def make_tch(file):
tch = [ncbi[file][0], '%s/%s' % (taxdir, ncbi[file][0])]
if check(tch[1]) is False:
if tch[0] == 'gi2taxid.tch':
db = hash.Hash()
db.open(tch[1])
gi2taxid = ['%s/%s' % (taxdir, file) for file in 'gi_taxid_prot.dmp', 'gi_taxid_nucl.dmp']
for file in gi2taxid:
for line in open(file):
gi, taxid = line.strip().split()
db[gi] = taxid
db.close()
elif file == 'names.dmp':
names2ids, ids2names = ['%s/%s' % (taxdir, i) for i in ncbi[file]]
names2idsdb = hash.Hash()
names2idsdb.open(names2ids)
ids2namesdb = hash.Hash()
ids2namesdb.open(ids2names)
for line in open('%s/%s' % (taxdir, file)):
if 'scientific name' in line:
id, sciname = [i.strip() for i in line.strip().split('|')[0:2]]
names2idsdb[sciname] = id
ids2namesdb[id] = sciname
names2idsdb.close()
ids2namesdb.close()
elif file == 'nodes.dmp':
db = hash.Hash()
db.open(tch[1])
for line in open('%s/%s' % (taxdir, file)):
id, parent_id, parent = [i.strip() for i in line.strip().split('|')[0:3]]
db[id] = '%s %s' % (parent_id, parent)
db.close()
def get_db(database, blast):
if database.rsplit('.', 1)[1] == 'tch':
id2desc = hash.Hash()
id2desc.open(database)
return id2desc
else:
return headerid2desc(database, get_subset(blast))
def combine_with_hits(clean, s_db, search_out, hits):
"""
combine sequences with best hits from search
"""
best = set([hit[1].split()[0] for hit in numblast(open(search_out), hits, False, False)])
combo = '%s.best%srefs.fa' % (clean.rsplit('.', 1)[0], hits)
if os.path.exists(combo) is True:
return combo
combo = open(combo, 'w')
for seq in parse_fasta(clean):
print >> combo, '\n'.join(seq)
# create/open tch for search database
s_tch = '%s.tch' % (s_db)
if os.path.exists(s_tch) is False:
fasta2tch(s_db)
id2seq = hash.Hash()
id2seq.open(s_tch)
# get sequences for best hits from tch
for hit in best:
seq = id2seq[hit].split('\n')
header = remove_char(seq[0].split()[0]).replace('>', '>best-hit_')
print >> combo, '\n'.join([header, seq[1].upper()])
combo.close()
id2seq.close()
return combo.name
def tch(fasta):
tch = '%s.tch' % (fasta)
db = hash.Hash()
db.open(tch)
for sequence in fasta_parser.iterate_fasta(fasta):
db[sequence[0].split('>')[1].split()[0]] = '\n'.join(sequence)
db.close()
def _get_tch(path):
if not path.endswith('.tch'):
path += '.tch'
if path not in _TCH_POOL:
_TCH_POOL[path] = tch.Hash()
_TCH_POOL[path].open(path, tch.HDBOREADER | tch.HDBONOLCK)
# _TCH_POOL[path].setmutex()
return _TCH_POOL[path]
def get_tchs():
[download_file(file) for file in ncbi]
[make_tch(file) for file in ncbi]
# database directory
tchs = {} # dictionary of tch files with their open files as keys
for tch in set([f for i in ncbi.values() for f in i]):
full_tch = '%s/%s' % (taxdir, tch)
db = hash.Hash()
db.open(full_tch)
tchs[tch] = db
return tchs
def ko2kegg(file, option, file_type):
tch = option2kegg(option)
kegg = hash.Hash()
kegg.open(tch)
if file_type == 'fasta':
for sequence in parse_fasta(file):
header = sequence[0].split('>')[1]
id = header.split()[0]
yield header
ks = set(find_ko(header.split()))
for k in ks:
if k in kegg:
for function in kegg[k].split('|'):
# - id - k - function
yield '\t%s\t%s\t%s' % (id, k, function)
else:
yield '\t%s\t%s\tn/a' % (id, k)
elif file_type == 'list':
for line in file:
line = line.strip()
if len(line.split()) != 0:
id = line.split()[0]
yield line
ks = set(find_ko(line.split()))
for k in ks:
if k in kegg:
for function in kegg[k].split('|'):
# - id - k - function
yield '\t%s\t%s\t%s' % (id, k, function)
else:
yield '\t%s\t%s\tn/a' % (id, k)
else:
ks = set(find_ko(file))
for k in ks:
if k in kegg:
for function in kegg[k].split('|'):
yield [k, function]
else:
yield [k, 'n/a']
kegg.close()