 PABPC4 UPF1
## 105 Levels: ACE2 ANPEP AP3B1 ATXN2L BTF3 BZW2 CKAP5 CLCC1 ... YTHDF2
\end{verbatim}
\begin{alltt}
\hlcom{# Uniquement dans le tableau pancorona}
\hlkwd{sort}\hlstd{(pancorona}\hlopt{$}\hlstd{tmp.Gene.name[(pancorona}\hlopt{$}\hlstd{tmp.Gene.name} \hlopt{%in%} \hlstd{tablo}\hlopt{$}\hlstd{tmp.Gene.name)}\hlopt{==}\hlnum{FALSE}\hlstd{])}
\end{alltt}
\begin{verbatim}
## [1] ANPEP ATXN2L BTF3 CKAP5 CTSB CTSL
## [7] CYB5R3 DDX1 DDX5 DDX58 DHX9 DNM1L
## [13] EEF1A1 EIF2A EIF3F EIF4B EZR FLNA
## [19] FURIN FUS GSK3A GSK3B HDLBP HNRNPA1
## [25] HNRNPD HNRNPF HNRNPU IFIH1 IGF2BP1 IKBKB
## [31] IKBKE IRF3 ISG15 KPNA3 KPNB1 MYH9
## [37] NCL POLD1 POLR2B PRKRA RBM14 RCHY1
## [43] RPL13A RPL26 RPS13 RPS17 RPS19 RPS9
## [49] SDCBP SERBP1 SGTA SLC1A5 SNAP47 SSB
## [55] STING1 SYNCRIP TANC1 TBCB TMPRSS11D TRAF3
## [61] TUBA4A TUBB2A TUBB4A TUBB6 USP10 VPS36
## [67] XRCC5 XRCC6 YBX1 YTHDF2
## 105 Levels: ACE2 ANPEP AP3B1 ATXN2L BTF3 BZW2 CKAP5 CLCC1 ... YTHDF2
\end{verbatim}
\begin{alltt}
\hlcom{## Uniquement dans tableau }
\hlkwd{sort}\hlstd{(tablo}\hlopt{$}\hlstd{tmp.Gene.name[(tablo}\hlopt{$}\hlstd{tmp.Gene.name} \hlopt{%in%} \hlstd{pancorona}\hlopt{$}\hlstd{tmp.Gene.name)}\hlopt{==}\hlnum{FALSE}\hlstd{])}
\end{alltt}
\begin{verbatim}
## [1] AAR2 AASS AATF ABCC1 ACAD9 ACADM
## [7] ACSL3 ADAM9 ADAMTS1 AGPS AKAP8 AKAP8L
## [13] AKAP9 ALG11 ALG5 ALG8 ANO6 AP2A2
## [19] AP2M1 ARF6 ATE1 ATP13A3 ATP1B1 ATP6AP1
## [25] ATP6V1A BAG5 BCKDK BRD2 BRD4 CCDC86
## [31] CDK5RAP2 CENPF CEP112 CEP135 CEP250 CEP350
## [37] CEP68 CHMP2A CHPF CHPF2 CISD3 CIT
## [43] CLIP4 CNTRL COL6A1 COLGALT1 COMT COQ8B
## [49] CRTC3 CSNK2A2 CSNK2B CUL2 CWC27 CYB5B
## [55] DCAF7 DCAKD DCTPP1 DDX10 DNAJC11 DNAJC19
## [61] DNMT1 DPH5 DPY19L1 ECSIT EDEM3 EIF4H
## [67] ELOC EMC1 ERC1 ERGIC1 ERLEC1 ERMP1
## [73] ERO1B ERP44 ETFA EXOSC2 EXOSC3 EXOSC5
## [79] EXOSC8 F2RL1 FAM162A FAM8A1 FAR2 FASTKD5
## [85] FBLN5 FBN1 FBN2 FBXL12 FKBP10 FKBP15
## [91] FKBP7 FOXRED2 FYCO1 GCC1 GCC2 GDF15
## [97] GFER GGCX GGH GHITM GLA GNB1
## [103] GNG5 GOLGA2 GOLGA3 GOLGA7 GOLGB1 GORASP1
## [109] GPAA1 GPX1 GRIPAP1 GRPEL1 GTF2F2 HDAC2
## [115] HEATR3 HMOX1 HOOK1 HS2ST1 HS6ST2 HSBP1
## [121] HYOU1 IDE IL17RA IMPDH2 INHBE INTS4
## [127] ITGB1 JAKMIP1 KDELC1 KDELC2 LARP4B LARP7
## [133] LMAN2 LOX MAP7D1 MARC1 MAT2B MDN1
## [139] MIB1 MIPOL1 MOGS MPHOSPH10 MRPS2 MRPS25
## [145] MRPS27 MRPS5 MTCH1 MYCBP2 NARS2 NAT14
## [151] NDFIP2 NDUFAF1 NDUFAF2 NDUFB9 NEK9 NEU1
## [157] NGDN NGLY1 NIN NINL NLRX1 NOL10
## [163] NPC2 NPTX1 NSD2 NUP210 NUP214 NUP54
## [169] NUP58 NUP62 NUP88 NUP98 NUTF2 OS9
## [175] PCNT PCSK5 PCSK6 PDZD11 PIGO PIGS
## [181] PITRM1 PKP2 PLAT PLD3 PLEKHA5 PLEKHF2
## [187] PLOD2 PMPCA PMPCB POFUT1 POLA1 POLA2
## [193] PPIL3 PPT1 PRIM1 PRIM2 PRKACA PRKAR2A
## [199] PRRC2B PSMD8 PTBP2 PTGES2 PUSL1 PVR
## [205] QSOX2 RAB10 RAB14 RAB18 RAB1A RAB2A
## [211] RAB7A RAB8A RAE1 RALA RAP1GDS1 RBM28
## [217] RBM41 RBX1 RDX REEP5 REEP6 RETREG3
## [223] RHOA RIPK1 RNF41 RPL36 RRP9 SAAL1
## [229] SBNO1 SCAP SCARB1 SCCPDH SDF2 SELENOS
## [235] SEPSECS SIL1 SIRT5 SLC25A21 SLC27A2 SLC30A6
## [241] SLC30A7 SLC30A9 SLC44A2 SLC9A3R1 SLU7 SNIP1
## [247] SRP19 SRP72 STC2 STOM SUN2 TAPT1
## [253] TARS2 TBCA TBKBP1 TCF12 THTPA TIMM10
## [259] TIMM10B TIMM29 TIMM8B TIMM9 TLE1 TLE3
## [265] TM2D3 TMED5 TMEM39B TMEM97 TOMM70 TOR1A
## [271] TOR1AIP1 TRIM59 TRMT1 TUBGCP2 TUBGCP3 TYSND1
## [277] UGGT2 USP54 VPS11 VPS39 WASHC4 WFS1
## [283] YIF1A ZC3H18 ZC3H7A ZDHHC5 ZNF318 ZNF503
## [289] ZYG11B
## 324 Levels: AAR2 AASS AATF ABCC1 ACAD9 ACADM ACE2 ACSL3 ... ZYG11B
\end{verbatim}
\end{kframe}
\end{knitrout}
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{pancorona}\hlkwb{<-}\hlstd{pancorona[,}\hlkwd{c}\hlstd{(}\hlstr{"tmp.Gene.name"}\hlstd{,} \hlstr{"TOTAL"}\hlstd{)]}
