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 (11)
Expand all Hide whitespace changes
Inline Side-by-side
Showing
with 3301 additions and 704 deletions
covid_comp_alldginn.txt
View file @ 77f559a1
......@@ -364,7 +364,7 @@ But Genetic Innovation by splicing variants YES.
" "" "onlybats"
"350" "SCCPDH" "SCCPDH_sequences_filtered_longestORFs_mafft_mincov_prank" "SCCPDH_all" 717 23 "0.297146699972" "0.323" "Y" "0.0242" 4 "203, 437, 632, 635" "N" "0.16718066834449946" 0 "na" "N" "0.05798336825737528" 0 "na" "Y" "0.03951796106177764" 1 "590" "Y" "0.015732919159708345" 1 "590" "SCCPDH_sequences_filtered_longestORFs_mafft_prank" "SCCPDH" 654 12 "0.281129406592" "0.291" "N" 0.1315 11 "46, 70, 87, 228, 229, 231, 238, 327, 379, 594, 644" "N" "0.0747269312417341" 0 "na" "Y" "0.005045637026761042" 1 "367" "Y" "0.047028569511397056" 0 "" "Y" "0.0063709925831932045" 1 "367" "PS ok. Splice variants" "" "shared"
"351" "SDF2" "SDF2_sequences_filtered_longestORFs_mafft_mincov_prank" "SDF2_all" 364 23 "0.091229165614" "0.089" "N" "0.7862" 0 "na" "N" "0.9999997541511068" 0 "na" "N" "0.9999998942125841" 0 "na" "N" "1.0" 0 "na" "N" "0.9990004998331715" 0 "na" "SDF2_bat_select_mafft_prank" "SDF2" 246 12 "0.082797829312181" "0.080" "N" 0.2145 0 "na" "N" "0.999999439606811" 0 "na" "N" "0.999999993020992" 0 "na" "N" "1.0" 0 "na" "N" "1.0" 0 "na" "" "" "shared"
"352" "SELENOS" NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA "SELENOS_bat_select_mafft_prank" "SELENOS" 218 8 "0.1693975661318" "0.172" "N" 0.8176 5 "71, 72, 85, 128, 173" "N" "0.999999579118228" 0 "na" "N" "0.389714156459387" 0 "na" "N" "0.9970044955034437" 0 "na" "N" "0.2133118712228997" 0 "na" "" "" "onlybats"
"352" "SELENOS" "SELENOS_sequences_filtered_longestORFs_mafft_mincov_prank" "SELENOS_all" 367 24 "0.207287174753623" "0.196" "Y" "0" 1 "90" "N" "0.999999228305" 0 "na" "N" "0.986116909613" 0 "na" "N" "1" 0 "na" "N" "0.692117181689" 0 "na" "SELENOS_bat_select_mafft_prank" "SELENOS" 218 8 "0.1693975661318" "0.172" "N" 0.8176 5 "71, 72, 85, 128, 173" "N" "0.999999579118228" 0 "na" "N" "0.389714156459387" 0 "na" "N" "0.9970044955034437" 0 "na" "N" "0.2133118712228997" 0 "na" "" "" "shared"
"353" "SELENOS[0-927]" NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA "SELENOS_sequences_filtered_longestORFs_mafft_prank_frag0to927" "SELENOS[0-927]" 309 11 "0.213235744659" "0.250" "Y" 0.0085 3 "126, 148, 154" "N" "0.3022734485269354" 0 "na" "N" "0.1168296305173564" 0 "na" "N" "1.0" 0 "na" "N" "0.24268280925769264" 0 "na" "Recomb triggered by aln with lots of indels" "" "onlybats"
"354" "SELENOS[926-1137]" NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA "SELENOS_sequences_filtered_longestORFs_mafft_prank_frag926to1137" "SELENOS[926-1137]" 70 11 "0.233147569842" "0.246" "N" 1 0 "na" "N" "0.9999999153342323" 0 "na" "N" "0.9999906640992244" 0 "na" "N" "0.9694755730759651" 0 "na" "N" "0.3348743138811512" 0 "na" "" "" "onlybats"
"355" "SEPSECS" "SEPSECS_sequences_filtered_longestORFs_mafft_mincov_prank" "SEPSECS_all" 1204 24 "0.200383584131" "0.191" "Y" "0.0012" 4 "411, 792, 871, 1131" "Y" "0.04699410636855563" 1 "871" "Y" "0.000675790377354786" 1 "871" "Y" "0.022573017543302893" 0 "" "Y" "0.002544044860029952" 1 "871" "SEPSECS_sequences_filtered_longestORFs_mafft_prank" "SEPSECS" 642 12 "0.207760285718" "0.221" "Y" 0.0113 0 "na" "N" "0.4067707665111908" 0 "na" "Y" "0.00326458340100601" 2 "577, 585" "N" "0.4269877306527835" 0 "na" "N" "0.0707218996108505" 0 "na" "" "" "shared"
......
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_complete.txt
View file @ 77f559a1
......@@ -273,7 +273,7 @@ But Genetic Innovation by splicing variants YES.
