Commit 72879ec6 authored by mcariou's avatar mcariou
Browse files

update doc

parent 3afc5354
......@@ -281,33 +281,89 @@ I will try with PSI-BLAST.
list.files(path = paste0(home, "/genes/78genes/prot_pneumo78"))
@
For the other species, use of PSI BLAST.
\textit{When using PSI-BLAST the results of a normal BLAST search are aligned and used to construct a pattern of conserved residues. This pattern is used for the next round of searching instead of the original query sequence. The process is repeated (iterated) until a final database search finds no more related sequences. When the process ends in this fashion, it is said to have converged.}
\section{Phylogeny}
\textbf{TO DO:}
\subsection{Genes alignement}
\begin{itemize}
\item install PSI BLAST
\item Use PSI-BLAST
\item Find way to filter within DB.
\item Or make a sub db?
\end{itemize}
Représenter le nombre de gènes obtenus par espèces, et le nombre d'espèces par gènes.
<<>>=
library(ape)
aln<-paste0(home, "fasta/78Lp/")
subrep<-list.files(aln)
subrep<-subrep[grep(x=subrep, pattern="Q5")]
subrep
cat<-vector()
subrepcurrent<-subrep[1]
#### fuction
# make a cat list containing all species names
for (subrepcurrent in subrep){
print(subrepcurrent)
file<-list.files(paste0(aln, "/", subrepcurrent))
file<-file[grep(x=file, pattern="aln")]
if (length(file)>0){
fasta<-read.dna(paste0(aln, "/",subrepcurrent, "/", file), format="fasta", as.character=TRUE)
rownames(fasta)<-sapply(rownames(fasta), function(x) strsplit(x, split=".", fixed=TRUE)[[1]][1])
cat<-c(cat, rownames(fasta))
}
}
cat<-unique(cat)
tab<-matrix("", ncol=length(subrep), nrow=length(cat))
tab<-as.data.frame(tab)
rownames(tab)<-cat
colnames(tab)<-subrep
########################################################
# make a cat list containing all species names
for (subrepcurrent in subrep){
print(subrepcurrent)
file<-list.files(paste0(aln, "/", subrepcurrent))
file<-file[grep(x=file, pattern="aln")]
if (length(file)>0){
fasta<-read.dna(paste0(aln, "/",subrepcurrent, "/", file), format="fasta", as.character=TRUE)
rownames(fasta)<-sapply(rownames(fasta), function(x) strsplit(x, split=".", fixed=TRUE)[[1]][1])
tmp<-ifelse(rownames(tab) %in% rownames(fasta), 1, 0)
tab[,subrepcurrent]<-tmp
}
}
@
\subsection{Get 78 sequences from Gupta species}
<<barplot1, fig.height=12>>=
par(mar=c(4,12,1,1))
vectsp<-sapply(1:nrow(tab), function(x) sum(as.numeric(tab[x,])))
names(vectsp)<-(rownames(tab))
barplot(vectsp, horiz=TRUE, las=2)
@
<<barplot2, fig.height=12>>=
par(mar=c(4,12,1,1))
vectgene<-sapply(1:ncol(tab), function(x) sum(as.numeric(tab[,x])))
names(vectgene)<-(colnames(tab))
barplot(vectgene, horiz=TRUE, las=2)
@
\subsection{Get legionella pneumophila strains sequences}
\section{Phylogeny}
\subsection{Genes alignement}
\subsection{Concatenate and Supertree}
\subsection{Concatenate}
<<tree, fig.height=12>>=
treepath<-paste0(home, "fasta/78Lp/cat.phylip_phyml_tree")
\subsection{Supertree}
tree<-read.tree(treepath)
plot(root(tree, outgroup = "Coxiella_burnetii"))
@
\end{document}
......
