def parse_file_fasta_seqkey(file_fasta, hsh, options):
if options.get('-a') == '':
print_stderr('reading file into hash\n')
_id = ''
seq = ''
running_1 = 0
FASTA = open_or_die2(file_fasta, 'rb')
while True:
l = FASTA.readline().strip()
if not l:
break
m = re.match(r'^>(\S+)', l)
if m:
_id = m.group()
seq = ''
while True:
ll = FASTA.readline().strip()
if not ll:
break
mm = re.match(r'^>(\S+)', ll)
if mm:
cnt = find_cnt(_id)
seq = tr(seq, '[acgtun.]', '[ACGTTNN]')
# ATTR: Performance issue below:
# create_hash_key_chain(hsh, 0, seq)
try:
hsh[seq] = (hsh[seq]) + cnt
except KeyError:
hsh[seq] = cnt
running_1 += 1
if options.get('-a') == '':
print_stderr('{}\r'.format(running_1))
_id = mm.group()
seq = ''
continue
seq += ll
cnt = find_cnt(_id)
seq = tr(seq, '[acgtun.]', '[ACGTTNN]')
create_hash_key_chain(hsh, 0, seq)
hsh[seq] += cnt
running_1 += 1
if options.get('-a') == '':
print_stderr('{}\r'.format(running_1))
FASTA.close()
def read_handler(handle):
global counter
while True:
rin = handle.readline().strip()
if not rin:
break
counter += 1
m = re.match(r'^\>(.+)$', rin)
if m:
m = m.groups()
_id = m[0]
if re.search(r'\s+', _id):
die('Error in line {}: The identifier\n {}\n\ncontains white spaces\n\n{}\n\nYou could run remove_white_space_in_id.py inputfile > newfile\nThis will remove everything from the id line after the first whitespace\n'
.format(Nicenumber(counter), _id, hint))
else:
create_hash_key_chain(hash_num, 0, _id)
hash_num[_id] += 1
elif not re.match(r'^([A|C|G|T|U|N|a|c|g|t|u|n]+)$', rin):
die('Error in line {}: The sequence\n{}\n\ncontains characters others than [acgtunACGTUN]\n\n{}'
.format(Nicenumber(counter), rin, hint))
def resolve_entry_file_mrd_permuted(score, permutation, refs, _hash, options):
if permutation is None:
print_stderr('The {} file is not properly formatted.\nMaybe it does not contain the lines with \"permutation int\"?\n'.format(
options.get('-a')
))
sys.exit(0)
floor = int(math.floor(score))
create_hash_key_chain(_hash, 0, 'total', permutation, floor)
_hash['total'][permutation][floor] += 1
if refs:
create_hash_key_chain(_hash, 0, 'known', permutation, floor)
_hash['known'][permutation][floor] += 1
else:
create_hash_key_chain(_hash, 0, 'novel', permutation, floor)
_hash['novel'][permutation][floor] += 1
for i in range(len(refs)):
refs.pop()
def resolve_entry_file_mrd(score, refs, _hash):
global hash_sig
floor = int(math.floor(score))
create_hash_key_chain(_hash, 0, 'total', floor)
_hash['total'][floor] += 1
if refs:
create_hash_key_chain(_hash, 0, 'known', floor)
_hash['known'][floor] += 1
for ref in refs:
if hash_sig[ref] < floor:
hash_sig[ref] = floor
else:
create_hash_key_chain(_hash, 0, 'novel', floor)
_hash['novel'][floor] += 1
for i in range(len(refs)):
refs.pop() # clear refs array
def insertfeature(db, strand, db_beg, db_end, freq):
global hash_pos
create_hash_key_chain(hash_pos, 0, db, strand, db_beg, db_end)
hash_pos[db][strand][db_beg][db_end] += freq
def parse_file_arf(file_arf, options):
global running, gscan, hash_edits
FILE_ARF = open_or_die(file_arf, 'rb',
'can not open {}\n'.format(file_arf))
while True:
line = FILE_ARF.readline()
if not line:
break
m = re.match(
r'^(\S+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\S+)\s+(\S+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)',
line)
if m:
m = m.groups()
query = m[0]
query_map_lng = int(m[1])
query_beg = m[2]
query_end = int(m[3])
query_seq = m[4]
db = m[5]
db_map_lng = int(m[6])
db_beg = m[7]
db_end = int(m[8])
db_seq = m[9]
strand = m[10]
edits = int(m[11])
edit_string = m[12]
running += 1
if options.get('-j') == '':
(query_map_lng, query_end, query_seq, db_map_lng, db_end,
db_seq, edits, edit_string) = remove_trailing_nts(
query_map_lng, query_end, query_seq, db_map_lng, db_end,
db_seq, edits, edit_string)
if '-a' in options.keys() and int(options.get('-a')) < edits:
continue
if options.get('-b') and query_map_lng < int(options.get('-b')):
continue
if options.get('-c') and int(options.get('-c')) < query_map_lng:
continue
if options.get('-d') and query not in hash_queries_incl.keys():
continue
if options.get('-e') and query in hash_queries_excl.keys():
continue
if options.get('-f') and db not in hash_dbs_incl.keys():
continue
if options.get('-g') and db in hash_dbs_excl.keys():
continue
if not (options.get('-h') == '' or options.get('-i')):
pprint('{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\n'.
format(query, query_map_lng, query_beg, query_end,
query_seq, db, db_map_lng, db_beg, db_end,
db_seq, strand, edits, edit_string))
continue
if gscan:
create_hash_key_chain(hash_edits, 0, query, edits)
hash_edits[query][edits] += 1
else:
evaluation = evaluate_query(query, edits, options)
if evaluation:
pprint(
"{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\n".
format(query, query_map_lng, query_beg, query_end,
query_seq, db, db_map_lng, db_beg, db_end,
db_seq, strand, edits, edit_string))
def parse_file_arf(file_arf):
'''
read through the signature blastparsed file, fills up a hash with information on queries
(deep sequences) mapping to the current db (potential precursor) and resolve each
potential precursor in turn
'''
global db_old, hash_query
FILENAME = open_or_die(file_arf, 'rb',
'could not open file {}\n'.format(file_arf))
while True:
line = FILENAME.readline()
if not line:
break
m = re.match(
r'^(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)',
line)
if m:
m = m.groups()
query = m[0]
query_lng = int(m[1])
query_beg = int(m[2])
query_end = int(m[3])
query_seq = m[4]
db = m[5]
db_lng = int(m[6])
db_beg = int(m[7])
db_end = int(m[8])
db_seq = m[9]
strand = m[10]
edits = int(m[11])
edit_string = m[12]
# only reads that map sense to the potential precursor are
# considered
if strand == "-":
continue
# if the new line concerns a new db (potential precursor) then the
# old db must be resolved
if db_old and db_old != db:
# print(db, db_old)
resolve_potential_precursor()
# resolve the number of reads that the deep sequence represents
freq = find_freq(query)
# read information of the query (deep sequence) into hash
create_hash_key_chain(hash_query, db_beg, query, 'db_beg')
create_hash_key_chain(hash_query, db_end, query, 'db_end')
create_hash_key_chain(hash_query, strand, query, 'strand')
create_hash_key_chain(hash_query, freq, query, 'freq')
hash_query[query]["db_beg"] = db_beg
hash_query[query]["db_end"] = db_end
hash_query[query]["strand"] = strand
hash_query[query]["freq"] = freq
db_old = db
resolve_potential_precursor()