"SCARB1" "SCARB1" "SCARB1" "nsp7" "SCARB1" "list26_COV_list4dataset2nonOrf" "scavenger receptor class B member 1" "CD36L1|CLA-1|CLA1|HDLQTL6|SR-BI|SRB1" "no" 25 1530 510 0.10383 0.62207 0.0784 0.7554 1 1 1 1 1 1 NA NA NA "" "" "" "" NA NA NA NA NA NA NA NA NA NA NA NA NA "" "SCARB1" "ENSG00000073060.15" "ENST00000545493.1" 14 146 100 0.221176368 0.1874 0.49354 0.49355 -910.195166 -910.195401 0.999765028 NA NA NA "" "SCARB1" 0.06378625 0.750735805 "" NA NA NA "" "" 1059 353 0.12908 0.34857 0.0509 0.3941 1 1 1 1 1 1 NA NA NA "" "SCARB1" "SCARB1_sequences_filtered_longestORFs_mafft_mincov_prank_part2_prank" "SCARB1_all_part2" 1623 24 "0.094947443872" "0.131" "Y" "0.0000" 11 "549, 607, 630, 703, 733, 911, 965, 993, 1432, 1531, 1622" "N" "0.9999999983037924" 0 "na" "N" "0.42297612986890076" 0 "na" "Y" "7.551887340080195e-27" 1 "1531" "na" "na" 0 "na" "SCARB1_sequences_filtered_longestORFs_mafft_prank" "SCARB1" 763 10 "0.218091439138" "0.155" "Y" 0 19 "5, 7, 132, 133, 137, 157, 176, 236, 277, 417, 476, 509, 592, 674, 688, 724, 740, 741, 763" "N" "0.9999998503026403" 0 "na" "N" "0.4515726499701246" 0 "na" "N" "1.0" 0 "na" "Y" "0.0002460440433622239" 1 "763" "PS. Splicing variants" "" "shared"
"SCCPDH" "SCCPDH" "SCCPDH" "nsp7" "SCCPDH" "list24_COV_list2nonOrf" "saccharopine dehydrogenase (putative)" "CGI-49|NET11" "no" 24 1290 430 0.26038 0.57846 0.1053 0.4043 1 1 1 1 1 1 NA NA NA "" "" "" "" NA NA NA NA NA NA NA NA NA NA NA NA NA "" "SCCPDH" "ENSG00000143653.9" "ENST00000366510.3" 15 430 97.6744186 0.196343201 0.1627 0.45905 0.45905 -2886.510879 -2886.510885 0.999994 NA NA NA "" "SCCPDH" 0.002019556 0.09129021 "" NA NA NA "" "" 999 333 0.29684 0.36519 0.074 0.2492 1 1 1 1 1 1 NA NA NA "" "SCCPDH" "SCCPDH_sequences_filtered_longestORFs_mafft_mincov_prank" "SCCPDH_all" 717 23 "0.297146699972" "0.323" "Y" "0.0242" 4 "203, 437, 632, 635" "N" "0.16718066834449946" 0 "na" "N" "0.05798336825737528" 0 "na" "Y" "0.03951796106177764" 1 "590" "Y" "0.015732919159708345" 1 "590" "SCCPDH_sequences_filtered_longestORFs_mafft_prank" "SCCPDH" 654 12 "0.281129406592" "0.291" "N" 0.1315 11 "46, 70, 87, 228, 229, 231, 238, 327, 379, 594, 644" "N" "0.0747269312417341" 0 "na" "Y" "0.005045637026761042" 1 "367" "Y" "0.047028569511397056" 0 "" "Y" "0.0063709925831932045" 1 "367" "PS ok. Splice variants" "" "shared"
"SDF2" "SDF2" "SDF2" "orf8" "SDF2" "list25_COV_list3dataset2orf" "stromal cell derived factor 2" "-" "no" 23 636 212 0.13507 0.3131 0.0364 0.2694 1 1 1 1 1 1 NA NA NA "" "SDF2" "ENSMLUG00000012419.2" "ENSMLUT00000012419.2" 15 212 98.58490566 0.06852197 0.335 0.90704 0.90706 -1790.437725 -1790.438975 0.998750781 NA NA NA "" "SDF2" "ENSG00000132581.9" "ENST00000591903.1" 19 105 88.57142857 0.073449063 4.3067 9.69242 9.69891 -726.542628 -726.543552 0.999076427 NA NA NA "" "SDF2" 0.997743245 1 "" NA NA NA "" "" 522 174 0.10167 0.24504 0.0225 0.2215 1 1 0.96895 1 1 1 NA NA NA "" "SDF2" "SDF2_sequences_filtered_longestORFs_mafft_mincov_prank" "SDF2_all" 364 23 "0.091229165614" "0.089" "N" "0.7862" 0 "na" "N" "0.9999997541511068" 0 "na" "N" "0.9999998942125841" 0 "na" "N" "1.0" 0 "na" "N" "0.9990004998331715" 0 "na" "SDF2_bat_select_mafft_prank" "SDF2" 246 12 "0.082797829312181" "0.080" "N" 0.2145 0 "na" "N" "0.999999439606811" 0 "na" "N" "0.999999993020992" 0 "na" "N" "1.0" 0 "na" "N" "1.0" 0 "na" "" "" "shared"
"SELENOS" "SELENOS" "VIMP" "nsp7" "VIMP" "list26_COV_list4dataset2nonOrf" "selenoprotein S protein-coding" "AD-015|ADO15|SBBI8|SELS|SEPS1|VIMP" "no" 24 567 189 0.21832 0.68129 0.1108 0.5076 0.93424 1 0.91359 1 0.99621 1 NA NA NA "" "" "" "" NA NA NA NA NA NA NA NA NA NA NA NA NA "" "SELENOS" "ENSG00000131871.14" "ENST00000528346.1" 9 218 83.02752294 0.295972578 0.1231 0.34109 0.34109 -1105.646929 -1105.646929 1 NA NA NA "" "" NA NA "" NA NA NA "" "" 408 136 0.1532 0.50802 0.0684 0.4462 0.65661 1 0.78342 1 0.90578 1 NA NA NA "" "SELENOS" NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA "SELENOS_bat_select_mafft_prank" "SELENOS" 218 8 "0.1693975661318" "0.172" "N" 0.8176 5 "71, 72, 85, 128, 173" "N" "0.999999579118228" 0 "na" "N" "0.389714156459387" 0 "na" "N" "0.9970044955034437" 0 "na" "N" "0.2133118712228997" 0 "na" "" "" "onlybats"
