changeset 11:8e637098a8ab draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/dbbuilder commit 16ba4570b04301b774ee0420694f379cc640744b
author galaxyp
date Tue, 27 Sep 2022 13:22:04 +0000
parents e9df53a75f3c
children 983bf725dfc2
files dbbuilder.xml uniprotkb.py
diffstat 2 files changed, 103 insertions(+), 12 deletions(-) [+]
line wrap: on
line diff
--- a/dbbuilder.xml	Wed Nov 25 17:43:51 2020 +0000
+++ b/dbbuilder.xml	Tue Sep 27 13:22:04 2022 +0000
@@ -1,7 +1,9 @@
-<tool id="dbbuilder" name="Protein Database Downloader" version="0.3.2">
+<tool id="dbbuilder" name="Protein Database Downloader" version="0.3.3">
     <description></description>
     <requirements>
         <requirement type="package" version="1.20.1">wget</requirement>
+        <requirement type="package" version="3.8">python</requirement>
+        <requirement type="package" version="2.20.1">requests</requirement>
     </requirements>
     <stdio>
         <exit_code range="1:"  level="fatal" description="Error downloading database." />
@@ -14,8 +16,18 @@
     <command>
 <![CDATA[
         #if $source.from == "uniprot"
-            #set $url = 'http://www.uniprot.org/uniprot/?query=taxonomy:"' + str($source.taxon) + '"' + str($source.set) + str($source.reviewed) + '&force=yes&format=fasta' + str($source.include_isoform)
-            #set $type = "direct"
+            #if $source.set:
+                #set $modified_set = '&' + str($source.set) 
+            #else
+                #set $modified_set = ''
+            #end if
+            #if $source.taxon_id
+                #set $taxon_id = $source.taxon_id
+            #else
+                #set $taxon_id = $source.taxon
+            #end if
+            #set $url = 'https://rest.uniprot.org/uniprotkb/stream?compressed=true&format=fasta&query=taxonomy_id:"' + str($taxon_id) + '"' + str($modified_set) + str($source.reviewed) + str($source.include_isoform)
+            #set $type = "uniprotkb_stream"
         #elif $source.from == "cRAP"
             ##set $url = "ftp://ftp.thegpm.org/fasta/cRAP/crap.fasta"
             #set $url = "https://raw.githubusercontent.com/pravs3683/cRAP/master/cRAP_protein_database.fasta"
@@ -34,7 +46,9 @@
             #set $url = $source.url
             #set $type = $source.archive_type
         #end if
-        #if $type =="direct"
+        #if $type =="uniprotkb_stream"
+            python '$__tool_directory__/uniprotkb.py' --url '$url' -o 'tmp.gz' && gzip -dc 'tmp.gz' > '${output_database}' 
+        #elif $type =="direct"
             wget -nv '$url' -O '${output_database}' --no-check-certificate
         #elif $type =="zip"
             wget -nv '$url' -O tmp.zip --no-check-certificate && zcat -c tmp.zip > '${output_database}'
@@ -51,7 +65,8 @@
     </command>
     <inputs>
         <conditional name="source">
-            <param name="from" type="select" label="Download from" help="Select database source. cRAP acts as a database for common MS contaminants. UniProtKB is a cross species collection of functional protein databases">
+            <param name="from" type="select" label="Download from"
+                help="Select database source. cRAP acts as a database for common MS contaminants. UniProtKB is a cross species collection of functional protein databases">
                 <option value="uniprot">UniProtKB</option>
                 <option value="cRAP">cRAP (contaminants)</option>
                 <option value="HMP">Human Microbiome Project body sites</option>
@@ -64,12 +79,14 @@
                     <options from_file="uniprot_taxons.loc">
                         <column name="name" index="0" />
                         <column name="value" index="1" />
+                        <filter type="add_value" name="Escherichia coli (strain K12)" value="83333" />
                     </options>
                 </param>
+                <param name="taxon_id" type="integer" value="" min="1" optional="true" help="Specify a NCBI taxon id to override species selection"/>
                 <param name="reviewed" type="select" help="UniProtKB/TrEMBL (unreviewed)is a large, automatically annotated database- may contain redundant sequences, but there is a higher chance peptides will be identified. UniProtKB/Swiss-Prot (reviewed) is a smaller, manually annotated database- less of a chance peptides will be identified but less sequence redundancy">
-                    <option value="+">UniProtKB</option>
-                    <option value="+reviewed%3Ayes">UniProtKB/Swiss-Prot (reviewed only)</option>
-                    <option value="+reviewed%3Ano">UniProtKB/TrEMBL (unreviewed only)</option>
+                    <option value="">UniProtKB</option>
+                    <option value="+reviewed%3Atrue">UniProtKB/Swiss-Prot (reviewed only)</option>
