diff --git a/covid_comp_dataset.Rnw b/covid_comp_dataset.Rnw new file mode 100644 index 0000000000000000000000000000000000000000..bc6395ba8e8e242e9e2f436631ba3ec0837d688c --- /dev/null +++ b/covid_comp_dataset.Rnw @@ -0,0 +1,199 @@ +\documentclass[11pt, oneside]{article} % use "amsart" instead of "article" for AMSLaTeX format +%\usepackage{geometry} % See geometry.pdf to learn the layout options. There are lots. +%\geometry{letterpaper} % ... or a4paper or a5paper or ... +%\geometry{landscape} % Activate for for rotated page geometry +%\usepackage[parfill]{parskip} % Activate to begin paragraphs with an empty line rather than an indent +%\usepackage{graphicx} % Use pdf, png, jpg, or eps with pdflatex; use eps in DVI mode + % TeX will automatically convert eps --> pdf in pdflatex +%\usepackage{amssymb} + +\usepackage[utf8]{inputenc} +%\usepackage[cyr]{aeguill} +%\usepackage[francais]{babel} +%\usepackage{hyperref} + + +\title{Positive selection on genes interacting with SARS-Cov2, comparison of different analysis} +\author{Marie Cariou} +\date{Janvier 2021} % Activate to display a given date or no date + +\begin{document} +\maketitle + +\tableofcontents + +\newpage + +\section{Data} + +Analysis were formatted by the script covid\_comp\_script0\_table.Rnw. + + +<<>>= +workdir<-"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/" + +tab<-read.delim(paste0(workdir, + "covid_comp/covid_comp_complete.txt"), h=T, sep="\t") +dim(tab) +@ + + +\section{Comparison of dataset} + +\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")]) +dim(tmp) +@ +\subsection{Mondrian} + +<<mondrianbats>>= +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.primat_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$primate_dginn4<-ifelse(primatetmp>=4, 1,0) + +mondrian(monddata[,2:3], labels=c("DGINN bats >3", "DGINN primate >3")) + +mondrian(monddata[,4:5], labels=c("DGINN bats >4", "DGINN primate >4")) + +@ + +\subsection{subsetR} + +<<subsetbats>>= +library(UpSetR) + +upset(monddata, nsets = 4, matrix.color = "#DC267F", +main.bar.color = "#648FFF", sets.bar.color = "#FE6100") + +upset(monddata[,1:3], nsets = 2, matrix.color = "#DC267F", +main.bar.color = "#648FFF", sets.bar.color = "#FE6100") + +upset(monddata[,c(1,4,5)], nsets = 2, matrix.color = "#DC267F", +main.bar.color = "#648FFF", sets.bar.color = "#FE6100") +@ + +\section{Which are these genes?} + +\subsection{Gene under positive selection in both bats and primates} + +4 methods: + +<<>>= +monddata[monddata$bats_dginn4==1 & monddata$primate_dginn4==1,] +@ + +3 methods: + +<<>>= +monddata[monddata$bats_dginn3==1 & monddata$primate_dginn3==1,] +@ + + +\subsection{Gene under positive selection only in primates} + +4 methods: + +<<>>= +monddata[monddata$bats_dginn4==0 & monddata$primate_dginn4==1,] +@ + +3 methods: + +<<t>>= +monddata[monddata$bats_dginn3==0 & monddata$primate_dginn3==1,] +@ + + +\subsection{Gene under positive selection only in bats} + +4 methods: + +<<>>= +monddata[monddata$bats_dginn4==1 & monddata$primate_dginn4==0,] +@ + +3 methods: + +<<>>= +monddata[monddata$bats_dginn3==1 & monddata$primate_dginn3==0,] +@ + +\subsection{Figure tableau} + +<<tablo>>= +tablo<-as.data.frame(tmp$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") + +text(x=rep(-0.6, 6), y=0:5, 0:5) +text(y=rep(-0.65, 6), x=0:5, 0:5) +sapply(seq(from=-0.5, to=5.5, by=1), function(x){ + segments(x0=x, x1=x, y0=-0.5, y1=5.5) +}) + +sapply(seq(from=-0.5, to=5.5, by=1), function(x){ + segments(x0=-0.5, x1=5.5, y0=x, y1=x) +}) + +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) + }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) + }else if (length(tmp)>16){ + text(b,p, paste0(length(tmp), " values")) + } + } +} + + +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=3, length.out = length(tmp)-18),-1.3, tmp[19: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=2, 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] +text(-0.4,-2.2, "p=0/n=0", cex=0.6) +text(seq(from=0.1, to=5.5, length.out = 17),-2.1, tmp[1:17], cex=0.4) +text(seq(from=0.1, to=4.4, length.out = length(tmp)-17),-2.3, tmp[18:length(tmp)], cex=0.4) + +tmp<-tablo$`tmp$Gene.name`[tablo$nbats==2 & tablo$nprimates==0] +text(-0.4,-2.7, "p=0/n=2", cex=0.6) +text(seq(from=0.1, to=5.5, length.out = 18),-2.6, tmp[1:18], cex=0.4) +text(seq(from=0.1, to=1, length.out = length(tmp)-18),-2.8, tmp[19:length(tmp)], cex=0.4) + + + +@ + +\end{document} + diff --git a/covid_comp_dataset.pdf b/covid_comp_dataset.pdf new file mode 100644 index 0000000000000000000000000000000000000000..922d30e3b054eaa7f607931e6ffc2f352e90fe11 Binary files /dev/null and b/covid_comp_dataset.pdf differ diff --git a/covid_comp_dataset.tex b/covid_comp_dataset.tex new file mode 100644 index 0000000000000000000000000000000000000000..a64505b5f74343baae9d22fb7c655cb75b68704c --- /dev/null +++ b/covid_comp_dataset.tex @@ -0,0 +1,454 @@ +\documentclass[11pt, oneside]{article}\usepackage[]{graphicx}\usepackage[]{color} +% maxwidth is the original width if it is less than linewidth +% otherwise use linewidth (to make sure the graphics do not exceed the margin) +\makeatletter +\def\maxwidth{ % + \ifdim\Gin@nat@width>\linewidth + \linewidth + \else + \Gin@nat@width + \fi +} +\makeatother + +\definecolor{fgcolor}{rgb}{0.345, 0.345, 0.345} +\newcommand{\hlnum}[1]{\textcolor[rgb]{0.686,0.059,0.569}{#1}}% +\newcommand{\hlstr}[1]{\textcolor[rgb]{0.192,0.494,0.8}{#1}}% +\newcommand{\hlcom}[1]{\textcolor[rgb]{0.678,0.584,0.686}{\textit{#1}}}% +\newcommand{\hlopt}[1]{\textcolor[rgb]{0,0,0}{#1}}% +\newcommand{\hlstd}[1]{\textcolor[rgb]{0.345,0.345,0.345}{#1}}% +\newcommand{\hlkwa}[1]{\textcolor[rgb]{0.161,0.373,0.58}{\textbf{#1}}}% +\newcommand{\hlkwb}[1]{\textcolor[rgb]{0.69,0.353,0.396}{#1}}% +\newcommand{\hlkwc}[1]{\textcolor[rgb]{0.333,0.667,0.333}{#1}}% +\newcommand{\hlkwd}[1]{\textcolor[rgb]{0.737,0.353,0.396}{\textbf{#1}}}% +\let\hlipl\hlkwb + +\usepackage{framed} +\makeatletter +\newenvironment{kframe}{% + \def\at@end@of@kframe{}% + \ifinner\ifhmode% + \def\at@end@of@kframe{\end{minipage}}% + \begin{minipage}{\columnwidth}% + \fi\fi% + \def\FrameCommand##1{\hskip\@totalleftmargin \hskip-\fboxsep + \colorbox{shadecolor}{##1}\hskip-\fboxsep + % There is no \\@totalrightmargin, so: + \hskip-\linewidth \hskip-\@totalleftmargin \hskip\columnwidth}% + \MakeFramed {\advance\hsize-\width + \@totalleftmargin\z@ \linewidth\hsize + \@setminipage}}% + {\par\unskip\endMakeFramed% + \at@end@of@kframe} +\makeatother + +\definecolor{shadecolor}{rgb}{.97, .97, .97} +\definecolor{messagecolor}{rgb}{0, 0, 0} +\definecolor{warningcolor}{rgb}{1, 0, 1} +\definecolor{errorcolor}{rgb}{1, 0, 0} +\newenvironment{knitrout}{}{} % an empty environment to be redefined in TeX + +\usepackage{alltt} % use "amsart" instead of "article" for AMSLaTeX format +%\usepackage{geometry} % See geometry.pdf to learn the layout options. There are lots. +%\geometry{letterpaper} % ... or a4paper or a5paper or ... +%\geometry{landscape} % Activate for for rotated page geometry +%\usepackage[parfill]{parskip} % Activate to begin paragraphs with an empty line rather than an indent +%\usepackage{graphicx} % Use pdf, png, jpg, or eps with pdflatex; use eps in DVI mode + % TeX will automatically convert eps --> pdf in pdflatex +%\usepackage{amssymb} + +\usepackage[utf8]{inputenc} +%\usepackage[cyr]{aeguill} +%\usepackage[francais]{babel} +%\usepackage{hyperref} + + +\title{Positive selection on genes interacting with SARS-Cov2, comparison of different analysis} +\author{Marie Cariou} +\date{Janvier 2021} % Activate to display a given date or no date +\IfFileExists{upquote.sty}{\usepackage{upquote}}{} +\begin{document} +\maketitle + +\tableofcontents + +\newpage + +\section{Data} + +Analysis were formatted by the script covid\_comp\_script0\_table.Rnw. + + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlstd{workdir}\hlkwb{<-}\hlstr{"/home/adminmarie/Documents/CIRI_BIBS_projects/2020_05_Etienne_covid/"} + +\hlstd{tab}\hlkwb{<-}\hlkwd{read.delim}\hlstd{(}\hlkwd{paste0}\hlstd{(workdir,} + \hlstr{"covid_comp/covid_comp_complete.txt"}\hlstd{),} \hlkwc{h}\hlstd{=T,} \hlkwc{sep}\hlstd{=}\hlstr{"\textbackslash{}t"}\hlstd{)} +\hlkwd{dim}\hlstd{(tab)} +\end{alltt} +\begin{verbatim} +## [1] 333 161 +\end{verbatim} +\end{kframe} +\end{knitrout} + + +\section{Comparison of dataset} + +\subsection{Data} + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlstd{tmp}\hlkwb{<-}\hlkwd{na.omit}\hlstd{(tab[,}\hlkwd{c}\hlstd{(}\hlstr{"Gene.name"}\hlstd{,} \hlstr{"bats_BUSTED"}\hlstd{,} \hlstr{"bats_BppM1M2"}\hlstd{,} \hlstr{"bats_BppM7M8"}\hlstd{,} + \hlstr{"bats_codemlM1M2"}\hlstd{,} \hlstr{"bats_codemlM7M8"}\hlstd{,} \hlstr{"dginn.primate_codemlM1M2"}\hlstd{,} + \hlstr{"dginn.primate_codemlM7M8"}\hlstd{,} \hlstr{"dginn.primate_BppM1M2"}\hlstd{,} + \hlstr{"dginn.primate_BppM7M8"}\hlstd{,} \hlstr{"dginn.primate_BUSTED"}\hlstd{)])} +\hlkwd{dim}\hlstd{(tmp)} +\end{alltt} +\begin{verbatim} +## [1] 206 11 +\end{verbatim} +\end{kframe} +\end{knitrout} +\subsection{Mondrian} + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlkwd{library}\hlstd{(Mondrian)} + +\hlstd{monddata}\hlkwb{<-}\hlkwd{as.data.frame}\hlstd{(tmp}\hlopt{$}\hlstd{Gene.name)} + +\hlstd{batstmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tmp}\hlopt{$}\hlstd{bats_codemlM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{, tmp}\hlopt{$}\hlstd{bats_codemlM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{,} +\hlstd{tmp}\hlopt{$}\hlstd{bats_BppM1M2}\hlopt{==}\hlstr{"Y"}\hlstd{, tmp}\hlopt{$}\hlstd{bats_BppM7M8}\hlopt{==}\hlstr{"Y"}\hlstd{, tmp}\hlopt{$}\hlstd{bats_BUSTED}\hlopt{==}\hlstr{"Y"}\hlstd{))} + +\hlstd{primatetmp}\hlkwb{<-}\hlkwd{rowSums}\hlstd{(}\hlkwd{cbind}\hlstd{(tmp}\hlopt{$}\hlstr{"dginn.primate_codemlM1M2"}\hlopt{==}\hlstr{"Y"}\hlstd{,} + \hlstd{tmp}\hlopt{$}\hlstr{"dginn.primat_codemlM7M8"}\hlopt{==}\hlstr{"Y"}\hlstd{, tmp}\hlopt{$}\hlstr{"dginn.primate_BppM1M2"}\hlopt{==}\hlstr{"Y"}\hlstd{,} + \hlstd{tmp}\hlopt{$}\hlstr{"dginn.primate_BppM7M8"}\hlopt{==}\hlstr{"Y"}\hlstd{, tmp}\hlopt{$}\hlstr{"dginn.primate_BUSTED"}\hlopt{==}\hlstr{"Y"}\hlstd{))} + +\hlstd{monddata}\hlopt{$}\hlstd{bats_dginn3}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(batstmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)} +\hlstd{monddata}\hlopt{$}\hlstd{primate_dginn3}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(primatetmp}\hlopt{>=}\hlnum{3}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)} +\hlstd{monddata}\hlopt{$}\hlstd{bats_dginn4}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(batstmp}\hlopt{>=}\hlnum{4}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)} +\hlstd{monddata}\hlopt{$}\hlstd{primate_dginn4}\hlkwb{<-}\hlkwd{ifelse}\hlstd{(primatetmp}\hlopt{>=}\hlnum{4}\hlstd{,} \hlnum{1}\hlstd{,}\hlnum{0}\hlstd{)} + +\hlkwd{mondrian}\hlstd{(monddata[,}\hlnum{2}\hlopt{:}\hlnum{3}\hlstd{],} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"DGINN bats >3"}\hlstd{,} \hlstr{"DGINN primate >3"}\hlstd{))} +\end{alltt} +\end{kframe} +\includegraphics[width=\maxwidth]{figure/mondrianbats-1} +\begin{kframe}\begin{alltt} +\hlkwd{mondrian}\hlstd{(monddata[,}\hlnum{4}\hlopt{:}\hlnum{5}\hlstd{],} \hlkwc{labels}\hlstd{=}\hlkwd{c}\hlstd{(}\hlstr{"DGINN bats >4"}\hlstd{,} \hlstr{"DGINN primate >4"}\hlstd{))} +\end{alltt} +\end{kframe} +\includegraphics[width=\maxwidth]{figure/mondrianbats-2} + +\end{knitrout} + +\subsection{subsetR} + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlkwd{library}\hlstd{(UpSetR)} + +\hlkwd{upset}\hlstd{(monddata,} \hlkwc{nsets} \hlstd{=} \hlnum{4}\hlstd{,} \hlkwc{matrix.color} \hlstd{=} \hlstr{"#DC267F"}\hlstd{,} +\hlkwc{main.bar.color} \hlstd{=} \hlstr{"#648FFF"}\hlstd{,} \hlkwc{sets.bar.color} \hlstd{=} \hlstr{"#FE6100"}\hlstd{)} +\end{alltt} +\end{kframe} +\includegraphics[width=\maxwidth]{figure/subsetbats-1} +\begin{kframe}\begin{alltt} +\hlkwd{upset}\hlstd{(monddata[,}\hlnum{1}\hlopt{:}\hlnum{3}\hlstd{],} \hlkwc{nsets} \hlstd{=} \hlnum{2}\hlstd{,} \hlkwc{matrix.color} \hlstd{=} \hlstr{"#DC267F"}\hlstd{,} +\hlkwc{main.bar.color} \hlstd{=} \hlstr{"#648FFF"}\hlstd{,} \hlkwc{sets.bar.color} \hlstd{=} \hlstr{"#FE6100"}\hlstd{)} +\end{alltt} +\end{kframe} +\includegraphics[width=\maxwidth]{figure/subsetbats-2} +\begin{kframe}\begin{alltt} +\hlkwd{upset}\hlstd{(monddata[,}\hlkwd{c}\hlstd{(}\hlnum{1}\hlstd{,}\hlnum{4}\hlstd{,}\hlnum{5}\hlstd{)],} \hlkwc{nsets} \hlstd{=} \hlnum{2}\hlstd{,} \hlkwc{matrix.color} \hlstd{=} \hlstr{"#DC267F"}\hlstd{,} +\hlkwc{main.bar.color} \hlstd{=} \hlstr{"#648FFF"}\hlstd{,} \hlkwc{sets.bar.color} \hlstd{=} \hlstr{"#FE6100"}\hlstd{)} +\end{alltt} +\end{kframe} +\includegraphics[width=\maxwidth]{figure/subsetbats-3} + +\end{knitrout} + +\section{Which are these genes?