switched from ncbi to ebi for taxonomy retriever

providers.yaml

@@ -27,6 +27,7 @@
   prefixes: ["Taxon", "taxon", "taxid"]
   resources:
       html: ["http://www.uniprot.org/taxonomy/%i"]
+      json: ["https://www.ebi.ac.uk/ena/data/taxonomy/v1/taxon/tax-id/%i"]
       xml: ["http://www.uniprot.org/taxonomy/%i.rdf"]
       xml_ncbi: ["https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=taxonomy&id=%i"]
   check_existence: "http://www.uniprot.org/taxonomy/%i"

scripts/retrieve_gene_ontology.py

@@ -16,6 +16,9 @@ def main():
 	parser.add_argument('--relations', '-r', action='store_true', help='Include id, parents and children')
 	parser.add_argument('dbxrefs', nargs=argparse.REMAINDER)
 	args = parser.parse_args()
+	if not args.basic and not args.relations:
+		args.basic = True
+		args.relations = True
 	resolved = dbxref.resolver.resolve(args.dbxrefs, check_existence=False)
 	documents = []
 	for entry in resolved:
@@ -32,9 +35,6 @@ def main():
 				output.update(read_basic(d))
 			if args.relations:
 				output.update(read_relations(d))
-			if not args.basic and not args.relations:
-				output.update(read_basic(d))
-				output.update(read_relations(d))
 		documents.append(output)
 	print (json.dumps(documents))
 

scripts/retrieve_taxonomy.py

@@ -4,43 +4,62 @@ import env
 import dbxref.config
 import dbxref.resolver
 import requests
-import xml.etree.ElementTree as ET
 import logging
 import json
 import argparse
 
 logger = logging.getLogger(__name__)
-ns = {'TaxaSet': 'https://eutils.ncbi.nlm.nih.gov/'}
 
 def main():
 	parser = argparse.ArgumentParser(description='Retrieve taxonomy xml documents for dbxrefs and convert them into json')
-	parser.add_argument('--basic', '-b', action='store_true', help='Include dbxref and ......................')
+	parser.add_argument('--basic', '-b', action='store_true', help='Include dbxref, scientificName, commonName, lineage and rank')
+	parser.add_argument('--geneticcodes', '-g', action='store_true', help='Include geneticCode and mitochondrialGeneticCode')
 	parser.add_argument('dbxrefs', nargs=argparse.REMAINDER)
 	args = parser.parse_args()
+	if not args.basic and not args.geneticcodes:
+		args.basic = True
+		args.geneticcodes = True
 	resolved = dbxref.resolver.resolve(args.dbxrefs, check_existence=False)
 	documents = []
 	for entry in resolved:
-		xml_url = entry['locations']['xml_ncbi'][0]
-		logger.debug('URL: %s', xml_url)
-		r = requests.get(xml_url)
+		json_url = entry['locations']['json'][0]
+		logger.debug('URL: %s', json_url)
+		r = requests.get(json_url)
 		logger.debug('Content: %s', r.text)
-		root = ET.fromstring(r.text)
-
 		output = {'id': entry['dbxref']}
-		error = root.find('ERROR')
-		if error is not None:
-			output['message'] = error.text.strip()
+		d = {}
+		try:
+			d = json.loads(r.text)
+		except:
+			pass
+		if len(d) > 0:
+			if args.basic:
+				output.update(read_basic(d))
+			if args.geneticcodes:
+				output.update(read_geneticCodes(d))
 		else:
-			for child in root.findall('Taxon'):
-				output['name'] = child.find('ScientificName').text.strip()
-				lineage = child.find('Lineage')
-				if lineage.text is not None:
-					output['lineage'] = lineage.text.strip()
-				else:
-					output['lineage'] = 'No lineage found'
-		if 'name' not in output and 'message' not in output:
-			output['message'] = 'No entries found! Possibly invalid ID provided'
+			output['message'] = "An error occurred! probably invalid ID"
 		documents.append(output)
 	print (json.dumps(documents))
 
+def read_basic(d):
+	out = {}
+	if 'scientificName' in d:
+		out['scientificName'] = d['scientificName']
+	if 'commonName' in d:
+		out['commonName'] = d['commonName']
+	if 'lineage' in d:
+		out['lineage'] = d['lineage']
+	if 'rank' in d:
+		out['rank'] = d['rank']
+	return (out)
+
+def read_geneticCodes(d):
+	out = {'geneticCodes': {}}
+	if 'geneticCode' in d:
+		out['geneticCodes']['geneticCode'] = d['geneticCode']
+	if 'mitochondrialGeneticCode' in d:
+		out['geneticCodes']['mitochondrialGeneticCode'] = d['mitochondrialGeneticCode']
+	return (out)
+
 main()