+                    <option value="+reviewed%3Afalse">UniProtKB/TrEMBL (unreviewed only)</option>
                     <sanitizer>
                         <valid>
                             <add value="%"/>
@@ -77,15 +94,16 @@
                     </sanitizer>
                 </param>
                 <param name="set" type="select" label="Proteome Set">
-                    <option value="+">Any</option>
-                    <option value="+keyword%3a1185" selected="true">Reference Proteome Set</option>
+                    <option value="">Any</option>
+                    <option value="keyword%3aKW-1185" selected="true">Reference Proteome Set</option>
                     <sanitizer>
                         <valid>
                             <add value="%"/>
                         </valid>
                     </sanitizer>
                 </param>
-                <param name="include_isoform" type="boolean" truevalue="&amp;include=yes" falsevalue="" label="Include isoform data" help="several different forms of a given protein are incorporated into database" />
+                <param name="include_isoform" type="boolean" truevalue="&amp;includeIsoform=true" falsevalue="" 
+                    label="Include isoform data" help="several different forms of a given protein are incorporated into database" />
             </when>
             <when value="cRAP" />
             <when value="HMP">
@@ -129,7 +147,9 @@
     </outputs>
     <tests>
         <test>
-            <param name="from" value="cRAP" />
+            <conditional name="source">
+                <param name="from" value="cRAP" />
+            </conditional>
             <output name="output_database">
                 <assert_contents>
                     <has_text text="KKA1_ECOLX" />
@@ -137,6 +157,47 @@
             </output>
         </test>
         <test>
+            <conditional name="source">
+                <param name="from" value="uniprot" />
+                <param name="taxon" value="83333"/>
+                <param name="taxon_id" value="2697049"/>
+            </conditional>
+            <output name="output_database">
+                <assert_contents>
+                    <has_text text="SPIKE_SARS2" />
+                </assert_contents>
+            </output>
+        </test>
+        <test>
+            <conditional name="source">
+                <param name="from" value="uniprot" />
+                <param name="taxon_id" value="2697049"/>
+                <param name="reviewed" value="+reviewed%3Atrue"/>
+                <param name="set" value=""/>
+            </conditional>
+            <output name="output_database">
+                <assert_contents>
+                    <has_text text=">sp|P0DTC1|R1A_SARS2" />
+                    <not_has_text text=">tr|A0A679G4D8|A0A679G4D8_SARS2" />
+                </assert_contents>
+            </output>
+        </test>
+        <test>
+            <conditional name="source">
+                <param name="from" value="uniprot" />
+                <param name="taxon_id" value="2697049"/>
+                <param name="reviewed" value="+reviewed%3Afalse"/>
+                <param name="set" value=""/>
+            </conditional>
+            <output name="output_database">
+                <assert_contents>
+                    <has_text text=">tr|A0A679G4D8|A0A679G4D8_SARS2" />
+                    <not_has_text text=">sp|P0DTC1|R1A_SARS2" />
+                </assert_contents>
+            </output>
+        </test>
+
+        <test>
             <param name="from" value="url" />
             <param name="url" value="https://raw.githubusercontent.com/pravs3683/cRAP/master/cRAP_protein_database.fasta" />
             <param name="archive_type" value="direct" />
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/uniprotkb.py	Tue Sep 27 13:22:04 2022 +0000
@@ -0,0 +1,30 @@
+#!/usr/bin/env python
+
+import argparse
+import sys
+
+import requests
+
+uniprotkb_url = 'https://rest.uniprot.org/uniprotkb/stream?compressed=true&format=fasta&query='
+
+
+def __main__():
+    parser = argparse.ArgumentParser(
+        description='Retrieve Uniprot data using streaming')
+    parser.add_argument('-u', '--url', help="Uniprot rest api URL")
+    parser.add_argument('-q', '--query', help="UniprotKB Query")
+    parser.add_argument('-o', '--output', type=argparse.FileType('wb'), default=sys.stdout, help='data')
+    parser.add_argument('-d', '--debug', action='store_true', help='Debug')
+    args = parser.parse_args()
+    if args.url:
+        url = args.url
+    else:
+        url = uniprotkb_url + args.query
+    with requests.get(url, stream=True) as request:
+        request.raise_for_status()
+        for chunk in request.iter_content(chunk_size=2**20):
+            args.output.write(chunk)
+
+
+if __name__ == "__main__":
+    __main__()