| Previous changeset 5:2f7cd31eba49 (2020-11-13) Next changeset 7:e9fbb65451f6 (2022-02-08) |
|
Commit message:
"planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb" |
|
modified:
README.rst averageFragSpectra.R combineAnnotations.R createDatabase.R createMSP.R dbconfig.R dimsPredictPuritySingle.R filterFragSpectra.R flagRemove.R frag4feature.R macros.xml purityA.R purityX.R spectralMatching.R test-data/createDatabase_output.sqlite test-data/createDatabase_output_eic.sqlite test-data/createMSP_output_av_all_metadata.msp test-data/createMSP_output_av_all_metadata_custom_adducts.msp test-data/spectralMatching_db_with_spectral_matching.sqlite test-data/spectralMatching_db_with_spectral_matching_instrumentTypes.sqlite test-data/spectralMatching_matched_results.tsv test-data/spectralMatching_matched_results_instrumentTypes.tsv test-data/spectralMatching_xcms_matched_results.tsv test-data/spectralMatching_xcms_matched_results_instrumentTypes.tsv |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a README.rst --- a/README.rst Fri Nov 13 09:52:35 2020 +0000 +++ b/README.rst Thu Mar 04 12:34:06 2021 +0000 |
| b |
| @@ -3,13 +3,13 @@ |Build Status (Travis)| |Git| |Bioconda| |License| -Version v1.12.2+galaxy2 ------- +Version v1.16.2+galaxy0 +------------------------ - msPurity - - bioconductor-mspurity v1.12.2 + - bioconductor-mspurity v1.16.2 - Galaxy tools - - v3 + - v0 About ------ @@ -35,17 +35,17 @@ Dependencies ------- -Dependencies for these Galaxy tools should be handled by CONDA. The most recent version of the msPurity R package can found on channel `tomnl <https://anaconda.org/tomnl/bioconductor-mspurity>`_ on `anaconda <https://anaconda.org/tomnl/bioconductor-mspurity>`_. Warning this will be a different version of the package compared to the BICONDA bioconductor-mspurity. +------------------ +Dependencies for these Galaxy tools should be handled by CONDA. Galaxy ------- +------------------ `Galaxy <https://galaxyproject.org>`_ is an open, web-based platform for data intensive biomedical research. Whether on the free public server or your own instance, you can perform, reproduce, and share complete analyses. Authors, contributors & contacts -------------------------- +------------------------------------- - Thomas N. Lawson (t.n.lawson@bham.ac.uk) - `University of Birmingham (UK) <http://www.birmingham.ac.uk/index.aspx>`_ - Ralf J. M. Weber (r.j.weber@bham.ac.uk) - `University of Birmingham (UK) <http://www.birmingham.ac.uk/index.aspx>`_ @@ -55,6 +55,15 @@ Changes ------------------------- +v1.16.2-galaxy0 + - Version bump + - Fix for intra spectral matching + - Fix for typo https://github.com/computational-metabolomics/mspurity-galaxy/pull/43 + - Lint fixes + +v1.12.2-galaxy3 + - Bug fix reference to offsets in conditional #41 + v1.12.2-galaxy2 - Bug fix for using custom library sqlite database from Galaxy UI - Bug fix for "allfrag" for createDatabase @@ -70,7 +79,7 @@ - Update to version v1.12.2 of `msPurity <https://github.com/computational-metabolomics/msPurity/pull/71>`_ - Optional summary output for combineAnnotations (for very large output) - Extra column added to flagRemove output - - Hide probmetab input + - Hide probmetab input - Make dimsPredictPuritySingle more compatible with "simple workflow inputs" @@ -83,7 +92,7 @@ - Username updated in Toolshed yaml v1.12.0-galaxy0 - - Updates for Bioconductor stable msPurity v1.12.0 release + - Updates for Bioconductor stable msPurity v1.12.0 release - Additional columns added for spectral matching (for msnpy use case) - Merge of v1.11.4-galaxy1 |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a averageFragSpectra.R --- a/averageFragSpectra.R Fri Nov 13 09:52:35 2020 +0000 +++ b/averageFragSpectra.R Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| b'@@ -4,33 +4,33 @@\n print(sessionInfo())\n \n \n-get_av_spectra <- function(x){\n+get_av_spectra <- function(x) {\n \n- if (length(x$av_intra)>0){\n+ if (length(x$av_intra) > 0) {\n av_intra_df <- plyr::ldply(x$av_intra)\n \n- if (nrow(av_intra_df)==0){\n+ if (nrow(av_intra_df) == 0) {\n av_intra_df <- NULL\n }else{\n- av_intra_df$method <- \'intra\'\n+ av_intra_df$method <- "intra"\n }\n \n }else{\n av_intra_df <- NULL\n }\n \n- if ((is.null(x$av_inter)) || (nrow(x$av_inter)==0)){\n+ if ((is.null(x$av_inter)) || (nrow(x$av_inter) == 0)) {\n av_inter_df <- NULL\n }else{\n av_inter_df <- x$av_inter\n- av_inter_df$method <- \'inter\'\n+ av_inter_df$method <- "inter"\n }\n \n- if ((is.null(x$av_all)) || (nrow(x$av_all)==0)){\n+ if ((is.null(x$av_all)) || (nrow(x$av_all) == 0)) {\n av_all_df <- NULL\n }else{\n av_all_df <- x$av_all\n- av_all_df$method <- \'all\'\n+ av_all_df$method <- "all"\n }\n \n combined <- plyr::rbind.fill(av_intra_df, av_inter_df, av_all_df)\n@@ -40,126 +40,116 @@\n \n \n option_list <- list(\n- make_option("--out_rdata", type="character"),\n- make_option("--out_peaklist", type="character"),\n- make_option("--pa", type="character"),\n-\n- make_option("--av_level", type="character"),\n-\n- make_option("--minfrac", default=0.5),\n- make_option("--minnum", default=1),\n- make_option("--ppm", default=5.0),\n-\n- make_option("--snr", default=0),\n-\n- make_option("--ra", default=0),\n-\n- make_option("--av", default="median", type="character"),\n- make_option("--sumi", action="store_true"),\n-\n- make_option("--rmp", action="store_true"),\n- make_option("--cores", default=1)\n+ make_option("--out_rdata", type = "character"),\n+ make_option("--out_peaklist", type = "character"),\n+ make_option("--pa", type = "character"),\n+ make_option("--av_level", type = "character"),\n+ make_option("--minfrac", default = 0.5),\n+ make_option("--minnum", default = 1),\n+ make_option("--ppm", default = 5.0),\n+ make_option("--snr", default = 0),\n+ make_option("--ra", default = 0),\n+ make_option("--av", default = "median", type = "character"),\n+ make_option("--sumi", action = "store_true"),\n+ make_option("--rmp", action = "store_true"),\n+ make_option("--cores", default = 1)\n )\n \n-opt <- parse_args(OptionParser(option_list=option_list))\n+opt <- parse_args(OptionParser(option_list = option_list))\n print(opt)\n \n \n-loadRData <- function(rdata_path, name){\n-#loads an RData file, and returns the named xset object if it is there\n+load_r_data <- function(rdata_path, name) {\n+ #loads an RData file, and returns the named xset object if it is there\n load(rdata_path)\n return(get(ls()[ls() %in% name]))\n }\n \n # Requires\n-pa <- loadRData(opt$pa, \'pa\')\n+pa <- load_r_data(opt$pa, "pa")\n \n pa@cores <- opt$cores\n \n-if(is.null(opt$rmp)){\n- rmp = FALSE\n+if (is.null(opt$rmp)) {\n+ rmp <- FALSE\n }else{\n- rmp = TRUE\n+ rmp <- TRUE\n }\n \n-if(is.null(opt$sumi)){\n-\n- sumi = FALSE\n+if (is.null(opt$sumi)) {\n+ sumi <- FALSE\n }else{\n- sumi = TRUE\n-\n+ sumi <- TRUE\n }\n \n-\n-if(opt$av_level=="intra"){\n-\n+if (opt$av_level == "intra") {\n pa <- msPurity::averageIntraFragSpectra(pa,\n- minfrac=opt$minfrac,\n- minnum=opt$minnum,\n- ppm=opt$ppm,\n- snr=opt$snr,\n- ra=opt$ra,\n- av=opt$av,\n- sumi=sumi,\n- rmp=rmp,\n- cores=opt$cores)\n+ minfrac = opt$minfrac,\n+ minnum = opt$minnum,\n+ ppm = opt$ppm,\n+ snr = opt$snr,\n+ ra = opt$ra,\n+ av = opt$av,\n+ '..b' minfrac=opt$minfrac,\n- minnum=opt$minnum,\n- ppm=opt$ppm,\n- snr=opt$snr,\n- ra=opt$ra,\n- av=opt$av,\n- sumi=sumi,\n- rmp=rmp,\n- cores=opt$cores)\n-} else if(opt$av_level=="all"){\n+ minfrac = opt$minfrac,\n+ minnum = opt$minnum,\n+ ppm = opt$ppm,\n+ snr = opt$snr,\n+ ra = opt$ra,\n+ av = opt$av,\n+ sumi = sumi,\n+ rmp = rmp,\n+ cores = opt$cores)\n+} else if (opt$av_level == "all") {\n \n pa <- msPurity::averageAllFragSpectra(pa,\n- minfrac=opt$minfrac,\n- minnum=opt$minnum,\n- ppm=opt$ppm,\n- snr=opt$snr,\n- ra=opt$ra,\n- av=opt$av,\n- sumi=sumi,\n- rmp=rmp,\n- cores=opt$cores)\n-\n+ minfrac = opt$minfrac,\n+ minnum = opt$minnum,\n+ ppm = opt$ppm,\n+ snr = opt$snr,\n+ ra = opt$ra,\n+ av = opt$av,\n+ sumi = sumi,\n+ rmp = rmp,\n+ cores = opt$cores)\n }\n \n print(pa)\n-save(pa, file=opt$out_rdata)\n+save(pa, file = opt$out_rdata)\n \n-\n-if (length(pa)>0){\n+if (length(pa) > 0) {\n \n av_spectra <- plyr::ldply(pa@av_spectra, get_av_spectra)\n \n- if (nrow(av_spectra)==0){\n- message(\'No average spectra available\')\n- } else{\n- colnames(av_spectra)[1] <- \'grpid\'\n+ if (nrow(av_spectra) == 0) {\n+ message("No average spectra available")\n+ } else {\n+ colnames(av_spectra)[1] <- "grpid"\n av_spectra$grpid <- names(pa@av_spectra)[av_spectra$grpid]\n- \n- if((length(pa@av_intra_params)>0) || (length(pa@av_inter_params)>0) ){\n- # Add some extra info (only required if av_intra or av_inter performed)\n- colnames(av_spectra)[2] <- \'fileid\'\n- av_spectra$avid <- 1:nrow(av_spectra)\n- \n- filenames <- sapply(av_spectra$fileid, function(x) names(pa@fileList)[as.integer(x)])\n- # filenames_galaxy <- sapply(av_spectra$fileid, function(x) basename(pa@fileList[as.integer(x)]))\n- \n- av_spectra = as.data.frame(append(av_spectra, list(filename = filenames), after=2))\n+\n+ if ((length(pa@av_intra_params) > 0) || (length(pa@av_inter_params) > 0)) {\n+ # Add some extra info (only required if av_intra or av_inter performed)\n+ colnames(av_spectra)[2] <- "fileid"\n+ av_spectra$avid <- seq_len(nrow(av_spectra))\n+\n+ filenames <- sapply(av_spectra$fileid,\n+ function(x) names(pa@fileList)[as.integer(x)])\n+ # filenames_galaxy <- sapply(\n+ # av_spectra$fileid, function(x) basename(pa@fileList[as.integer(x)]))\n+\n+ av_spectra <- as.data.frame(\n+ append(av_spectra, list(filename = filenames), after = 2))\n }\n \n \n print(head(av_spectra))\n- write.table(av_spectra, opt$out_peaklist, row.names=FALSE, sep=\'\\t\')\n+ write.table(av_spectra, opt$out_peaklist, row.names = FALSE, sep = "\\t")\n \n }\n }\n-\n' |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a combineAnnotations.R --- a/combineAnnotations.R Fri Nov 13 09:52:35 2020 +0000 +++ b/combineAnnotations.R Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| b'@@ -4,115 +4,120 @@\n \n # Get the parameter\n option_list <- list(\n- make_option(c("-s","--sm_resultPth"),type="character"),\n- make_option(c("-m","--metfrag_resultPth"),type="character"),\n- make_option(c("-c","--sirius_csi_resultPth"),type="character"),\n- make_option(c("-p","--probmetab_resultPth"),type="character"),\n- make_option(c("-l","--ms1_lookup_resultPth"),type="character"),\n+ make_option(c("-s", "--sm_resultPth"), type = "character"),\n+ make_option(c("-m", "--metfrag_resultPth"), type = "character"),\n+ make_option(c("-c", "--sirius_csi_resultPth"), type = "character"),\n+ make_option(c("-p", "--probmetab_resultPth"), type = "character"),\n+ make_option(c("-l", "--ms1_lookup_resultPth"), type = "character"),\n \n- make_option("--ms1_lookup_checkAdducts", action="store_true"),\n- make_option("--ms1_lookup_keepAdducts", type="character", default=NA),\n- make_option("--ms1_lookup_dbSource", type="character", default="hmdb"),\n+ make_option("--ms1_lookup_checkAdducts", action = "store_true"),\n+ make_option("--ms1_lookup_keepAdducts", type = "character", default = NA),\n+ make_option("--ms1_lookup_dbSource", type = "character", default = "hmdb"),\n \n- make_option("--sm_weight", type="numeric"),\n- make_option("--metfrag_weight", type="numeric"),\n- make_option("--sirius_csi_weight", type="numeric"),\n- make_option("--probmetab_weight", type="numeric"),\n- make_option("--ms1_lookup_weight", type="numeric"),\n- make_option("--biosim_weight", type="numeric"),\n- \n- make_option("--summaryOutput", action="store_true"),\n- \n- make_option("--create_new_database", action="store_true"),\n- make_option("--outdir", type="character", default="."),\n+ make_option("--sm_weight", type = "numeric"),\n+ make_option("--metfrag_weight", type = "numeric"),\n+ make_option("--sirius_csi_weight", type = "numeric"),\n+ make_option("--probmetab_weight", type = "numeric"),\n+ make_option("--ms1_lookup_weight", type = "numeric"),\n+ make_option("--biosim_weight", type = "numeric"),\n+\n+ make_option("--summaryOutput", action = "store_true"),\n \n- make_option("--compoundDbType", type="character", default="sqlite"),\n- make_option("--compoundDbPth", type="character", default=NA),\n- make_option("--compoundDbHost", type="character", default=NA)\n+ make_option("--create_new_database", action = "store_true"),\n+ make_option("--outdir", type = "character", default = "."),\n+\n+ make_option("--compoundDbType", type = "character", default = "sqlite"),\n+ make_option("--compoundDbPth", type = "character", default = NA),\n+ make_option("--compoundDbHost", type = "character", default = NA)\n )\n-opt <- parse_args(OptionParser(option_list=option_list))\n+opt <- parse_args(OptionParser(option_list = option_list))\n \n print(opt)\n \n-if (!is.null(opt$create_new_database)){\n- sm_resultPth <- file.path(opt$outdir, \'combined_annotations.sqlite\')\n+if (!is.null(opt$create_new_database)) {\n+ sm_resultPth <- file.path(opt$outdir, "combined_annotations.sqlite")\n file.copy(opt$sm_resultPth, sm_resultPth)\n }else{\n sm_resultPth <- opt$sm_resultPth\n }\n \n-if (is.null(opt$ms1_lookup_checkAdducts)){\n+if (is.null(opt$ms1_lookup_checkAdducts)) {\n opt$ms1_lookup_checkAdducts <- FALSE\n }\n-if (!is.null(opt$ms1_lookup_keepAdducts)){\n+if (!is.null(opt$ms1_lookup_keepAdducts)) {\n opt$ms1_lookup_keepAdducts <- gsub("__ob__", "[", opt$ms1_lookup_keepAdducts)\n opt$ms1_lookup_keepAdducts <- gsub("__cb__", "]", opt$ms1_lookup_keepAdducts)\n ms1_lookup_keepAdducts <- strsplit(opt$ms1_lookup_keepAdducts, ",")[[1]]\n }\n \n-weights <-list(\'sm\'=opt$sm_weight,\n- \'metfrag\'=opt$metfrag_weight,\n- \'sirius_csifingerid\'= opt$sirius_csi_weight,\n- \'probmetab\'=opt$probmetab_weight,\n- \'ms1_lookup\'=opt$ms1_lookup_weight,\n- \'biosim\'=opt$biosim_weight\n+weights <- list("sm" = opt$sm_weight,\n+ "metfrag" = opt$metfrag_weight,\n+ "sirius_csifingerid" = opt$sirius_csi_weight,\n+ "probmetab'..b't(weights), 0) == 1)) {\n+ stop(paste0("The weights should sum to 1 not ", sum(unlist(weights))))\n }\n \n-if (is.null(opt$summaryOutput)){\n- summaryOutput = FALSE\n+if (is.null(opt$summaryOutput)) {\n+ summaryOutput <- FALSE\n }else{\n- summaryOutput = TRUE\n+ summaryOutput <- TRUE\n }\n \n-if (opt$compoundDbType==\'local_config\'){\n+if (opt$compoundDbType == "local_config") {\n # load in compound config\n # Soure local function taken from workflow4metabolomics\n- source_local <- function(fname){ argv <- commandArgs(trailingOnly=FALSE); base_dir <- dirname(substring(argv[grep("--file=", argv)], 8)); source(paste(base_dir, fname, sep="/")) }\n+ source_local <- function(fname) {\n+ argv <- commandArgs(trailingOnly = FALSE)\n+ base_dir <- dirname(substring(argv[grep("--file=", argv)], 8))\n+ source(paste(base_dir, fname, sep = "/"))\n+ }\n source_local("dbconfig.R")\n }else{\n- compoundDbPth = opt$compoundDbPth\n- compoundDbType = opt$compoundDbType\n- compoundDbName = NA\n- compoundDbHost = NA\n- compoundDbPort = NA\n- compoundDbUser = NA\n- compoundDbPass = NA\n+ compoundDbPth <- opt$compoundDbPth\n+ compoundDbType <- opt$compoundDbType\n+ compoundDbName <- NA\n+ compoundDbHost <- NA\n+ compoundDbPort <- NA\n+ compoundDbUser <- NA\n+ compoundDbPass <- NA\n }\n \n summary_output <- msPurity::combineAnnotations(\n- sm_resultPth = sm_resultPth,\n- compoundDbPth = compoundDbPth,\n- metfrag_resultPth = opt$metfrag_resultPth,\n- sirius_csi_resultPth = opt$sirius_csi_resultPth,\n- probmetab_resultPth = opt$probmetab_resultPth,\n- ms1_lookup_resultPth = opt$ms1_lookup_resultPth,\n- ms1_lookup_keepAdducts = ms1_lookup_keepAdducts,\n- ms1_lookup_checkAdducts = opt$ms1_lookup_checkAdducts,\n+ sm_resultPth = sm_resultPth,\n+ compoundDbPth = compoundDbPth,\n+ metfrag_resultPth = opt$metfrag_resultPth,\n+ sirius_csi_resultPth = opt$sirius_csi_resultPth,\n+ probmetab_resultPth = opt$probmetab_resultPth,\n+ ms1_lookup_resultPth = opt$ms1_lookup_resultPth,\n+ ms1_lookup_keepAdducts = ms1_lookup_keepAdducts,\n+ ms1_lookup_checkAdducts = opt$ms1_lookup_checkAdducts,\n \n- compoundDbType = compoundDbType,\n- compoundDbName = compoundDbName,\n- compoundDbHost = compoundDbHost,\n- compoundDbPort = compoundDbPort,\n- compoundDbUser = compoundDbUser,\n- compoundDbPass = compoundDbPass,\n- weights = weights,\n- summaryOutput = summaryOutput)\n-if (summaryOutput){\n- write.table(summary_output, file.path(opt$outdir, \'combined_annotations.tsv\'), sep = \'\\t\', row.names = FALSE)\n+ compoundDbType = compoundDbType,\n+ compoundDbName = compoundDbName,\n+ compoundDbHost = compoundDbHost,\n+ compoundDbPort = compoundDbPort,\n+ compoundDbUser = compoundDbUser,\n+ compoundDbPass = compoundDbPass,\n+ weights = weights,\n+ summaryOutput = summaryOutput)\n+if (summaryOutput) {\n+ write.table(summary_output,\n+ file.path(opt$outdir, "combined_annotations.tsv"),\n+ sep = "\\t", row.names = FALSE)\n }\n \n-\n-write.table(summary_output, file.path(opt$outdir, \'combined_annotations.tsv\'), sep = \'\\t\', row.names = FALSE)\n-\n+write.table(summary_output,\n+ file.path(opt$outdir, "combined_annotations.tsv"),\n+ sep = "\\t", row.names = FALSE)\n \n closeAllConnections()\n-\n' |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a createDatabase.R --- a/createDatabase.R Fri Nov 13 09:52:35 2020 +0000 +++ b/createDatabase.R Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| @@ -3,19 +3,18 @@ library(xcms) library(CAMERA) print(sessionInfo()) -print('CREATING DATABASE') +print("CREATING DATABASE") -xset_pa_filename_fix <- function(opt, pa, xset){ +xset_pa_filename_fix <- function(opt, pa, xset) { - if (!is.null(opt$mzML_files) && !is.null(opt$galaxy_names)){ + if (!is.null(opt$mzML_files) && !is.null(opt$galaxy_names)) { # NOTE: Relies on the pa@fileList having the names of files given as 'names' of the variables # needs to be done due to Galaxy moving the files around and screwing up any links to files - filepaths <- trimws(strsplit(opt$mzML_files, ',')[[1]]) + filepaths <- trimws(strsplit(opt$mzML_files, ",")[[1]]) filepaths <- filepaths[filepaths != ""] - new_names <- basename(filepaths) - galaxy_names <- trimws(strsplit(opt$galaxy_names, ',')[[1]]) + galaxy_names <- trimws(strsplit(opt$galaxy_names, ",")[[1]]) galaxy_names <- galaxy_names[galaxy_names != ""] nsave <- names(pa@fileList) @@ -28,10 +27,10 @@ } - if(!all(basename(pa@fileList)==basename(xset@filepaths))){ - if(!all(names(pa@fileList)==basename(xset@filepaths))){ - print('FILELISTS DO NOT MATCH') - message('FILELISTS DO NOT MATCH') + if (!all(basename(pa@fileList) == basename(xset@filepaths))) { + if (!all(names(pa@fileList) == basename(xset@filepaths))) { + print("FILELISTS DO NOT MATCH") + message("FILELISTS DO NOT MATCH") quit(status = 1) }else{ xset@filepaths <- unname(pa@fileList) @@ -48,23 +47,23 @@ option_list <- list( - make_option(c("-o", "--outDir"), type="character"), - make_option("--pa", type="character"), - make_option("--xset_xa", type="character"), - make_option("--xcms_camera_option", type="character"), - make_option("--eic", action="store_true"), - make_option("--cores", default=4), - make_option("--mzML_files", type="character"), - make_option("--galaxy_names", type="character"), - make_option("--grpPeaklist", type="character") + make_option(c("-o", "--outDir"), type = "character"), + make_option("--pa", type = "character"), + make_option("--xset_xa", type = "character"), + make_option("--xcms_camera_option", type = "character"), + make_option("--eic", action = "store_true"), + make_option("--cores", default = 4), + make_option("--mzML_files", type = "character"), + make_option("--galaxy_names", type = "character"), + make_option("--grpPeaklist", type = "character") ) # store options -opt<- parse_args(OptionParser(option_list=option_list)) +opt <- parse_args(OptionParser(option_list = option_list)) print(opt) -loadRData <- function(rdata_path, name){ +loadRData <- function(rdata_path, name) { #loads an RData file, and returns the named xset object if it is there load(rdata_path) return(get(ls()[ls() %in% name])) @@ -73,36 +72,36 @@ getxcmsSetObject <- function(xobject) { # XCMS 1.x if (class(xobject) == "xcmsSet") - return (xobject) + return(xobject) # XCMS 3.x if (class(xobject) == "XCMSnExp") { # Get the legacy xcmsSet object - suppressWarnings(xset <- as(xobject, 'xcmsSet')) - sampclass(xset) <- xset@phenoData$sample_group - return (xset) + suppressWarnings(xset <- as(xobject, "xcmsSet")) + xcms::sampclass(xset) <- xset@phenoData$sample_group + return(xset) } } -print(paste('pa', opt$pa)) +print(paste("pa", opt$pa)) print(opt$xset) print(opt$xcms_camera_option) # Requires -pa <- loadRData(opt$pa, 'pa') +pa <- loadRData(opt$pa, "pa") print(pa@fileList) # Missing list element causes failures (should be updated # in msPurity R package for future releases) -if (!exists('allfrag', where=pa@filter_frag_params)){ +if (!exists("allfrag", where = pa@filter_frag_params)) { pa@filter_frag_params$allfrag <- FALSE } -if (opt$xcms_camera_option=='xcms'){ +if (opt$xcms_camera_option == "xcms") { - xset <- loadRData(opt$xset, c('xset','xdata')) + xset <- loadRData(opt$xset, c("xset", "xdata")) xset <- getxcmsSetObject(xset) fix <- xset_pa_filename_fix(opt, pa, xset) pa <- fix[[1]] @@ -110,7 +109,7 @@ xa <- NULL }else{ - xa <- loadRData(opt$xset, 'xa') + xa <- loadRData(opt$xset, "xa") fix <- xset_pa_filename_fix(opt, pa, xa@xcmsSet) pa <- fix[[1]] xa@xcmsSet <- fix[[2]] @@ -118,36 +117,33 @@ } - -if(is.null(opt$grpPeaklist)){ - grpPeaklist = NA +if (is.null(opt$grpPeaklist)) { + grpPeaklist <- NA }else{ - grpPeaklist = opt$grpPeaklist + grpPeaklist <- opt$grpPeaklist } - - dbPth <- msPurity::createDatabase(pa, - xset=xset, - xsa=xa, - outDir=opt$outDir, - grpPeaklist=grpPeaklist, - dbName='createDatabase_output.sqlite' + xset = xset, + xsa = xa, + outDir = opt$outDir, + grpPeaklist = grpPeaklist, + dbName = "createDatabase_output.sqlite" ) -if (!is.null(opt$eic)){ +if (!is.null(opt$eic)) { - if (is.null(xset)){ + if (is.null(xset)) { xset <- xa@xcmsSet } # previous check should have matched filelists together xset@filepaths <- unname(pa@fileList) - convert2Raw <- function(x, xset){ + convert2Raw <- function(x, xset) { sid <- unique(x$sample) # for each file get list of peaks x$rt_raw <- xset@rt$raw[[sid]][match(x$rt, xset@rt$corrected[[sid]])] @@ -157,13 +153,14 @@ } - xset@peaks <- as.matrix(plyr::ddply(data.frame(xset@peaks), ~ sample, convert2Raw, xset=xset)) + xset@peaks <- as.matrix( + plyr::ddply(data.frame(xset@peaks), ~ sample, convert2Raw, xset = xset)) # Saves the EICS into the previously created database px <- msPurity::purityX(xset, saveEIC = TRUE, - cores=1, - sqlitePth=dbPth, + cores = 1, + sqlitePth = dbPth, rtrawColumns = TRUE) } |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a createMSP.R --- a/createMSP.R Fri Nov 13 09:52:35 2020 +0000 +++ b/createMSP.R Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| @@ -4,39 +4,40 @@ # Get the parameter option_list <- list( - make_option("--rdata_input",type="character"), - make_option("--method",type="character"), - make_option("--metadata",type="character"), - make_option("--metadata_cols",type="character"), - make_option("--metadata_cols_filter",type="character"), - make_option("--adduct_split", action="store_true"), - make_option("--xcms_groupids",type="character"), - make_option("--filter",action="store_true"), - make_option("--intensity_ra",type="character"), - make_option("--include_adducts",type="character"), - make_option("--msp_schema",type="character"), - make_option("--include_adducts_custom",type="character", default=""), - make_option("--out_dir",type="character", default=".") + make_option("--rdata_input", type = "character"), + make_option("--method", type = "character"), + make_option("--metadata", type = "character"), + make_option("--metadata_cols", type = "character"), + make_option("--metadata_cols_filter", type = "character"), + make_option("--adduct_split", action = "store_true"), + make_option("--xcms_groupids", type = "character"), + make_option("--filter", action = "store_true"), + make_option("--intensity_ra", type = "character"), + make_option("--include_adducts", type = "character"), + make_option("--msp_schema", type = "character"), + make_option("--include_adducts_custom", type = "character", default = ""), + make_option("--out_dir", type = "character", default = ".") ) -opt <- parse_args(OptionParser(option_list=option_list)) +opt <- parse_args(OptionParser(option_list = option_list)) print(opt) load(opt$rdata_input) -if (is.null(opt$metadata)){ +if (is.null(opt$metadata)) { metadata <- NULL }else{ - metadata <- read.table(opt$metadata, header = TRUE, sep='\t', stringsAsFactors = FALSE, check.names = FALSE) + metadata <- read.table(opt$metadata, header = TRUE, sep = "\t", + stringsAsFactors = FALSE, check.names = FALSE) - if(!opt$metadata_cols_filter==''){ - metadata_cols_filter <- strsplit(opt$metadata_cols_filter, ',')[[1]] + if (!opt$metadata_cols_filter == "") { + metadata_cols_filter <- strsplit(opt$metadata_cols_filter, ",")[[1]] - metadata <- metadata[,metadata_cols_filter, drop=FALSE] + metadata <- metadata[, metadata_cols_filter, drop = FALSE] print(metadata) - if (!"grpid" %in% colnames(metadata)){ - metadata$grpid <- 1:nrow(metadata) + if (!"grpid" %in% colnames(metadata)) { + metadata$grpid <- seq_len(nrow(metadata)) } print(metadata) @@ -47,7 +48,7 @@ -if (is.null(opt$metadata_cols) || opt$metadata_cols==''){ +if (is.null(opt$metadata_cols) || opt$metadata_cols == "") { metadata_cols <- NULL }else{ metadata_cols <- opt$metadata_cols @@ -55,36 +56,33 @@ } -if(is.null(opt$adduct_split)){ +if (is.null(opt$adduct_split)) { adduct_split <- FALSE }else{ adduct_split <- TRUE } -if (is.null(opt$xcms_groupids)){ +if (is.null(opt$xcms_groupids)) { xcms_groupids <- NULL }else{ - xcms_groupids <- trimws(strsplit(opt$xcms_groupids, ',')[[1]]) + xcms_groupids <- trimws(strsplit(opt$xcms_groupids, ",")[[1]]) } - - - -if (is.null(opt$include_adducts_custom)){ - include_adducts_custom <- '' +if (is.null(opt$include_adducts_custom)) { + include_adducts_custom <- "" }else{ include_adducts_custom <- opt$include_adducts_custom } -if (opt$include_adducts=='None'){ - include_adducts <- '' +if (opt$include_adducts == "None") { + include_adducts <- "" }else{ include_adducts <- opt$include_adducts } -include_adducts_all <- paste(include_adducts_custom, ',', include_adducts, sep="") +include_adducts_all <- paste(include_adducts_custom, ",", include_adducts, sep = "") include_adducts_all <- gsub("^,", "", include_adducts_all) include_adducts_all <- gsub(",$", "", include_adducts_all) @@ -96,7 +94,7 @@ -if(is.null(opt$filter)){ +if (is.null(opt$filter)) { filter <- FALSE }else{ filter <- TRUE @@ -105,15 +103,15 @@ msPurity::createMSP(pa, - msp_file_pth = file.path(opt$out_dir, 'lcmsms_spectra.msp'), + msp_file_pth = file.path(opt$out_dir, "lcmsms_spectra.msp"), metadata = metadata, metadata_cols = metadata_cols, method = opt$method, adduct_split = adduct_split, xcms_groupids = xcms_groupids, filter = filter, - intensity_ra=opt$intensity_ra, - include_adducts=include_adducts_all, - msp_schema=opt$msp_schema) + intensity_ra = opt$intensity_ra, + include_adducts = include_adducts_all, + msp_schema = opt$msp_schema) -print('msp created') +print("msp created") |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a dbconfig.R --- a/dbconfig.R Fri Nov 13 09:52:35 2020 +0000 +++ b/dbconfig.R Thu Mar 04 12:34:06 2021 +0000 |
| b |
| @@ -1,9 +1,9 @@ -compoundDbType <- 'mysql' +compoundDbType <- "mysql" compoundDbPth <- NA -compoundDbName <- 'metab_compound' -compoundDbPort <- '3306' -compoundDbUser <- 'metab_compound' -compoundDbPass <- 'metab_compound' +compoundDbName <- "metab_compound" +compoundDbPort <- "3306" +compoundDbUser <- "metab_compound" +compoundDbPass <- "metab_compound" q_dbPth <- NA q_dbType <- NA |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a dimsPredictPuritySingle.R --- a/dimsPredictPuritySingle.R Fri Nov 13 09:52:35 2020 +0000 +++ b/dimsPredictPuritySingle.R Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| b'@@ -3,27 +3,27 @@\n print(sessionInfo())\n \n option_list <- list(\n- make_option(c("--mzML_file"), type="character"),\n- make_option(c("--mzML_files"), type="character"),\n- make_option(c("--mzML_filename"), type="character", default=\'\'),\n- make_option(c("--mzML_galaxy_names"), type="character", default=\'\'),\n- make_option(c("--peaks_file"), type="character"),\n- make_option(c("-o", "--out_dir"), type="character"),\n- make_option("--minoffset", default=0.5),\n- make_option("--maxoffset", default=0.5),\n- make_option("--ilim", default=0.05),\n- make_option("--ppm", default=4),\n- make_option("--dimspy", action="store_true"),\n- make_option("--sim", action="store_true"),\n- make_option("--remove_nas", action="store_true"),\n- make_option("--iwNorm", default="none", type="character"),\n- make_option("--file_num_dimspy", default=1),\n- make_option("--exclude_isotopes", action="store_true"),\n- make_option("--isotope_matrix", type="character")\n+ make_option(c("--mzML_file"), type = "character"),\n+ make_option(c("--mzML_files"), type = "character"),\n+ make_option(c("--mzML_filename"), type = "character", default = ""),\n+ make_option(c("--mzML_galaxy_names"), type = "character", default = ""),\n+ make_option(c("--peaks_file"), type = "character"),\n+ make_option(c("-o", "--out_dir"), type = "character"),\n+ make_option("--minoffset", default = 0.5),\n+ make_option("--maxoffset", default = 0.5),\n+ make_option("--ilim", default = 0.05),\n+ make_option("--ppm", default = 4),\n+ make_option("--dimspy", action = "store_true"),\n+ make_option("--sim", action = "store_true"),\n+ make_option("--remove_nas", action = "store_true"),\n+ make_option("--iwNorm", default = "none", type = "character"),\n+ make_option("--file_num_dimspy", default = 1),\n+ make_option("--exclude_isotopes", action = "store_true"),\n+ make_option("--isotope_matrix", type = "character")\n )\n \n # store options\n-opt<- parse_args(OptionParser(option_list=option_list))\n+opt <- parse_args(OptionParser(option_list = option_list))\n \n print(sessionInfo())\n print(opt)\n@@ -31,119 +31,118 @@\n print(opt$mzML_files)\n print(opt$mzML_galaxy_names)\n \n-str_to_vec <- function(x){\n+str_to_vec <- function(x) {\n print(x)\n- x <- trimws(strsplit(x, \',\')[[1]])\n+ x <- trimws(strsplit(x, ",")[[1]])\n return(x[x != ""])\n }\n \n-find_mzml_file <- function(mzML_files, galaxy_names, mzML_filename){\n+find_mzml_file <- function(mzML_files, galaxy_names, mzML_filename) {\n mzML_filename <- trimws(mzML_filename)\n mzML_files <- str_to_vec(mzML_files)\n galaxy_names <- str_to_vec(galaxy_names)\n- if (mzML_filename %in% galaxy_names){\n- return(mzML_files[galaxy_names==mzML_filename])\n+ if (mzML_filename %in% galaxy_names) {\n+ return(mzML_files[galaxy_names == mzML_filename])\n }else{\n stop(paste("mzML file not found - ", mzML_filename))\n }\n }\n \n \n-if (is.null(opt$dimspy)){\n- df <- read.table(opt$peaks_file, header = TRUE, sep=\'\\t\')\n- if (file.exists(opt$mzML_file)){\n+if (is.null(opt$dimspy)) {\n+ df <- read.table(opt$peaks_file, header = TRUE, sep = "\\t")\n+ if (file.exists(opt$mzML_file)) {\n mzML_file <- opt$mzML_file\n- }else if (!is.null(opt$mzML_files)){\n- mzML_file <- find_mzml_file(opt$mzML_files, opt$mzML_galaxy_names, \n+ }else if (!is.null(opt$mzML_files)) {\n+ mzML_file <- find_mzml_file(opt$mzML_files, opt$mzML_galaxy_names,\n opt$mzML_filename)\n }else{\n- mzML_file <- file.path(opt$mzML_file, filename) \n- }\t\n+ mzML_file <- file.path(opt$mzML_file, filename)\n+ }\n }else{\n indf <- read.table(opt$peaks_file,\n- header = TRUE, sep=\'\\t\', stringsAsFactors = FALSE)\n- \n+ header = TRUE, sep = "\\t", stringsAsFactors = FALSE)\n+\n filename <- colnames(indf)[8:ncol(indf)][opt$file_num_dimspy]\n print(filename)\n # check if the data file is mzML or RAW (can only use mzML currently) so\n # we expe'..b' (!is.null(opt$mzML_files)) {\n mzML_file <- find_mzml_file(opt$mzML_files, opt$mzML_galaxy_names, filename)\n }else{\n- mzML_file <- file.path(opt$mzML_file, filename) \n- }\t\n- \n- # Update the dimspy output with the correct information \n- df <- indf[4:nrow(indf),]\n- if (\'blank_flag\' %in% colnames(df)){\n- df <- df[df$blank_flag==1,]\n+ mzML_file <- file.path(opt$mzML_file, filename)\n }\n- colnames(df)[colnames(df)==\'m.z\'] <- \'mz\'\n- \n- if (\'nan\' %in% df$mz){\n- df[df$mz==\'nan\',]$mz <- NA\n+\n+ # Update the dimspy output with the correct information\n+ df <- indf[4:nrow(indf), ]\n+ if ("blank_flag" %in% colnames(df)) {\n+ df <- df[df$blank_flag == 1, ]\n+ }\n+ colnames(df)[colnames(df) == "m.z"] <- "mz"\n+\n+ if ("nan" %in% df$mz) {\n+ df[df$mz == "nan", ]$mz <- NA\n }\n df$mz <- as.numeric(df$mz)\n }\n \n-if (!is.null(opt$remove_nas)){\n- df <- df[!is.na(df$mz),]\n+if (!is.null(opt$remove_nas)) {\n+ df <- df[!is.na(df$mz), ]\n }\n \n-if (is.null(opt$isotope_matrix)){\n+if (is.null(opt$isotope_matrix)) {\n im <- NULL\n }else{\n im <- read.table(opt$isotope_matrix,\n- header = TRUE, sep=\'\\t\', stringsAsFactors = FALSE)\n+ header = TRUE, sep = "\\t", stringsAsFactors = FALSE)\n }\n \n-if (is.null(opt$exclude_isotopes)){\n+if (is.null(opt$exclude_isotopes)) {\n isotopes <- FALSE\n }else{\n isotopes <- TRUE\n }\n \n-if (is.null(opt$sim)){\n- sim=FALSE\n+if (is.null(opt$sim)) {\n+ sim <- FALSE\n }else{\n- sim=TRUE\n+ sim <- TRUE\n }\n \n-minOffset = as.numeric(opt$minoffset)\n-maxOffset = as.numeric(opt$maxoffset)\n+minOffset <- as.numeric(opt$minoffset)\n+maxOffset <- as.numeric(opt$maxoffset)\n \n-if (opt$iwNorm==\'none\'){\n- iwNorm = FALSE\n- iwNormFun = NULL\n-}else if (opt$iwNorm==\'gauss\'){\n- iwNorm = TRUE\n- iwNormFun = msPurity::iwNormGauss(minOff=-minOffset, maxOff=maxOffset)\n-}else if (opt$iwNorm==\'rcosine\'){\n- iwNorm = TRUE\n- iwNormFun = msPurity::iwNormRcosine(minOff=-minOffset, maxOff=maxOffset)\n-}else if (opt$iwNorm==\'QE5\'){\n- iwNorm = TRUE\n- iwNormFun = msPurity::iwNormQE.5()\n+if (opt$iwNorm == "none") {\n+ iwNorm <- FALSE\n+ iwNormFun <- NULL\n+}else if (opt$iwNorm == "gauss") {\n+ iwNorm <- TRUE\n+ iwNormFun <- msPurity::iwNormGauss(minOff = -minOffset, maxOff = maxOffset)\n+}else if (opt$iwNorm == "rcosine") {\n+ iwNorm <- TRUE\n+ iwNormFun <- msPurity::iwNormRcosine(minOff = -minOffset, maxOff = maxOffset)\n+}else if (opt$iwNorm == "QE5") {\n+ iwNorm <- TRUE\n+ iwNormFun <- msPurity::iwNormQE.5()\n }\n \n-print(\'FIRST ROWS OF PEAK FILE\')\n+print("FIRST ROWS OF PEAK FILE")\n print(head(df))\n print(mzML_file)\n predicted <- msPurity::dimsPredictPuritySingle(df$mz,\n- filepth=mzML_file,\n- minOffset=minOffset,\n- maxOffset=maxOffset,\n- ppm=opt$ppm,\n- mzML=TRUE,\n+ filepth = mzML_file,\n+ minOffset = minOffset,\n+ maxOffset = maxOffset,\n+ ppm = opt$ppm,\n+ mzML = TRUE,\n sim = sim,\n ilim = opt$ilim,\n isotopes = isotopes,\n@@ -154,10 +153,8 @@\n predicted <- cbind(df, predicted)\n \n print(head(predicted))\n-print(file.path(opt$out_dir, \'dimsPredictPuritySingle_output.tsv\'))\n+print(file.path(opt$out_dir, "dimsPredictPuritySingle_output.tsv"))\n \n-write.table(predicted, \n- file.path(opt$out_dir, \'dimsPredictPuritySingle_output.tsv\'),\n- row.names=FALSE, sep=\'\\t\')\n-\n-\n+write.table(predicted,\n+ file.path(opt$out_dir, "dimsPredictPuritySingle_output.tsv"),\n+ row.names = FALSE, sep = "\\t")\n' |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a filterFragSpectra.R --- a/filterFragSpectra.R Fri Nov 13 09:52:35 2020 +0000 +++ b/filterFragSpectra.R Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| @@ -5,96 +5,95 @@ option_list <- list( - make_option("--out_rdata", type="character"), - make_option("--out_peaklist_prec", type="character"), - make_option("--out_peaklist_frag", type="character"), - make_option("--pa", type="character"), + make_option("--out_rdata", type = "character"), + make_option("--out_peaklist_prec", type = "character"), + make_option("--out_peaklist_frag", type = "character"), + make_option("--pa", type = "character"), - make_option("--ilim", default=0.0), - make_option("--plim", default=0.0), + make_option("--ilim", default = 0.0), + make_option("--plim", default = 0.0), - make_option("--ra", default=0.0), - make_option("--snr", default=0.0), + make_option("--ra", default = 0.0), + make_option("--snr", default = 0.0), - make_option("--rmp", action="store_true"), - make_option("--snmeth", default="median", type="character") + make_option("--rmp", action = "store_true"), + make_option("--snmeth", default = "median", type = "character") ) -opt <- parse_args(OptionParser(option_list=option_list)) +opt <- parse_args(OptionParser(option_list = option_list)) print(opt) -loadRData <- function(rdata_path, name){ +loadRData <- function(rdata_path, name) { #loads an RData file, and returns the named xset object if it is there load(rdata_path) return(get(ls()[ls() %in% name])) } # Requires -pa <- loadRData(opt$pa, 'pa') +pa <- loadRData(opt$pa, "pa") -if(is.null(opt$rmp)){ - opt$rmp = FALSE +if (is.null(opt$rmp)) { + opt$rmp <- FALSE }else{ - opt$rmp = TRUE + opt$rmp <- TRUE } -pa <- filterFragSpectra(pa, - ilim=opt$ilim, - plim=opt$plim, - ra=opt$ra, - snr=opt$snr, - rmp=opt$rmp, - snmeth=opt$snmeth) +pa <- filterFragSpectra(pa, + ilim = opt$ilim, + plim = opt$plim, + ra = opt$ra, + snr = opt$snr, + rmp = opt$rmp, + snmeth = opt$snmeth) print(pa) -save(pa, file=opt$out_rdata) +save(pa, file = opt$out_rdata) # get the msms data for grpid from the purityA object -msmsgrp <- function(grpid, pa){ +msmsgrp <- function(grpid, pa) { msms <- pa@grped_ms2[grpid] - - grpinfo <- pa@grped_df[pa@grped_df$grpid==grpid,] - - grpinfo$subsetid <- 1:nrow(grpinfo) - result <- plyr::ddply(grpinfo, ~subsetid, setid, msms=msms) + + grpinfo <- pa@grped_df[pa@grped_df$grpid == grpid, ] + + grpinfo$subsetid <- seq_len(nrow(grpinfo)) + result <- plyr::ddply(grpinfo, ~subsetid, setid, msms = msms) return(result) } -# Set the relevant details -setid <- function(grpinfo_i, msms){ +# Set the relevant details +setid <- function(grpinfo_i, msms) { msms_i <- msms[[1]][[grpinfo_i$subsetid]] n <- nrow(msms_i) msms_i <- data.frame(msms_i) - colnames(msms_i)[1:2] <- c('mz', 'i') - m <- cbind('grpid'=rep(grpinfo_i$grpid,n), 'pid'=rep(grpinfo_i$pid,n), 'fileid'=rep(grpinfo_i$fileid,n), msms_i) + colnames(msms_i)[1:2] <- c("mz", "i") + m <- cbind("grpid" = rep(grpinfo_i$grpid, n), "pid" = rep(grpinfo_i$pid, n), "fileid" = rep(grpinfo_i$fileid, n), msms_i) return(m) } -if (length(pa)>0){ +if (length(pa) > 0) { - if (length(pa@grped_ms2)==0){ - message('No spectra available') - } else{ + if (length(pa@grped_ms2) == 0) { + message("No spectra available") + } else { # get group ids grpids <- unique(as.character(pa@grped_df$grpid)) # loop through all the group ids - df_fragments = plyr::adply(grpids, 1, msmsgrp, pa=pa) - df_fragments = merge(df_fragments, pa@puritydf[,c("pid", "acquisitionNum", "precursorScanNum")], by="pid") - df_fragments = df_fragments[order(df_fragments$grpid, df_fragments$pid, df_fragments$mz),] + df_fragments <- plyr::adply(grpids, 1, msmsgrp, pa = pa) + df_fragments <- merge(df_fragments, pa@puritydf[, c("pid", "acquisitionNum", "precursorScanNum")], by = "pid") + df_fragments <- df_fragments[order(df_fragments$grpid, df_fragments$pid, df_fragments$mz), ] #select and reorder columns - df_fragments = df_fragments[,c("grpid", "pid", "precursorScanNum", "acquisitionNum", "fileid", "mz", "i", "snr", "ra", "purity_pass_flag", "intensity_pass_flag", "ra_pass_flag", "snr_pass_flag", "pass_flag")] + df_fragments <- df_fragments[, c("grpid", "pid", "precursorScanNum", "acquisitionNum", "fileid", "mz", "i", "snr", "ra", "purity_pass_flag", "intensity_pass_flag", "ra_pass_flag", "snr_pass_flag", "pass_flag")] - pa@grped_df$filename = sapply(pa@grped_df$fileid, function(x) names(pa@fileList)[as.integer(x)]) + pa@grped_df$filename <- sapply(pa@grped_df$fileid, function(x) names(pa@fileList)[as.integer(x)]) - print(head(pa@grped_df)) - write.table(pa@grped_df, opt$out_peaklist_prec, row.names=FALSE, sep='\t') + print(head(pa@grped_df)) + write.table(pa@grped_df, opt$out_peaklist_prec, row.names = FALSE, sep = "\t") print(head(df_fragments)) - write.table(df_fragments, opt$out_peaklist_frag, row.names=FALSE, sep='\t') + write.table(df_fragments, opt$out_peaklist_frag, row.names = FALSE, sep = "\t") } } - |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a flagRemove.R --- a/flagRemove.R Fri Nov 13 09:52:35 2020 +0000 +++ b/flagRemove.R Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| b'@@ -2,105 +2,100 @@\n library(optparse)\n print(sessionInfo())\n option_list <- list(\n- make_option(c("-o", "--out_dir"), type="character", default=getwd(),\n- help="Output folder for resulting files [default = %default]"\n+ make_option(c("-o", "--out_dir"), type = "character", default = getwd(),\n+ help = "Output folder for resulting files [default = %default]"\n ),\n- make_option(c("-x", "--xset_path"), type="character", default=file.path(getwd(),"xset.rds"),\n- help="The path to the xcmsSet object [default = %default]"\n+ make_option(c("-x", "--xset_path"), type = "character", default = file.path(getwd(), "xset.rds"),\n+ help = "The path to the xcmsSet object [default = %default]"\n ),\n- make_option("--polarity", default=NA,\n- help="polarity (just used for naming purpose for files being saved) [positive, negative, NA] [default %default]"\n+ make_option("--polarity", default = NA,\n+ help = "polarity (just used for naming purpose for files being saved) [positive, negative, NA] [default %default]"\n ),\n- make_option("--rsd_i_blank", default=100,\n- help="RSD threshold for the blank [default = %default]"\n+ make_option("--rsd_i_blank", default = 100,\n+ help = "RSD threshold for the blank [default = %default]"\n ),\n- make_option("--minfrac_blank", default=0.5,\n- help="minimum fraction of files for features needed for the blank [default = %default]"\n+ make_option("--minfrac_blank", default = 0.5,\n+ help = "minimum fraction of files for features needed for the blank [default = %default]"\n ),\n- make_option("--rsd_rt_blank", default=100,\n- help="RSD threshold for the RT of the blank [default = %default]"\n+ make_option("--rsd_rt_blank", default = 100,\n+ help = "RSD threshold for the RT of the blank [default = %default]"\n ),\n \n- make_option("--ithres_blank", default=0,\n- help="Intensity threshold for the blank [default = %default]"\n+ make_option("--ithres_blank", default = 0,\n+ help = "Intensity threshold for the blank [default = %default]"\n ),\n- make_option("--s2b", default=10,\n- help="fold change (sample/blank) needed for sample peak to be allowed. e.g.\n+ make_option("--s2b", default = 10,\n+ help = "fold change (sample/blank) needed for sample peak to be allowed. e.g.\n if s2b set to 10 and the recorded sample \'intensity\' value was 100 and blank was 10.\n 1000/10 = 100, so sample has fold change higher than the threshold and the peak\n is not considered a blank [default = %default]"\n ),\n- make_option("--blank_class", default=\'blank\', type="character",\n- help="A string representing the class that will be used for the blank.[default = %default]"\n+ make_option("--blank_class", default = "blank", type = "character",\n+ help = "A string representing the class that will be used for the blank.