Mercurial > repos > tomnl > mspurity_createmsp
changeset 11:4b3b0f5a55d9 draft
planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit b6b8da66a6eef180ca8e333f98fc4b7575bac7b3
| author | tomnl |
|---|---|
| date | Thu, 27 Jun 2019 12:34:09 -0400 |
| parents | 1dd282c0294e |
| children | 5dd61e94d70d |
| files | createDatabase.R createMSP.xml macros.xml spectralMatching.R test-data/createDatabase_output.sqlite test-data/createDatabase_output_eic.sqlite test-data/spectralMatching_db_with_spectral_matching.sqlite |
| diffstat | 7 files changed, 101 insertions(+), 98 deletions(-) [+] |
line wrap: on
line diff
--- a/createDatabase.R Tue Jun 25 12:34:19 2019 -0400 +++ b/createDatabase.R Thu Jun 27 12:34:09 2019 -0400 @@ -154,15 +154,13 @@ } xset@peaks <- as.matrix(plyr::ddply(data.frame(xset@peaks), ~ sample, convert2Raw, xset=xset)) - + # Saves the EICS into the previously created database - xgroups <- as.numeric(as.character(unique(pa@grped_df$grpid))) - px <- msPurity::purityX(xset, + px <- msPurity::purityX(xset, saveEIC = TRUE, cores=1, sqlitePth=dbPth, - rtrawColumns = TRUE, - xgroups = xgroups) + rtrawColumns = TRUE) }
--- a/createMSP.xml Tue Jun 25 12:34:19 2019 -0400 +++ b/createMSP.xml Thu Jun 27 12:34:09 2019 -0400 @@ -1,4 +1,4 @@ -<tool id="mspurity_createmsp" name="msPurity.createMSP" version="0.2.4"> +<tool id="mspurity_createmsp" name="msPurity.createMSP" version="@TOOL_VERSION@+galaxy@GALAXY_TOOL_VERSION@"> <description>Create MSP files from msPurity processed data</description> <macros> <import>macros.xml</import>
--- a/macros.xml Tue Jun 25 12:34:19 2019 -0400 +++ b/macros.xml Thu Jun 27 12:34:09 2019 -0400 @@ -1,11 +1,16 @@ <?xml version="1.0"?> <macros> + <token name="@TOOL_VERSION@">1.11.3</token> + <token name="@GALAXY_TOOL_VERSION@">0.2.5</token> + <xml name="requirements"> <requirements> - <requirement type="package" version="1.11.2" >bioconductor-mspurity</requirement> + <requirement type="package" version="@TOOL_VERSION@" >bioconductor-mspurity</requirement> <yield /> </requirements> </xml> + + <xml name="offsets"> <param name="minoffset" type="float" label="minoffset" value="0.5" argument='--minoffset' help="Offset to the 'left' for the precursor range e.g. if precursor of interest is @@ -96,7 +101,7 @@ </when> </conditional> </xml> - + <xml name="sm_input" token_ql='Query' token_dblabel="SQLite database" token_ql_shrt="Q" token_user="True" token_mspuritydatalib="False" token_msp="False" token_help=""> @@ -105,28 +110,28 @@ <option value="userdb" selected="@USER@" >SQLite database of (LC)-MS/MS data</option> <option value="msPurityData" selected="@MSPURITYDATALIB@" >Prepared database of MassBank, HMDB, LipidBlast and GNPS</option> <option value="msp" >MSP file (SQLite database will be created using using msp2db)</option> - </param> + </param> <when value="userdb"> <param type="data" name="@QL_SHRT@_dbPth" label="@QL@ SQLite database" format="sqlite" help=""/> </when> <when value="msp"> <param type="data" name="@QL_SHRT@_msp" label="@QL@ MSP file" format="msp" help=""/> </when> - + <when value="msPurityData"> </when> </conditional> </xml> - - + + <xml name="filters" token_ql="Query" token_polarity_positive="false" token_ql_shrt="Q" token_sources_select="false" token_instrument_types_select="false"> - + <section name="@QL_SHRT@_filters" title="Filters" expanded="False"> - + <param name="@QL_SHRT@_ppmPrec" type="float" value="5" label="ppm error of the precursor for spectra"/> <param name="@QL_SHRT@_ppmProd" type="float" value="10" label="ppm error of the product for spectra"/> - + <conditional name="@QL_SHRT@_raThres_cond"> <param name="@QL_SHRT@_raThres_bool" type="boolean" label="Filter on relative abundance threshold?"