Mercurial > repos > proteore > proteore_expression_levels_by_tissue
changeset 4:5cd79aa7aac9 draft
planemo upload commit ed42daf54e6d0fa2a693b501c7ebca4efe4d95e3-dirty
| author | proteore |
|---|---|
| date | Mon, 13 May 2019 11:45:29 -0400 |
| parents | 3bedd074c485 |
| children | b5be6d94f2a1 |
| files | get_expression_profiles.R get_expression_profiles.xml proteore_protein_atlas_normal_tissue.loc.sample proteore_protein_atlas_tumor_tissue.loc.sample |
| diffstat | 4 files changed, 21 insertions(+), 9 deletions(-) [+] |
line wrap: on
line diff
--- a/get_expression_profiles.R Wed Mar 06 09:19:05 2019 -0500 +++ b/get_expression_profiles.R Mon May 13 11:45:29 2019 -0400 @@ -69,6 +69,15 @@ return(res) } +clean_ids <- function(ids){ + + ids = gsub(" ","",ids) + ids = ids[which(ids!="")] + ids = ids[which(ids!="NA")] + ids = ids[!is.na(ids)] + + return(ids) +} main <- function() { args <- commandArgs(TRUE) @@ -109,16 +118,17 @@ # Extract input input_type = args$input_type if (input_type == "list") { - list_id = strsplit(args$input, "[ \t\n]+")[[1]] + ids = unlist(strsplit(strsplit(args$input, "[ \t\n]+")[[1]],";")) } else if (input_type == "file") { filename = args$input column_number = as.numeric(gsub("c", "" ,args$column_number)) header = str2bool(args$header) file = read_file(filename, header) - list_id = sapply(strsplit(file[,column_number], ";"), "[", 1) + ids = unlist(strsplit(file[,column_number], ";")) } - input = list_id - + #filter ids + ids = clean_ids(ids) + # Read reference file reference_file = read_file(args$ref_file, TRUE) @@ -130,11 +140,11 @@ level = strsplit(args$level, ",")[[1]] reliability = strsplit(args$reliability, ",")[[1]] # Calculation - res = annot.HPAnorm(input, reference_file, tissue, level, reliability, not_mapped_option) + res = annot.HPAnorm(ids, reference_file, tissue, level, reliability, not_mapped_option) } else if (atlas=="cancer") { cancer = strsplit(args$cancer, ",")[[1]] # Calculation - res = annot.HPAcancer(input, reference_file, cancer, not_mapped_option) + res = annot.HPAcancer(ids, reference_file, cancer, not_mapped_option) } # Write output
--- a/get_expression_profiles.xml Wed Mar 06 09:19:05 2019 -0500 +++ b/get_expression_profiles.xml Mon May 13 11:45:29 2019 -0400 @@ -1,4 +1,4 @@ -<tool id="sel_ann_hpa" name="Get expression profiles" version="2019.03.06"> +<tool id="sel_ann_hpa" name="Get expression profiles" version="2019.03.13"> <description>by (normal or tumor) tissue/cell type [Human Protein Atlas] </description> <requirements> @@ -196,6 +196,8 @@ A list of ENSG (Ensembl gene) IDs must be entered (either via a copy/paste or by choosing a file); if it's not the case, please use the ID_Converter tool of ProteoRE. +A line can contains multiple ids if separated by ";". + ----- **Parameters**
--- a/proteore_protein_atlas_normal_tissue.loc.sample Wed Mar 06 09:19:05 2019 -0500 +++ b/proteore_protein_atlas_normal_tissue.loc.sample Mon May 13 11:45:29 2019 -0400 @@ -1,2 +1,2 @@ #<id> <name> <tissue> <value> -HPA_normal_tissue_19-07-2018 HPA normal tissue 19/07/2018 HPA_normal_tissue /tool-data/HPA_normal_tissue_23-10-2018.tsv +HPA_normal_tissue_23-10-2018 HPA normal tissue 23/10/2018 HPA_normal_tissue /tool-data/HPA_normal_tissue_23-10-2018.tsv
--- a/proteore_protein_atlas_tumor_tissue.loc.sample Wed Mar 06 09:19:05 2019 -0500 +++ b/proteore_protein_atlas_tumor_tissue.loc.sample Mon May 13 11:45:29 2019 -0400 @@ -1,2 +1,2 @@ #<id> <name> <tissue> <value> -HPA_pathology_19-07-2018 HPA pathology 19/07/2018 HPA_pathology /tool-data/HPA_pathology_23-10-2018.tsv +HPA_pathology_23-10-2018 HPA pathology 23/10/2018 HPA_pathology /tool-data/HPA_pathology_23-10-2018.tsv