# HG changeset patch # User proteore # Date 1596101125 0 # Node ID bdbc7620e804729cf1879d9976041dbac80d60e9 # Parent 3c5fafe2f338e881d5999636b7024fc0fbab7803 "planemo upload commit 6a3a63d9870148e6fee84e771db614f9da9a8245" diff -r 3c5fafe2f338 -r bdbc7620e804 add_protein_features.R --- a/add_protein_features.R Thu Jun 27 09:36:34 2019 -0400 +++ b/add_protein_features.R Thu Jul 30 09:25:25 2020 +0000 @@ -48,9 +48,7 @@ --column: the column number which you would like to apply... --header: true/false if your file contains a header --type: the type of input IDs (Uniprot_AC/EntrezID) - --pc_features: IsoPoint,SeqLength,MW - --localization: Chr,SubcellLocations - --diseases_info: Diseases + --pc_features: IsoPoint,SeqLength,MW,Chr,SubcellLocations,Diseases,protein_name,function,post_trans_mod,protein_family,pathway --output: text output filename \n") q(save="no") @@ -122,12 +120,7 @@ # Get information from neXtProt get_nextprot_info <- function(nextprot,input,pc_features,localization,diseases_info){ - if(diseases_info){ - cols = c("NextprotID",pc_features,localization,"Diseases") - } else { - cols = c("NextprotID",pc_features,localization) - } - + cols = c("NextprotID",pc_features) cols=cols[cols!="None"] info = nextprot[match(input,nextprot$NextprotID),cols] return(info) @@ -172,8 +165,6 @@ # Parse arguments id_type = args$type pc_features = strsplit(args$pc_features, ",")[[1]] - localization = strsplit(args$localization, ",")[[1]] - diseases_info = str2bool(args$diseases_info) output = args$output # Change the sample ids if they are Uniprot_AC ids to be able to match them with @@ -191,7 +182,7 @@ if (all(!NextprotID %in% nextprot[,1])){ write.table("None of the input ids can be found in Nextprot",file=output,sep="\t",quote=FALSE,col.names=TRUE,row.names=FALSE) } else { - res <- get_nextprot_info(nextprot,NextprotID,pc_features,localization,diseases_info) + res <- get_nextprot_info(nextprot,NextprotID,pc_features) res = res[!duplicated(res$NextprotID),] output_content = merge(file, res,by.x=ncol,by.y="NextprotID",incomparables = NA,all.x=T) output_content = order_columns(output_content,ncol,id_type,file) diff -r 3c5fafe2f338 -r bdbc7620e804 add_protein_features.xml --- a/add_protein_features.xml Thu Jun 27 09:36:34 2019 -0400 +++ b/add_protein_features.xml Thu Jul 30 09:25:25 2020 +0000 @@ -1,5 +1,5 @@ - -[neXtProt] + +[neXtProt, Human] R @@ -19,9 +19,7 @@ #end if --type='$idtype' - --pc_features='$Nextprot_params.pc_features' - --localization='$Nextprot_params.localization' - --diseases_info='$Nextprot_params.diseases_info' + --pc_features='$pc_features' --output='$output' #if 'proteore_nextprot_ref' in str($ref_file).split("/") @@ -34,7 +32,7 @@ - + @@ -63,32 +61,31 @@ - - - - -
- - - - - - - + + + + + + + + + + + + + + + + + + + - - - - - - - -
- + - +
@@ -110,12 +107,7 @@ - -
- - - -
+ @@ -161,6 +153,10 @@ - nextProt release 07-05-2019 (release Feb 13, 2019) - neXtProt release 08-10-2018 (release Feb 21, 2018) +.. class:: warningmark + +For "Protein function", "Post translational modifications" and "Pathway(s)", only results with gold quality are returned. + ----- .. class:: infomark