diff --git a/doc/1_reference_legio_phylo.Rnw b/doc/1_reference_legio_phylo.Rnw index effc056040d58ff7d4ebefa6bbf59443925fd99b..c9edac49297779c180db4a13011a914d0961488e 100644 --- a/doc/1_reference_legio_phylo.Rnw +++ b/doc/1_reference_legio_phylo.Rnw @@ -80,10 +80,15 @@ tabPRJNA<-read.table(paste0(data, "PRJNA285910_AssemblyDetails.txt"), header=FAL tabPRJNA<-tabPRJNA[,1:6] names(tabPRJNA)<-c("Assembly", "Level", "WGS", "BioSample", "Strain", "Taxonomy") + +tabAss<-tabPRJNA[, c("Assembly","Taxonomy")] +tabAss$Origin<-"Burstein" + + @ - +Data from the seconde publication: \url{https://pubmed.ncbi.nlm.nih.gov/33881638/} @@ -136,6 +141,55 @@ ncbi2<-read.table(paste0(data, "tab_ncbi_contigs_parsed.csv"), sep=";", fill=TRU @ + +Data from Legionella pneumophila reference strains: +\begin{itemize} + \item Legionella pneumophila Paris complete genome : CR628336.1 - GCA\_000048645.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/CR628336) + + \item Legionella pneumophila Lens complete genome : CR628337.1 - GCA\_000048665.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/CR628337) + + \item Legionella pneumophila Philadelphia complete genome : NC\_002942 - GCA\_000008485.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/52840256) + + \item Legionella pneumophila Corby complete genome : NC\_009494 - GCA\_000092545.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/NC\_009494.2) + \item Legionella pneumophila Alcoy complete genome : NC\_014125 - GCA\_000092625.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/NC\_014125.1) + + \item Optionnel : Legionella pneumophila Lorraine complete genome : FQ958210.1 - GCA\_000306865.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/FQ958210.1) +\end{itemize} + +<<>>= +Taxonomy<-c("Legionella pneumophila Paris", + "Legionella pneumophila Lens", + "Legionella pneumophila Philadelphia", + "Legionella pneumophila Corby", + "Legionella pneumophila Alcoy", + "Legionella pneumophila Lorraine") + +Assembly<-c("GCA_000048645.1", "GCA_000048665.1", + "GCA_000008485.1", "GCA_000092545.1", + "GCA_000092625.1", "GCA_000306865.1") + + +Origin<-rep("pneumo", 6) + +tabAss<-rbind(tabAss, cbind(Taxonomy, Assembly, Origin)) + +@ + + + + \section{Get genes sequences} diff --git a/doc/1_reference_legio_phylo.log b/doc/1_reference_legio_phylo.log index 93091f66c8c67d9d2ed1fc1755cd8d488617211b..2715b2247797331de96b21d98c7d8445a8a76a1e 100644 --- a/doc/1_reference_legio_phylo.log +++ b/doc/1_reference_legio_phylo.log @@ -1,4 +1,4 @@ -This is pdfTeX, Version 3.14159265-2.6-1.40.18 (TeX Live 2017/Debian) (preloaded format=pdflatex 2021.6.16) 20 SEP 2021 16:35 +This is pdfTeX, Version 3.14159265-2.6-1.40.18 (TeX Live 2017/Debian) (preloaded format=pdflatex 2021.6.16) 4 OCT 2021 16:53 entering extended mode restricted \write18 enabled. %&-line parsing enabled. @@ -881,10 +881,10 @@ Overfull \hbox (209.12009pt too wide) in paragraph at lines 158--158 [] -Package xcolor Warning: Incompatible color definition on input line 170. +Package xcolor Warning: Incompatible color definition on input line 173. -Overfull \hbox (208.8464pt too wide) in paragraph at lines 176--176 +Overfull \hbox (208.8464pt too wide) in paragraph at lines 179--179 [][]\OT1/cmtt/m/n/10.95 gupta1[][]<-[][]read.table[][]([][]paste0[][](data, dat alist2[[][]1[][]]),[] []sep[][]=[][]"\OMS/cmsy/m/n/10.95 n\OT1/cmtt/m/n/10.95 t "[][],[] []fill[][]=[][]TRUE[][],[] []header[][]=[][]TRUE[][],[] []comment.char @@ -892,7 +892,7 @@ alist2[[][]1[][]]),[] []sep[][]=[][]"\OMS/cmsy/m/n/10.95 n\OT1/cmtt/m/n/10.95 t [] -Overfull \hbox (208.8464pt too wide) in paragraph at lines 180--180 +Overfull \hbox (208.8464pt too wide) in paragraph at lines 183--183 [][]\OT1/cmtt/m/n/10.95 gupta2[][]<-[][]read.table[][]([][]paste0[][](data, dat alist2[[][]2[][]]),[] []sep[][]=[][]"\OMS/cmsy/m/n/10.95 n\OT1/cmtt/m/n/10.95 t "[][],[] []fill[][]=[][]TRUE[][],[] []header[][]=[][]TRUE[][],[] []comment.char @@ -900,76 +900,116 @@ alist2[[][]2[][]]),[] []sep[][]=[][]"\OMS/cmsy/m/n/10.95 n\OT1/cmtt/m/n/10.95 t [] -Package xcolor Warning: Incompatible color definition on input line 192. +Package xcolor Warning: Incompatible color definition on input line 195. -Overfull \hbox (30.91077pt too wide) in paragraph at lines 198--198 +Overfull \hbox (30.91077pt too wide) in paragraph at lines 201--201 [] []\OT1/cmtt/m/n/10.95 is.there[][]<-[][]sum[][]([][]sapply[][](species,[] []function[][]([][]y[][])[] []grepl[][](x,[][]pattern[] []= y)))[][] [] -Overfull \hbox (128.63846pt too wide) in paragraph at lines 210--210 +Overfull \hbox (128.63846pt too wide) in paragraph at lines 213--213 [][]\OT1/cmtt/m/n/10.95 list[][]<-[][]c[][](list[[][]grep[][](list,[] []pattern [][]=[][]"Legionella"[][])], list[[][]grep[][](list,[] []pattern[][]=[][]"Coxie lla"[][])])[][] [] +[3] -Package xcolor Warning: Incompatible color definition on input line 217. +Package xcolor Warning: Incompatible color definition on input line 220. -[3] -Overfull \hbox (232.11484pt too wide) in paragraph at lines 219--219 + +Overfull \hbox (232.11484pt too wide) in paragraph at lines 222--222 [][]\OT1/cmtt/m/n/10.95 ncbi[][]<-[][]read.table[][]([][]paste0[][](data,[] []" tab_ncbi_file.csv"[][]),[] []sep[][]=[][]";"[][],[] []fill[][]=[][]TRUE[][],[] []header[][]=[][]TRUE[][],[] []comment.char[] []=[] []""[][])[][] [] -Overfull \hbox (7.91602pt too wide) in paragraph at lines 220--220 +Overfull \hbox (7.91602pt too wide) in paragraph at lines 223--223 [][]\OT1/cmtt/m/n/10.95 sp[][]<-[][]c[][]([][]"adelaidensis"[][],[] []"birmingh amensis"[][],[] []"brunensis"[][],[] []"cherrii"[][])[][] [] -Overfull \hbox (295.3504pt too wide) in paragraph at lines 221--221 +Overfull \hbox (295.3504pt too wide) in paragraph at lines 224--224 [][]\OT1/cmtt/m/n/10.95 ncbi2[][]<-[][]read.table[][]([][]paste0[][](data,[] [] "tab_ncbi_contigs_parsed.csv"[][]),[] []sep[][]=[][]";"[][],[] []fill[][]=[][]T RUE[][],[] []header[][]=[][]TRUE[][],[] []comment.char[] []=[] []""[][])[][] [] -Package atveryend Info: Empty hook `BeforeClearDocument' on input line 246. +LaTeX Font Info: Try loading font information for TS1+cmr on input line 232. + +(/usr/share/texlive/texmf-dist/tex/latex/base/ts1cmr.fd +File: ts1cmr.fd 2014/09/29 v2.5h Standard LaTeX font definitions +) +Overfull \hbox (51.54103pt too wide) in paragraph at lines 232--233 +[]\OT1/cmr/m/n/10.95 Legionella pneu-mophila Paris com-plete genome : CR628336. +1 - GCA[]000048645.1 + [] + + +Overfull \hbox (49.38147pt too wide) in paragraph at lines 236--237 +[]\OT1/cmr/m/n/10.95 Legionella pneu-mophila Lens com-plete genome : CR628337.1 + - GCA[]000048665.1 + [] + + +Overfull \hbox (52.07639pt too wide) in paragraph at lines 244--245 +[]\OT1/cmr/m/n/10.95 Legionella pneu-mophila Corby com-plete genome : NC[]00949 +4 - GCA[]000092545.1 + [] + + +Overfull \hbox (49.9168pt too wide) in paragraph at lines 247--248 +[]\OT1/cmr/m/n/10.95 Legionella pneu-mophila Al-coy com-plete genome : NC[]0141 +25 - GCA[]000092625.1 + [] + + +Overfull \hbox (29.24263pt too wide) in paragraph at lines 251--252 +[]\OT1/cmr/m/n/10.95 Optionnel : Le-gionella pneu-mophila Lor-raine com-plete g +enome : FQ958210.1 + [] + + +Package xcolor Warning: Incompatible color definition on input line 257. + [4] -Package atveryend Info: Empty hook `AfterLastShipout' on input line 246. +Package atveryend Info: Empty hook `BeforeClearDocument' on input line 301. +[5] +Package atveryend Info: Empty hook `AfterLastShipout' on input line 301. (./1_reference_legio_phylo.aux) -Package atveryend Info: Executing hook `AtVeryEndDocument' on input line 246. -Package atveryend Info: Executing hook `AtEndAfterFileList' on input line 246. +Package atveryend Info: Executing hook `AtVeryEndDocument' on input line 301. +Package atveryend Info: Executing hook `AtEndAfterFileList' on input line 301. Package rerunfilecheck Info: File `1_reference_legio_phylo.out' has not changed . (rerunfilecheck) Checksum: C7F3B916942DAC9C7581F4EFD94AC3C7;701. -Package atveryend Info: Empty hook `AtVeryVeryEnd' on input line 246. +Package atveryend Info: Empty hook `AtVeryVeryEnd' on input line 301. ) Here is how much of TeX's memory you used: - 7779 strings out of 492982 - 110784 string characters out of 6134896 + 7806 strings out of 492982 + 111725 string characters out of 6134896 201483 words of memory out of 5000000 - 11249 multiletter control sequences out of 15000+600000 - 9493 words of font info for 34 fonts, out of 8000000 for 9000 + 11271 multiletter control sequences out of 15000+600000 + 9834 words of font info for 35 fonts, out of 8000000 for 9000 1141 hyphenation exceptions out of 8191 - 28i,6n,35p,438b,356s stack positions out of 5000i,500n,10000p,200000b,80000s -</usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmbx10.pfb></us -r/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmbx12.pfb></usr/shar -e/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmitt10.pfb></usr/share/tex -live/texmf-dist/fonts/type1/public/amsfonts/cm/cmr10.pfb></usr/share/texlive/te -xmf-dist/fonts/type1/public/amsfonts/cm/cmr12.pfb></usr/share/texlive/texmf-dis -t/fonts/type1/public/amsfonts/cm/cmr17.pfb></usr/share/texlive/texmf-dist/fonts -/type1/public/amsfonts/cm/cmsy10.pfb></usr/share/texlive/texmf-dist/fonts/type1 -/public/amsfonts/cm/cmti10.pfb></usr/share/texlive/texmf-dist/fonts/type1/publi -c/amsfonts/cm/cmtt10.pfb> -Output written on 1_reference_legio_phylo.pdf (4 pages, 116032 bytes). + 28i,6n,35p,438b,371s stack positions out of 5000i,500n,10000p,200000b,80000s +{/usr/share/texmf/fonts/enc/dvips/cm-super/cm-super-ts1.enc}</usr/share/texli +ve/texmf-dist/fonts/type1/public/amsfonts/cm/cmbx10.pfb></usr/share/texlive/tex +mf-dist/fonts/type1/public/amsfonts/cm/cmbx12.pfb></usr/share/texlive/texmf-dis +t/fonts/type1/public/amsfonts/cm/cmitt10.pfb></usr/share/texlive/texmf-dist/fon +ts/type1/public/amsfonts/cm/cmr10.pfb></usr/share/texlive/texmf-dist/fonts/type +1/public/amsfonts/cm/cmr12.pfb></usr/share/texlive/texmf-dist/fonts/type1/publi +c/amsfonts/cm/cmr17.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfo +nts/cm/cmsy10.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm +/cmti10.