\hlstd{pandginn}\hlkwb{<-}\hlkwd{na.omit}\hlstd{(}\hlkwd{merge}\hlstd{(pancorona, tablo,} \hlkwc{by}\hlstd{=}\hlstr{"tmp.Gene.name"}\hlstd{,} \hlkwc{all.x}\hlstd{=}\hlnum{TRUE}\hlstd{))}
\hlstd{pandginn}\hlkwb{<-}\hlstd{pandginn[}\hlkwd{order}\hlstd{(pandginn}\hlopt{$}\hlstd{nprimates),]}
\hlstd{pandginn}\hlkwb{<-}\hlstd{pandginn[}\hlkwd{order}\hlstd{(pandginn}\hlopt{$}\hlstd{TOTAL),]}
\hlkwd{dotchart}\hlstd{(}\hlkwd{as.matrix}\hlstd{(pandginn[,}\hlnum{2}\hlstd{]),} \hlkwc{labels} \hlstd{= pandginn}\hlopt{$}\hlstd{tmp.Gene.name,} \hlkwc{xlim}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{0}\hlstd{,}\hlnum{5}\hlstd{))}
\hlkwd{points}\hlstd{(pandginn[,}\hlnum{4}\hlstd{],} \hlnum{1}\hlopt{:}\hlkwd{nrow}\hlstd{(pandginn),} \hlkwc{col}\hlstd{=}\hlstr{"blue"}\hlstd{,} \hlkwc{pch}\hlstd{=}\hlnum{20}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.7}\hlstd{)}
\hlkwd{points}\hlstd{(pandginn[,}\hlnum{3}\hlstd{],} \hlnum{1}\hlopt{:}\hlkwd{nrow}\hlstd{(pandginn),} \hlkwc{col}\hlstd{=}\hlstr{"blue"}\hlstd{,} \hlkwc{pch}\hlstd{=}\hlnum{4}\hlstd{)}
\hlkwd{legend}\hlstd{(}\hlstr{"bottomright"}\hlstd{,} \hlkwd{c}\hlstd{(}\hlstr{"pancorona score"}\hlstd{,} \hlstr{"dginn primate score"}\hlstd{,} \hlstr{"dginn bats score"}\hlstd{),} \hlkwc{pch}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{1}\hlstd{,}\hlnum{20}\hlstd{,}\hlnum{4}\hlstd{),} \hlkwc{col}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"black"}\hlstd{,} \hlstr{"blue"}\hlstd{,} \hlstr{"blue"}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/pancorona-1}
\end{knitrout}
\end{document}
covid_comp_primate-Young-focus.Rnw
View file @ 77f559a1
......@@ -15,7 +15,7 @@
\title{Positive selection on genes interacting with SARS-Cov2, comparison of different analysis}
\author{Marie Cariou}
\date{February 2021} % Activate to display a given date or no date
\date{March 2021} % Activate to display a given date or no date
\begin{document}
\maketitle
......@@ -29,7 +29,8 @@
\subsection{Complete table}
<<>>=
workdir<-"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"
home<-"/home/adminmarie/Documents/"
workdir<-paste0(home, "CIRI_BIBS_projects/2020_05_Etienne_covid/")
tab<-read.delim(paste0(workdir,
"covid_comp/covid_comp_complete.txt"), h=T, sep="\t")
......@@ -89,48 +90,18 @@ names(tmp)<-c("Gene.name", "NbSites_MEME", "PSS_MEME")
tab<-merge(tab, tmp, by="Gene.name")
dim(tab)
@
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\section{Comparisons Primates}
\subsection{DGINN results on Janet Young's alignments (DGINN-Young-primate) VS Janet Young's results}
Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" dans la sortie de dginn.
<<omegaM7M8>>=
tab$whole.gene.dN.dS.model.0<-as.numeric(as.character(tab$whole.gene.dN.dS.model.0))
tab$whole.gene.dN.dS.model.0<-as.numeric(
as.character(tab$whole.gene.dN.dS.model.0))
plot(tab$whole.gene.dN.dS.model.0, tab$Omega_PamlM7M8,
xlab="Omega Young-primate", ylab="Omega DGINN-Young-primate")
abline(0,1)
......@@ -143,16 +114,16 @@ outlier<-tab[tab$whole.gene.dN.dS.model.0<0.6 & tab$Omega_PamlM7M8>0.7,]
text(x=outlier$whole.gene.dN.dS.model.0,
y=(outlier$Omega_PamlM7M8+0.01),
outlier$Gene.name)
@
\subsection{DGINN results on Janet Young's alignments (DGINN-Young-primate) VS DGINN-full's results}
Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" dans la sortie de dginn.
<<omegaM7M8_2>>=
tab$'dginn.primate_omegaM0Bpp'<-as.numeric(as.character(tab$'dginn.primate_omegaM0Bpp'))
tab$'dginn.primate_omegaM0Bpp'<-as.numeric(
as.character(tab$'dginn.primate_omegaM0Bpp'))
plot(tab$'dginn.primate_omegaM0Bpp', tab$Omega_PamlM7M8,
xlab="DGINN-full's", ylab="Omega DGINN-Young-primate")
abline(0,1)
......@@ -173,72 +144,72 @@ y=(outlier$Omega_PamlM7M8+0.01),
outlier$Gene.name)
@
\subsection{Janet Young's results (Young-primate) VS DGINN-full's results}
Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" dans la sortie de dginn.
