# HG changeset patch # User proteore # Date 1561713075 14400 # Node ID 3ddc1f78773d431ab96a2a07cde882b9f5f9a6e4 # Parent 2138e0035e57f68ae44aaeda3feffc948d0b5e72 planemo upload commit 4ba1ebe7b3f5e3fabf78b5fed7ed0b92e2cbf9e5-dirty diff -r 2138e0035e57 -r 3ddc1f78773d README.rst --- a/README.rst Mon Mar 04 08:20:52 2019 -0500 +++ b/README.rst Fri Jun 28 05:11:15 2019 -0400 @@ -28,3 +28,11 @@ For more details about GoProfiles, please read: Salicrú et al. Comparison of lists of genes based on functional profiles. BMC Bioinformatics. 2011;12:401.(https://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-12-401) If your type of identifiers is not supported (i.e. different form Uniprot and Entrez), please use the **ID Converter** component in the ProteoRE section to convert your list of IDs first. + + +**Packages used** + - bioconductor-org.hs.eg.db v3.5.0 + - bioconductor-org.mm.eg.db v3.5.0 + - bioconductor-annotationdbi v1.40.0 + - bioconductor-biobase v2.98.0 + - goprofiles v1.38.0 diff -r 2138e0035e57 -r 3ddc1f78773d goprofiles.R --- a/goprofiles.R Mon Mar 04 08:20:52 2019 -0500 +++ b/goprofiles.R Fri Jun 28 05:11:15 2019 -0400 @@ -65,20 +65,13 @@ # Extract Gene Entrez ID if (id_type == "Entrez") { id = select(package, ids, "ENTREZID", multiVals = "first") - genes_ids = id$ENTREZID[which( ! is.na(id$ENTREZID))] } else { - genes_ids = c() id = select(package, ids, "ENTREZID", "UNIPROT", multiVals = "first") - if (duplicate == "TRUE") { - id = unique(id) - } - print(id[[1]]) - genes_ids = id$ENTREZID[which( ! is.na(id$ENTREZID))] - # IDs that have NA ENTREZID - NAs = id$UNIPROT[which(is.na(id$ENTREZID))] - #print("IDs unable to convert to ENTREZID: ") - #print(NAs) } + if (duplicate) { id = unique(id) } + genes_ids = id$ENTREZID[which( ! is.na(id$ENTREZID))] + NAs = id$UNIPROT[which(is.na(id$ENTREZID))] # IDs that have NA ENTREZID + # Create basic profiles profile.CC = basicProfile(genes_ids, onto='CC', level=level, orgPackage=species, empty.cats=F, ord=T, na.rm=T) profile.BP = basicProfile(genes_ids, onto='BP', level=level, orgPackage=species, empty.cats=F, ord=T, na.rm=T) @@ -163,7 +156,7 @@ id_type = args$id_type input_type = args$input_type if (input_type == "text") { - input = strsplit(args$input, "[ \t\n]+")[[1]] + input = unlist(strsplit(strsplit(args$input, "[ \t\n]+")[[1]],";")) } else if (input_type == "file") { filename = args$input ncol = args$ncol @@ -178,8 +171,8 @@ file = read_file(filename, header) # Extract Protein IDs list input = unlist(strsplit(as.character(file[,ncol]),";")) - input = input [which(!is.na(input))] } + input = input [which(!is.na(gsub("NA",NA,input)))] if (! any(check_ids(input,id_type))){ stop(paste(id_type,"not found in your ids list, please check your IDs in input or the selected column of your input file")) @@ -191,7 +184,7 @@ level = args$level per = as.logical(args$per) title = args$title - duplicate = args$duplicate + duplicate = str2bool(args$duplicate) text_output = args$text_output species=args$species diff -r 2138e0035e57 -r 3ddc1f78773d goprofiles.xml --- a/goprofiles.xml Mon Mar 04 08:20:52 2019 -0500 +++ b/goprofiles.xml Fri Jun 28 05:11:15 2019 -0400 @@ -1,4 +1,4 @@ - + (Human, Mouse) [goProfiles] R @@ -70,7 +70,7 @@ - + @@ -146,7 +146,7 @@ **Description** -This tool is based on the goProfiles R package; it performs statistical analysis of functional profiles based on Gene Ontology (GO). Functional profile at a given GO level is obtained by counting the +This tool relies on the goProfiles R package; it performs statistical analysis of functional profiles based on Gene Ontology (GO). Functional profile at a given GO level is obtained by counting the number of identifiers having a hit in each category of this level. ----- @@ -154,7 +154,11 @@ **Input** Two modes are allowed: either by copy/pasting your IDs (separated by a space) or by supplying a tabular file (.csv, .tsv, .txt, .tab) including your IDs (identifiers). -Only entrez gene ID (e.g : 4151) or Uniprot accession number (e.g. P31946) are allowed. If your list is not in this form, please use the ID_Converter tool of ProteoRE. +Only entrez gene ID (e.g. 4151) or Uniprot accession number (e.g. P31946) are allowed. If your list is not in this form, please use the ID_Converter tool of ProteoRE. + +.. class:: warningmark + +In copy/paste mode, the number of IDs considered in input is limited to 5000. ----- @@ -172,7 +176,18 @@ Diagram output: graphical output in the form of bar-plot or dot-plot (png (default format), jpeg or pdf format), one figure for each GO category. -text output: with the following information GO category description (e.g.BP.Description), GO term identifier (e.g. BP.GOID) and GO term frequency (e.g. BP.Frequency) +Text output: with the following information GO category description (e.g.BP.Description), GO term identifier (e.g. BP.GOID) and GO term frequency (e.g. BP.Frequency) + +----- + +.. class:: infomark + +Packages used: + - bioconductor-org.hs.eg.db v3.5.0 + - bioconductor-org.mm.eg.db v3.5.0 + - bioconductor-annotationdbi v1.40.0 + - bioconductor-biobase v2.98.0 + - goprofiles v1.38.0 ----- @@ -188,14 +203,13 @@ **Galaxy integration** -T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR +D. Christiany, T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit,Migale Bioinformatics platform, FR This work has been partially funded through the French National Agency for Research (ANR) IFB project. -Contact support@proteore.org for any questions or concerns about the Galaxy implementation of this tool. - +Help: contact@proteore.org for any questions or concerns about this tool. ]]>