Mercurial > repos > proteore > proteore_prot_features

changeset 18:bdbc7620e804 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit 6a3a63d9870148e6fee84e771db614f9da9a8245"
author proteore
date Thu, 30 Jul 2020 09:25:25 +0000
parents 3c5fafe2f338
children 381e18f13ed2
files add_protein_features.R add_protein_features.xml
diffstat 2 files changed, 33 insertions(+), 46 deletions(-) [+]
line wrap: on
line diff
--- 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)
--- 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 @@
-<tool id="prot_features" name="Add protein features" version="2019.06.27.2">
-<description>[neXtProt]
+<tool id="prot_features" name="Add protein features" version="2020.07.30">
+<description>[neXtProt, Human]
 </description>
 <requirements>
   <requirement type="package" version="3.4.1">R</requirement>
@@ -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 @@
 
 <inputs>
   <conditional name="inputtype">
-    <param name="filetype" type="select" label="Enter your IDs (neXtProt or UniProt; e.g. P05090 or NX_P05090)" help="Copy/paste or from a file" > 
+    <param name="filetype" type="select" label="Enter your IDs (neXtProt or UniProt; e.g. NX_P05090 or P05090)" help="Copy/paste or from a file" > 
       <option value="file" selected="true">Input file containing your IDs </option>
       <option value="copy_paste">Copy/paste your list of IDs</option> 
     </param>
@@ -63,32 +61,31 @@
     </when>
   </conditional>
 
-      <param name="idtype" type="select" label="Type of IDs" multiple="false" optional="false"> 
-            <option value="NextprotID" selected="true">neXtProt IDs</option>
- 	        <option value="Uniprot_AC" selected="false">UniProt accession number</option>
-      </param>
-      <section name="Nextprot_params" title="Select features (Physico-chemical, localization, disease infiormation)" expanded="True">
-        <param name="pc_features" type="select" label="Select information to add to your list" multiple="true" help="" display="checkboxes" optional="false"> 
-          <option value="SeqLength" selected="false">Sequence Length</option>
-          <option value="MW" selected="false">Molecular Weight</option>
-          <option value="IsoPoint" selected="false">Isoelectric point</option>
-          <option value="TMDomains" selected="false">Number of transmembrane domains</option>
-          <option value="ProteinExistence" selected="false">Protein Existence (evidence score from 1 to 5)</option>
-          </param>
+    <param name="idtype" type="select" label="Type of IDs" multiple="false" optional="false"> 
+        <option value="NextprotID" selected="true">neXtProt IDs</option>
+        <option value="Uniprot_AC" selected="false">UniProt accession number</option>
+    </param>
+    <param name="pc_features" type="select" label="Features/Annotation" multiple="true" help="" display="checkboxes" optional="false">
+        <option value="SeqLength" selected="false">Sequence Length</option>
+        <option value="MW" selected="false">Molecular Weight</option>
+        <option value="IsoPoint" selected="false">Isoelectric point</option>
+        <option value="TMDomains" selected="false">Number of transmembrane domains</option>
+        <option value="ProteinExistence" selected="false">Protein Existence (evidence score from 1 to 5)</option>
+        <option value="Chr" selected="false">Chromosome</option>
+        <option value="SubcellLocations" selected="false">Subcellular Location</option>
+        <option value="Diseases" selected="false">Disease information</option>
+        <option value="ProteinName" selected="false">Protein name</option>
+        <option value="Function" selected="false">Protein function</option>
+        <option value="PostTranslationalModifications" selected="false">Post translational modifications</option>
+        <option value="ProteinFamily" selected="false">Protein family</option>
+        <option value="Pathway" selected="false">Pathway(s)</option>
+    </param>
 
-        <param name="localization" type="select" label="Localization" multiple="true" help="" display="checkboxes" optional="true">
-          <option value="Chr" selected="false">Chromosome</option>
- 	      <option value="SubcellLocations" selected="false">Subcellular Location</option>
-        </param>
-
-        <param name="diseases_info" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Disease information" />
-
-      </section>
-      <param name="ref_file" type="select" label="Release of neXtProt reference file to use">
+    <param name="ref_file" type="select" label="Release of neXtProt reference file to use">
         <options from_data_table="proteore_nextprot_ref">
             <filter type="sort_by" column="0"/>
         </options>
-      </param>
+    </param>
 
 </inputs>
 
@@ -110,12 +107,7 @@
     </conditional>
 
     <param name="idtype" value="Uniprot_AC"/> 
-
-    <section name="Nextprot_params">
-      <param name="pc_features" value="SeqLength,MW,IsoPoint,TMDomains,ProteinExistence"/> 
-      <param name="localization" value="Chr,SubcellLocations"/> 
-      <param name="diseases_info" value="true"/> 
-    </section>
+    <param name="pc_features" value="SeqLength,MW,IsoPoint,TMDomains,ProteinExistence"/> 
       
     <param name="ref_file" value="test-data/cached_locally/nextprot_ref_07-05-2019.tsv"/>
     <output name="output" file="Add_information_from_neXtProt.tsv"/>
@@ -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