"SELENOS" "SELENOS" "VIMP" "nsp7" "VIMP" "list26_COV_list4dataset2nonOrf" "selenoprotein S protein-coding" "AD-015|ADO15|SBBI8|SELS|SEPS1|VIMP" "no" 24 567 189 0.21832 0.68129 0.1108 0.5076 0.93424 1 0.91359 1 0.99621 1 NA NA NA "" "" "" "" NA NA NA NA NA NA NA NA NA NA NA NA NA "" "SELENOS" "ENSG00000131871.14" "ENST00000528346.1" 9 218 83.02752294 0.295972578 0.1231 0.34109 0.34109 -1105.646929 -1105.646929 1 NA NA NA "" "" NA NA "" NA NA NA "" "" 408 136 0.1532 0.50802 0.0684 0.4462 0.65661 1 0.78342 1 0.90578 1 NA NA NA "" "SELENOS" "SELENOS_sequences_filtered_longestORFs_mafft_mincov_prank" "SELENOS_all" 367 24 "0.207287174753623" "0.196" "Y" "0" 1 "90" "N" "0.999999228305" 0 "na" "N" "0.986116909613" 0 "na" "N" "1" 0 "na" "N" "0.692117181689" 0 "na" "SELENOS_bat_select_mafft_prank" "SELENOS" 218 8 "0.1693975661318" "0.172" "N" 0.8176 5 "71, 72, 85, 128, 173" "N" "0.999999579118228" 0 "na" "N" "0.389714156459387" 0 "na" "N" "0.9970044955034437" 0 "na" "N" "0.2133118712228997" 0 "na" "" "" "shared"
"SEPSECS" "SEPSECS" "SEPSECS" "nsp8" "SEPSECS" "list24_COV_list2nonOrf" "Sep (O-phosphoserine) tRNA:Sec (selenocysteine) tRNA synthase" "LP|PCH2D|SLA|SLA/LP" "yes" 24 1506 502 0.23138 0.39192 0.0699 0.3022 0.00014539 0.0027987575 0.00073465 0.0104755648148148 0.00073013 0.0140550025 5.009 3.57509 6 "246_D_0.971,375_M_1.000,383_H_0.956,385_D_0.950,386_E_0.925,456_K_0.990" "SEPSECS" "ENSMLUG00000005883.2" "ENSMLUT00000005885.2" 11 505 92.07920792 0.157833305 0.327 0.84904 0.84915 -3816.572052 -3816.423878 0.862281065 NA NA NA "" "" "" "" NA NA NA NA NA NA NA NA NA NA NA NA NA "" "" NA NA "" NA NA NA "" "" 1296 432 0.24565 0.28571 0.0539 0.2196 8.3292e-06 0.000458106 4.8623e-05 0.002339981875 4.9379e-05 0.002715845 1.667 8.61509 5 "325_M_1.000,333_H_0.980,345_A_0.902,394_K_0.996,428_Y_0.910" "SEPSECS" "SEPSECS_sequences_filtered_longestORFs_mafft_mincov_prank" "SEPSECS_all" 1204 24 "0.200383584131" "0.191" "Y" "0.0012" 4 "411, 792, 871, 1131" "Y" "0.04699410636855563" 1 "871" "Y" "0.000675790377354786" 1 "871" "Y" "0.022573017543302893" 0 "" "Y" "0.002544044860029952" 1 "871" "SEPSECS_sequences_filtered_longestORFs_mafft_prank" "SEPSECS" 642 12 "0.207760285718" "0.221" "Y" 0.0113 0 "na" "N" "0.4067707665111908" 0 "na" "Y" "0.00326458340100601" 2 "577, 585" "N" "0.4269877306527835" 0 "na" "N" "0.0707218996108505" 0 "na" "" "" "shared"
"SIGMAR1" "SIGMAR1" "SIGMAR1" "nsp6" "SIGMAR1" "list26_COV_list4dataset2nonOrf" "sigma non-opioid intracellular receptor 1" "ALS16|DSMA2|OPRS1|SIG-1R|SR-BP|SR-BP1|SRBP|hSigmaR1|sigma1R" "no" 24 672 224 0.05548 0.42023 0.0297 0.5354 0.38838 0.874422807017544 0.596 1 0.67815 1 NA NA NA "" "SIGMAR1" "ENSMLUG00000003061.1" "ENSMLUT00000003059.1" 9 224 98.66071429 0.085786955 0.2738 0.68602 0.68531 -1513.500222 -1513.071044 0.651044033 NA NA NA "" "SIGMAR1" "ENSG00000147955.16" "ENST00000477726.1" 16 193 87.56476684 0.045269245 0.2398 0.42429 0.42002 -1002.547639 -1002.375629 0.841970753 NA NA NA "" "" NA NA "" NA NA NA "" "" 429 143 0.0585 0.29391 0.0203 0.3471 1 1 1 1 1 1 NA NA NA "" "SIGMAR1" NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA "SIGMAR1_sequences_filtered_longestORFs_mafft_prank" "SIGMAR1" 463 11 "0.063555782622" "0.062" "N" 1 0 "na" "N" "0.9999998523637823" 0 "na" "Y" "0.03935837746698778" 3 "28, 43, 296" "N" "1.0" 0 "na" "N" "0.3163202908753499" 0 "na" "" "" "onlybats"
"SIL1" "SIL1" "SIL1" "orf8" "SIL1" "list23_COV_list1orf" "SIL1 nucleotide exchange factor" "BAP|MSS|ULG5" "no" 24 1386 462 0.15942 0.59934 0.0829 0.52 0.12745 0.434232300884956 1 1 1 1 NA NA NA "" "SIL1" "ENSMLUG00000005198.2" "ENSMLUT00000005199.2" 11 385 98.44155844 0.116118369 0.3877 1.00231 1.00231 -3151.512186 -3151.512306 0.999880007 NA NA NA "" "SIL1" "ENSG00000120725.12" "ENST00000505353.1" 19 94 90.42553191 0.221006576 0.2776 0.74645 0.74672 -692.585908 -692.585983 0.999925003 NA NA NA "" "" NA NA "" NA NA NA "" "" 1059 353 0.20076 0.29004 0.047 0.2343 1 1 1 1 0.57402 1 NA NA NA "" "SIL1" "SIL1_sequences_filtered_longestORFs_mafft_mincov_prank" "SIL1_all" 586 24 "0.187714729747" "0.164" "N" "0.5261" 5 "98, 119, 143, 208, 560" "N" "0.9999991549406264" 0 "na" "N" "0.2610615228717177" 0 "na" "N" "1.0" 0 "na" "N" "0.5210027286033118" 0 "na" "SIL1_sequences_filtered_longestORFs_mafft_prank" "SIL1" 670 12 "0.168133221490" "0.160" "Y" 0 5 "212, 241, 273, 568, 647" "N" "0.8329986992390037" 0 "na" "N" "0.10828949711717219" 0 "na" "N" "0.3426656803484229" 0 "na" "N" "0.05535435177850455" 0 "na" "" "" "shared"
......
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.
......@@ -269,6 +311,201 @@ sort(krogan[krogan %in% tablo$`tmp$Gene.name`==F])
write.csv(tabloK, "primatesVbats_onlykrogan.csv", row.names=FALSE, quote=FALSE)
@
\section{Tanglegram}
<<eval=TRUE>>=
#install.packages('dendextend') # stable CRAN version
library(dendextend) # load the package
#install.packages("phytools") # stable CRAN version
library(phytools) # load the package
library(ggraph)
library(igraph)
library(tidyverse)
tmp<-tablo[(tablo$nbats!=0 | tablo$nprimates!=0),]
#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$nbats),]
dendpri<-as.dendrogram(matpri)
dendbats<-as.dendrogram(matbats)
labels(dendpri)<-as.character(tmp$`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$Gene.name'-> order
dendbats<-dendextend::rotate(dendbats, order=order)
#### Il faut swapper certains neud de l'arbrese
class(labels(dendpri))
dend12 <- dendlist(dendbats, dendpri)
png("figure/tanglegramm.png", width = 1800, height = 3000)
tanglegram(dend12, columns_width=c(3, 3,3), axes=FALSE,
edge.lwd=0, margin_inner=6,
margin_top=2,
main_left=" bats",
main_right = "primates ",
lwd=0.5,
cex_main=1,
lab.cex=1,
k_labels=6)
dev.off()
@
<<eval=TRUE>>=
ace<-264
tmprss2<-75
znf318<-81
sepsecs<-228
tbk1<-273
ripk1<-224
col<-rep("grey", length(labels(dendpri)))
col[ace]<-"black"
col[tmprss2]<-"black"
col[znf318]<-"black"
col[sepsecs]<-"black"
col[tbk1]<-"black"
col[ripk1]<-"black"
font<-rep(1, length(labels(dendpri))*2)
#font[ace]<-1.3
#font[tmprss2]<-1.3
#font[length(labels(dendpri))+160]<-1.3
png("figure/tanglegramm.png", width = 1800, height = 3000)
tanglegram(dend12, columns_width=c(3, 3,3), axes=FALSE,
edge.lwd=0, margin_inner=6,
margin_top=2,
main_left=" bats",
main_right = "primates ",
lwd=0.5,
cex_main=1,
lab.cex=font,
k_labels=6,
color_lines=col)
dev.off()
@
<<>>=
tmp<-tablo[(tablo$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$nprimates))
setEPS()
postscript("figure/tanglegramsup3_V2.eps", height=15, width=5)
tanglegram(dend12, columns_width=c(3, 3,3), axes=FALSE,
edge.lwd=0, margin_inner=6,
margin_top=3,
main_left=" bats",
main_right = "primates ",
lwd=0.5,
cex_main=2,
lab.cex=1,
# k_labels=6,
color_lines=col)
dev.off()
@
\end{document}
......
covid_comp_dataset.pdf
View file @ 77f559a1
No preview for this file type
covid_comp_dataset.tex
View file @ 77f559a1
This diff is collapsed.
covid_comp_maic-pancorona.Rnw 0 → 100644
View file @ 77f559a1
\documentclass[11pt, oneside]{article} % use "amsart" instead of "article" for AMSLaTeX format
%\usepackage{geometry} % See geometry.pdf to learn the layout options. There are lots.
%\geometry{letterpaper} % ... or a4paper or a5paper or ...
%\geometry{landscape} % Activate for for rotated page geometry
%\usepackage[parfill]{parskip} % Activate to begin paragraphs with an empty line rather than an indent
%\usepackage{graphicx} % Use pdf, png, jpg, or eps with pdflatex; use eps in DVI mode
% TeX will automatically convert eps --> pdf in pdflatex
%\usepackage{amssymb}
\usepackage[utf8]{inputenc}
%\usepackage[cyr]{aeguill}
%\usepackage[francais]{babel}
%\usepackage{hyperref}
\title{Positive selection on genes interacting with SARS-Cov2, comparison of different analysis, maic}
\author{Marie Cariou}
\date{March 2021} % Activate to display a given date or no date
\begin{document}
\maketitle
\tableofcontents
\newpage
\section{Data}
output from covid\_comp\_dataset.
<<>>=
tablo<-read.table("primatesVbats.csv",
h=T, sep=",")
@
Output MAIC formatted by Léa. This table includes the DGINN "score".
<<>>=
home<-"/home/adminmarie/Documents/"
workdir<-paste0(home, "CIRI_BIBS_projects/2020_05_Etienne_covid/")
maic<-read.table(paste0(workdir, "data/covid_comp_maic.txt"),
h=T)
@
\section{MAIC}
\subsection{Boxplot}
<<boxplot, fig.height=12>>=
par(mfrow=c(2,1))
boxplot(maic$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{$}\hlstd{tmp.Gene.name,} \hlkwc{xlim}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{0}\hlstd{,}\hlnum{5}\hlstd{))}
\hlkwd{points}\hlstd{(pandginn[,}\hlnum{4}\hlstd{],} \hlnum{1}\hlopt{:}\hlkwd{nrow}\hlstd{(pandginn),} \hlkwc{col}\hlstd{=}\hlstr{"blue"}\hlstd{,} \hlkwc{pch}\hlstd{=}\hlnum{20}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.7}\hlstd{)}
\hlkwd{points}\hlstd{(pandginn[,}\hlnum{3}\hlstd{],} \hlnum{1}\hlopt{:}\hlkwd{nrow}\hlstd{(pandginn),} \hlkwc{col}\hlstd{=}\hlstr{"blue"}\hlstd{,} \hlkwc{pch}\hlstd{=}\hlnum{4}\hlstd{)}
\hlkwd{legend}\hlstd{(}\hlstr{"bottomright"}\hlstd{,} \hlkwd{c}\hlstd{(}\hlstr{"pancorona score"}\hlstd{,} \hlstr{"dginn primate score"}\hlstd{,} \hlstr{"dginn bats score"}\hlstd{),} \hlkwc{pch}\hlstd{=}\hlkwd{c}\hlstd{(}\hlnum{1}\hlstd{,}\hlnum{20}\hlstd{,}\hlnum{4}\hlstd{),} \hlkwc{col}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"black"}\hlstd{,} \hlstr{"blue"}\hlstd{,} \hlstr{"blue"}\hlstd{))}
\end{alltt}
\end{kframe}
\includegraphics[width=\maxwidth]{figure/pancorona-1}
\end{knitrout}
\end{document}
covid_comp_primate-Young-focus.Rnw
View file @ 77f559a1
......@@ -15,7 +15,7 @@
\title{Positive selection on genes interacting with SARS-Cov2, comparison of different analysis}
\author{Marie Cariou}
\date{October 2020} % Activate to display a given date or no date
\date{March 2021} % Activate to display a given date or no date
\begin{document}
\maketitle
......@@ -26,20 +26,21 @@
\section{Files manipulations}
\subsection{Read Janet Young's table}
\subsection{Complete table}
<<>>=
workdir<-"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"
home<-"/home/adminmarie/Documents/"
workdir<-paste0(home, "CIRI_BIBS_projects/2020_05_Etienne_covid/")
tab<-read.delim(paste0(workdir,
"data/COVID_PAMLresults_332hits_plusBatScreens_2020_Apr14.csv"),
fill=T, h=T, dec=",")
"covid_comp/covid_comp_complete.txt"), h=T, sep="\t")
dim(tab)
#names(tab)
tab$Gene.name<-as.character(tab$Gene.name.x)
tab$Gene.name[tab$PreyGene=="MARC1"]<-"MARC1"
@
\subsection{Read DGINN Young table}
DGINN-Young-primate table correspond to DGINN results, on the SAME alignment as Young-primate.
......@@ -56,45 +57,6 @@ dim(dginnY)
names(dginnY)
@
\subsection{Joining Young and DGINN Young table}
\textit{I hide some code corresponding to verifications of gene names coherence between tables}
<<results="hide", echo=FALSE>>=
head(tab)[,1:5]
# gene avec un nom bizar dans certaines colomne
tab[158,1:10]
#
length(unique(dginnY$Gene))
length(unique(tab$PreyGene))
length(unique(tab$Gene.name))
#quelle paire de colonne contient le plus de noms identiques
sum(unique(dginnY$Gene) %in% unique(tab$PreyGene))
sum(unique(dginnY$Gene) %in% unique(tab$Gene.name))
# dginn$Gene et tab$Gene.name presque identiques sauf 1 ligne.
# Je soupçonne que c'est celle là:
tab[158,1:10]
# Verif:
tab[,1:10][(tab$Gene.name %in% unique(dginnY$Gene))==F,]
# yep
# Remplacement manuel par
as.character(unique(dginnY$Gene)[(unique(dginnY$Gene) %in% tab$Gene.name)==F])
# dans le tableau de Janet
val_remp=as.character(unique(dginnY$Gene)[(unique(dginnY$Gene) %in% tab$Gene.name)==F])
tab$Gene.name<-as.character(tab$Gene.name)
tab$Gene.name[158]<-val_remp
sum(unique(dginnY$Gene) %in% unique(tab$Gene.name))
@
<<>>=
add_col<-function(method="PamlM1M2"){
......@@ -127,79 +89,19 @@ tmp<-dginnY[dginnY$Method=="MEME",c("Gene", "NbSites", "PSS")]
names(tmp)<-c("Gene.name", "NbSites_MEME", "PSS_MEME")
tab<-merge(tab, tmp, by="Gene.name")
dim(tab)
@
\subsection{Read DGINN Table}
<<>>=
dginnT<-read.delim(paste0(workdir,
"/data/DGINN_202005281649summary_cleaned.csv"),
fill=T, h=T, sep=",")
dim(dginnT)
names(dginnT)
# Number of genes in dginn-primate output not present in the original table
dginnT[(dginnT$Gene %in% tab$Gene.name)==F,"Gene"]
# This includes paralogs, recombinations found by DGINN
# and additionnal genes included on purpose
# Number of genes from the original list not present in DGINN output
tab[(tab$Gene.name %in% dginnT$Gene)==F,"Gene.name"]
names(dginnT)<-c("File", "Name", "Gene.name", "GeneSize", "dginn-primate_NbSpecies", "dginn-primate_omegaM0Bpp",
"dginn-primate_omegaM0codeml", "dginn-primate_BUSTED", "dginn-primate_BUSTED.p.value",
"dginn-primate_MEME.NbSites", "dginn-primate_MEME.PSS", "dginn-primate_BppM1M2",
"dginn-primate_BppM1M2.p.value", "dginn-primate_BppM1M2.NbSites", "dginn-primate_BppM1M2.PSS",
"dginn-primate_BppM7M8", "dginn-primate_BppM7M8.p.value", "dginn-primate_BppM7M8.NbSites",
"dginn-primate_BppM7M8.PSS", "dginn-primate_codemlM1M2", "dginn-primate_codemlM1M2.p.value",
"dginn-primate_codemlM1M2.NbSites", "dginn-primate_codemlM1M2.PSS", "dginn-primate_codemlM7M8",
"dginn-primate_codemlM7M8.p.value", "dginn-primate_codemlM7M8.NbSites", "dginn-primate_codemlM7M8.PSS")
@
\subsection{Join Table and DGINN table}
<<>>=
tab<-merge(tab,dginnT, by="Gene.name", all.x=T)
@
\subsection{Write new table}
<<>>=
write.table(tab,
"COVID_PAMLresults_332hits_plusBatScreens_plusDGINN_20201014.txt",
row.names=F, quote=F, sep="\t")
@
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\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>>=
<<omegaM7M8>>=
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)
......@@ -212,159 +114,207 @@ 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$'dginn-primate_omegaM0Bpp'))
plot(tab$'dginn-primate_omegaM0Bpp', tab$Omega_PamlM7M8,
tab$'dginn.primate_omegaM0Bpp'<-as.numeric(
as.character(tab$'dginn.primate_omegaM0Bpp'))
plot(tab$'dginn.primate_omegaM0Bpp', tab$Omega_PamlM7M8,
xlab="DGINN-full's", ylab="Omega DGINN-Young-primate")
abline(0,1)
outlier<-tab[tab$'dginn-primate_omegaM0Bpp'>0.4 & tab$Omega_PamlM7M8<0.2,]
text(x=outlier$'dginn-primate_omegaM0Bpp',
outlier<-tab[tab$'dginn.primate_omegaM0Bpp'>0.4 & tab$Omega_PamlM7M8<0.2,]
text(x=outlier$'dginn.primate_omegaM0Bpp',
y=(outlier$Omega_PamlM7M8+0.01),
outlier$Gene.name)
outlier<-tab[tab$'dginn-primate_omegaM0Bpp'>0.5 & tab$Omega_PamlM7M8<0.4,]
text(x=outlier$'dginn-primate_omegaM0Bpp',
outlier<-tab[tab$'dginn.primate_omegaM0Bpp'>0.5 & tab$Omega_PamlM7M8<0.4,]
text(x=outlier$'dginn.primate_omegaM0Bpp',
y=(outlier$Omega_PamlM7M8+0.01),
outlier$Gene.name)
outlier<-tab[tab$'dginn.primate_omegaM0Bpp'>0.2 & tab$Omega_PamlM7M8>0.6,]
text(x=outlier$'dginn.primate_omegaM0Bpp',
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$whole.gene.dN.dS.model.0<0.4 & tab$'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',
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,]
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$'dginn.primate_omegaM0Bpp'))>0.3,]
text(x=outlier$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$primates_dginn_full<-ifelse(dginnfulltmp>=4, 1,0)
mondrian(na.omit(monddata[,2:4]), labels=c("Young", "DGINN-Young >=4", "DGINN-full >=4"))
mondrian(na.omit(monddata[,2:4]),
labels=c("Young", "DGINN-Young >=4", "DGINN-full >=4"))
@
Comparison of results with the same method.