<<omegaM7M8_3>>=
plot(tab$whole.gene.dN.dS.model.0, as.numeric(as.character(tab$'dginn.primate_omegaM0Bpp')),
plot(tab$whole.gene.dN.dS.model.0,
as.numeric(as.character(tab$'dginn.primate_omegaM0Bpp')),
xlab="Omega Young-primate", ylab="DGINN-full's")
abline(0,1)
outlier<-tab[tab$whole.gene.dN.dS.model.0<0.4 & as.numeric(as.character(tab$'dginn.primate_omegaM0Bpp'))>0.5,]
outlier<-tab[tab$whole.gene.dN.dS.model.0<0.4 &
as.numeric(as.character(tab$'dginn.primate_omegaM0Bpp'))>0.5,]
text(x=outlier$whole.gene.dN.dS.model.0,
y=outlier$'dginn.primate_omegaM0Bpp',
outlier$Gene.name)
outlier<-tab[tab$whole.gene.dN.dS.model.0>0.7 & as.numeric(as.character(tab$'dginn.primate_omegaM0Bpp'))>0,]
outlier<-tab[tab$whole.gene.dN.dS.model.0>0.7 &
as.numeric(as.character(tab$'dginn.primate_omegaM0Bpp'))>0,]
text(x=outlier$whole.gene.dN.dS.model.0,
y=outlier$'dginn.primate_omegaM0Bpp',
outlier$Gene.name)
outlier<-tab[tab$whole.gene.dN.dS.model.0<0.1 & as.numeric(as.character(tab$'dginn.primate_omegaM0Bpp'))>0.3,]
outlier<-tab[tab$whole.gene.dN.dS.model.0<0.1 &
as.numeric(as.character(tab$'dginn.primate_omegaM0Bpp'))>0.3,]
text(x=outlier$whole.gene.dN.dS.model.0+0.03,
y=outlier$'dginn.primate_omegaM0Bpp',
outlier$Gene.name)
@
\section{Overlap}
\subsection{Mondrian}
<<mondrianprimates>>=
library(Mondrian)
monddata<-as.data.frame(tab$Gene.name)
dim(monddata)
dginnyoungtmp<-rowSums(cbind(tab$PosSel_PamlM1M2=="Y", tab$PosSel_PamlM7M8=="Y",
tab$PosSel_BppM1M2=="Y", tab$PosSel_BppM7M8=="Y", tab$PosSel_BUSTED=="Y"))
#monddata$primates_dginn_young<-ifelse(tmp$PosSel_PamlM7M8=="Y", 1,0)
dginnfulltmp<-rowSums(cbind(tab$'dginn.primate_BUSTED'=="Y", tab$'dginn.primate_BppM1M2'=="Y",
tab$'dginn.primate_BppM7M8'=="Y", tab$'dginn.primate_codemlM1M2'=="Y", tab$'dginn.primate_codemlM7M8'=="Y"))
dginnyoungtmp<-rowSums(cbind(tab$PosSel_PamlM1M2=="Y",
tab$PosSel_PamlM7M8=="Y",
tab$PosSel_BppM1M2=="Y",
tab$PosSel_BppM7M8=="Y",
tab$PosSel_BUSTED=="Y"))
dginnfulltmp<-rowSums(cbind(tab$'dginn.primate_BUSTED'=="Y",
tab$'dginn.primate_BppM1M2'=="Y",
tab$'dginn.primate_BppM7M8'=="Y",
tab$'dginn.primate_codemlM1M2'=="Y",
tab$'dginn.primate_codemlM7M8'=="Y"))
monddata$primates_young<-ifelse(tab$pVal.M8vsM7<0.05, 1, 0)
#monddata$primates_cooper<-ifelse(tab$cooper.primates.M7.M8_p_val<0.05, 1, 0)
monddata$primates_dginn_young<-ifelse(dginnyoungtmp>=3, 1,0)
monddata$primates_dginn_full<-ifelse(dginnfulltmp>=3, 1,0)
mondrian(na.omit(monddata[,2:4]), labels=c("Young", "DGINN-Young >=3", "DGINN-full >=3" ))
mondrian(na.omit(monddata[,2:4]),
labels=c("Young", "DGINN-Young >=3", "DGINN-full >=3" ))
#####
monddata$primates_dginn_young<-ifelse(dginnyoungtmp>=4, 1,0)
monddata$primates_dginn_full<-ifelse(dginnfulltmp>=4, 1,0)
mondrian(na.omit(monddata[,2:4]), labels=c("Young", "DGINN-Young >=4", "DGINN-full >=4"))
mondrian(na.omit(monddata[,2:4]),
labels=c("Young", "DGINN-Young >=4", "DGINN-full >=4"))
@
Comparison of results with the same method.
......@@ -246,7 +217,9 @@ Comparison of results with the same method.
monddata$primates_dginn_young<-tab$PosSel_BppM7M8=="Y"
monddata$primates_dginn_full<-tab$'dginn.primate_codemlM7M8'=="Y"
mondrian(na.omit(monddata[,2:4]), labels=c("Young", "DGINN-Young", "DGINN-full"), main="posel codeml M7M8")
mondrian(na.omit(monddata[,2:4]),
labels=c("Young", "DGINN-Young", "DGINN-full"),
main="posel codeml M7M8")
@
\subsection{subsetR}
......
covid_comp_primate-Young-focus.pdf
View file @ 77f559a1
No preview for this file type
covid_comp_primate-Young-focus.tex
View file @ 77f559a1
......@@ -65,7 +65,7 @@
\title{Positive selection on genes interacting with SARS-Cov2, comparison of different analysis}
\author{Marie Cariou}
\date{February 2021} % Activate to display a given date or no date
\date{March 2021} % Activate to display a given date or no date
\IfFileExists{upquote.sty}{\usepackage{upquote}}{}
\begin{document}
\maketitle
......@@ -81,7 +81,8 @@
\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{home}\hlkwb{<-}\hlstr{"/home/adminmarie/Documents/"}
\hlstd{workdir}\hlkwb{<-}\hlkwd{paste0}\hlstd{(home,} \hlstr{"CIRI_BIBS_projects/2020_05_Etienne_covid/"}\hlstd{)}
\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{)}
......@@ -168,46 +169,17 @@ I will merge the 2 tables.
\end{knitrout}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\section{Comparisons Primates}
\subsection{DGINN results on Janet Young's alignments (DGINN-Young-primate) VS Janet Young's results}
Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" dans la sortie de dginn.
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0))}
\hlstd{tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}
\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0))}
\hlkwd{plot}\hlstd{(tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0, tab}\hlopt{$}\hlstd{Omega_PamlM7M8,}
\hlkwc{xlab}\hlstd{=}\hlstr{"Omega Young-primate"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"Omega DGINN-Young-primate"}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlnum{0}\hlstd{,}\hlnum{1}\hlstd{)}
......@@ -228,12 +200,13 @@ Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" d
\subsection{DGINN results on Janet Young's alignments (DGINN-Young-primate) VS DGINN-full's results}
Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" dans la sortie de dginn.
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlstd{tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{))}
\hlstd{tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}
\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{))}
\end{alltt}
......@@ -262,30 +235,33 @@ Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" d
\end{knitrout}
\subsection{Janet Young's results (Young-primate) VS DGINN-full's results}
Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" dans la sortie de dginn.