[default = %default]"\n ),\n- make_option("--egauss_thr", default=NA,\n- help="Threshold for filtering out non gaussian shaped peaks. Note this only works\n+ make_option("--egauss_thr", default = NA,\n+ help = "Threshold for filtering out non gaussian shaped peaks. Note this only works\n if the \'verbose columns\' and \'fit gauss\' was used with xcms\n [default = %default]"\n ),\n- make_option("--rsd_i_sample", default=100,\n- help="RSD threshold for the samples [default = %default]"\n+ make_option("--rsd_i_sample", default = 100,\n+ help = "RSD threshold for the samples [default = %default]"\n ),\n- make_option("--minfrac_sample", default=0.8,\n- help="minimum fraction of files for features needed for the samples [default = %default]"\n+ make_option("--minfrac_sample", default = 0.8,\n+ help = "minimum fraction of files for f'..b' is currently allowed to be used with this tool\')\n+ if (length(chosen_blank) > 1) {\n+ print("ERROR: only 1 blank is currently allowed to be used with this tool")\n quit()\n }\n blank_class <- as.character(chosen_blank)\n@@ -145,47 +140,47 @@\n }\n \n \n-if (is.null(opt$multilist)){\n+if (is.null(opt$multilist)) {\n ffrm_out <- flag_remove(xset,\n- pol=opt$polarity,\n- rsd_i_blank=opt$rsd_i_blank,\n- minfrac_blank=opt$minfrac_blank,\n- rsd_rt_blank=opt$rsd_rt_blank,\n- ithres_blank=opt$ithres_blank,\n- s2b=opt$s2b,\n- ref.class=blank_class,\n- egauss_thr=opt$egauss_thr,\n- rsd_i_sample=opt$rsd_i_sample,\n- minfrac_sample=opt$minfrac_sample,\n- rsd_rt_sample=opt$rsd_rt_sample,\n- ithres_sample=opt$ithres_sample,\n- minfrac_xcms=opt$minfrac_xcms,\n- mzwid=opt$mzwid,\n- bw=opt$bw,\n- out_dir=opt$out_dir,\n- temp_save=temp_save,\n- remove_spectra=remove_spectra,\n- grp_rm_ids=unlist(strsplit(as.character(opt$grp_rm_ids), split=", "))[[1]])\n- print(\'flag remove finished\')\n+ pol = opt$polarity,\n+ rsd_i_blank = opt$rsd_i_blank,\n+ minfrac_blank = opt$minfrac_blank,\n+ rsd_rt_blank = opt$rsd_rt_blank,\n+ ithres_blank = opt$ithres_blank,\n+ s2b = opt$s2b,\n+ ref.class = blank_class,\n+ egauss_thr = opt$egauss_thr,\n+ rsd_i_sample = opt$rsd_i_sample,\n+ minfrac_sample = opt$minfrac_sample,\n+ rsd_rt_sample = opt$rsd_rt_sample,\n+ ithres_sample = opt$ithres_sample,\n+ minfrac_xcms = opt$minfrac_xcms,\n+ mzwid = opt$mzwid,\n+ bw = opt$bw,\n+ out_dir = opt$out_dir,\n+ temp_save = temp_save,\n+ remove_spectra = remove_spectra,\n+ grp_rm_ids = unlist(strsplit(as.character(opt$grp_rm_ids), split = ", "))[[1]])\n+ print("flag remove finished")\n xset <- ffrm_out[[1]]\n grp_peaklist <- ffrm_out[[2]]\n removed_peaks <- ffrm_out[[3]]\n \n- save.image(file=file.path(opt$out_dir, \'xset_filtered.RData\'), version=2)\n+ save.image(file = file.path(opt$out_dir, "xset_filtered.RData"), version = 2)\n \n # grpid needed for mspurity ID needed for deconrank... (will clean up at some up)\n- peak_pth <- file.path(opt$out_dir, \'peaklist_filtered.tsv\')\n+ peak_pth <- file.path(opt$out_dir, "peaklist_filtered.tsv")\n print(peak_pth)\n- write.table(data.frame(\'grpid\'=rownames(grp_peaklist), \'ID\'=rownames(grp_peaklist), grp_peaklist),\n- peak_pth, row.names=FALSE, sep=\'\\t\')\n+ write.table(data.frame("grpid" = rownames(grp_peaklist), "ID" = rownames(grp_peaklist), grp_peaklist),\n+ peak_pth, row.names = FALSE, sep = "\\t")\n \n removed_peaks <- data.frame(removed_peaks)\n- write.table(data.frame(\'ID\'=rownames(removed_peaks),removed_peaks),\n- file.path(opt$out_dir, \'removed_peaks.tsv\'), row.names=FALSE, sep=\'\\t\')\n+ write.table(data.frame("ID" = rownames(removed_peaks), removed_peaks),\n+ file.path(opt$out_dir, "removed_peaks.tsv"), row.names = FALSE, sep = "\\t")\n \n }else{\n \n- \n+ # nolint start\n # TODO\n #xsets <- split(xset, multilist_df$multlist)\n #\n@@ -193,12 +188,10 @@\n #\n #for (mgrp in mult_grps){\n # xset_i <- xsets[mgrp]\n- # xcms::group(xset_i, \n+ # xcms::group(xset_i,\n #\n # }\n-\n+ # nolint end\n \n \n }\n-\n-\n' |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a frag4feature.R --- a/frag4feature.R Fri Nov 13 09:52:35 2020 +0000 +++ b/frag4feature.R Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| @@ -3,18 +3,18 @@ library(xcms) print(sessionInfo()) -xset_pa_filename_fix <- function(opt, pa, xset=NULL){ +xset_pa_filename_fix <- function(opt, pa, xset=NULL) { - if (!is.null(opt$mzML_files) && !is.null(opt$galaxy_names)){ + if (!is.null(opt$mzML_files) && !is.null(opt$galaxy_names)) { # NOTE: Relies on the pa@fileList having the names of files given as 'names' of the variables # needs to be done due to Galaxy moving the files around and screwing up any links to files - filepaths <- trimws(strsplit(opt$mzML_files, ',')[[1]]) + filepaths <- trimws(strsplit(opt$mzML_files, ",")[[1]]) # nolint + filepaths <- filepaths[filepaths != ""] - new_names <- basename(filepaths) - galaxy_names <- trimws(strsplit(opt$galaxy_names, ',')[[1]]) + galaxy_names <- trimws(strsplit(opt$galaxy_names, ",")[[1]]) galaxy_names <- galaxy_names[galaxy_names != ""] nsave <- names(pa@fileList) @@ -28,14 +28,14 @@ } print(pa@fileList) - if(!is.null(xset)){ + if (!is.null(xset)) { print(xset@filepaths) - if(!all(basename(pa@fileList)==basename(xset@filepaths))){ - if(!all(names(pa@fileList)==basename(xset@filepaths))){ - print('FILELISTS DO NOT MATCH') - message('FILELISTS DO NOT MATCH') + if (!all(basename(pa@fileList) == basename(xset@filepaths))) { + if (!all(names(pa@fileList) == basename(xset@filepaths))) { + print("FILELISTS DO NOT MATCH") + message("FILELISTS DO NOT MATCH") quit(status = 1) }else{ xset@filepaths <- unname(pa@fileList) @@ -48,26 +48,26 @@ option_list <- list( - make_option(c("-o", "--out_dir"), type="character"), - make_option("--pa", type="character"), - make_option("--xset", type="character"), - make_option("--ppm", default=10), - make_option("--plim", default=0.0), - make_option("--convert2RawRT", action="store_true"), - make_option("--intense", action="store_true"), - make_option("--createDB", action="store_true"), - make_option("--cores", default=4), - make_option("--mzML_files", type="character"), - make_option("--galaxy_names", type="character"), - make_option("--grp_peaklist", type="character"), - make_option("--useGroup", action="store_true") + make_option(c("-o", "--out_dir"), type = "character"), + make_option("--pa", type = "character"), + make_option("--xset", type = "character"), + make_option("--ppm", default = 10), + make_option("--plim", default = 0.0), + make_option("--convert2RawRT", action = "store_true"), + make_option("--intense", action = "store_true"), + make_option("--createDB", action = "store_true"), + make_option("--cores", default = 4), + make_option("--mzML_files", type = "character"), + make_option("--galaxy_names", type = "character"), + make_option("--grp_peaklist", type = "character"), + make_option("--useGroup", action = "store_true") ) # store options -opt<- parse_args(OptionParser(option_list=option_list)) +opt <- parse_args(OptionParser(option_list = option_list)) print(opt) -loadRData <- function(rdata_path, name){ +loadRData <- function(rdata_path, name) { #loads an RData file, and returns the named xset object if it is there load(rdata_path) return(get(ls()[ls() %in% name])) @@ -78,19 +78,19 @@ getxcmsSetObject <- function(xobject) { # XCMS 1.x if (class(xobject) == "xcmsSet") - return (xobject) + return(xobject) # XCMS 3.x if (class(xobject) == "XCMSnExp") { # Get the legacy xcmsSet object - suppressWarnings(xset <- as(xobject, 'xcmsSet')) + suppressWarnings(xset <- as(xobject, "xcmsSet")) sampclass(xset) <- xset@phenoData$sample_group - return (xset) + return(xset) } } # Requires -pa <- loadRData(opt$pa, 'pa') -xset <- loadRData(opt$xset, c('xset','xdata')) +pa <- loadRData(opt$pa, "pa") +xset <- loadRData(opt$xset, c("xset", "xdata")) xset <- getxcmsSetObject(xset) pa@cores <- opt$cores @@ -98,63 +98,60 @@ print(pa@fileList) print(xset@filepaths) -if(is.null(opt$intense)){ - intense = FALSE +if (is.null(opt$intense)) { + intense <- FALSE }else{ - intense = TRUE + intense <- TRUE } -if(is.null(opt$convert2RawRT)){ - convert2RawRT = FALSE +if (is.null(opt$convert2RawRT)) { + convert2RawRT <- FALSE }else{ - convert2RawRT= TRUE + convert2RawRT <- TRUE } -if(is.null(opt$createDB)){ - createDB = FALSE +if (is.null(opt$createDB)) { + createDB <- FALSE }else{ - createDB = TRUE + createDB <- TRUE } -if(is.null(opt$useGroup)){ +if (is.null(opt$useGroup)) { fix <- xset_pa_filename_fix(opt, pa, xset) pa <- fix[[1]] xset <- fix[[2]] - useGroup=FALSE + useGroup <- FALSE }else{ # if are only aligning to the group not eah file we do not need to align the files between the xset and pa object - print('useGroup') + print("useGroup") fix <- xset_pa_filename_fix(opt, pa) pa <- fix[[1]] - useGroup=TRUE + useGroup <- TRUE } -if(is.null(opt$grp_peaklist)){ - grp_peaklist = NA +if (is.null(opt$grp_peaklist)) { + grp_peaklist <- NA }else{ - grp_peaklist = opt$grp_peaklist + grp_peaklist <- opt$grp_peaklist } print(useGroup) - - -pa <- msPurity::frag4feature(pa=pa, - xset=xset, - ppm=opt$ppm, - plim=opt$plim, - intense=intense, - convert2RawRT=convert2RawRT, - db_name='alldata.sqlite', - out_dir=opt$out_dir, - grp_peaklist=grp_peaklist, - create_db=createDB, - use_group=useGroup) - +pa <- msPurity::frag4feature(pa = pa, + xset = xset, + ppm = opt$ppm, + plim = opt$plim, + intense = intense, + convert2RawRT = convert2RawRT, + db_name = "alldata.sqlite", + out_dir = opt$out_dir, + grp_peaklist = grp_peaklist, + create_db = createDB, + use_group = useGroup) print(pa) -save(pa, file=file.path(opt$out_dir, 'frag4feature_output.RData')) +save(pa, file = file.path(opt$out_dir, "frag4feature_output.RData")) pa@grped_df$filename <- sapply(pa@grped_df$fileid, function(x) names(pa@fileList)[as.integer(x)]) print(head(pa@grped_df)) -write.table(pa@grped_df, file.path(opt$out_dir, 'frag4feature_output.tsv'), row.names=FALSE, sep='\t') +write.table(pa@grped_df, file.path(opt$out_dir, "frag4feature_output.tsv"), row.names = FALSE, sep = "\t") |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a macros.xml --- a/macros.xml Fri Nov 13 09:52:35 2020 +0000 +++ b/macros.xml Thu Mar 04 12:34:06 2021 +0000 |
| b |