/> <when value="true"> @@ -135,7 +140,7 @@ <when value="false"> </when> </conditional> - + <conditional name="@QL_SHRT@_polarity_cond"> <param name="@QL_SHRT@_polarity_bool" type="boolean" label="Filter on polarity?" help="" /> <when value="true"> @@ -148,7 +153,7 @@ <when value="false"> </when> </conditional> - + <conditional name="@QL_SHRT@_purity_cond"> <param name="@QL_SHRT@_purity_bool" type="boolean" label="Filter on precursor ion purity?"/> <when value="true"> @@ -158,35 +163,35 @@ <when value="false"> </when> </conditional> - + <conditional name="@QL_SHRT@_xcmsGroups_cond"> <param name="@QL_SHRT@_xcmsGroups_bool" type="boolean" label="Filter on XCMS groups ids?"/> <when value="true"> <param name="@QL_SHRT@_xcmsGroups" type="text" value="" - label="XCMS group ids of spectra" + label="XCMS group ids of spectra" help="comma seperated list of grpids (correspond to column 'grpid in c_peak_group')) e.g '12,27,30'" /> </when> <when value="false"> </when> </conditional> - - + + <conditional name="@QL_SHRT@_pids_cond"> <param name="@QL_SHRT@_pids_bool" type="boolean" label="Filter on pids?"/> <when value="true"> <param name="@QL_SHRT@_pids" type="text" value="" - label="pids of spectra (correspond to column 'pid; in s_peak_meta)" + label="pids of spectra (correspond to column 'pid; in s_peak_meta)" help="comma seperated list of pids (correspond to column 'pid; in s_peak_meta)) e.g '3001,5561'" /> </when> <when value="false"> </when> </conditional> - - + + <conditional name="@QL_SHRT@_rtrange_cond"> - <param name="@QL_SHRT@_rtrange_bool" type="boolean" + <param name="@QL_SHRT@_rtrange_bool" type="boolean" label="Filter on retention time range?" help="Filter the spectra between two points of retention time range"/> <when value="true"> @@ -198,32 +203,32 @@ <when value="false"> </when> </conditional> - - - + + + <conditional name="@QL_SHRT@_accessions_cond"> - <param name="@QL_SHRT@_accessions_bool" type="boolean" + <param name="@QL_SHRT@_accessions_bool" type="boolean" label="Filter on accessions?" help="Filter on unique accessions IDs (e.g. from MassBank and MoNA)"/> <when value="true"> <param name="@QL_SHRT@_accessions" type="text" value="" - label="Spectra accessions" + label="Spectra accessions" help="Comma seperated list of accessions)) e.g 'AC000001,BS001003,LIT00001'" /> </when> <when value="false"> </when> </conditional> - - + + <conditional name="@QL_SHRT@_sources_cond"> - <param name="@QL_SHRT@_sources_bool" type="boolean" + <param name="@QL_SHRT@_sources_bool" type="boolean" label="Filter on sources?" help="" value="@SOURCES_SELECT@" /> <when value="true"> <param name="@QL_SHRT@_sources" type="select" multiple="true" - help="@QL_SHRT@ The default internal SQLite database of library (reference) spectra - contains fragmentation spectra from MassBank, LipidBlast and GNPS. A copy is - available from here: + help="@QL_SHRT@ The default internal SQLite database of library (reference) spectra + contains fragmentation spectra from MassBank, LipidBlast and GNPS. A copy is + available from here: https://bioconductor.org/packages/release/data/experiment/html/msPurityData.html" > <option value="massbank" selected="true">MassBank from MoNa</option> <option value="gnps" selected="true">GNPS</option> @@ -239,7 +244,7 @@ </when> </conditional> <conditional name="@QL_SHRT@_instrumentTypes_cond"> - <param name="@QL_SHRT@_instrumentTypes_bool" type="boolean" + <param name="@QL_SHRT@_instrumentTypes_bool" type="boolean" value="@INSTRUMENT_TYPES_SELECT@" label="Filter on instrument type?" help="" /> <when value="true"> @@ -278,7 +283,7 @@ <option value="none">None</option> </param> <param name="@QL_SHRT@_instrumentTypesUser" type="text" value="" - help="Types of the instruments to be included in the search. Use a comma to + help="Types of the instruments to be included in the search. Use a comma to separate the instrument types or leave empty to ignore filter."