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{plot}\hlstd{(tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,} \hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{)),}
\hlkwd{plot}\hlstd{(tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{)),}
\hlkwc{xlab}\hlstd{=}\hlstr{"Omega Young-primate"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"DGINN-full's"}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlnum{0}\hlstd{,}\hlnum{1}\hlstd{)}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{<}\hlnum{0.4} \hlopt{&} \hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{))}\hlopt{>}\hlnum{0.5}\hlstd{,]}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{<}\hlnum{0.4} \hlopt{&}
\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{))}\hlopt{>}\hlnum{0.5}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name)}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{>}\hlnum{0.7} \hlopt{&} \hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{))}\hlopt{>}\hlnum{0}\hlstd{,]}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{>}\hlnum{0.7} \hlopt{&}
\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{))}\hlopt{>}\hlnum{0}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name)}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{<}\hlnum{0.1} \hlopt{&} \hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{))}\hlopt{>}\hlnum{0.3}\hlstd{,]}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{<}\hlnum{0.1} \hlopt{&}
\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{))}\hlopt{>}\hlnum{0.3}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{+}\hlnum{0.03}\hlstd{,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstr{'dginn.primate_omegaM0Bpp'}\hlstd{,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name)}
......@@ -295,10 +271,8 @@ Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" d
\end{knitrout}
\section{Overlap}
\subsection{Mondrian}
\begin{knitrout}
......@@ -313,33 +287,34 @@ Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" d
## [1] 332 1
\end{verbatim}
\begin{alltt}
\hlstd{dginnyoungtmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tab}\hlopt{$}\hlstd{PosSel_PamlM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{, tab}\hlopt{$}\hlstd{PosSel_PamlM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstd{PosSel_BppM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{, tab}\hlopt{$}\hlstd{PosSel_BppM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{, tab}\hlopt{$}\hlstd{PosSel_BUSTED}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlcom{#monddata$primates_dginn_young<-ifelse(tmp$PosSel_PamlM7M8=="Y", 1,0)}
\hlstd{dginnfulltmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_BUSTED'}\hlopt{==}\hlstr{"Y"}\hlstd{, tab}\hlopt{$}\hlstr{'dginn.primate_BppM1M2'}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstr{'dginn.primate_BppM7M8'}\hlopt{==}\hlstr{"Y"}\hlstd{, tab}\hlopt{$}\hlstr{'dginn.primate_codemlM1M2'}\hlopt{==}\hlstr{"Y"}\hlstd{, tab}\hlopt{$}\hlstr{'dginn.primate_codemlM7M8'}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlstd{dginnyoungtmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tab}\hlopt{$}\hlstd{PosSel_PamlM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstd{PosSel_PamlM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstd{PosSel_BppM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstd{PosSel_BppM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstd{PosSel_BUSTED}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlstd{dginnfulltmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tab}\hlopt{$}\hlstr{'dginn.primate_BUSTED'}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstr{'dginn.primate_BppM1M2'}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstr{'dginn.primate_BppM7M8'}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstr{'dginn.primate_codemlM1M2'}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstr{'dginn.primate_codemlM7M8'}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlstd{monddata}\hlopt{$}\hlstd{primates_young}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(tab}\hlopt{$}\hlstd{pVal.M8vsM7}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlcom{#monddata$primates_cooper<-ifelse(tab$cooper.primates.M7.M8_p_val<0.05, 1, 0)}
\hlstd{monddata}\hlopt{$}\hlstd{primates_dginn_young}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginnyoungtmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{primates_dginn_full}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginnfulltmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlkwd{mondrian}\hlstd{(}\hlkwd{na.omit}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{]),} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"Young"}\hlstd{,} \hlstr{"DGINN-Young >=3"}\hlstd{,} \hlstr{"DGINN-full >=3"} \hlstd{))}
\hlkwd{mondrian}\hlstd{(}\hlkwd{na.omit}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{]),}
\hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"Young"}\hlstd{,} \hlstr{"DGINN-Young >=3"}\hlstd{,} \hlstr{"DGINN-full >=3"} \hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/mondrianprimates-1}
\begin{kframe}\begin{alltt}
\hlcom{#####}
\hlstd{monddata}\hlopt{$}\hlstd{primates_dginn_young}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginnyoungtmp}\hlopt{>=}\hlnum{4}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{primates_dginn_full}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginnfulltmp}\hlopt{>=}\hlnum{4}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlkwd{mondrian}\hlstd{(}\hlkwd{na.omit}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{]),} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"Young"}\hlstd{,} \hlstr{"DGINN-Young >=4"}\hlstd{,} \hlstr{"DGINN-full >=4"}\hlstd{))}
\hlkwd{mondrian}\hlstd{(}\hlkwd{na.omit}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{]),}
\hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"Young"}\hlstd{,} \hlstr{"DGINN-Young >=4"}\hlstd{,} \hlstr{"DGINN-full >=4"}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/mondrianprimates-2}
......@@ -353,7 +328,9 @@ Comparison of results with the same method.
\hlstd{monddata}\hlopt{$}\hlstd{primates_dginn_young}\hlkwb{<-}\hlstd{tab}\hlopt{$}\hlstd{PosSel_BppM7M8}\hlopt{==}\hlstr{"Y"}
\hlstd{monddata}\hlopt{$}\hlstd{primates_dginn_full}\hlkwb{<-}\hlstd{tab}\hlopt{$}\hlstr{'dginn.primate_codemlM7M8'}\hlopt{==}\hlstr{"Y"}
\hlkwd{mondrian}\hlstd{(}\hlkwd{na.omit}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{]),} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"Young"}\hlstd{,} \hlstr{"DGINN-Young"}\hlstd{,} \hlstr{"DGINN-full"}\hlstd{),} \hlkwc{main}\hlstd{=}\hlstr{"posel codeml M7M8"}\hlstd{)}
\hlkwd{mondrian}\hlstd{(}\hlkwd{na.omit}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{]),}
\hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"Young"}\hlstd{,} \hlstr{"DGINN-Young"}\hlstd{,} \hlstr{"DGINN-full"}\hlstd{),}
\hlkwc{main}\hlstd{=}\hlstr{"posel codeml M7M8"}\hlstd{)}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/unnamed-chunk-4-1}
......@@ -500,7 +477,7 @@ List of the 44 genes found under positive selection ONLY in full-DGINN.
## [29] MYCBP2 NAT14 NGLY1 NPC2 NUPL1 PITRM1 PLOD2
## [36] PMPCB POR PRKAR2A PTBP2 RAB14 RAB1A RAB2A
## [43] RAP1GDS1 RBX1 REEP6 RPL36 SCCPDH <NA> <NA>
## [50] TIMM8B TRIM59 TUBGCP2 <NA> <NA>
## [50] TIMM8B TRIM59 TUBGCP2 <NA>
## 332 Levels: AAR2 AASS AATF ABCC1 ACAD9 ACADM ACSL3 ADAM9 ... ZYG11B
\end{verbatim}
\end{kframe}
......
covid_comp_primate.Rnw
View file @ 77f559a1
......@@ -30,108 +30,166 @@
Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
<<>>=
workdir<-"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"
home<-"/home/adminmarie/Documents/"
workdir<-paste0(home, "CIRI_BIBS_projects/2020_05_Etienne_covid/")
tab<-read.delim(paste0(workdir,
"covid_comp/covid_comp_complete.txt"), h=T, sep="\t")
dim(tab)
tab$Gene.name<-as.character(tab$Gene.name)
tab$Gene.name<-as.character(tab$Gene.name.x)
tab$Gene.name[tab$PreyGene=="MTARC1"]<-"MTARC1"
@
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\section{Comparisons Primates}
\subsection{Janet Young's results (Young-primate) VS DGINN-full's results}
Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" dans la sortie de dginn.