......@@ -20,13 +20,10 @@
\@writefile{toc}{\contentsline {subsection}{\numberline {1.1}Objective}{2}{subsection.1.1}}
\@writefile{toc}{\contentsline {subsection}{\numberline {1.2}Data}{2}{subsection.1.2}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {1.2.1}Data from the first publication:}{2}{subsubsection.1.2.1}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {1.2.2}Data from the seconde publication:}{3}{subsubsection.1.2.2}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {1.2.3}Data from Legionella pneumophila reference strains:}{8}{subsubsection.1.2.3}}
\@writefile{toc}{\contentsline {section}{\numberline {2}Get genes sequences}{9}{section.2}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Get sequences from Burstein et al.}{9}{subsection.2.1}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}Get 78 sequences from Gupta species}{10}{subsection.2.2}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Get legionella pneumophila strains sequences}{10}{subsection.2.3}}
\@writefile{toc}{\contentsline {section}{\numberline {3}Phylogeny}{10}{section.3}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Genes alignement}{10}{subsection.3.1}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.2}Concatenate}{10}{subsection.3.2}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.3}Supertree}{10}{subsection.3.3}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {1.2.2}Data from the seconde publication:}{4}{subsubsection.1.2.2}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {1.2.3}Data from Legionella pneumophila reference strains:}{11}{subsubsection.1.2.3}}
\@writefile{toc}{\contentsline {section}{\numberline {2}Get genes sequences}{12}{section.2}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Get sequences from Burstein et al.}{12}{subsection.2.1}}
\@writefile{toc}{\contentsline {section}{\numberline {3}Phylogeny}{13}{section.3}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Genes alignement}{13}{subsection.3.1}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.2}Concatenate and Supertree}{23}{subsection.3.2}}
This diff is collapsed.
......@@ -6,9 +6,6 @@
\BOOKMARK [3][-]{subsubsection.1.2.3}{Data from Legionella pneumophila reference strains:}{subsection.1.2}% 6
\BOOKMARK [1][-]{section.2}{Get genes sequences}{}% 7
\BOOKMARK [2][-]{subsection.2.1}{Get sequences from Burstein et al.}{section.2}% 8
\BOOKMARK [2][-]{subsection.2.2}{Get 78 sequences from Gupta species}{section.2}% 9
\BOOKMARK [2][-]{subsection.2.3}{Get legionella pneumophila strains sequences}{section.2}% 10
\BOOKMARK [1][-]{section.3}{Phylogeny}{}% 11
\BOOKMARK [2][-]{subsection.3.1}{Genes alignement}{section.3}% 12
\BOOKMARK [2][-]{subsection.3.2}{Concatenate}{section.3}% 13
\BOOKMARK [2][-]{subsection.3.3}{Supertree}{section.3}% 14
\BOOKMARK [1][-]{section.3}{Phylogeny}{}% 9
\BOOKMARK [2][-]{subsection.3.1}{Genes alignement}{section.3}% 10
\BOOKMARK [2][-]{subsection.3.2}{Concatenate and Supertree}{section.3}% 11
This diff is collapsed.
......@@ -2,13 +2,10 @@
\contentsline {subsection}{\numberline {1.1}Objective}{2}{subsection.1.1}
\contentsline {subsection}{\numberline {1.2}Data}{2}{subsection.1.2}
\contentsline {subsubsection}{\numberline {1.2.1}Data from the first publication:}{2}{subsubsection.1.2.1}
\contentsline {subsubsection}{\numberline {1.2.2}Data from the seconde publication:}{3}{subsubsection.1.2.2}
\contentsline {subsubsection}{\numberline {1.2.3}Data from Legionella pneumophila reference strains:}{8}{subsubsection.1.2.3}
\contentsline {section}{\numberline {2}Get genes sequences}{9}{section.2}
\contentsline {subsection}{\numberline {2.1}Get sequences from Burstein et al.}{9}{subsection.2.1}
\contentsline {subsection}{\numberline {2.2}Get 78 sequences from Gupta species}{10}{subsection.2.2}
\contentsline {subsection}{\numberline {2.3}Get legionella pneumophila strains sequences}{10}{subsection.2.3}
\contentsline {section}{\numberline {3}Phylogeny}{10}{section.3}
\contentsline {subsection}{\numberline {3.1}Genes alignement}{10}{subsection.3.1}
\contentsline {subsection}{\numberline {3.2}Concatenate}{10}{subsection.3.2}
\contentsline {subsection}{\numberline {3.3}Supertree}{10}{subsection.3.3}
\contentsline {subsubsection}{\numberline {1.2.2}Data from the seconde publication:}{4}{subsubsection.1.2.2}
\contentsline {subsubsection}{\numberline {1.2.3}Data from Legionella pneumophila reference strains:}{11}{subsubsection.1.2.3}
\contentsline {section}{\numberline {2}Get genes sequences}{12}{section.2}
\contentsline {subsection}{\numberline {2.1}Get sequences from Burstein et al.}{12}{subsection.2.1}
\contentsline {section}{\numberline {3}Phylogeny}{13}{section.3}
\contentsline {subsection}{\numberline {3.1}Genes alignement}{13}{subsection.3.1}
\contentsline {subsection}{\numberline {3.2}Concatenate and Supertree}{23}{subsection.3.2}
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment