update doc

doc/1_reference_legio_phylo.Rnw

@@ -331,7 +331,7 @@ Représenter le nombre de gènes obtenus par espèces, et le nombre d'espèces p
 <<>>=
 library(ape)
 
-aln<-paste0(home, "fasta/78Lp/")
+aln<-paste0(home, "fasta/78Lp_V2/")
 subrep<-list.files(aln)
 subrep<-subrep[grep(x=subrep, pattern="Q5")]
 subrep
@@ -348,8 +348,10 @@ 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))
+        tmprownames<-ifelse(grepl(rownames(fasta), pattern = "pneumo"), 
+            substr(rownames(fasta)[grep(pattern = "pneumophila",rownames(fasta))], 1,31),                    
+            sapply(rownames(fasta), function(x) strsplit(x, split=".", fixed=TRUE)[[1]][1]))
+        cat<-c(cat, tmprownames)
     }
 }
 
@@ -364,14 +366,17 @@ colnames(tab)<-subrep
 
 # make a cat list containing all species names
 for (subrepcurrent in subrep){
-print(subrepcurrent)
+#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)
+        tmprownames<-ifelse(grepl(rownames(fasta), pattern = "pneumo"), 
+        substr(rownames(fasta)[grep(pattern = "pneumophila",rownames(fasta))], 1,31),                    
+        sapply(rownames(fasta), function(x) strsplit(x, split=".", fixed=TRUE)[[1]][1]))
+        
+        tmp<-ifelse(rownames(tab) %in% tmprownames, 1, 0)
         tab[,subrepcurrent]<-tmp
     }
 }
@@ -397,7 +402,7 @@ barplot(vectgene, horiz=TRUE, las=2)
 \subsection{Concatenate and Supertree}
 
 <<tree, fig.height=12>>=
-treepath<-paste0(home, "fasta/78Lp/cat.phylip_phyml_tree")
+treepath<-paste0(home, "fasta/78Lp_V2/cat.phylip_phyml_tree")
 
 tree<-read.tree(treepath)
 plot(root(tree, outgroup = "Coxiella_burnetii"))

doc/1_reference_legio_phylo.aux

@@ -20,11 +20,11 @@
 \@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:}{5}{subsubsection.1.2.2}}
-\@writefile{toc}{\contentsline {subsubsection}{\numberline {1.2.3}Data from Legionella pneumophila reference strains:}{13}{subsubsection.1.2.3}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {1.3}Add missing species}{14}{subsection.1.3}}
-\@writefile{toc}{\contentsline {section}{\numberline {2}Get genes sequences}{15}{section.2}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Get sequences from Burstein et al.}{15}{subsection.2.1}}
-\@writefile{toc}{\contentsline {section}{\numberline {3}Phylogeny}{16}{section.3}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Genes alignement}{16}{subsection.3.1}}
-\@writefile{toc}{\contentsline {subsection}{\numberline {3.2}Concatenate and Supertree}{26}{subsection.3.2}}
+\@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:}{10}{subsubsection.1.2.3}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {1.3}Add missing species}{11}{subsection.1.3}}
+\@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}{20}{subsection.3.2}}

doc/1_reference_legio_phylo.toc

@@ -2,11 +2,11 @@
 \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:}{5}{subsubsection.1.2.2}
-\contentsline {subsubsection}{\numberline {1.2.3}Data from Legionella pneumophila reference strains:}{13}{subsubsection.1.2.3}
-\contentsline {subsection}{\numberline {1.3}Add missing species}{14}{subsection.1.3}
-\contentsline {section}{\numberline {2}Get genes sequences}{15}{section.2}
-\contentsline {subsection}{\numberline {2.1}Get sequences from Burstein et al.}{15}{subsection.2.1}
-\contentsline {section}{\numberline {3}Phylogeny}{16}{section.3}
-\contentsline {subsection}{\numberline {3.1}Genes alignement}{16}{subsection.3.1}
-\contentsline {subsection}{\numberline {3.2}Concatenate and Supertree}{26}{subsection.3.2}
+\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:}{10}{subsubsection.1.2.3}
+\contentsline {subsection}{\numberline {1.3}Add missing species}{11}{subsection.1.3}
+\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}{20}{subsection.3.2}

doc/tabAss_V2.txt

@@ -64,7 +64,6 @@ GCA_900461525.1;Legionella busanensis;Pillon
 GCA_000236145.1;Legionella dumoffi;Pillon
 GCA_003990055.1;Legionella septentrionalis;Pillon
 GCA_900452385.1;Legionella donaldsonii;Pillon
-GCA_001648685.1;Legionella gormannii;Pillon
 GCA_001886835.1;Legionella fraseri Dallas1E;Pillon
 GCA_003003865.1;Legionella fraseri Lansing 3;Pillon
 GCA_003003755.1;Legionella fraseri Los Angeles 1;Pillon