<<omegaM7M8_1>>=
plot(tab$whole.gene.dN.dS.model.0, as.numeric(as.character(tab$dginn.primate_omegaM0Bpp)),
xlab="Omega Young-primate", ylab="DGINN-full's")
<<omegaM7M8_1>>=
tab$dginn.primate_omegaM0Bpp[tab$dginn.primate_omegaM0Bpp=="na"]<-NA
tab$dginn.primate_omegaM0Bpp<-as.numeric(as.character(
tab$dginn.primate_omegaM0Bpp))
plot(tab$whole.gene.dN.dS.model.0,
tab$dginn.primate_omegaM0Bpp,
xlab="Omega Young-primate",
ylab="DGINN-full's",
cex=0.3)
abline(0,1)
abline(lm(as.numeric(as.character(tab$dginn.primate_omegaM0Bpp))~tab$whole.gene.dN.dS.model.0), col="red")
abline(lm(tab$dginn.primate_omegaM0Bpp~tab$whole.gene.dN.dS.model.0),
col="red")
outlier<-tab[tab$whole.gene.dN.dS.model.0<0.4 & tab$dginn.primate_omegaM0Bpp>0.5,]
outlier<-tab[tab$whole.gene.dN.dS.model.0<0.4 &
tab$dginn.primate_omegaM0Bpp>0.5,]
text(x=outlier$whole.gene.dN.dS.model.0,
y=outlier$dginn.primate_omegaM0Bpp,
outlier$Gene.name)
outlier<-tab[tab$whole.gene.dN.dS.model.0<0.1 &
tab$dginn.primate_omegaM0Bpp>0.3,]
text(x=outlier$whole.gene.dN.dS.model.0,
y=outlier$dginn.primate_omegaM0Bpp,
outlier$Gene.name)
outlier<-tab[tab$whole.gene.dN.dS.model.0>0.33 &
tab$dginn.primate_omegaM0Bpp<0.2,]
text(x=outlier$whole.gene.dN.dS.model.0,
y=outlier$dginn.primate_omegaM0Bpp,
outlier$Gene.name)
outlier<-tab[tab$whole.gene.dN.dS.model.0>0.6 &
tab$dginn.primate_omegaM0Bpp<0.6,]
text(x=outlier$whole.gene.dN.dS.model.0,
y=outlier$dginn.primate_omegaM0Bpp,
outlier$Gene.name)
@
\subsection{Janet Young's results (Young-primate) VS Cooper's result}
Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "cooper.primates.Average\_dNdS".
<<omegaM7M8_2>>=
plot(tab$whole.gene.dN.dS.model.0, as.numeric(as.character(tab$cooper.primates.Average_dNdS)),
xlab="Omega Young-primate", ylab="Omega Cooper-primate")
<<omegaM7M8_2>>=
tab$cooper.primates.Average_dNdS<-as.numeric(as.character(
tab$cooper.primates.Average_dNdS))
plot(tab$whole.gene.dN.dS.model.0,
tab$cooper.primates.Average_dNdS,
xlab="Omega Young-primate",
ylab="Omega Cooper-primate",
cex=0.3)
abline(0,1)
abline(lm(as.numeric(as.character(tab$cooper.primates.Average_dNdS))~tab$whole.gene.dN.dS.model.0), col="red")
abline(lm(tab$cooper.primates.Average_dNdS~tab$whole.gene.dN.dS.model.0),
col="red")
outlier<-tab[tab$whole.gene.dN.dS.model.0<0.15 &
tab$cooper.primates.Average_dNdS>0.4,]
text(x=outlier$whole.gene.dN.dS.model.0,
y=outlier$cooper.primates.Average_dNdS,
outlier$Gene.name, cex=0.5)
outlier<-tab[tab$whole.gene.dN.dS.model.0<0.4 & tab$cooper.primates.Average_dNdS>0.5,]
outlier<-tab[tab$whole.gene.dN.dS.model.0<0.3 &
tab$cooper.primates.Average_dNdS>0.5,]
text(x=outlier$whole.gene.dN.dS.model.0,
y=outlier$cooper.primates.Average_dNdS,
outlier$Gene.name)
outlier$Gene.name, cex=0.5)
outlier<-tab[tab$whole.gene.dN.dS.model.0>0.3 &
tab$cooper.primates.Average_dNdS<0.1,]
text(x=outlier$whole.gene.dN.dS.model.0,
y=outlier$cooper.primates.Average_dNdS,
outlier$Gene.name, cex=0.5)
@
\subsection{Cooper's results (Cooper-primate) VS DGINN-full's results}
Comparaison des Omega: colonne "cooper.primates.Average\_dNdS" VS colonne "omega" dans la sortie de dginn.
<<omegaM7M8_3>>=
plot(tab$cooper.primates.Average_dNd, as.numeric(as.character(tab$dginn.primate_omegaM0Bpp)),
xlab="Omega Cooper-primate", ylab="DGINN-full's")
<<omegaM7M8_3>>=
plot(tab$cooper.primates.Average_dNd,
tab$dginn.primate_omegaM0Bpp,
xlab="Omega Cooper-primate",
ylab="DGINN-full's",
cex=0.3)
abline(0,1)
abline(lm(as.numeric(as.character(tab$dginn.primate_omegaM0Bpp))~tab$cooper.primates.Average_dNd), col="red")
abline(lm(tab$dginn.primate_omegaM0Bpp~tab$cooper.primates.Average_dNd), col="red")
outlier<-tab[tab$cooper.primates.Average_dNd<0.4 & tab$dginn.primate_omegaM0Bpp>0.5,]
outlier<-tab[tab$cooper.primates.Average_dNd<0.4 &
tab$dginn.primate_omegaM0Bpp>0.5,]
text(x=outlier$cooper.primates.Average_dNd,
y=outlier$dginn.primate_omegaM0Bpp,
outlier$Gene.name)
@
outlier$Gene.name, cex=0.5)
outlier<-tab[tab$cooper.primates.Average_dNd<0.1 &
tab$dginn.primate_omegaM0Bpp>0.3,]
text(x=outlier$cooper.primates.Average_dNd,
y=outlier$dginn.primate_omegaM0Bpp,
outlier$Gene.name, cex=0.5)
outlier<-tab[tab$cooper.primates.Average_dNd>0.7 &
tab$dginn.primate_omegaM0Bpp<0.3,]
text(x=outlier$cooper.primates.Average_dNd,
y=outlier$dginn.primate_omegaM0Bpp,
outlier$Gene.name, cex=0.5)
outlier<-tab[tab$cooper.primates.Average_dNd>0.45 &
tab$dginn.primate_omegaM0Bpp<0.2,]
text(x=outlier$cooper.primates.Average_dNd,
y=outlier$dginn.primate_omegaM0Bpp,
outlier$Gene.name, cex=0.5)
@
\section{Overlap}
\subsection{Mondrian}
<<mondrianprimates>>=
library(Mondrian)
#######
monddata<-as.data.frame(tab$Gene.name)
dim(monddata)
dginnfulltmp<-rowSums(cbind(tab$dginn.primate_BUSTED=="Y",
tab$dginn.primate_BppM1M2=="Y",
tab$dginn.primate_BppM7M8=="Y",
tab$dginn.primate_codemlM1M2=="Y",
tab$dginn.primate_codemlM7M8=="Y"))
dginnfulltmp<-rowSums(cbind(tab$dginn.primate_BUSTED=="Y", tab$dginn.primate_BppM1M2=="Y",
tab$dginn.primate_BppM7M8=="Y", tab$dginn.primate_codemlM1M2=="Y", tab$dginn.primate_codemlM7M8=="Y"))
monddata$primates_young<-ifelse(tab$pVal.M8vsM7<0.05, 1, 0)
monddata$primate_cooper<-ifelse(tab$cooper.primates.M7.M8_p_value<0.05, 1, 0)
monddata$primates_dginn_full<-ifelse(dginnfulltmp>=3, 1,0)
monddata$primates_young<-ifelse(
tab$pVal.M8vsM7<0.05, 1, 0)
monddata$primate_cooper<-ifelse(
tab$cooper.primates.M7.M8_p_value<0.05, 1, 0)
monddata$primates_dginn_full<-ifelse(
dginnfulltmp>=3, 1,0)
mondrian(na.omit(monddata[,2:4]), labels=c("Young", "Cooper", "DGINN-full >=3" ))
mondrian(na.omit(monddata[,2:4]),
labels=c("Young", "Cooper", "DGINN-full >=3" ))
#####
monddata$primates_dginn_full<-ifelse(dginnfulltmp>=4, 1,0)
monddata$primates_dginn_full<-ifelse(
dginnfulltmp>=4, 1,0)
mondrian(na.omit(monddata[,2:4]), labels=c("Young", "Cooper", "DGINN-full >=4"))
mondrian(na.omit(monddata[,2:4]),
labels=c("Young", "Cooper", "DGINN-full >=4"))
@
......@@ -144,7 +202,8 @@ library(UpSetR)
upsetdata<-as.data.frame(tab$Gene.name)
upsetdata$primates_young<-ifelse(tab$pVal.M8vsM7<0.05, 1, 0)
upsetdata$primate_cooper<-ifelse(tab$cooper.primates.M7.M8_p_value<0.05, 1, 0)
upsetdata$primate_cooper<-ifelse(
tab$cooper.primates.M7.M8_p_value<0.05, 1, 0)
upsetdata$primates_dginn_full<-ifelse(dginnfulltmp>=3, 1,0)
......
covid_comp_primate.pdf
View file @ 77f559a1
No preview for this file type
covid_comp_primate.tex
View file @ 77f559a1
......@@ -82,51 +82,65 @@ 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{home}\hlkwb{<-}\hlstr{"/home/adminmarie/Documents/"}
\hlstd{workdir}\hlkwb{<-}\hlkwd{paste0}\hlstd{(home,} \hlstr{"CIRI_BIBS_projects/2020_05_Etienne_covid/"}\hlstd{)}
\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] 332 139
## [1] 332 141
\end{verbatim}
\begin{alltt}
\hlstd{tab}\hlopt{$}\hlstd{Gene.name}\hlkwb{<-}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{Gene.name)}
\hlstd{tab}\hlopt{$}\hlstd{Gene.name}\hlkwb{<-}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{Gene.name.x)}
\hlstd{tab}\hlopt{$}\hlstd{Gene.name[tab}\hlopt{$}\hlstd{PreyGene}\hlopt{==}\hlstr{"MTARC1"}\hlstd{]}\hlkwb{<-}\hlstr{"MTARC1"}
\end{alltt}
\end{kframe}
\end{knitrout}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\section{Comparisons Primates}
\subsection{Janet Young's results (Young-primate) VS DGINN-full's results}
Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" dans la sortie de dginn.
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{plot}\hlstd{(tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,} \hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp)),}
\hlkwc{xlab}\hlstd{=}\hlstr{"Omega Young-primate"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"DGINN-full's"}\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}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp[tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{==}\hlstr{"na"}\hlstd{]}\hlkwb{<-}\hlnum{NA}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp))}
\hlkwd{plot}\hlstd{(tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp,}
\hlkwc{xlab}\hlstd{=}\hlstr{"Omega Young-primate"}\hlstd{,}
\hlkwc{ylab}\hlstd{=}\hlstr{"DGINN-full's"}\hlstd{,}
\hlkwc{cex}\hlstd{=}\hlnum{0.3}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlnum{0}\hlstd{,}\hlnum{1}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlkwd{lm}\hlstd{(}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp))}\hlopt{~}\hlstd{tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0),} \hlkwc{col}\hlstd{=}\hlstr{"red"}\hlstd{)}
\end{alltt}
\hlkwd{abline}\hlstd{(}\hlkwd{lm}\hlstd{(tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{~}\hlstd{tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0),}
\hlkwc{col}\hlstd{=}\hlstr{"red"}\hlstd{)}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{<}\hlnum{0.4} \hlopt{&}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{>}\hlnum{0.5}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name)}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning in eval(predvars, data, env): NAs introduits lors de la conversion automatique}}\begin{alltt}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{<}\hlnum{0.4} \hlopt{&} \hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{>}\hlnum{0.5}\hlstd{,]}
\end{alltt}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{<}\hlnum{0.1} \hlopt{&}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{>}\hlnum{0.3}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name)}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{>}\hlnum{0.33} \hlopt{&}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{<}\hlnum{0.2}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name)}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning in Ops.factor(tab\$dginn.primate\_omegaM0Bpp, 0.5): '>' not meaningful for factors}}\begin{alltt}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{>}\hlnum{0.6} \hlopt{&}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{<}\hlnum{0.6}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name)}
......@@ -139,19 +153,39 @@ Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "omega" d
\subsection{Janet Young's results (Young-primate) VS Cooper's result}
Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "cooper.primates.Average\_dNdS".
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{plot}\hlstd{(tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,} \hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{cooper.primates.Average_dNdS)),}
\hlkwc{xlab}\hlstd{=}\hlstr{"Omega Young-primate"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"Omega Cooper-primate"}\hlstd{)}
\hlstd{tab}\hlopt{$}\hlstd{cooper.primates.Average_dNdS}\hlkwb{<-}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(}
\hlstd{tab}\hlopt{$}\hlstd{cooper.primates.Average_dNdS))}
\hlkwd{plot}\hlstd{(tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlstd{tab}\hlopt{$}\hlstd{cooper.primates.Average_dNdS,}
\hlkwc{xlab}\hlstd{=}\hlstr{"Omega Young-primate"}\hlstd{,}
\hlkwc{ylab}\hlstd{=}\hlstr{"Omega Cooper-primate"}\hlstd{,}
\hlkwc{cex}\hlstd{=}\hlnum{0.3}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlnum{0}\hlstd{,}\hlnum{1}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlkwd{lm}\hlstd{(}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{cooper.primates.Average_dNdS))}\hlopt{~}\hlstd{tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0),} \hlkwc{col}\hlstd{=}\hlstr{"red"}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlkwd{lm}\hlstd{(tab}\hlopt{$}\hlstd{cooper.primates.Average_dNdS}\hlopt{~}\hlstd{tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0),}
\hlkwc{col}\hlstd{=}\hlstr{"red"}\hlstd{)}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{<}\hlnum{0.15} \hlopt{&}
\hlstd{tab}\hlopt{$}\hlstd{cooper.primates.Average_dNdS}\hlopt{>}\hlnum{0.4}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstd{cooper.primates.Average_dNdS,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name,} \hlkwc{cex}\hlstd{=}\hlnum{0.5}\hlstd{)}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{<}\hlnum{0.4} \hlopt{&} \hlstd{tab}\hlopt{$}\hlstd{cooper.primates.Average_dNdS}\hlopt{>}\hlnum{0.5}\hlstd{,]}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{<}\hlnum{0.3} \hlopt{&}
\hlstd{tab}\hlopt{$}\hlstd{cooper.primates.Average_dNdS}\hlopt{>}\hlnum{0.5}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstd{cooper.primates.Average_dNdS,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name)}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name,} \hlkwc{cex}\hlstd{=}\hlnum{0.5}\hlstd{)}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0}\hlopt{>}\hlnum{0.3} \hlopt{&}
\hlstd{tab}\hlopt{$}\hlstd{cooper.primates.Average_dNdS}\hlopt{<}\hlnum{0.1}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{whole.gene.dN.dS.model.0,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstd{cooper.primates.Average_dNdS,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name,} \hlkwc{cex}\hlstd{=}\hlnum{0.5}\hlstd{)}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/omegaM7M8_2-1}
......@@ -161,43 +195,49 @@ Comparaison des Omega: colonne L "whole.gene.dN.dS.model.0" VS colonne "cooper.p
\subsection{Cooper's results (Cooper-primate) VS DGINN-full's results}
Comparaison des Omega: colonne "cooper.primates.Average\_dNdS" VS colonne "omega" dans la sortie de dginn.
