# HG changeset patch
# User galaxyp
# Date 1688678139 0
# Node ID a371252a2cf6970bb9e84d3cce48e226626f9cb0
# Parent 265c35540faa8119c4565d6db18aef35a0e73073
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/uniprotxml_downloader commit 0c5222345ace5054df44da29cab278f4a02e2b41
diff -r 265c35540faa -r a371252a2cf6 macros.xml
--- a/macros.xml Fri Nov 04 15:08:37 2022 +0000
+++ b/macros.xml Thu Jul 06 21:15:39 2023 +0000
@@ -3,6 +3,7 @@
+
diff -r 265c35540faa -r a371252a2cf6 test-data/Helicobacter_protein_accessions.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/Helicobacter_protein_accessions.tsv Thu Jul 06 21:15:39 2023 +0000
@@ -0,0 +1,2 @@
+E1Q2I0
+E1Q3C4
\ No newline at end of file
diff -r 265c35540faa -r a371252a2cf6 uniprotxml_downloader.py
--- a/uniprotxml_downloader.py Fri Nov 04 15:08:37 2022 +0000
+++ b/uniprotxml_downloader.py Thu Jul 06 21:15:39 2023 +0000
@@ -47,16 +47,16 @@
def __main__():
# Parse Command Line
parser = optparse.OptionParser()
- parser.add_option('-i', '--input', dest='input', default=None, help='Tabular file containing a column of NCBI Taxon IDs')
- parser.add_option('-c', '--column', dest='column', type='int', default=0, help='The column (zero-based) in the tabular file that contains Taxon IDs')
- parser.add_option('-t', '--taxon', dest='taxon', action='append', default=[], help='NCBI taxon ID to download')
+ parser.add_option('-i', '--input', dest='input', default=None, help='Tabular file containing a column of search search_ids')
+ parser.add_option('-c', '--column', dest='column', type='int', default=0, help='The column (zero-based) in the tabular file that contains search search_ids')
+ parser.add_option('-s', '--search-id', dest='search_id', action='append', default=[], help='ID to search in Uniprot')
parser.add_option('-r', '--reviewed', dest='reviewed', help='Only uniprot reviewed entries')
parser.add_option('-f', '--format', dest='format', choices=['xml', 'fasta'], default='xml', help='output format')
- parser.add_option('-k', '--field', dest='field', choices=['taxonomy_name', 'taxonomy_id'], default='taxonomy_name', help='query field')
+ parser.add_option('-k', '--field', dest='field', choices=['taxonomy_name', 'taxonomy_id', 'accession'], default='taxonomy_name', help='query field')
parser.add_option('-o', '--output', dest='output', help='file path for the downloaded uniprot xml')
parser.add_option('-d', '--debug', dest='debug', action='store_true', default=False, help='Turn on wrapper debugging to stderr')
(options, args) = parser.parse_args()
- taxids = set(options.taxon)
+ search_ids = set(options.search_id)
if options.input:
with open(options.input, 'r') as inputFile:
for linenum, line in enumerate(inputFile):
@@ -64,19 +64,19 @@
continue
fields = line.rstrip('\r\n').split('\t')
if len(fields) > abs(options.column):
- taxid = fields[options.column].strip()
- if taxid:
- taxids.add(taxid)
- taxon_queries = [f'{options.field}:"{taxid}"' for taxid in taxids]
- taxon_query = ' OR '.join(taxon_queries)
+ search_id = fields[options.column].strip()
+ if search_id:
+ search_ids.add(search_id)
+ search_queries = [f'{options.field}:"{search_id}"' for search_id in search_ids]
+ search_query = ' OR '.join(search_queries)
if options.output:
dest_path = options.output
else:
- dest_path = "uniprot_%s.xml" % '_'.join(taxids)
+ dest_path = "uniprot_%s.xml" % '_'.join(search_ids)
reviewed = " reviewed:%s" % options.reviewed if options.reviewed else ''
try:
url = 'https://rest.uniprot.org/uniprotkb/stream'
- query = "%s%s" % (taxon_query, reviewed)
+ query = "%s%s" % (search_query, reviewed)
params = {'query': query, 'format': options.format}
if options.debug:
print("%s ? %s" % (url, params), file=sys.stderr)
@@ -112,7 +112,7 @@
else:
print("failed: Not a uniprot xml file", file=sys.stderr)
exit(1)
- print("NCBI Taxon ID:%s" % taxids, file=sys.stdout)
+ print("Search IDs:%s" % search_ids, file=sys.stdout)
if 'X-UniProt-Release' in response.headers:
print("UniProt-Release:%s" % response.headers['X-UniProt-Release'], file=sys.stdout)
if 'X-Total-Results' in response.headers:
diff -r 265c35540faa -r a371252a2cf6 uniprotxml_downloader.xml
--- a/uniprotxml_downloader.xml Fri Nov 04 15:08:37 2022 +0000
+++ b/uniprotxml_downloader.xml Thu Jul 06 21:15:39 2023 +0000
@@ -1,4 +1,4 @@
-
+
download proteome as XML or fasta
macros.xml
@@ -12,32 +12,32 @@
-
+
-
-
+
+
UniProtKB/TrEMBL (unreviewed only)
-
-
+
+
^\w+( \w+)*(,\w+( \w+)*)*$
-
-
+
+
@@ -86,8 +86,8 @@
-
-
+
+
-
-
+
+
-
-
+
+
+
+
+
+
+
+
+
-
+
@@ -134,7 +146,7 @@
-
+
@@ -145,6 +157,19 @@
+
+
+
+
+
+
+
+