} + +\subsection{Gene under positive selection in both bats and primates} + +4 methods: + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn4}\hlopt{==}\hlnum{1} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn4}\hlopt{==}\hlnum{1}\hlstd{,]} +\end{alltt} +\begin{verbatim} +## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4 +## 4 ACADM 1 1 1 1 +## 73 GGH 1 1 1 1 +## 78 GOLGA7 1 1 1 1 +## 89 IDE 1 1 1 1 +## 94 ITGB1 1 1 1 1 +## 132 POLA1 1 1 1 1 +## 188 TOR1AIP1 1 1 1 1 +## 201 VPS39 1 1 1 1 +\end{verbatim} +\end{kframe} +\end{knitrout} + +3 methods: + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn3}\hlopt{==}\hlnum{1} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn3}\hlopt{==}\hlnum{1}\hlstd{,]} +\end{alltt} +\begin{verbatim} +## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4 +## 4 ACADM 1 1 1 1 +## 20 CDK5RAP2 1 1 0 1 +## 48 EDEM3 1 1 1 0 +## 73 GGH 1 1 1 1 +## 78 GOLGA7 1 1 1 1 +## 89 IDE 1 1 1 1 +## 94 ITGB1 1 1 1 1 +## 97 LMAN2 1 1 1 0 +## 132 POLA1 1 1 1 1 +## 164 SLC27A2 1 1 1 0 +## 188 TOR1AIP1 1 1 1 1 +## 201 VPS39 1 1 1 1 +\end{verbatim} +\end{kframe} +\end{knitrout} + + +\subsection{Gene under positive selection only in primates} + +4 methods: + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn4}\hlopt{==}\hlnum{0} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn4}\hlopt{==}\hlnum{1}\hlstd{,]} +\end{alltt} +\begin{verbatim} +## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4 +## 20 CDK5RAP2 1 1 0 1 +## 26 CEP68 0 1 0 1 +## 50 EMC1 0 1 0 1 +## 68 FYCO1 0 1 0 1 +## 83 HECTD1 0 1 0 1 +## 108 MYCBP2 0 1 0 1 +## 160 SEPSECS 0 1 0 1 +## 204 ZNF318 0 1 0 1 +\end{verbatim} +\end{kframe} +\end{knitrout} + +3 methods: + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn3}\hlopt{==}\hlnum{0} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn3}\hlopt{==}\hlnum{1}\hlstd{,]} +\end{alltt} +\begin{verbatim} +## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4 +## 23 CEP135 0 1 0 0 +## 26 CEP68 0 1 0 1 +## 32 CLIP4 0 1 0 0 +## 33 CNTRL 0 1 0 0 +## 45 DPH5 0 1 0 0 +## 50 EMC1 0 1 0 1 +## 68 FYCO1 0 1 0 1 +## 74 GIGYF2 0 1 0 0 +## 75 GLA 0 1 0 0 +## 79 GOLGB1 0 1 0 0 +## 83 HECTD1 0 1 0 1 +## 95 LARP1 0 1 0 0 +## 108 MYCBP2 0 1 0 1 +## 111 NDUFB9 0 1 0 0 +## 138 PRKAR2A 0 1 0 0 +## 153 RIPK1 0 1 0 0 +## 156 SAAL1 0 1 0 0 +## 160 SEPSECS 0 1 0 1 +## 162 SIRT5 0 1 0 0 +## 163 SLC25A21 0 1 0 0 +## 185 TMEM39B 0 1 0 0 +## 191 TUBGCP2 0 1 0 0 +## 194 UBAP2 0 1 0 0 +## 197 UGGT2 0 1 0 0 +## 199 USP54 0 1 0 0 +## 204 ZNF318 0 1 0 1 +\end{verbatim} +\end{kframe} +\end{knitrout} + + +\subsection{Gene under positive selection only in bats} + +4 methods: + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn4}\hlopt{==}\hlnum{1} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn4}\hlopt{==}\hlnum{0}\hlstd{,]} +\end{alltt} +\begin{verbatim} +## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4 +## 48 EDEM3 1 1 1 0 +## 52 ERGIC1 1 0 1 0 +## 91 IMPDH2 1 0 1 0 +## 92 INHBE 1 0 1 0 +## 97 LMAN2 1 1 1 0 +## 164 SLC27A2 1 1 1 0 +## 166 SLC44A2 1 0 1 0 +## 177 TBK1 1 0 1 0 +\end{verbatim} +\end{kframe} +\end{knitrout} + +3 methods: + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlstd{monddata[monddata}\hlopt{$}\hlstd{bats_dginn3}\hlopt{==}\hlnum{1} \hlopt{&} \hlstd{monddata}\hlopt{$}\hlstd{primate_dginn3}\hlopt{==}\hlnum{0}\hlstd{,]} +\end{alltt} +\begin{verbatim} +## tmp$Gene.name bats_dginn3 primate_dginn3 bats_dginn4 primate_dginn4 +## 7 AGPS 1 0 0 0 +## 52 ERGIC1 1 0 1 0 +## 81 GRIPAP1 1 0 0 0 +## 82 GRPEL1 1 0 0 0 +## 91 IMPDH2 1 0 1 0 +## 92 INHBE 1 0 1 0 +## 104 MOV10 1 0 0 0 +## 120 NUP214 1 0 0 0 +## 136 PRIM1 1 0 0 0 +## 165 SLC30A9 1 0 0 0 +## 166 SLC44A2 1 0 1 0 +## 177 TBK1 1 0 1 0 +\end{verbatim} +\end{kframe} +\end{knitrout} + +\subsection{Figure tableau} + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlstd{tablo}\hlkwb{<-}\hlkwd{as.data.frame}\hlstd{(tmp}\hlopt{$}\hlstd{Gene.name)} +\hlstd{tablo}\hlopt{$}\hlstd{nbats}\hlkwb{<-}\hlstd{batstmp} +\hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlkwb{<-}\hlstd{primatetmp} + +\hlkwd{plot}\hlstd{(}\hlkwa{NULL}\hlstd{,} \hlkwc{xlim}\hlstd{=}\hlkwd{c}\hlstd{(}\hlopt{-}\hlnum{0.5}\hlstd{,}\hlnum{5.5}\hlstd{),} \hlkwc{ylim}\hlstd{=}\hlkwd{c}\hlstd{(}\hlopt{-}\hlnum{3}\hlstd{,}\hlnum{5.5}\hlstd{),} \hlkwc{xlab}\hlstd{=}\hlstr{"bats"}\hlstd{,} \hlkwc{ylab}\hlstd{=}\hlstr{"primates"}\hlstd{,} \hlkwc{main}\hlstd{=}\hlstr{"Genes supported by x,y methods in bats and primates"}\hlstd{,} \hlkwc{bty}\hlstd{=}\hlstr{"n"}\hlstd{,} \hlkwc{xaxt}\hlstd{=}\hlstr{"n"}\hlstd{,} \hlkwc{yaxt}\hlstd{=}\hlstr{"n"}\hlstd{)} + +\hlkwd{text}\hlstd{(}\hlkwc{x}\hlstd{=}\hlkwd{rep}\hlstd{(}\hlopt{-}\hlnum{0.6}\hlstd{,} \hlnum{6}\hlstd{),} \hlkwc{y}\hlstd{=}\hlnum{0}\hlopt{:}\hlnum{5}\hlstd{,} \hlnum{0}\hlopt{:}\hlnum{5}\hlstd{)} +\hlkwd{text}\hlstd{(}\hlkwc{y}\hlstd{=}\hlkwd{rep}\hlstd{(}\hlopt{-}\hlnum{0.65}\hlstd{,} \hlnum{6}\hlstd{),} \hlkwc{x}\hlstd{=}\hlnum{0}\hlopt{:}\hlnum{5}\hlstd{,} \hlnum{0}\hlopt{:}\hlnum{5}\hlstd{)} +\hlkwd{sapply}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlopt{-}\hlnum{0.5}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{by}\hlstd{=}\hlnum{1}\hlstd{),} \hlkwa{function}\hlstd{(}\hlkwc{x}\hlstd{)\{} + \hlkwd{segments}\hlstd{(}\hlkwc{x0}\hlstd{=x,} \hlkwc{x1}\hlstd{=x,} \hlkwc{y0}\hlstd{=}\hlopt{-}\hlnum{0.5}\hlstd{,} \hlkwc{y1}\hlstd{=}\hlnum{5.5}\hlstd{)} +\hlstd{\})} +\end{alltt} +\begin{verbatim} +## [[1]] +## NULL +## +## [[2]] +## NULL +## +## [[3]] +## NULL +## +## [[4]] +## NULL +## +## [[5]] +## NULL +## +## [[6]] +## NULL +## +## [[7]] +## NULL +\end{verbatim} +\begin{alltt} +\hlkwd{sapply}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlopt{-}\hlnum{0.5}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{by}\hlstd{=}\hlnum{1}\hlstd{),} \hlkwa{function}\hlstd{(}\hlkwc{x}\hlstd{)\{} + \hlkwd{segments}\hlstd{(}\hlkwc{x0}\hlstd{=}\hlopt{-}\hlnum{0.5}\hlstd{,} \hlkwc{x1}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{y0}\hlstd{=x,} \hlkwc{y1}\hlstd{=x)} +\hlstd{\})} +\end{alltt} +\begin{verbatim} +## [[1]] +## NULL +## +## [[2]] +## NULL +## +## [[3]] +## NULL +## +## [[4]] +## NULL +## +## [[5]] +## NULL +## +## [[6]] +## NULL +## +## [[7]] +## NULL +\end{verbatim} +\begin{alltt} +\hlkwa{for} \hlstd{(p} \hlkwa{in} \hlnum{0}\hlopt{:}\hlnum{5}\hlstd{)\{} + \hlkwa{for} \hlstd{(b} \hlkwa{in} \hlnum{0}\hlopt{:}\hlnum{5}\hlstd{)\{} + \hlstd{tmp}\hlkwb{<-}\hlstd{tablo}\hlopt{$}\hlstd{`tmp$Gene.name`[tablo}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlstd{b} \hlopt{&} \hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlstd{p]} + \hlkwa{if}\hlstd{(}\hlkwd{length}\hlstd{(tmp)}\hlopt{>}\hlnum{0} \hlopt{&} \hlkwd{length}\hlstd{(tmp)}\hlopt{<}\hlnum{8}\hlstd{)\{} + \hlkwd{text}\hlstd{(b,}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=(p}\hlopt{-}\hlnum{0.4}\hlstd{),} \hlkwc{to}\hlstd{=(p}\hlopt{+}\hlnum{0.4}\hlstd{),} \hlkwc{length.out} \hlstd{=} \hlkwd{length}\hlstd{(tmp)), tmp,} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)} + \hlstd{\}}\hlkwa{else if} \hlstd{(}\hlkwd{length}\hlstd{(tmp)}\hlopt{>}\hlnum{8} \hlopt{&} \hlkwd{length}\hlstd{(tmp)}\hlopt{<}\hlnum{16}\hlstd{)\{} + \hlkwd{print}\hlstd{(}\hlkwd{c}\hlstd{(p, b))} + \hlkwd{text}\hlstd{((b}\hlopt{-}\hlnum{0.3}\hlstd{),}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=(p}\hlopt{-}\hlnum{0.4}\hlstd{),} \hlkwc{to}\hlstd{=(p}\hlopt{+}\hlnum{0.4}\hlstd{),} \hlkwc{length.out} \hlstd{=} \hlnum{8}\hlstd{), tmp[}\hlnum{1}\hlopt{:}\hlnum{8}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)} + \hlkwd{text}\hlstd{((b}\hlopt{+}\hlnum{0.3}\hlstd{),}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=(p}\hlopt{-}\hlnum{0.4}\hlstd{),} \hlkwc{to}\hlstd{=(p}\hlopt{+}\hlnum{0.4}\hlstd{),} \hlkwc{length.out} \hlstd{= (}\hlkwd{length}\hlstd{(tmp)}\hlopt{-}\hlnum{8}\hlstd{)), tmp[}\hlnum{9}\hlopt{:}\hlkwd{length}\hlstd{(tmp)],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)} + \hlstd{\}}\hlkwa{else if} \hlstd{(}\hlkwd{length}\hlstd{(tmp)}\hlopt{>}\hlnum{16}\hlstd{)\{} + \hlkwd{text}\hlstd{(b,p,} \hlkwd{paste0}\hlstd{(}\hlkwd{length}\hlstd{(tmp),} \hlstr{" values"}\hlstd{))} + \hlstd{\}} + \hlstd{\}} +\hlstd{\}} +\end{alltt} +\begin{verbatim} +## [1] 0 1 +## [1] 2 0 +## [1] 2 1 +## [1] 3 1 +\end{verbatim} +\begin{alltt} +\hlstd{tmp}\hlkwb{<-}\hlstd{tablo}\hlopt{$}\hlstd{`tmp$Gene.name`[tablo}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{0} \hlopt{&} \hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{1}\hlstd{]} +\hlkwd{text}\hlstd{(}\hlopt{-}\hlnum{0.4}\hlstd{,}\hlopt{-}\hlnum{1.2}\hlstd{,} \hlstr{"p=1/n=0"}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.6}\hlstd{)} +\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlnum{18}\hlstd{),}\hlopt{-}\hlnum{1.1}\hlstd{, tmp[}\hlnum{1}\hlopt{:}\hlnum{18}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)} +