\begin{knitrout}
\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe}
\begin{alltt}
\hlkwd{plot}\hlstd{(tab}\hlopt{$}\hlstd{cooper.primates.Average_dNd,} \hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp)),}
\hlkwc{xlab}\hlstd{=}\hlstr{"Omega Cooper-primate"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"DGINN-full's"}\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{plot}\hlstd{(tab}\hlopt{$}\hlstd{cooper.primates.Average_dNd,}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp,}
\hlkwc{xlab}\hlstd{=}\hlstr{"Omega Cooper-primate"}\hlstd{,}
\hlkwc{ylab}\hlstd{=}\hlstr{"DGINN-full's"}\hlstd{,}
\hlkwc{cex}\hlstd{=}\hlnum{0.3}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlnum{0}\hlstd{,}\hlnum{1}\hlstd{)}
\hlkwd{abline}\hlstd{(}\hlkwd{lm}\hlstd{(}\hlkwd{as.numeric}\hlstd{(}\hlkwd{as.character}\hlstd{(tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp))}\hlopt{~}\hlstd{tab}\hlopt{$}\hlstd{cooper.primates.Average_dNd),} \hlkwc{col}\hlstd{=}\hlstr{"red"}\hlstd{)}
\end{alltt}
\hlkwd{abline}\hlstd{(}\hlkwd{lm}\hlstd{(tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{~}\hlstd{tab}\hlopt{$}\hlstd{cooper.primates.Average_dNd),} \hlkwc{col}\hlstd{=}\hlstr{"red"}\hlstd{)}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{cooper.primates.Average_dNd}\hlopt{<}\hlnum{0.4} \hlopt{&}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{>}\hlnum{0.5}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{cooper.primates.Average_dNd,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name,} \hlkwc{cex}\hlstd{=}\hlnum{0.5}\hlstd{)}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning in eval(predvars, data, env): NAs introduits lors de la conversion automatique}}\begin{alltt}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{cooper.primates.Average_dNd}\hlopt{<}\hlnum{0.4} \hlopt{&} \hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{>}\hlnum{0.5}\hlstd{,]}
\end{alltt}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{cooper.primates.Average_dNd}\hlopt{<}\hlnum{0.1} \hlopt{&}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{>}\hlnum{0.3}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{cooper.primates.Average_dNd,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name,} \hlkwc{cex}\hlstd{=}\hlnum{0.5}\hlstd{)}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{cooper.primates.Average_dNd}\hlopt{>}\hlnum{0.7} \hlopt{&}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{<}\hlnum{0.3}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{cooper.primates.Average_dNd,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name,} \hlkwc{cex}\hlstd{=}\hlnum{0.5}\hlstd{)}
{\ttfamily\noindent\color{warningcolor}{\#\# Warning in Ops.factor(tab\$dginn.primate\_omegaM0Bpp, 0.5): '>' not meaningful for factors}}\begin{alltt}
\hlstd{outlier}\hlkwb{<-}\hlstd{tab[tab}\hlopt{$}\hlstd{cooper.primates.Average_dNd}\hlopt{>}\hlnum{0.45} \hlopt{&}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp}\hlopt{<}\hlnum{0.2}\hlstd{,]}
\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=outlier}\hlopt{$}\hlstd{cooper.primates.Average_dNd,}
\hlkwc{y}\hlstd{=outlier}\hlopt{$}\hlstd{dginn.primate_omegaM0Bpp,}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name)}
\hlstd{outlier}\hlopt{$}\hlstd{Gene.name,} \hlkwc{cex}\hlstd{=}\hlnum{0.5}\hlstd{)}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/omegaM7M8_3-1}
\end{knitrout}
\section{Overlap}
\subsection{Mondrian}
\begin{knitrout}
......@@ -205,8 +245,6 @@ Comparaison des Omega: colonne "cooper.primates.Average\_dNdS" VS colonne "omega
\begin{alltt}
\hlkwd{library}\hlstd{(Mondrian)}
\hlcom{#######}
\hlstd{monddata}\hlkwb{<-}\hlkwd{as.data.frame}\hlstd{(tab}\hlopt{$}\hlstd{Gene.name)}
\hlkwd{dim}\hlstd{(monddata)}
\end{alltt}
......@@ -214,22 +252,30 @@ Comparaison des Omega: colonne "cooper.primates.Average\_dNdS" VS colonne "omega
## [1] 332 1
\end{verbatim}
\begin{alltt}
\hlstd{dginnfulltmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tab}\hlopt{$}\hlstd{dginn.primate_BUSTED}\hlopt{==}\hlstr{"Y"}\hlstd{, tab}\hlopt{$}\hlstd{dginn.primate_BppM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_BppM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{, tab}\hlopt{$}\hlstd{dginn.primate_codemlM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{, tab}\hlopt{$}\hlstd{dginn.primate_codemlM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlstd{monddata}\hlopt{$}\hlstd{primates_young}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(tab}\hlopt{$}\hlstd{pVal.M8vsM7}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{primate_cooper}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(tab}\hlopt{$}\hlstd{cooper.primates.M7.M8_p_value}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{primates_dginn_full}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginnfulltmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlkwd{mondrian}\hlstd{(}\hlkwd{na.omit}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{]),} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"Young"}\hlstd{,} \hlstr{"Cooper"}\hlstd{,} \hlstr{"DGINN-full >=3"} \hlstd{))}
\hlstd{dginnfulltmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tab}\hlopt{$}\hlstd{dginn.primate_BUSTED}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_BppM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_BppM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_codemlM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{,}
\hlstd{tab}\hlopt{$}\hlstd{dginn.primate_codemlM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{))}
\hlstd{monddata}\hlopt{$}\hlstd{primates_young}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(}
\hlstd{tab}\hlopt{$}\hlstd{pVal.M8vsM7}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{primate_cooper}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(}
\hlstd{tab}\hlopt{$}\hlstd{cooper.primates.M7.M8_p_value}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{primates_dginn_full}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(}
\hlstd{dginnfulltmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlkwd{mondrian}\hlstd{(}\hlkwd{na.omit}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{]),}
\hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"Young"}\hlstd{,} \hlstr{"Cooper"}\hlstd{,} \hlstr{"DGINN-full >=3"} \hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/mondrianprimates-1}
\begin{kframe}\begin{alltt}
\hlcom{#####}
\hlstd{monddata}\hlopt{$}\hlstd{primates_dginn_full}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginnfulltmp}\hlopt{>=}\hlnum{4}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlstd{monddata}\hlopt{$}\hlstd{primates_dginn_full}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(}
\hlstd{dginnfulltmp}\hlopt{>=}\hlnum{4}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
\hlkwd{mondrian}\hlstd{(}\hlkwd{na.omit}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{]),} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"Young"}\hlstd{,} \hlstr{"Cooper"}\hlstd{,} \hlstr{"DGINN-full >=4"}\hlstd{))}
\hlkwd{mondrian}\hlstd{(}\hlkwd{na.omit}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{4}\hlstd{]),}
\hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"Young"}\hlstd{,} \hlstr{"Cooper"}\hlstd{,} \hlstr{"DGINN-full >=4"}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/mondrianprimates-2}
......@@ -248,7 +294,8 @@ Just another representation of the same result.
\hlstd{upsetdata}\hlkwb{<-}\hlkwd{as.data.frame}\hlstd{(tab}\hlopt{$}\hlstd{Gene.name)}
\hlstd{upsetdata}\hlopt{$}\hlstd{primates_young}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(tab}\hlopt{$}\hlstd{pVal.M8vsM7}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{upsetdata}\hlopt{$}\hlstd{primate_cooper}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(tab}\hlopt{$}\hlstd{cooper.primates.M7.M8_p_value}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{upsetdata}\hlopt{$}\hlstd{primate_cooper}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(}
\hlstd{tab}\hlopt{$}\hlstd{cooper.primates.M7.M8_p_value}\hlopt{<}\hlnum{0.05}\hlstd{,} \hlnum{1}\hlstd{,} \hlnum{0}\hlstd{)}
\hlstd{upsetdata}\hlopt{$}\hlstd{primates_dginn_full}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(dginnfulltmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)}
......@@ -287,14 +334,14 @@ Genes under positive selection for at least 4 methods.
\begin{verbatim}
## [1] "ACADM" "BCS1L" "BRD4" "CDK5RAP2" "CEP135"
## [6] "CEP68" "CLIP4" "DNMT1" "DPH5" "EMC1"
## [11] "FYCO1" "GCC2" "GGH" "GHITM" "GIGYF2"
## [16] "GLA" "GOLGA7" "HECTD1" "IDE" "ITGB1"
## [21] "LARP1" "LARP4B" "LMAN2" "MARK1" "MIPOL1"
## [26] "MPHOSPH10" "MYCBP2" "NDUFAF2" "NDUFB9" "PCNT"
## [31] "POLA1" "PRIM2" "PRKAR2A" "PVR" "REEP6"
## [36] "RIPK1" "SAAL1" "SEPSECS" "SIRT5" "SLC25A21"
## [41] "SLC27A2" "TMEM39B" "TOR1AIP1" "TUBGCP2" "UBAP2"
## [46] "UGGT2" "VPS39" "ZNF318"
## [11] "ERO1LB" "FYCO1" "GCC2" "GGH" "GHITM"
## [16] "GIGYF2" "GLA" "GOLGA7" "HECTD1" "IDE"
## [21] "ITGB1" "LARP1" "LARP4B" "LMAN2" "MARK1"
## [26] "MIPOL1" "MPHOSPH10" "MYCBP2" "NDUFAF2" "NDUFB9"
## [31] "NUPL1" "PCNT" "POLA1" "PRIM2" "PRKAR2A"
## [36] "PVR" "REEP6" "RIPK1" "SAAL1" "SEPSECS"
## [41] "SIRT5" "SLC25A21" "SLC27A2" "TMEM39B" "TOR1AIP1"
## [46] "TUBGCP2" "UBAP2" "UGGT2" "VPS39" "ZNF318"
\end{verbatim}
\begin{alltt}
\hlstd{tab}\hlopt{$}\hlstd{Gene.name[dginnfulltmp}\hlopt{>=}\hlnum{3} \hlopt{&} \hlkwd{is.na}\hlstd{(dginnfulltmp)}\hlopt{==}\hlstd{F]}
......@@ -303,20 +350,21 @@ Genes under positive selection for at least 4 methods.
## [1] "ACADM" "ADAM9" "AP2A2" "ATE1" "BCS1L"
## [6] "BRD4" "BZW2" "CDK5RAP2" "CEP135" "CEP68"
## [11] "CLIP4" "CNTRL" "DNMT1" "DPH5" "EDEM3"
## [16] "EIF4E2" "EMC1" "EXOSC2" "FYCO1" "GCC2"
## [21] "GGH" "GHITM" "GIGYF2" "GLA" "GOLGA7"
## [26] "GOLGB1" "GORASP1" "HDAC2" "HECTD1" "HS6ST2"
## [31] "IDE" "ITGB1" "LARP1" "LARP4B" "LARP7"
## [36] "LMAN2" "MARK1" "MDN1" "MIPOL1" "MOV10"
## [41] "MPHOSPH10" "MRPS5" "MYCBP2" "NAT14" "NDUFAF2"
## [46] "NDUFB9" "NGLY1" "NPC2" "PCNT" "PITRM1"
## [51] "PLAT" "PLOD2" "PMPCB" "POLA1" "POR"
## [56] "PRIM2" "PRKAR2A" "PTBP2" "PVR" "RAB14"
## [61] "RAB1A" "RAB2A" "RAP1GDS1" "RBX1" "REEP6"
## [66] "RIPK1" "RPL36" "SAAL1" "SCCPDH" "SEPSECS"
## [71] "SIRT5" "SLC25A21" "SLC27A2" "STOM" "TIMM8B"
## [76] "TMEM39B" "TOR1AIP1" "TRIM59" "TRMT1" "TUBGCP2"
## [81] "UBAP2" "UGGT2" "USP54" "VPS39" "ZNF318"
## [16] "EIF4E2" "EMC1" "ERO1LB" "EXOSC2" "FYCO1"
## [21] "GCC2" "GGH" "GHITM" "GIGYF2" "GLA"
## [26] "GOLGA7" "GOLGB1" "GORASP1" "HDAC2" "HECTD1"
## [31] "HS6ST2" "IDE" "ITGB1" "LARP1" "LARP4B"
## [36] "LARP7" "LMAN2" "MARK1" "MDN1" "MIPOL1"
## [41] "MOV10" "MPHOSPH10" "MRPS5" "MYCBP2" "NAT14"
## [46] "NDUFAF2" "NDUFB9" "NGLY1" "NPC2" "NUPL1"
## [51] "PCNT" "PITRM1" "PLAT" "PLOD2" "PMPCB"
## [56] "POLA1" "POR" "PRIM2" "PRKAR2A" "PTBP2"
## [61] "PVR" "RAB14" "RAB1A" "RAB2A" "RAP1GDS1"
## [66] "RBX1" "REEP6" "RIPK1" "RPL36" "SAAL1"
## [71] "SCCPDH" "SEPSECS" "SIRT5" "SLC25A21" "SLC27A2"
## [76] "STOM" "TIMM8B" "TMEM39B" "TOR1AIP1" "TRIM59"
## [81] "TRMT1" "TUBGCP2" "UBAP2" "UGGT2" "USP54"
## [86] "VPS39" "ZNF318"
\end{verbatim}
\begin{alltt}
\hlstd{tmp}\hlkwb{<-}\hlstd{tab[dginnfulltmp}\hlopt{>=}\hlnum{4} \hlopt{&} \hlkwd{is.na}\hlstd{(dginnfulltmp)}\hlopt{==}\hlstd{F,}
......
figure/boxplot-1.pdf 0 → 100644
View file @ 77f559a1
File added
figure/dotbats-1.pdf 0 → 100644
View file @ 77f559a1
File added