| @@ -1,17 +1,17 @@ <?xml version="1.0"?> <macros> - <token name="@TOOL_VERSION@">1.12.2</token> - <token name="@GALAXY_TOOL_VERSION@">3</token> + <token name="@TOOL_VERSION@">1.16.2</token> + <token name="@GALAXY_TOOL_VERSION@">0</token> <xml name="requirements"> <requirements> <requirement type="package" version="@TOOL_VERSION@" >bioconductor-mspurity</requirement> - <requirement type="package" version="1.42.0" >bioconductor-camera</requirement> - <requirement type="package" version="3.8.0" >bioconductor-xcms</requirement> - <requirement type="package" version="1.14.0" >bioconductor-mspuritydata</requirement> - <requirement type="package" version="1.6.4">r-optparse</requirement> - <requirement type="package" version="1.1.1">r-rpostgres</requirement> - <requirement type="package" version="0.10.17">r-rmysql</requirement> + <requirement type="package" version="1.46.0" >bioconductor-camera</requirement> + <requirement type="package" version="3.12.0" >bioconductor-xcms</requirement> + <requirement type="package" version="1.16.0" >bioconductor-mspuritydata</requirement> + <requirement type="package" version="1.6.6">r-optparse</requirement> + <requirement type="package" version="1.3.1">r-rpostgres</requirement> + <requirement type="package" version="0.10.21">r-rmysql</requirement> <yield /> </requirements> </xml> @@ -23,13 +23,13 @@ <xml name="offsets"> <param argument="--minoffset" type="float" label="minoffset" value="0.5" help="Offset to the 'left' for the precursor range e.g. if precursor of interest is - 100.0 then the range would be from 999.5 to 100.0"/> + 100.0 then the range would be from 99.5 to 100.0"/> <param argument="--maxoffset" type="float" label="maxoffset" value="0.5" help="Offset to the 'right' for the precursor range e.g. if precursor of interest is 100.0 then the range would be from 100.0 to 100.5"/> </xml> <xml name="general_params"> - <param argument="--ilim" type="float" value="0.05" + <param argument="--ilim" type="float" value="0.05" label="Threshold to remove peaks below x % of the relative intensity of precursor of interest" help="All peaks less than this percentage of the precursor ion of interest will be @@ -337,8 +337,8 @@ <when value="true"> <param argument="--@QL_SHRT@_spectraTypes" type="select" multiple="true" label="Spectra type" > <option value="av_all" selected="true">Averaged all spectra ignoring inter-intra relationships </option> - <option value="av_inter">Averaged inter spectra</option> - <option value="av_intra">Averaged intra spectra </option> + <option value="inter">Averaged inter spectra</option> + <option value="intra">Averaged intra spectra </option> <option value="scans">All individual scans</option> <option value="NA">Not applicable/defined</option> </param> |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a purityA.R --- a/purityA.R Fri Nov 13 09:52:35 2020 +0000 +++ b/purityA.R Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| @@ -3,91 +3,90 @@ print(sessionInfo()) option_list <- list( - make_option(c("-o", "--out_dir"), type="character"), - make_option("--mzML_files", type="character"), - make_option("--galaxy_names", type="character"), - make_option("--minOffset", type="numeric"), - make_option("--maxOffset", type="numeric"), - make_option("--ilim", type="numeric"), - make_option("--iwNorm", default="none", type="character"), - make_option("--exclude_isotopes", action="store_true"), - make_option("--isotope_matrix", type="character"), - make_option("--mostIntense", action="store_true"), - make_option("--plotP", action="store_true"), - make_option("--nearest", action="store_true"), - make_option("--cores", default=4), - make_option("--ppmInterp", default=7) + make_option(c("-o", "--out_dir"), type = "character"), + make_option("--mzML_files", type = "character"), + make_option("--galaxy_names", type = "character"), + make_option("--minOffset", type = "numeric"), + make_option("--maxOffset", type = "numeric"), + make_option("--ilim", type = "numeric"), + make_option("--iwNorm", default = "none", type = "character"), + make_option("--exclude_isotopes", action = "store_true"), + make_option("--isotope_matrix", type = "character"), + make_option("--mostIntense", action = "store_true"), + make_option("--plotP", action = "store_true"), + make_option("--nearest", action = "store_true"), + make_option("--cores", default = 4), + make_option("--ppmInterp", default = 7) ) -opt <- parse_args(OptionParser(option_list=option_list)) +opt <- parse_args(OptionParser(option_list = option_list)) print(opt) - -if (opt$iwNorm=='none'){ - iwNorm = FALSE - iwNormFun = NULL -}else if (opt$iwNorm=='gauss'){ - iwNorm = TRUE - if (is.null(opt$minOffset) || is.null(opt$maxOffset)){ - print('User has to define offsets if using Gaussian normalisation') +if (opt$iwNorm == "none") { + iwNorm <- FALSE + iwNormFun <- NULL +}else if (opt$iwNorm == "gauss") { + iwNorm <- TRUE + if (is.null(opt$minOffset) || is.null(opt$maxOffset)) { + print("User has to define offsets if using Gaussian normalisation") }else{ - iwNormFun = msPurity::iwNormGauss(minOff=-as.numeric(opt$minOffset), - maxOff=as.numeric(opt$maxOffset)) + iwNormFun <- msPurity::iwNormGauss(minOff = -as.numeric(opt$minOffset), + maxOff = as.numeric(opt$maxOffset)) } -}else if (opt$iwNorm=='rcosine'){ - iwNorm = TRUE - if (is.null(opt$minOffset) || is.null(opt$maxOffset)){ - print('User has to define offsets if using R-cosine normalisation') +}else if (opt$iwNorm == "rcosine") { + iwNorm <- TRUE + if (is.null(opt$minOffset) || is.null(opt$maxOffset)) { + print("User has to define offsets if using R-cosine normalisation") }else{ - iwNormFun = msPurity::iwNormRcosine(minOff=-as.numeric(opt$minOffset), - maxOff=as.numeric(opt$maxOffset)) + iwNormFun <- msPurity::iwNormRcosine(minOff = -as.numeric(opt$minOffset), + maxOff = as.numeric(opt$maxOffset)) } -}else if (opt$iwNorm=='QE5'){ - iwNorm = TRUE - iwNormFun = msPurity::iwNormQE.5() +}else if (opt$iwNorm == "QE5") { + iwNorm <- TRUE + iwNormFun <- msPurity::iwNormQE.5() } -filepaths <- trimws(strsplit(opt$mzML_files, ',')[[1]]) +filepaths <- trimws(strsplit(opt$mzML_files, ",")[[1]]) filepaths <- filepaths[filepaths != ""] -if(is.null(opt$minOffset) || is.null(opt$maxOffset)){ - offsets = NA +if (is.null(opt$minOffset) || is.null(opt$maxOffset)) { + offsets <- NA }else{ - offsets = as.numeric(c(opt$minOffset, opt$maxOffset)) + offsets <- as.numeric(c(opt$minOffset, opt$maxOffset)) } -if(is.null(opt$mostIntense)){ - mostIntense = FALSE +if (is.null(opt$mostIntense)) { + mostIntense <- FALSE }else{ - mostIntense = TRUE + mostIntense <- TRUE } -if(is.null(opt$nearest)){ - nearest = FALSE +if (is.null(opt$nearest)) { + nearest <- FALSE }else{ - nearest = TRUE + nearest <- TRUE } -if(is.null(opt$plotP)){ - plotP = FALSE - plotdir = NULL +if (is.null(opt$plotP)) { + plotP <- FALSE + plotdir <- NULL }else{ - plotP = TRUE - plotdir = opt$out_dir + plotP <- TRUE + plotdir <- opt$out_dir } -if (is.null(opt$isotope_matrix)){ +if (is.null(opt$isotope_matrix)) { im <- NULL }else{ im <- read.table(opt$isotope_matrix, - header = TRUE, sep='\t', stringsAsFactors = FALSE) + header = TRUE, sep = "\t", stringsAsFactors = FALSE) } -if (is.null(opt$exclude_isotopes)){ +if (is.null(opt$exclude_isotopes)) { isotopes <- FALSE }else{ isotopes <- TRUE @@ -110,20 +109,16 @@ ppmInterp = opt$ppmInterp) -if (!is.null(opt$galaxy_names)){ - galaxy_names <- trimws(strsplit(opt$galaxy_names, ',')[[1]]) +if (!is.null(opt$galaxy_names)) { + galaxy_names <- trimws(strsplit(opt$galaxy_names, ",")[[1]]) galaxy_names <- galaxy_names[galaxy_names != ""] names(pa@fileList) <- galaxy_names } print(pa) -save(pa, file=file.path(opt$out_dir, 'purityA_output.RData')) +save(pa, file = file.path(opt$out_dir, "purityA_output.RData")) pa@puritydf$filename <- sapply(pa@puritydf$fileid, function(x) names(pa@fileList)[as.integer(x)]) print(head(pa@puritydf)) -write.table(pa@puritydf, file.path(opt$out_dir, 'purityA_output.tsv'), row.names=FALSE, sep='\t') - -# removed_peaks <- data.frame(removed_peaks) -# write.table(data.frame('ID'=rownames(removed_peaks),removed_peaks), -# file.path(opt$out_dir, 'removed_peaks.txt'), row.names=FALSE, sep='\t') +write.table(pa@puritydf, file.path(opt$out_dir, "purityA_output.tsv"), row.names = FALSE, sep = "\t") |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a purityX.R --- a/purityX.R Fri Nov 13 09:52:35 2020 +0000 +++ b/purityX.R Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| b'@@ -3,67 +3,66 @@\n print(sessionInfo())\n \n option_list <- list(\n- make_option(c("--xset_path"), type="character"),\n- make_option(c("-o", "--out_dir"), type="character"),\n- make_option(c("--mzML_path"), type="character"),\n- make_option("--minOffset", default=0.5),\n- make_option("--maxOffset", default=0.5),\n- make_option("--ilim", default=0.05),\n- make_option("--iwNorm", default="none", type="character"),\n- make_option("--exclude_isotopes", action="store_true"),\n- make_option("--isotope_matrix", type="character"),\n- make_option("--purityType", default="purityFWHMmedian"),\n- make_option("--singleFile", default=0),\n- make_option("--cores", default=4),\n- make_option("--xgroups", type="character"),\n- make_option("--rdata_name", default=\'xset\'),\n- make_option("--camera_xcms", default=\'xset\'),\n- make_option("--files", type="character"),\n- make_option("--galaxy_files", type="character"),\n- make_option("--choose_class", type="character"),\n- make_option("--ignore_files", type="character"),\n- make_option("--rtraw_columns", action="store_true")\n+ make_option(c("--xset_path"), type = "character"),\n+ make_option(c("-o", "--out_dir"), type = "character"),\n+ make_option(c("--mzML_path"), type = "character"),\n+ make_option("--minOffset", default = 0.5),\n+ make_option("--maxOffset", default = 0.5),\n+ make_option("--ilim", default = 0.05),\n+ make_option("--iwNorm", default = "none", type = "character"),\n+ make_option("--exclude_isotopes", action = "store_true"),\n+ make_option("--isotope_matrix", type = "character"),\n+ make_option("--purityType", default = "purityFWHMmedian"),\n+ make_option("--singleFile", default = 0),\n+ make_option("--cores", default = 4),\n+ make_option("--xgroups", type = "character"),\n+ make_option("--rdata_name", default = "xset"),\n+ make_option("--camera_xcms", default = "xset"),\n+ make_option("--files", type = "character"),\n+ make_option("--galaxy_files", type = "character"),\n+ make_option("--choose_class", type = "character"),\n+ make_option("--ignore_files", type = "character"),\n+ make_option("--rtraw_columns", action = "store_true")\n )\n \n \n-opt<- parse_args(OptionParser(option_list=option_list))\n+opt <- parse_args(OptionParser(option_list = option_list))\n print(opt)\n \n \n-if (!is.null(opt$xgroups)){\n- xgroups = as.numeric(strsplit(opt$xgroups, \',\')[[1]])\n+if (!is.null(opt$xgroups)) {\n+ xgroups <- as.numeric(strsplit(opt$xgroups, ",")[[1]])\n }else{\n- xgroups = NULL\n+ xgroups <- NULL\n }\n \n \n-\n print(xgroups)\n \n-if (!is.null(opt$remove_nas)){\n- df <- df[!is.na(df$mz),]\n+if (!is.null(opt$remove_nas)) {\n+ df <- df[!is.na(df$mz), ]\n }\n \n-if (is.null(opt$isotope_matrix)){\n+if (is.null(opt$isotope_matrix)) {\n im <- NULL\n }else{\n im <- read.table(opt$isotope_matrix,\n- header = TRUE, sep=\'\\t\', stringsAsFactors = FALSE)\n+ header = TRUE, sep = "\\t", stringsAsFactors = FALSE)\n }\n \n-if (is.null(opt$exclude_isotopes)){\n+if (is.null(opt$exclude_isotopes)) {\n isotopes <- FALSE\n }else{\n isotopes <- TRUE\n }\n \n-if (is.null(opt$rtraw_columns)){\n+if (is.null(opt$rtraw_columns)) {\n rtraw_columns <- FALSE\n }else{\n rtraw_columns <- TRUE\n }\n \n-loadRData <- function(rdata_path, xset_name){\n+loadRData <- function(rdata_path, xset_name) {\n #loads an RData file, and returns the named xset object if it is there\n load(rdata_path)\n return(get(ls()[ls() == xset_name]))\n@@ -71,7 +70,7 @@\n \n target_obj <- loadRData(opt$xset_path, opt$rdata_name)\n \n-if (opt$camera_xcms==\'camera\'){\n+if (opt$camera_xcms == "camera") {\n xset <- target_obj@xcmsSet\n }else{\n xset <- target_obj\n@@ -79,36 +78,35 @@\n \n print(xset)\n \n-minOffset = as.numeric(opt$minOffset)\n-maxOffset = as.numeric(opt$maxOffset)\n-\n+minOffset <- as.numeric(opt$minOffset)\n+maxOffset <- as.numeric(opt$maxOffset)\n \n-if (opt$iwNorm==\'none\'){\n- iwNorm = FALSE\n- iwNormFun = NULL\n-}else if (opt$iwNorm==\'gauss\'){\n- iwNorm = TRUE\n- iwNormFun = msPurity::iwNormGauss(mi'..b'rimws(strsplit(opt$galaxy_files, ",")[[1]])\n galaxy_files <- galaxy_files[galaxy_files != ""]\n xset@filepaths <- galaxy_files[update_idx]\n }else{\n@@ -116,27 +114,26 @@\n }\n }\n \n-if (!is.null(opt$choose_class)){\n- classes <- trimws(strsplit(opt$choose_class, \',\')[[1]])\n-\n+if (!is.null(opt$choose_class)) {\n+ classes <- trimws(strsplit(opt$choose_class, ",")[[1]])\n \n ignore_files_class <- which(!as.character(xset@phenoData$class) %in% classes)\n \n- print(\'choose class\')\n+ print("choose class")\n print(ignore_files_class)\n }else{\n ignore_files_class <- NA\n }\n \n-if (!is.null(opt$ignore_files)){\n- ignore_files_string <- trimws(strsplit(opt$ignore_files, \',\')[[1]])\n+if (!is.null(opt$ignore_files)) {\n+ ignore_files_string <- trimws(strsplit(opt$ignore_files, ",")[[1]])\n filenames <- rownames(xset@phenoData)\n ignore_files <- which(filenames %in% ignore_files_string)\n \n ignore_files <- unique(c(ignore_files, ignore_files_class))\n ignore_files <- ignore_files[ignore_files != ""]\n }else{\n- if (anyNA(ignore_files_class)){\n+ if (anyNA(ignore_files_class)) {\n ignore_files <- NULL\n }else{\n ignore_files <- ignore_files_class\n@@ -144,41 +141,40 @@\n \n }\n \n-print(\'ignore_files\')\n+print("ignore_files")\n print(ignore_files)\n \n \n-ppLCMS <- msPurity::purityX(xset=xset,\n- offsets=c(minOffset, maxOffset),\n- cores=opt$cores,\n- xgroups=xgroups,\n- purityType=opt$purityType,\n- ilim = opt$ilim,\n- isotopes = isotopes,\n- im = im,\n- iwNorm = iwNorm,\n- iwNormFun = iwNormFun,\n- singleFile = opt$singleFile,\n- fileignore = ignore_files,\n- rtrawColumns=rtraw_columns)\n-\n+ppLCMS <- msPurity::purityX(xset = xset,\n+ offsets = c(minOffset, maxOffset),\n+ cores = opt$cores,\n+ xgroups = xgroups,\n+ purityType = opt$purityType,\n+ ilim = opt$ilim,\n+ isotopes = isotopes,\n+ im = im,\n+ iwNorm = iwNorm,\n+ iwNormFun = iwNormFun,\n+ singleFile = opt$singleFile,\n+ fileignore = ignore_files,\n+ rtrawColumns = rtraw_columns)\n \n dfp <- ppLCMS@predictions\n \n # to make compatable with deconrank\n-colnames(dfp)[colnames(dfp)==\'grpid\'] = \'peakID\'\n-colnames(dfp)[colnames(dfp)==\'median\'] = \'medianPurity\'\n-colnames(dfp)[colnames(dfp)==\'mean\'] = \'meanPurity\'\n-colnames(dfp)[colnames(dfp)==\'sd\'] = \'sdPurity\'\n-colnames(dfp)[colnames(dfp)==\'stde\'] = \'sdePurity\'\n-colnames(dfp)[colnames(dfp)==\'RSD\'] = \'cvPurity\'\n-colnames(dfp)[colnames(dfp)==\'pknm\'] = \'pknmPurity\'\n-if(sum(is.na(dfp$medianPurity))>0){\n- dfp[is.na(dfp$medianPurity),]$medianPurity = 0\n+colnames(dfp)[colnames(dfp) == "grpid"] <- "peakID"\n+colnames(dfp)[colnames(dfp) == "median"] <- "medianPurity"\n+colnames(dfp)[colnames(dfp) == "mean"] <- "meanPurity"\n+colnames(dfp)[colnames(dfp) == "sd"] <- "sdPurity"\n+colnames(dfp)[colnames(dfp) == "stde"] <- "sdePurity"\n+colnames(dfp)[colnames(dfp) == "RSD"] <- "cvPurity"\n+colnames(dfp)[colnames(dfp) == "pknm"] <- "pknmPurity"\n+\n+if (sum(is.na(dfp$medianPurity)) > 0) {\n+ dfp[is.na(dfp$medianPurity), ]$medianPurity <- 0\n }\n \n+print(head(dfp))\n+write.table(dfp, file.path(opt$out_dir, "purityX_output.tsv"), row.names = FALSE, sep = "\\t")\n \n-print(head(dfp))\n-write.table(dfp, file.path(opt$out_dir, \'purityX_output.tsv\'), row.names=FALSE, sep=\'\\t\')\n-\n-save.image(file.path(opt$out_dir, \'purityX_output.RData\'))\n+save.image(file.path(opt$out_dir, "purityX_output.RData"))\n' |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a spectralMatching.R --- a/spectralMatching.R Fri Nov 13 09:52:35 2020 +0000 +++ b/spectralMatching.R Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| b'@@ -3,107 +3,111 @@\n library(optparse)\n print(sessionInfo())\n # load in library spectra config\n-source_local <- function(fname){ argv <- commandArgs(trailingOnly=FALSE); base_dir <- dirname(substring(argv[grep("--file=", argv)], 8)); source(paste(base_dir, fname, sep="/")) }\n+source_local <- function(fname) {\n+ argv <- commandArgs(trailingOnly = FALSE)\n+ base_dir <- dirname(substring(argv[grep("--file=", argv)], 8))\n+ source(paste(base_dir, fname, sep = "/"))\n+}\n source_local("dbconfig.R")\n \n option_list <- list(\n- make_option(c("-o", "--outDir"), type="character"),\n- make_option("--q_dbPth", type="character"),\n- make_option("--l_dbPth", type="character"),\n+ make_option(c("-o", "--outDir"), type = "character"),\n+ make_option("--q_dbPth", type = "character"),\n+ make_option("--l_dbPth", type = "character"),\n \n- make_option("--q_dbType", type="character", default=NA),\n- make_option("--l_dbType", type="character", default=NA),\n+ make_option("--q_dbType", type = "character", default = NA),\n+ make_option("--l_dbType", type = "character", default = NA),\n \n- make_option("--q_msp", type="character", default=NA),\n- make_option("--l_msp", type="character", default=NA),\n+ make_option("--q_msp", type = "character", default = NA),\n+ make_option("--l_msp", type = "character", default = NA),\n \n- make_option("--q_defaultDb", action="store_true"),\n- make_option("--l_defaultDb", action="store_true"),\n+ make_option("--q_defaultDb", action = "store_true"),\n+ make_option("--l_defaultDb", action = "store_true"),\n \n- make_option("--q_ppmPrec", type="double"),\n- make_option("--l_ppmPrec", type="double"),\n+ make_option("--q_ppmPrec", type = "double"),\n+ make_option("--l_ppmPrec", type = "double"),\n \n- make_option("--q_ppmProd", type="double"),\n- make_option("--l_ppmProd", type="double"),\n+ make_option("--q_ppmProd", type = "double"),\n+ make_option("--l_ppmProd", type = "double"),\n \n- make_option("--q_raThres", type="double", default=NA),\n- make_option("--l_raThres", type="double", default=NA),\n+ make_option("--q_raThres", type = "double", default = NA),\n+ make_option("--l_raThres", type = "double", default = NA),\n \n- make_option("--q_polarity", type="character", default=NA),\n- make_option("--l_polarity", type="character", default=NA),\n+ make_option("--q_polarity", type = "character", default = NA),\n+ make_option("--l_polarity", type = "character", default = NA),\n \n- make_option("--q_purity", type="double", default=NA),\n- make_option("--l_purity", type="double", default=NA),\n+ make_option("--q_purity", type = "double", default = NA),\n+ make_option("--l_purity", type = "double", default = NA),\n \n- make_option("--q_xcmsGroups", type="character", default=NA),\n- make_option("--l_xcmsGroups", type="character", default=NA),\n+ make_option("--q_xcmsGroups", type = "character", default = NA),\n+ make_option("--l_xcmsGroups", type = "character", default = NA),\n \n- make_option("--q_pids", type="character", default=NA),\n- make_option("--l_pids", type="character", default=NA),\n+ make_option("--q_pids", type = "character", default = NA),\n+ make_option("--l_pids", type = "character", default = NA),\n \n- make_option("--q_rtrangeMin", type="double", default=NA),\n- make_option("--l_rtrangeMin", type="double", default=NA),\n+ make_option("--q_rtrangeMin", type = "double", default = NA),\n+ make_option("--l_rtrangeMin", type = "double", default = NA),\n \n- make_option("--q_rtrangeMax", type="double", default=NA),\n- make_option("--l_rtrangeMax", type="double", default=NA),\n+ make_option("--q_rtrangeMax", type = "double", default = NA),\n+ make_option("--l_rtrangeMax", type = "double", default = NA),\n \n- make_option("--q_accessions", type="character", default=NA),\n- make_option("--l_accessions", type="character", default=NA),\n+ make_option("--q_accessions", type = "character", default = NA),\n+ make_option("--l_accessions", type = "character", default = NA),\n \n- make_option("--q_sources", type="character", default=NA),\n'..b'(opt$q_spectraFilter)){\n+if (!is.null(opt$q_spectraFilter)) {\n q_spectraFilter <- TRUE\n }else{\n q_spectraFilter <- FALSE\n }\n \n-if(!is.null(opt$updateDb)){\n+if (!is.null(opt$updateDb)) {\n updateDb <- TRUE\n }else{\n updateDb <- FALSE\n }\n \n-if(!is.null(opt$copyDb)){\n+if (!is.null(opt$copyDb)) {\n copyDb <- TRUE\n }else{\n copyDb <- FALSE\n }\n \n-if(!is.null(opt$l_rtrangeMax)){\n+if (!is.null(opt$l_rtrangeMax)) {\n l_rtrangeMax <- opt$l_rtrangeMax\n }else{\n l_rtrangeMax <- NA\n }\n \n-if(!is.null(opt$q_rtrangeMax)){\n+if (!is.null(opt$q_rtrangeMax)) {\n q_rtrangeMax <- opt$q_rtrangeMax\n }else{\n q_rtrangeMax <- NA\n }\n \n-if(!is.null(opt$l_rtrangeMin)){\n+if (!is.null(opt$l_rtrangeMin)) {\n l_rtrangeMin <- opt$l_rtrangeMin\n }else{\n l_rtrangeMin <- NA\n }\n \n-if(!is.null(opt$q_rtrangeMin)){\n+if (!is.null(opt$q_rtrangeMin)) {\n q_rtrangeMin <- opt$q_rtrangeMin\n }else{\n q_rtrangeMin <- NA\n }\n \n-q_check <- checkSPeakMeta(opt$q_dbPth, \'query\')\n-l_check <- checkSPeakMeta(opt$l_dbPth, \'library\')\n+q_check <- checkSPeakMeta(opt$q_dbPth, "query")\n+l_check <- checkSPeakMeta(opt$l_dbPth, "library")\n \n \n-if (q_check && l_check){\n+if (q_check && l_check) {\n sm <- msPurity::spectralMatching(\n q_purity = opt$q_purity,\n l_purity = opt$l_purity,\n- \n+\n q_ppmProd = opt$q_ppmProd,\n l_ppmProd = opt$l_ppmProd,\n- \n+\n q_ppmPrec = opt$q_ppmPrec,\n l_ppmPrec = opt$l_ppmPrec,\n- \n+\n q_raThres = opt$q_raThres,\n l_raThres = opt$l_raThres,\n- \n+\n q_pol = q_polarity,\n l_pol = l_polarity,\n- \n+\n+ q_spectraFilter = q_spectraFilter,\n+ l_spectraFilter = l_spectraFilter,\n+\n q_xcmsGroups = q_xcmsGroups,\n l_xcmsGroups = l_xcmsGroups,\n- \n+\n q_pids = q_pids,\n l_pids = l_pids,\n- \n+\n q_sources = q_sources,\n l_sources = l_sources,\n- \n+\n q_instrumentTypes = q_instrumentTypes,\n l_instrumentTypes = l_instrumentTypes,\n- \n- q_spectraFilter= q_spectraFilter,\n- l_spectraFilter= l_spectraFilter,\n- \n- l_rtrange=c(l_rtrangeMin, l_rtrangeMax),\n- q_rtrange=c(q_rtrangeMin, q_rtrangeMax),\n- \n+\n+ q_spectraTypes = q_spectraTypes,\n+ l_spectraTypes = l_spectraTypes,\n+\n+ l_rtrange = c(l_rtrangeMin, l_rtrangeMax),\n+ q_rtrange = c(q_rtrangeMin, q_rtrangeMax),\n+\n q_accessions = opt$q_accessions,\n- l_accessions= opt$l_accessions,\n- \n+ l_accessions = opt$l_accessions,\n+\n raW = opt$raW,\n mzW = opt$mzW,\n- rttol=opt$rttol,\n- cores=opt$cores,\n- \n- copyDb=copyDb,\n- updateDb=updateDb,\n+ rttol = opt$rttol,\n+ cores = opt$cores,\n+\n+ copyDb = copyDb,\n+ updateDb = updateDb,\n outPth = "db_with_spectral_matching.sqlite",\n- \n+\n q_dbPth = q_dbPth,\n q_dbType = q_dbType,\n q_dbName = q_dbName,\n@@ -347,7 +355,7 @@\n q_dbUser = q_dbUser,\n q_dbPass = q_dbPass,\n q_dbPort = q_dbPort,\n- \n+\n l_dbPth = l_dbPth,\n l_dbType = l_dbType,\n l_dbName = l_dbName,\n@@ -355,15 +363,15 @@\n l_dbUser = l_dbUser,\n l_dbPass = l_dbPass,\n l_dbPort = l_dbPort\n- \n+\n )\n- \n+\n sm <- addQueryNameColumn(sm)\n # Get name of the query results (and merged with the data frames)\n- write.table(sm$matchedResults, \'matched_results.tsv\', sep = \'\\t\', row.names = FALSE, col.names = TRUE)\n- write.table(sm$xcmsMatchedResults, \'xcms_matched_results.tsv\', sep = \'\\t\', row.names = FALSE, col.names = TRUE)\n- \n- if(updateDb){\n+ write.table(sm$matchedResults, "matched_results.tsv", sep = "\\t", row.names = FALSE, col.names = TRUE)\n+ write.table(sm$xcmsMatchedResults, "xcms_matched_results.tsv", sep = "\\t", row.names = FALSE, col.names = TRUE)\n+\n+ if (updateDb) {\n updateDbF(q_con, l_con)\n }\n }\n' |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a test-data/createDatabase_output.sqlite |
