def parse(columns, metadata, lines):
status = Status('networks', logger=log).n(len(lines)).start()
for idx, line in enumerate(lines):
status.log(idx)
tokens = line.split('\t')
if not len(tokens) == len(columns) + 3:
continue
source = tokens[0]
target = tokens[1]
# humannet composite score
#score = float(tokens[-1])
for column, token in itertools.izip(columns, tokens[2:-1]):
try:
# individual edge score
score = float(token)
metadata[column]['count'] += 1
yield {
'source': source,
'target': target,
'score': score,
'meta': metadata[column]['_id']
}
except ValueError:
pass
status.stop()
def parse(columns, metadata, lines):
status = Status('networks', logger=log).n(len(lines)).start()
for idx, line in enumerate(lines):
status.log(idx)
tokens = line.split('\t')
if not len(tokens) == len(columns) + 3:
continue
source = tokens[0]
target = tokens[1]
# humannet composite score
#score = float(tokens[-1])
for column, token in itertools.izip(columns, tokens[2:-1]):
try:
# individual edge score
score = float(token)
metadata[column]['count'] += 1
yield {
'source': source,
'target': target,
'score': score,
'meta': metadata[column]['_id']
}
except ValueError:
pass
status.stop()
def load_entrez_identifiers():
db = pymongo.MongoClient().identifiers
db.genemania_entrez.drop()
collection = db.genemania_entrez
url = 'http://genemania.org/data/current/Homo_sapiens/identifier_mappings.txt'
status = Status('loading genemania identifiers from ' + url,
logger=log).start()
r = requests.get(url)
lines = r.iter_lines()
lines.next() # ignore header row
def parse(lines):
for line in lines:
try:
preferred, name, source = line.split('\t')
if (source == 'Entrez Gene ID'):
yield {
'preferred': preferred,
'name': name,
'NAME': name.upper(
), # indexed to support case-insensitive queries
'source': source
}
except Exception as e:
log.warn(e.message)
count = 0
iterator = parse(lines)
while True:
records = [record for record in islice(iterator, 1000)]
if len(records) > 0:
count += len(collection.insert_many(records).inserted_ids)
log.debug('inserted %d identifiers (%d total)', len(records),
count)
else:
break
log.info('creating NAME and preferred indexes')
collection.create_index([("NAME", pymongo.ASCENDING)])
collection.create_index([("preferred", pymongo.ASCENDING)])
status.stop()
def load_identifiers():
db = pymongo.MongoClient().identifiers
db.genemania.drop()
collection = db.genemania
url = 'http://genemania.org/data/current/Danio_rerio/identifier_mappings.txt'
status = Status('loading genemania identifiers from ' + url, logger=log).start()
r = requests.get(url)
lines = r.iter_lines()
lines.next() # ignore header row
def parse(lines):
for line in lines:
try:
preferred, name, source = line.split('\t')
yield {
'preferred': preferred,
'name': name,
'NAME': name.upper(), # indexed to support case-insensitive queries
'source': source
}
except Exception as e:
log.warn(e.message)
count = 0
iterator = parse(lines)
while True:
records = [record for record in islice(iterator, 1000)]
if len(records) > 0:
count += len(collection.insert_many(records).inserted_ids)
log.debug('inserted %d identifiers (%d total)', len(records), count)
else:
break
log.info('creating NAME and preferred indexes')
collection.create_indexes([
pymongo.IndexModel([('NAME', pymongo.ASCENDING)]),
pymongo.IndexModel([('preferred', pymongo.ASCENDING)])
])
status.stop()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--warmstart', action='store_true', help='warmstart')
args = parser.parse_args()
if not args.warmstart:
load_identifiers()
client = pymongo.MongoClient()
db = client.networks
# collection stores metadata about source networks
meta = db.meta
# collection stores edge data
edges = db.edges
create_edges_index()
url = 'http://genemania.org/data/current/Homo_sapiens/networks.txt'
log.info('reading network list from %s', url)
r = requests.get(url)
lines = list(r.iter_lines())[1:] # ignore header line
status = Status('networks', logger=log).n(len(lines)).start()
for idx, line in enumerate(lines):
status.log(idx)
file_name, network_group_name, network_name, source, pubmed_id = line.split('\t')
metadata = {
'collection': 'identifiers',
'type': network_group_name.lower(),
'source': source,
'name': network_name,
'pubmed': int(pubmed_id) if not pubmed_id == '' else 0
}
if not args.warmstart or meta.find_one(dict(metadata.items() + [('status', 'success')])) is None:
# old metadata records and their associated edges will be dropped after the new network is finished processing
_ids = [result['_id'] for result in meta.find(metadata)]
log.info('found %d matching network(s) that will be replaced: %s', len(_ids), ', '.join([str(_id) for _id in _ids]))
set_status(metadata, 'parsing')
_id = meta.insert_one(metadata).inserted_id
metadata['count'] = load_network('http://genemania.org/data/current/Homo_sapiens/' + file_name, _id)
log.info('%s %s %s network has %d edges', metadata['source'], metadata['name'], metadata['type'], metadata['count'])
set_status(metadata, 'success')
meta.save(metadata)
if len(_ids) > 0:
log.info('dropping old network metadata')
meta.delete_many({'_id': {'$in': _ids}})
log.info('dropping old edge data')
edges.delete_many({'meta': {'$nin': [it['_id'] for it in meta.find()]}})
status.stop()
return 0
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--id', action='store_true', help='load identifiers only')
parser.add_argument('--batch', type=int, default=10000, help='insert records batch size')
parser.add_argument('--warmstart', action='store_true', help='warmstart')
args = parser.parse_args()
if not args.warmstart:
load_identifiers()
if not args.id:
client = pymongo.MongoClient()
db = client.networks
# collection stores metadata about source networks
meta = db.meta
# collection stores edge data
edges = db.edges
create_edges_index()
url = 'http://genemania.org/data/current/Homo_sapiens/networks.txt'
log.info('reading network list from %s', url)
r = requests.get(url)
lines = list(r.iter_lines())[1:] # ignore header line
status = Status('networks', logger=log).n(len(lines)).start()
for idx, line in enumerate(lines):
status.log(idx)
file_name, network_group_name, network_name, source, pubmed_id = line.split('\t')
metadata = {
'collection': 'genemania',
'type': network_group_name.lower(),
'source': source,
'name': network_name,
'pubmed': int(pubmed_id) if not pubmed_id == '' else 0
}
if not args.warmstart or meta.find_one(dict(metadata.items() + [('status', 'success')])) is None:
# old metadata records and their associated edges will be dropped after the new network is finished processing
_ids = [result['_id'] for result in meta.find(metadata)]
log.info('found %d matching network(s) that will be replaced: %s', len(_ids), ', '.join([str(_id) for _id in _ids]))
set_status(metadata, 'parsing')
_id = meta.insert_one(metadata).inserted_id
metadata['count'] = load_network('http://genemania.org/data/current/Homo_sapiens/' + file_name, _id, args.batch)
log.info('%s %s %s network has %d edges', metadata['source'], metadata['name'], metadata['type'], metadata['count'])
set_status(metadata, 'success')
meta.save(metadata)
if len(_ids) > 0:
log.info('dropping old network metadata')
meta.delete_many({'_id': {'$in': _ids}})
cleanup_edges()
status.stop()
return 0