/> </when> <when value="false"> @@ -288,17 +293,17 @@ <param name="@QL_SHRT@_instruments_bool" type="boolean" label="Filter on instrument name?" help="" /> <when value="true"> <param name="@QL_SHRT@_instruments" type="text" value="" - help="Known instrument names to filter on. Use a comma to + help="Known instrument names to filter on. Use a comma to separate the instrument types or leave empty to ignore filter."/> </when> <when value="false"> </when> </conditional> - - + + <conditional name="@QL_SHRT@_spectraTypes_cond"> - <param name="@QL_SHRT@_spectraTypes_bool" type="boolean" label="Filter on spectral type?" + <param name="@QL_SHRT@_spectraTypes_bool" type="boolean" label="Filter on spectral type?" help="" /> <when value="true"> <param name="@QL_SHRT@_spectraTypes" type="select" multiple="true" label="Spectra type" > @@ -314,14 +319,14 @@ </conditional> <param name="@QL_SHRT@_spectraFilter" type="boolean" checked="true" - label="Ignore any peaks flagged in the spectra in previous stages?" + label="Ignore any peaks flagged in the spectra in previous stages?" help="" /> - + </section> </xml> - + - + <xml name="citations"> <citations>
--- a/spectralMatching.R Tue Jun 25 12:34:19 2019 -0400 +++ b/spectralMatching.R Thu Jun 27 12:34:09 2019 -0400 @@ -8,76 +8,76 @@ make_option(c("-o", "--outDir"), type="character"), make_option("--q_dbPth", type="character"), make_option("--l_dbPth", type="character"), - + make_option("--q_msp", type="character", default=NA), make_option("--l_msp", type="character", default=NA), - + make_option("--q_defaultDb", action="store_true"), make_option("--l_defaultDb", action="store_true"), - + make_option("--q_ppmPrec", type="double"), make_option("--l_ppmPrec", type="double"), - + make_option("--q_ppmProd", type="double"), make_option("--l_ppmProd", type="double"), - + make_option("--q_raThres", type="double", default=NA), make_option("--l_raThres", type="double", default=NA), - + make_option("--q_polarity", type="character", default=NA), make_option("--l_polarity", type="character", default=NA), make_option("--q_purity", type="double", default=NA), make_option("--l_purity", type="double", default=NA), - + make_option("--q_xcmsGroups", type="character", default=NA), make_option("--l_xcmsGroups", type="character", default=NA), - + make_option("--q_pids", type="character", default=NA), make_option("--l_pids", type="character", default=NA), - + make_option("--q_rtrangeMin", type="double", default=NA), make_option("--l_rtrangeMin", type="double", default=NA), - + make_option("--q_rtrangeMax", type="double", default=NA), make_option("--l_rtrangeMax", type="double", default=NA), - + make_option("--q_accessions", type="character", default=NA), make_option("--l_accessions", type="character", default=NA), - + make_option("--q_sources", type="character", default=NA), make_option("--l_sources", type="character", default=NA), - + make_option("--q_sourcesUser", type="character", default=NA), make_option("--l_sourcesUser", type="character", default=NA), - + make_option("--q_instrumentTypes", type="character