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmtt1 +0.pfb></usr/share/texmf/fonts/type1/public/cm-super/sfrm1095.pfb> +Output written on 1_reference_legio_phylo.pdf (5 pages, 127639 bytes). PDF statistics: - 126 PDF objects out of 1000 (max. 8388607) - 109 compressed objects within 2 object streams - 17 named destinations out of 1000 (max. 500000) + 135 PDF objects out of 1000 (max. 8388607) + 116 compressed objects within 2 object streams + 18 named destinations out of 1000 (max. 500000) 89 words of extra memory for PDF output out of 10000 (max. 10000000) diff --git a/doc/1_reference_legio_phylo.pdf b/doc/1_reference_legio_phylo.pdf index ca5c11ebcefdd893edfe2a8611fb73fe566695cf..aa180512d7fd1fac5703b92975d78b8f89898be4 100644 Binary files a/doc/1_reference_legio_phylo.pdf and b/doc/1_reference_legio_phylo.pdf differ diff --git a/doc/1_reference_legio_phylo.tex b/doc/1_reference_legio_phylo.tex index 4d19f7ec8eb94635c78912de479ccaeb8ee23a21..1a7dad090814000ef4354bd2fc28209bfc576d40 100644 --- a/doc/1_reference_legio_phylo.tex +++ b/doc/1_reference_legio_phylo.tex @@ -156,12 +156,15 @@ Data from the first publication: \hlstd{tabPRJNA}\hlkwb{<-}\hlstd{tabPRJNA[,}\hlnum{1}\hlopt{:}\hlnum{6}\hlstd{]} \hlkwd{names}\hlstd{(tabPRJNA)}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"Assembly"}\hlstd{,} \hlstr{"Level"}\hlstd{,} \hlstr{"WGS"}\hlstd{,} \hlstr{"BioSample"}\hlstd{,} \hlstr{"Strain"}\hlstd{,} \hlstr{"Taxonomy"}\hlstd{)} + +\hlstd{tabAss}\hlkwb{<-}\hlstd{tabPRJNA[,} \hlkwd{c}\hlstd{(}\hlstr{"Assembly"}\hlstd{,}\hlstr{"Taxonomy"}\hlstd{)]} +\hlstd{tabAss}\hlopt{$}\hlstd{Origin}\hlkwb{<-}\hlstr{"Burstein"} \end{alltt} \end{kframe} \end{knitrout} - +Data from the seconde publication: \url{https://pubmed.ncbi.nlm.nih.gov/33881638/} @@ -223,6 +226,58 @@ Which species are present in gupta not in the previous datasets. \end{kframe} \end{knitrout} + +Data from Legionella pneumophila reference strains: +\begin{itemize} + \item Legionella pneumophila Paris complete genome : CR628336.1 - GCA\_000048645.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/CR628336) + + \item Legionella pneumophila Lens complete genome : CR628337.1 - GCA\_000048665.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/CR628337) + + \item Legionella pneumophila Philadelphia complete genome : NC\_002942 - GCA\_000008485.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/52840256) + + \item Legionella pneumophila Corby complete genome : NC\_009494 - GCA\_000092545.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/NC\_009494.2) + \item Legionella pneumophila Alcoy complete genome : NC\_014125 - GCA\_000092625.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/NC\_014125.1) + + \item Optionnel : Legionella pneumophila Lorraine complete genome : FQ958210.1 - GCA\_000306865.1 + + (https://www.ncbi.nlm.nih.gov/nuccore/FQ958210.1) +\end{itemize} + +\begin{knitrout} +\definecolor{shadecolor}{rgb}{0.969, 0.969, 0.969}\color{fgcolor}\begin{kframe} +\begin{alltt} +\hlstd{Taxonomy}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"Legionella pneumophila Paris"}\hlstd{,} + \hlstr{"Legionella pneumophila Lens"}\hlstd{,} + \hlstr{"Legionella pneumophila Philadelphia"}\hlstd{,} + \hlstr{"Legionella pneumophila Corby"}\hlstd{,} + \hlstr{"Legionella pneumophila Alcoy"}\hlstd{,} + \hlstr{"Legionella pneumophila Lorraine"}\hlstd{)} + +\hlstd{Assembly}\hlkwb{<-}\hlkwd{c}\hlstd{(}\hlstr{"GCA_000048645.1"}\hlstd{,} \hlstr{"GCA_000048665.1"}\hlstd{,} + \hlstr{"GCA_000008485.1"}\hlstd{,} \hlstr{"GCA_000092545.1"}\hlstd{,} + \hlstr{"GCA_000092625.1"}\hlstd{,} \hlstr{"GCA_000306865.1"}\hlstd{)} + + +\hlstd{Origin}\hlkwb{<-}\hlkwd{rep}\hlstd{(}\hlstr{"pneumo"}\hlstd{,} \hlnum{6}\hlstd{)} + +\hlstd{tabAss}\hlkwb{<-}\hlkwd{rbind}\hlstd{(tabAss,} \hlkwd{cbind}\hlstd{(Taxonomy, Assembly, Origin))} +\end{alltt} +\end{kframe} +\end{knitrout} + + + + \section{Get genes sequences}