\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{3}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlkwd{length}\hlstd{(tmp)}\hlopt{-}\hlnum{18}\hlstd{),}\hlopt{-}\hlnum{1.3}\hlstd{, tmp[}\hlnum{19}\hlopt{:}\hlkwd{length}\hlstd{(tmp)],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)} + +\hlstd{tmp}\hlkwb{<-}\hlstd{tablo}\hlopt{$}\hlstd{`tmp$Gene.name`[tablo}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{1} \hlopt{&} \hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{1}\hlstd{]} +\hlkwd{text}\hlstd{(}\hlopt{-}\hlnum{0.4}\hlstd{,}\hlopt{-}\hlnum{1.7}\hlstd{,} \hlstr{"p=1/n=1"}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.6}\hlstd{)} +\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlnum{18}\hlstd{),}\hlopt{-}\hlnum{1.6}\hlstd{, tmp[}\hlnum{1}\hlopt{:}\hlnum{18}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)} +\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{2}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlkwd{length}\hlstd{(tmp)}\hlopt{-}\hlnum{18}\hlstd{),}\hlopt{-}\hlnum{1.8}\hlstd{, tmp[}\hlnum{19}\hlopt{:}\hlkwd{length}\hlstd{(tmp)],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)} + + +\hlstd{tmp}\hlkwb{<-}\hlstd{tablo}\hlopt{$}\hlstd{`tmp$Gene.name`[tablo}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{0} \hlopt{&} \hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{0}\hlstd{]} +\hlkwd{text}\hlstd{(}\hlopt{-}\hlnum{0.4}\hlstd{,}\hlopt{-}\hlnum{2.2}\hlstd{,} \hlstr{"p=0/n=0"}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.6}\hlstd{)} +\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlnum{17}\hlstd{),}\hlopt{-}\hlnum{2.1}\hlstd{, tmp[}\hlnum{1}\hlopt{:}\hlnum{17}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)} +\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{4.4}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlkwd{length}\hlstd{(tmp)}\hlopt{-}\hlnum{17}\hlstd{),}\hlopt{-}\hlnum{2.3}\hlstd{, tmp[}\hlnum{18}\hlopt{:}\hlkwd{length}\hlstd{(tmp)],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)} + +\hlstd{tmp}\hlkwb{<-}\hlstd{tablo}\hlopt{$}\hlstd{`tmp$Gene.name`[tablo}\hlopt{$}\hlstd{nbats}\hlopt{==}\hlnum{2} \hlopt{&} \hlstd{tablo}\hlopt{$}\hlstd{nprimates}\hlopt{==}\hlnum{0}\hlstd{]} +\hlkwd{text}\hlstd{(}\hlopt{-}\hlnum{0.4}\hlstd{,}\hlopt{-}\hlnum{2.7}\hlstd{,} \hlstr{"p=0/n=2"}\hlstd{,} \hlkwc{cex}\hlstd{=}\hlnum{0.6}\hlstd{)} +\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{5.5}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlnum{18}\hlstd{),}\hlopt{-}\hlnum{2.6}\hlstd{, tmp[}\hlnum{1}\hlopt{:}\hlnum{18}\hlstd{],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)} +\hlkwd{text}\hlstd{(}\hlkwd{seq}\hlstd{(}\hlkwc{from}\hlstd{=}\hlnum{0.1}\hlstd{,} \hlkwc{to}\hlstd{=}\hlnum{1}\hlstd{,} \hlkwc{length.out} \hlstd{=} \hlkwd{length}\hlstd{(tmp)}\hlopt{-}\hlnum{18}\hlstd{),}\hlopt{-}\hlnum{2.8}\hlstd{, tmp[}\hlnum{19}\hlopt{:}\hlkwd{length}\hlstd{(tmp)],} \hlkwc{cex}\hlstd{=}\hlnum{0.4}\hlstd{)} +\end{alltt} +\end{kframe} +\includegraphics[width=\maxwidth]{figure/tablo-1} + +\end{knitrout} + +\end{document} +