| b |
| Binary file test-data/createDatabase_output.sqlite has changed |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a test-data/createDatabase_output_eic.sqlite |
| b |
| Binary file test-data/createDatabase_output_eic.sqlite has changed |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a test-data/createMSP_output_av_all_metadata.msp --- a/test-data/createMSP_output_av_all_metadata.msp Fri Nov 13 09:52:35 2020 +0000 +++ b/test-data/createMSP_output_av_all_metadata.msp Thu Mar 04 12:34:06 2021 +0000 |
| b |
| @@ -10,7 +10,7 @@ CH$LINK: PUBCHEM CID:5328 CH$NAME Unknown XCMS groupid (grpid): 12 -COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.12.2 +COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.16.2 PK$NUM_PEAK: 2 PK$PEAK: m/z int. rel.int. 112.050884246826 502873.46875 100 @@ -28,7 +28,7 @@ CH$LINK: PUBCHEM CID:5328 CH$NAME Unknown XCMS groupid (grpid): 12 -COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.12.2 +COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.16.2 PK$NUM_PEAK: 2 PK$PEAK: m/z int. rel.int. 112.050884246826 502873.46875 100 |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a test-data/createMSP_output_av_all_metadata_custom_adducts.msp --- a/test-data/createMSP_output_av_all_metadata_custom_adducts.msp Fri Nov 13 09:52:35 2020 +0000 +++ b/test-data/createMSP_output_av_all_metadata_custom_adducts.msp Thu Mar 04 12:34:06 2021 +0000 |
| b |
| @@ -10,7 +10,7 @@ CH$LINK: PUBCHEM CID:5328 CH$NAME Unknown XCMS groupid (grpid): 12 -COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.12.2 +COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.16.2 PK$NUM_PEAK: 2 PK$PEAK: m/z int. rel.int. 112.050884246826 502873.46875 100 @@ -28,7 +28,7 @@ CH$LINK: PUBCHEM CID:5328 CH$NAME Unknown XCMS groupid (grpid): 12 -COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.12.2 +COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.16.2 PK$NUM_PEAK: 2 PK$PEAK: m/z int. rel.int. 112.050884246826 502873.46875 100 @@ -46,7 +46,7 @@ CH$LINK: PUBCHEM CID:5328 CH$NAME Unknown XCMS groupid (grpid): 12 -COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.12.2 +COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.16.2 PK$NUM_PEAK: 2 PK$PEAK: m/z int. rel.int. 112.050884246826 502873.46875 100 @@ -64,7 +64,7 @@ CH$LINK: PUBCHEM CID:5328 CH$NAME Unknown XCMS groupid (grpid): 12 -COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.12.2 +COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.16.2 PK$NUM_PEAK: 2 PK$PEAK: m/z int. rel.int. 112.050884246826 502873.46875 100 @@ -82,7 +82,7 @@ CH$LINK: PUBCHEM CID:5328 CH$NAME Unknown XCMS groupid (grpid): 12 -COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.12.2 +COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.16.2 PK$NUM_PEAK: 2 PK$PEAK: m/z int. rel.int. 112.050884246826 502873.46875 100 @@ -100,7 +100,7 @@ CH$LINK: PUBCHEM CID:5328 CH$NAME Unknown XCMS groupid (grpid): 12 -COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.12.2 +COMMENT: Exported from msPurity purityA object using function createMSP, using method 'av_all' msPurity version:1.16.2 PK$NUM_PEAK: 2 PK$PEAK: m/z int. rel.int. 112.050884246826 502873.46875 100 |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a test-data/spectralMatching_db_with_spectral_matching.sqlite |
| b |
| Binary file test-data/spectralMatching_db_with_spectral_matching.sqlite has changed |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a test-data/spectralMatching_db_with_spectral_matching_instrumentTypes.sqlite |
| b |
| Binary file test-data/spectralMatching_db_with_spectral_matching_instrumentTypes.sqlite has changed |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a test-data/spectralMatching_matched_results.tsv --- a/test-data/spectralMatching_matched_results.tsv Fri Nov 13 09:52:35 2020 +0000 +++ b/test-data/spectralMatching_matched_results.tsv Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| @@ -1,3 +1,3 @@ "pid" "grpid" "mz" "mzmin" "mzmax" "rt" "rtmin" "rtmax" "npeaks" "sample" "LCMSMS_2" "LCMSMS_1" "LCMS_2" "LCMS_1" "grp_name" "lpid" "mid" "dpc" "rdpc" "cdpc" "mcount" "allcount" "mpercent" "library_rt" "query_rt" "rtdiff" "library_precursor_mz" "query_precursor_mz" "library_precursor_ion_purity" "query_precursor_ion_purity" "library_accession" "library_precursor_type" "library_entry_name" "inchikey" "library_source_name" "library_compound_name" "query_entry_name" -1663 14 113.035283604395 113.035156497997 113.03541992282 80.50932 77.16429 83.64567 4 4 88462324.9597518 92812020.095242 77298864.2688328 77198465.9156761 "M113T81" 56653 1 0.942265461847349 0.996860823822942 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA -1664 14 113.035283604395 113.035156497997 113.03541992282 80.50932 77.16429 83.64567 4 4 88462324.9597518 92812020.095242 77298864.2688328 77198465.9156761 "M113T81" 56653 2 0.942265461847349 0.996860823822942 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA +1665 14 113.035283604395 113.035156497997 113.03541992282 80.50932 77.16429 83.64567 4 4 88462324.9597518 92812020.095242 77298864.2688328 77198465.9156761 "M113T81" 56653 1 0.942265461847349 0.945232713864488 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA +1666 14 113.035283604395 113.035156497997 113.03541992282 80.50932 77.16429 83.64567 4 4 88462324.9597518 92812020.095242 77298864.2688328 77198465.9156761 "M113T81" 56653 2 0.942265461847349 0.945232713864488 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a test-data/spectralMatching_matched_results_instrumentTypes.tsv --- a/test-data/spectralMatching_matched_results_instrumentTypes.tsv Fri Nov 13 09:52:35 2020 +0000 +++ b/test-data/spectralMatching_matched_results_instrumentTypes.tsv Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| @@ -1,3 +1,3 @@ "pid" "grpid" "mz" "mzmin" "mzmax" "rt" "rtmin" "rtmax" "npeaks" "sample" "LCMSMS_2" "LCMSMS_1" "LCMS_2" "LCMS_1" "grp_name" "lpid" "mid" "dpc" "rdpc" "cdpc" "mcount" "allcount" "mpercent" "library_rt" "query_rt" "rtdiff" "library_precursor_mz" "query_precursor_mz" "library_precursor_ion_purity" "query_precursor_ion_purity" "library_accession" "library_precursor_type" "library_entry_name" "inchikey" "library_source_name" "library_compound_name" "query_entry_name" -1663 14 113.035283604395 113.035156497997 113.03541992282 80.50932 77.16429 83.64567 4 4 88462324.9597518 92812020.095242 77298864.2688328 77198465.9156761 "M113T81" 56653 1 0.942265461847349 0.996860823822942 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA -1664 14 113.035283604395 113.035156497997 113.03541992282 80.50932 77.16429 83.64567 4 4 88462324.9597518 92812020.095242 77298864.2688328 77198465.9156761 "M113T81" 56653 2 0.942265461847349 0.996860823822942 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA +1665 14 113.035283604395 113.035156497997 113.03541992282 80.50932 77.16429 83.64567 4 4 88462324.9597518 92812020.095242 77298864.2688328 77198465.9156761 "M113T81" 56653 1 0.942265461847349 0.945232713864488 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA +1666 14 113.035283604395 113.035156497997 113.03541992282 80.50932 77.16429 83.64567 4 4 88462324.9597518 92812020.095242 77298864.2688328 77198465.9156761 "M113T81" 56653 2 0.942265461847349 0.945232713864488 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a test-data/spectralMatching_xcms_matched_results.tsv --- a/test-data/spectralMatching_xcms_matched_results.tsv Fri Nov 13 09:52:35 2020 +0000 +++ b/test-data/spectralMatching_xcms_matched_results.tsv Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| @@ -1,3 +1,3 @@ "qpid" "lpid" "mid" "dpc" "rdpc" "cdpc" "mcount" "allcount" "mpercent" "library_rt" "query_rt" "rtdiff" "library_precursor_mz" "query_precursor_mz" "library_precursor_ion_purity" "query_precursor_ion_purity" "library_accession" "library_precursor_type" "library_entry_name" "inchikey" "library_source_name" "library_compound_name" "query_entry_name" -1663 56653 1 0.942265461847349 0.996860823822942 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA -1664 56653 2 0.942265461847349 0.996860823822942 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA +1665 56653 1 0.942265461847349 0.945232713864488 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA +1666 56653 2 0.942265461847349 0.945232713864488 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA |
| b |
| diff -r 2f7cd31eba49 -r d4a17be5429a test-data/spectralMatching_xcms_matched_results_instrumentTypes.tsv --- a/test-data/spectralMatching_xcms_matched_results_instrumentTypes.tsv Fri Nov 13 09:52:35 2020 +0000 +++ b/test-data/spectralMatching_xcms_matched_results_instrumentTypes.tsv Thu Mar 04 12:34:06 2021 +0000 |
| [ |
| @@ -1,3 +1,3 @@ "qpid" "lpid" "mid" "dpc" "rdpc" "cdpc" "mcount" "allcount" "mpercent" "library_rt" "query_rt" "rtdiff" "library_precursor_mz" "query_precursor_mz" "library_precursor_ion_purity" "query_precursor_ion_purity" "library_accession" "library_precursor_type" "library_entry_name" "inchikey" "library_source_name" "library_compound_name" "query_entry_name" -1663 56653 1 0.942265461847349 0.996860823822942 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA -1664 56653 2 0.942265461847349 0.996860823822942 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA +1665 56653 1 0.942265461847349 0.945232713864488 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA +1666 56653 2 0.942265461847349 0.945232713864488 0.753812369477879 1 4 0.25 NA 80.50932 NA "113.03508" 113.035283604395 NA 1 "PR100037" "[M+H]+" "Uracil" "ISAKRJDGNUQOIC-UHFFFAOYSA-N" "massbank" "Uracil" NA |