Mercurial > repos > computational-metabolomics > mspurity_combineannotations
diff combineAnnotations.R @ 0:7f3183988100 draft
"planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
author | computational-metabolomics |
---|---|
date | Wed, 27 Nov 2019 13:51:34 -0500 |
parents | |
children | d4376a743f7b |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/combineAnnotations.R Wed Nov 27 13:51:34 2019 -0500 @@ -0,0 +1,103 @@ +library(optparse) +library(msPurity) +print(sessionInfo()) + +# Get the parameter +option_list <- list( + make_option(c("-s","--sm_resultPth"),type="character"), + make_option(c("-m","--metfrag_resultPth"),type="character"), + make_option(c("-c","--sirius_csi_resultPth"),type="character"), + make_option(c("-p","--probmetab_resultPth"),type="character"), + make_option(c("-l","--ms1_lookup_resultPth"),type="character"), + + make_option("--ms1_lookup_checkAdducts", action="store_true"), + make_option("--ms1_lookup_keepAdducts", type="character", default=NA), + make_option("--ms1_lookup_dbSource", type="character", default="hmdb"), + + make_option("--sm_weight", type="numeric"), + make_option("--metfrag_weight", type="numeric"), + make_option("--sirius_csi_weight", type="numeric"), + make_option("--probmetab_weight", type="numeric"), + make_option("--ms1_lookup_weight", type="numeric"), + make_option("--biosim_weight", type="numeric"), + + make_option("--create_new_database", action="store_true"), + make_option("--outdir", type="character", default="."), + + make_option("--compoundDbType", type="character", default="sqlite"), + make_option("--compoundDbPth", type="character", default=NA), + make_option("--compoundDbHost", type="character", default=NA) +) +opt <- parse_args(OptionParser(option_list=option_list)) + +print(opt) + +if (!is.null(opt$create_new_database)){ + sm_resultPth <- file.path(opt$outdir, 'combined_annotations.sqlite') + file.copy(opt$sm_resultPth, sm_resultPth) +}else{ + sm_resultPth <- opt$sm_resultPth +} + +if (is.null(opt$ms1_lookup_checkAdducts)){ + opt$ms1_lookup_checkAdducts <- FALSE +} +if (!is.null(opt$ms1_lookup_keepAdducts)){ + opt$ms1_lookup_keepAdducts <- gsub("__ob__", "[", opt$ms1_lookup_keepAdducts) + opt$ms1_lookup_keepAdducts <- gsub("__cb__", "]", opt$ms1_lookup_keepAdducts) + ms1_lookup_keepAdducts <- strsplit(opt$ms1_lookup_keepAdducts, ",")[[1]] +} + +weights <-list('sm'=opt$sm_weight, + 'metfrag'=opt$metfrag_weight, + 'sirius_csifingerid'= opt$sirius_csi_weight, + 'probmetab'=opt$probmetab_weight, + 'ms1_lookup'=opt$ms1_lookup_weight, + 'biosim'=opt$biosim_weight + ) +print(weights) +if (round(!sum(unlist(weights),0)==1)){ + + stop(paste0('The weights should sum to 1 not ', sum(unlist(weights)))) +} + +if (opt$compoundDbType=='local_config'){ + # load in compound config + # Soure local function taken from workflow4metabolomics + source_local <- function(fname){ argv <- commandArgs(trailingOnly=FALSE); base_dir <- dirname(substring(argv[grep("--file=", argv)], 8)); source(paste(base_dir, fname, sep="/")) } + source_local("dbconfig.R") +}else{ + compoundDbPth = opt$compoundDbPth + compoundDbType = opt$compoundDbType + compoundDbName = NA + compoundDbHost = NA + compoundDbPort = NA + compoundDbUser = NA + compoundDbPass = NA +} + + + +summary_output <- msPurity::combineAnnotations( + sm_resultPth = sm_resultPth, + compoundDbPth = compoundDbPth, + metfrag_resultPth = opt$metfrag_resultPth, + sirius_csi_resultPth = opt$sirius_csi_resultPth, + probmetab_resultPth = opt$probmetab_resultPth, + ms1_lookup_resultPth = opt$ms1_lookup_resultPth, + ms1_lookup_keepAdducts = ms1_lookup_keepAdducts, + ms1_lookup_checkAdducts = opt$ms1_lookup_checkAdducts, + + compoundDbType = compoundDbType, + compoundDbName = compoundDbName, + compoundDbHost = compoundDbHost, + compoundDbPort = compoundDbPort, + compoundDbUser = compoundDbUser, + compoundDbPass = compoundDbPass, + weights = weights) + +write.table(summary_output, file.path(opt$outdir, 'combined_annotations.tsv'), sep = '\t', row.names = FALSE) + + +closeAllConnections() +