", default=NA), make_option("--l_instrumentTypes", type="character", default=NA), - + make_option("--q_instrumentTypesUser", type="character", default=NA), make_option("--l_instrumentTypesUser", type="character", default=NA), - + make_option("--q_instruments", type="character", default=NA), make_option("--l_instruments", type="character", default=NA), - + make_option("--q_spectraTypes", type="character", default=NA), make_option("--l_spectraTypes", type="character", default=NA), - + make_option("--q_spectraFilter", action="store_true"), make_option("--l_spectraFilter", action="store_true"), - + make_option("--usePrecursors", action="store_true"), - + make_option("--mzW", type="double"), make_option("--raW", type="double"), - + make_option("--rttol", type="double", default=NA), - + make_option("--updateDb", action="store_true"), make_option("--copyDb", action="store_true"), make_option("--cores", default=1) - - + + ) # store options @@ -93,7 +93,7 @@ param <- NA } return(param) - + } if(!is.null(opt$q_defaultDb)){ @@ -192,48 +192,48 @@ sm <- msPurity::spectralMatching(q_dbPth = q_dbPth, l_dbPth = l_dbPth, - + q_purity = opt$q_purity, l_purity = opt$l_purity, - + q_ppmProd = opt$q_ppmProd, l_ppmProd = opt$l_ppmProd, - + q_ppmPrec = opt$q_ppmPrec, l_ppmPrec = opt$l_ppmPrec, - + q_raThres = opt$q_raThres, l_raThres = opt$l_raThres, - + q_pol = q_polarity, l_pol = l_polarity, - + q_xcmsGroups = q_xcmsGroups, l_xcmsGroups = l_xcmsGroups, - + q_pids = q_pids, l_pids = l_pids, - + q_sources = q_sources, l_sources = l_sources, - + q_instrumentTypes = q_instrumentTypes, l_instrumentTypes = l_instrumentTypes, - + q_spectraFilter= q_spectraFilter, l_spectraFilter= l_spectraFilter, - + l_rtrange=c(l_rtrangeMin, l_rtrangeMax), q_rtrange=c(q_rtrangeMin, q_rtrangeMax), - + q_accessions = opt$q_accessions, l_accessions= opt$l_accessions, - + raW = opt$raW, mzW = opt$mzW, rttol=opt$rttol, cores=opt$cores, - + copyDb=copyDb, updateDb=updateDb, outPth = "db_with_spectral_matching.sqlite" @@ -254,34 +254,34 @@ l_s_peak_meta <- DBI::dbGetQuery(q_con, 'SELECT * FROM l_s_peak_meta') colnames(l_s_peak_meta)[1] <- 'pid' } - + l_con <- DBI::dbConnect(RSQLite::SQLite(),l_dbPth) - if (DBI::dbExistsTable(q_con, "s_peaks")){ + if (DBI::dbExistsTable(l_con, "s_peaks")){ l_s_peaks <- DBI::dbGetQuery(q_con, sprintf("SELECT * FROM s_peaks WHERE pid in (%s)", paste(unique(l_s_peak_meta$pid), collapse=','))) - - }else if(DBI::dbExistsTable(q_con, "library_spectra")){ - l_s_peaks <- DBI::dbGetQuery(q_con, sprintf("SELECT * FROM library_spectra + + }else if(DBI::dbExistsTable(l_con, "library_spectra")){ + l_s_peaks <- DBI::dbGetQuery(l_con, sprintf("SELECT * FROM library_spectra WHERE library_spectra_meta_id in (%s)", paste(unique(l_s_peak_meta$pid), collapse=','))) }else{ l_s_peaks = NULL } - - if (DBI::dbExistsTable(q_con, "source")){ - l_source <- DBI::dbGetQuery(q_con, 'SELECT * FROM source') - }else if (DBI::dbExistsTable(q_con, "library_spectra_source")) { - l_source <- DBI::dbGetQuery(q_con, 'library_spectra_source') + + if (DBI::dbExistsTable(l_con, "source")){ + l_source <- DBI::dbGetQuery(l_con, 'SELECT * FROM source') + }else if (DBI::dbExistsTable(l_con, "library_spectra_source")) { + l_source <- DBI::dbGetQuery(l_con, 'SELECT * FROM library_spectra_source') }else{ l_source = NULL } - + if (!is.null(l_s_peaks)){ DBI::dbWriteTable(q_con, name='l_s_peaks', value=l_s_peaks, row.names=FALSE, append=TRUE) } - + if (!is.null(l_source)){ DBI::dbWriteTable(q_con, name='l_source', value=l_source, row.names=FALSE, append=TRUE) } - + }