<<>>=
#####
monddata$primates_dginn_young<-tab$PosSel_BppM7M8=="Y"
monddata$primates_dginn_full<-tab$'dginn-primate_codemlM7M8'=="Y"
monddata$primates_dginn_full<-tab$'dginn.primate_codemlM7M8'=="Y"
mondrian(na.omit(monddata[,2:4]), labels=c("Young", "DGINN-Young", "DGINN-full"), main="posel codeml M7M8")
mondrian(na.omit(monddata[,2:4]),
labels=c("Young", "DGINN-Young", "DGINN-full"),
main="posel codeml M7M8")
@
\subsection{subsetR}
Just another representation of the same result.
Just another representation of the same result, for now, I focuse on the gene positive in 3 methodes for DGINN analysis.
<<subsetprimates>>=
library(UpSetR)
upsetdata<-as.data.frame(tab$Gene.name)
upsetdata$primates_young<-ifelse(tab$pVal.M8vsM7<0.05, 1, 0)
###
upsetdata$primates_dginn_young<-ifelse(dginnyoungtmp>=3, 1,0)
upsetdata$primates_dginn_full<-ifelse(dginnfulltmp>=3, 1,0)
upset(na.omit(upsetdata), nsets = 3, matrix.color = "#DC267F",
main.bar.color = "#648FFF", sets.bar.color = "#FE6100")
###
upsetdata$primates_dginn_young<-ifelse(dginnyoungtmp>=4, 1,0)
upsetdata$primates_dginn_full<-ifelse(dginnfulltmp>=4, 1,0)
@
upset(na.omit(upsetdata), nsets = 3, matrix.color = "#DC267F",
main.bar.color = "#648FFF", sets.bar.color = "#FE6100")
\section{Gene List}
<<setup, include=FALSE, cache=FALSE, tidy=TRUE>>=
options(tidy=TRUE, width=70)
@
List of the 34 genes found under positive selection in all analysis.
<<>>=
upsetdata$`tab$Gene.name`[(upsetdata$primates_young==TRUE &
upsetdata$primates_dginn_young==TRUE &
upsetdata$primates_dginn_full==TRUE)]
@
\section{Gene List}
Genes under positive selection for at least 4 methods.
List of the 13 genes found under positive selection in both Young analysis and DGINN-Young alignments (but not full-DGINN).
<<>>=
upsetdata$`tab$Gene.name`[(upsetdata$primates_young==TRUE &
upsetdata$primates_dginn_young==TRUE &
upsetdata$primates_dginn_full==FALSE)]
@
List of the 1 gene found under positive selection in both DGINN analysis, but not Young.
<<>>=
upsetdata$`tab$Gene.name`[(upsetdata$primates_young==FALSE &
upsetdata$primates_dginn_young==TRUE &
upsetdata$primates_dginn_full==TRUE)]
@
List of the 8 genes found under positive selection in both Young analysis and full-DGINN, but not DGINN-young.
<<>>=
upsetdata$`tab$Gene.name`[(upsetdata$primates_young==TRUE &
upsetdata$primates_dginn_young==FALSE &
upsetdata$primates_dginn_full==TRUE)]
@
List of the 18 genes found under positive selection ONLY in Young analysis.
<<>>=
upsetdata$`tab$Gene.name`[(upsetdata$primates_young==TRUE &
upsetdata$primates_dginn_young==FALSE &
upsetdata$primates_dginn_full==FALSE)]
@
List of the 1 genes found under positive selection ONLY in DGINN-Young.
<<>>=
upsetdata$`tab$Gene.name`[(upsetdata$primates_young==FALSE &
upsetdata$primates_dginn_young==TRUE &
upsetdata$primates_dginn_full==FALSE)]
@
List of the 44 genes found under positive selection ONLY in full-DGINN.
<<>>=
dginnfulltmp<-rowSums(cbind(tab$'dginn-primate_BUSTED'=="Y",
tab$'dginn-primate_BppM1M2'=="Y",
tab$'dginn-primate_BppM7M8'=="Y",
tab$'dginn-primate_codemlM1M2'=="Y",
tab$'dginn-primate_codemlM7M8'=="Y"))
upsetdata$`tab$Gene.name`[(upsetdata$primates_young==FALSE &
upsetdata$primates_dginn_young==FALSE &
upsetdata$primates_dginn_full==TRUE)]
@
<<echo=FALSE, results="hide">>=
dginnfulltmp<-rowSums(cbind(tab$'dginn.primate_BUSTED'=="Y",
tab$'dginn.primate_BppM1M2'=="Y",
tab$'dginn.primate_BppM7M8'=="Y",
tab$'dginn.primate_codemlM1M2'=="Y",
tab$'dginn.primate_codemlM7M8'=="Y"))
tab$Gene.name[dginnfulltmp>=4 & is.na(dginnfulltmp)==F]
tab$Gene.name[dginnfulltmp>=3 & is.na(dginnfulltmp)==F]
tmp<-tab[dginnfulltmp>=4 & is.na(dginnfulltmp)==F,
c("Gene.name","dginn-primate_BUSTED", "dginn-primate_BppM1M2",
"dginn-primate_BppM7M8","dginn-primate_codemlM1M2","dginn-primate_codemlM7M8")]
c("Gene.name","dginn.primate_BUSTED", "dginn.primate_BppM1M2",
"dginn.primate_BppM7M8","dginn.primate_codemlM1M2","dginn.primate_codemlM7M8")]
write.table(tmp, "geneList_DGINN_full_primate_pos4.txt", row.names=F, quote=F)
@
\section{Shiny like}
<<shiny, fig.height=11>>=
<<shiny, fig.height=11, echo=FALSE, results="hide", fig="hide">>=
makeFig1 <- function(df){
# prepare data for colors etc
......@@ -416,14 +366,11 @@ makeFig1 <- function(df){
)
}
df<-read.delim(paste0(workdir,
"/data/DGINN_202005281649summary_cleaned.csv"),
fill=T, h=T, sep=",")
makeFig1(df)
#makeFig1(df)
@
\end{document}
......
covid_comp_primate-Young-focus.pdf
View file @ 77f559a1
No preview for this file type
covid_comp_primate-Young-focus.tex
View file @ 77f559a1
This diff is collapsed.
covid_comp_primate-Young-focus_backup.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}
\author{Marie Cariou}
\date{October 2020} % Activate to display a given date or no date
\begin{document}
\maketitle
\tableofcontents
\newpage
\section{Files manipulations}
\subsection{Read Janet Young's table}
<<>>=
workdir<-"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"
tab<-read.delim(paste0(workdir,
"data/COVID_PAMLresults_332hits_plusBatScreens_2020_Apr14.csv"),
fill=T, h=T, dec=",")
dim(tab)
#names(tab)
@
\subsection{Read DGINN Young table}
DGINN-Young-primate table correspond to DGINN results, on the SAME alignment as Young-primate.
I will merge the 2 tables.
<<>>=
dginnY<-read.delim(paste0(workdir,
"data/summary_primate_young.res"),
fill=T, h=T)
dim(dginnY)
names(dginnY)
@
\subsection{Joining Young and DGINN Young table}
\textit{I hide some code corresponding to verifications of gene names coherence between tables}
<<results="hide", echo=FALSE>>=
head(tab)[,1:5]
# gene avec un nom bizar dans certaines colomne
tab[158,1:10]
#
length(unique(dginnY$Gene))
length(unique(tab$PreyGene))
length(unique(tab$Gene.name))
#quelle paire de colonne contient le plus de noms identiques
sum(unique(dginnY$Gene) %in% unique(tab$PreyGene))
sum(unique(dginnY$Gene) %in% unique(tab$Gene.name))
# dginn$Gene et tab$Gene.name presque identiques sauf 1 ligne.
# Je soupçonne que c'est celle là:
tab[158,1:10]
# Verif:
tab[,1:10][(tab$Gene.name %in% unique(dginnY$Gene))==F,]
# yep
# Remplacement manuel par
as.character(unique(dginnY$Gene)[(unique(dginnY$Gene) %in% tab$Gene.name)==F])
# dans le tableau de Janet
val_remp=as.character(unique(dginnY$Gene)[(unique(dginnY$Gene) %in% tab$Gene.name)==F])
tab$Gene.name<-as.character(tab$Gene.name)
tab$Gene.name[158]<-val_remp
sum(unique(dginnY$Gene) %in% unique(tab$Gene.name))
@
<<>>=
add_col<-function(method="PamlM1M2"){
tmp<-dginnY[dginnY$Method==method,
c("Gene", "Omega", "PosSel", "PValue", "NbSites", "PSS")]
names(tmp)<-c("Gene.name", paste0("Omega_", method),
paste0("PosSel_", method), paste0("PValue_", method),
paste0("NbSites_", method), paste0("PSS_", method))
tab<-merge(tab, tmp, by="Gene.name")
return(tab)
}
tab<-add_col("PamlM1M2")
tab<-add_col("PamlM7M8")
tab<-add_col("BppM1M2")
tab<-add_col("BppM7M8")
# Manip pour la colonne BUSTED
tmp<-dginnY[dginnY$Method=="BUSTED",c("Gene", "Omega", "PosSel", "PValue")]
names(tmp)<-c("Gene.name", "Omega_BUSTED", "PosSel_BUSTED", "PValue_BUSTED")
tab<-merge(tab, tmp, by="Gene.name")
tmp<-dginnY[dginnY$Method=="MEME",c("Gene", "NbSites", "PSS")]
names(tmp)<-c("Gene.name", "NbSites_MEME", "PSS_MEME")
tab<-merge(tab, tmp, by="Gene.name")
@
\subsection{Read DGINN Table}
<<>>=
dginnT<-read.delim(paste0(workdir,
"/data/DGINN_202005281649summary_cleaned.csv"),
fill=T, h=T, sep=",")
dim(dginnT)
names(dginnT)
# Number of genes in dginn-primate output not present in the original table
dginnT[(dginnT$Gene %in% tab$Gene.name)==F,"Gene"]
# This includes paralogs, recombinations found by DGINN
# and additionnal genes included on purpose
# Number of genes from the original list not present in DGINN output
tab[(tab$Gene.name %in% dginnT$Gene)==F,"Gene.name"]
names(dginnT)<-c("File", "Name", "Gene.name", "GeneSize", "dginn-primate_NbSpecies", "dginn-primate_omegaM0Bpp",
"dginn-primate_omegaM0codeml", "dginn-primate_BUSTED", "dginn-primate_BUSTED.p.value",
"dginn-primate_MEME.NbSites", "dginn-primate_MEME.PSS", "dginn-primate_BppM1M2",
"dginn-primate_BppM1M2.p.value", "dginn-primate_BppM1M2.NbSites", "dginn-primate_BppM1M2.PSS",
"dginn-primate_BppM7M8", "dginn-primate_BppM7M8.p.value", "dginn-primate_BppM7M8.NbSites",
"dginn-primate_BppM7M8.PSS", "dginn-primate_codemlM1M2", "dginn-primate_codemlM1M2.p.value",
"dginn-primate_codemlM1M2.NbSites", "dginn-primate_codemlM1M2.PSS", "dginn-primate_codemlM7M8",
"dginn-primate_codemlM7M8.p.value", "dginn-primate_codemlM7M8.NbSites", "dginn-primate_codemlM7M8.PSS")
@
\subsection{Join Table and DGINN table}
<<>>=
tab<-merge(tab,dginnT, by="Gene.name", all.x=T)
@
\subsection{Write new table}
<<>>=
write.table(tab,
"COVID_PAMLresults_332hits_plusBatScreens_plusDGINN_20201014.txt",
row.names=F, quote=F, sep="\t")
@
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\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>>=
plot(tab$whole.gene.dN.dS.model.0, tab$Omega_PamlM7M8,
xlab="Omega Young-primate", ylab="Omega DGINN-Young-primate")
abline(0,1)
outlier<-tab[tab$whole.gene.dN.dS.model.0<0.2 & tab$Omega_PamlM7M8>0.4,]
text(x=outlier$whole.gene.dN.dS.model.0,
y=(outlier$Omega_PamlM7M8+0.01),
outlier$Gene.name)
outlier<-tab[tab$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'))
plot(tab$'dginn-primate_omegaM0Bpp', tab$Omega_PamlM7M8,
xlab="DGINN-full's", ylab="Omega DGINN-Young-primate")
abline(0,1)
outlier<-tab[tab$'dginn-primate_omegaM0Bpp'>0.4 & tab$Omega_PamlM7M8<0.2,]
text(x=outlier$'dginn-primate_omegaM0Bpp',
y=(outlier$Omega_PamlM7M8+0.01),
outlier$Gene.name)
outlier<-tab[tab$'dginn-primate_omegaM0Bpp'>0.5 & tab$Omega_PamlM7M8<0.4,]
text(x=outlier$'dginn-primate_omegaM0Bpp',
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')),
xlab="Omega Young-primate", ylab="DGINN-full's")
abline(0,1)
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$Gene.name)
@
\section{Overlap}
\subsection{Mondrian}
<<mondrianprimates>>=
library(Mondrian)
#######
monddata<-as.data.frame(tab$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"))
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" ))
#####
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"))
@
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")
@
\subsection{subsetR}
Just another representation of the same result.
<<subsetprimates>>=
library(UpSetR)
upsetdata<-as.data.frame(tab$Gene.name)
upsetdata$primates_young<-ifelse(tab$pVal.M8vsM7<0.05, 1, 0)
###
upsetdata$primates_dginn_young<-ifelse(dginnyoungtmp>=3, 1,0)
upsetdata$primates_dginn_full<-ifelse(dginnfulltmp>=3, 1,0)
upset(na.omit(upsetdata), nsets = 3, matrix.color = "#DC267F",
main.bar.color = "#648FFF", sets.bar.color = "#FE6100")
###
upsetdata$primates_dginn_young<-ifelse(dginnyoungtmp>=4, 1,0)
upsetdata$primates_dginn_full<-ifelse(dginnfulltmp>=4, 1,0)
upset(na.omit(upsetdata), nsets = 3, matrix.color = "#DC267F",
main.bar.color = "#648FFF", sets.bar.color = "#FE6100")
@
\section{Gene List}
Genes under positive selection for at least 4 methods.
<<>>=
dginnfulltmp<-rowSums(cbind(tab$'dginn-primate_BUSTED'=="Y",
tab$'dginn-primate_BppM1M2'=="Y",
tab$'dginn-primate_BppM7M8'=="Y",
tab$'dginn-primate_codemlM1M2'=="Y",
tab$'dginn-primate_codemlM7M8'=="Y"))
tab$Gene.name[dginnfulltmp>=4 & is.na(dginnfulltmp)==F]
tab$Gene.name[dginnfulltmp>=3 & is.na(dginnfulltmp)==F]
tmp<-tab[dginnfulltmp>=4 & is.na(dginnfulltmp)==F,
c("Gene.name","dginn-primate_BUSTED", "dginn-primate_BppM1M2",
"dginn-primate_BppM7M8","dginn-primate_codemlM1M2","dginn-primate_codemlM7M8")]
write.table(tmp, "geneList_DGINN_full_primate_pos4.txt", row.names=F, quote=F)
@
\section{Shiny like}
<<shiny, fig.height=11>>=
makeFig1 <- function(df){
# prepare data for colors etc
colMethods <- c("deepskyblue4", "darkorange" , "deepskyblue3" , "mediumseagreen" , "yellow3" , "black")
nameMethods <- c("BUSTED", "BppM1M2", "BppM7M8", "codemlM1M2", "codemlM7M8", "MEME")
metColor <- data.frame(Name = nameMethods , Col = colMethods , stringsAsFactors = FALSE)
# subset for this specific figure
#df <- df[df$nbY >= 1, ] # to drop genes found by 0 methods (big datasets)
xt <- df[, c("BUSTED", "BppM1M2", "BppM7M8", "codemlM1M2", "codemlM7M8")]
xt$Gene <- df$Gene
nbrMeth <- 5
# reverse order of dataframe so that genes with the most Y are at the bottom (to be on top of the barplot)
xt[,1:5] <- ifelse(xt[,1:5] == "Y", 1, 0)
# sort and Filter the 0 lines
xt<-xt[order(rowSums(xt[,1:5])),]
xt<-xt[rowSums(xt[,1:5])>2,]
row.names(xt)<-xt$Gene
xt<-xt[,1:5]
colFig1 <- metColor[which(metColor$Name %in% colnames(xt)) , ]
##### PART 1 : NUMBER OF METHODS
par(xpd = NA , mar=c(2,7,4,0) , oma = c(0,0,0,0) , mgp = c(3,0.3,0))
h = barplot(
t(xt),
border = NA ,
axes = F ,
col = adjustcolor(colFig1$Col, alpha.f = 1),
horiz = T ,
las = 2 ,
main = "Methods detecting positive selection" ,
cex.main = 0.85,
cex.names = min(50/nrow(xt), 1.5)
)
axis(3, line = 0, at = c(0:nbrMeth), label = c("0", rep("", nbrMeth -1), nbrMeth), tck = 0.02)
legend("bottomleft",
horiz = T,
border = colFig1$Col,
legend = colFig1$Name,
fill = colFig1$Col,
cex = 0.8,
bty = "n",
xpd = NA
)
}
df<-read.delim(paste0(workdir,
"/data/DGINN_202005281649summary_cleaned.csv"),
fill=T, h=T, sep=",")
makeFig1(df)
@
\end{document}
covid_comp_primate-Young-focus_backup.pdf 0 → 100644
View file @ 77f559a1
File added
covid_comp_primate-Young-focus_backup.tex 0 → 100644
View file @ 77f559a1
This diff is collapsed.
covid_comp_primate.Rnw
View file @ 77f559a1
......@@ -30,108 +30,166 @@
Analysis were formatted by the script covid\_comp\_script0\_table.Rnw.
<<>>=
workdir<-"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"
home<-"/home/adminmarie/Documents/"
workdir<-paste0(home, "CIRI_BIBS_projects/2020_05_Etienne_covid/")
tab<-read.delim(paste0(workdir,
"covid_comp/covid_comp_complete.txt"), h=T, sep="\t")
dim(tab)
tab$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)
......