all_threads[i].start()
while len(mp.active_children()) > 1:
time.sleep(1)
queue.put("FINISHED")
while len(mp.active_children()) > 0:
time.sleep(1)
else:
queue = open(output_filename, 'w')
for chrom in sorted(list(input.keys())):
generate_bedgraph_lines(input[chrom], chrom, queue, parallel=False)
queue.close()
#'chromosomes' contains the lengths of all chromosomes the that BEDGRAPH contains values for.
genome = fu.import_genome(args.fasta)
chromosomes = dict([(ID, len(transcript))
for ID, transcript in genome.items()])
#'coverage' is a nested dictionary of float vectors for each nucleotide in the genome.
# Contains a dictionary for each BEDGRAPH file with values at each position.
coverage = {}
graph = open(args.input)
coverage = {}
for line in graph:
chrom, start, end, count = line.rstrip().split()
count = float(count)
if chrom not in coverage:
coverage[chrom] = {}
choices=['none', '5p', '3p', 'both'])
parser.add_argument(
"--nucfreqs",
dest='NUCFREQS',
help="Saves a table of nucleotide frequencies in selected genome region.",
default=False,
action="store_true")
args = parser.parse_args()
######################################
# ENVIRONMENT SETUP: DATA STRUCTURES #
######################################
if args.FASTA:
genome = fu.import_genome(args.FASTA)
if args.SOFTCLIP_TYPE != 'none' and not args.FASTA:
print(
'ERROR: Untemplated nucleotide analysis requires a reference genome. Use the --fasta argument.'
)
sys.exit(1)
chromosomes = {}
file = open(args.SAMFILES[0])
line = file.readline()
while line[0] == '@':
print(line.rstrip())
l = line.rstrip().split('\t')
if l[0] == '@SQ':
default=None,
help='filepath to output G content table')
args = parser.parse_args()
def which(x, value=True):
return [a for a, b in enumerate(x) if b == value]
#'chromosomes' contains the lengths of all chromosomes the that BEDGRAPH contains values for.
# Expects a two-column tab-separated file with:
# chromosome length
# Provided with the 'lengths' argument.
if args.genome:
genome = fu.import_genome(args.genome)
chromosomes = {}
lengths_file = open(args.lengths)
for line in lengths_file:
chrom, length = line.rstrip().split('\t')
chromosomes[chrom] = int(length)
#'coverage' is a nested dictionary of float vectors for each nucleotide in the genome.
# Contains a dictionary for each BEDGRAPH file with values at each position.
coverage = {}
ingraphs = args.input
for graph in ingraphs:
print('Importing {}...'.format(graph))
coverage[graph] = {}
"""Returns a list of locations in x that satisfy value"""
return [a for a, b in enumerate(x) if b == value]
def notwhich(x, value=0):
"""Returns a list of locations in x that do not satisty value"""
return [a for a, b in enumerate(x) if b != value]
def flatten(list_of_lists):
"""Collapses a list/tuple of lists into a single list"""
return [item for sublist in list_of_lists for item in sublist]
if args.GENOME:
genome = fu.import_genome(args.GENOME)
else:
if args.FEATURE != 'transcript':
print("ERROR: cannot locate {} features without a reference genome.".
format(args.FEATURE))
print("Provide genome FASTA file with -G")
sys.exit(1)
coverage = None
if args.PLUS_BEDGRAPH:
for i in args.PLUS_BEDGRAPH:
if not coverage:
coverage = bu.parse_bedgraph(i, '+')
else:
bu.add_bedgraph(coverage, i, '+')
'exon_nums', []) + [exon_number]
ref_IDs = sorted(list(ref_transcripts.keys()))
print('# {} reference transcripts: {}'.format(len(ref_IDs),
args.reference_GFF))
# 'picked_IDs' is an array of IDs to use from the reference_GFF
if args.subset:
picked_IDs = [
i.rstrip().split('\t')[0] for i in open(args.subset).readlines()
]
else:
picked_IDs = ref_IDs
# 'genome' is a dict of strings for each chromosome in 'genome_fasta'
genome = fu.import_genome(args.genome_fasta)
# 'chromosomes' contains the lengths of all chromosomes the that BEDGRAPH contains values for.
chromosomes = {}
for chrom in genome.keys():
length = len(genome[chrom])
chromosomes[chrom] = int(length)
# 'coverage' is a dictionary of float vectors for each nucleotide in the genome.
# Contains the value of the BEDGRAPH file at each position.
coverage = {}
coverage['+'] = {}
coverage['-'] = {}
for chrom, chromlen in chromosomes.items():
coverage['+'][chrom] = np.zeros(chromlen, dtype='float32')
]
notkeys = [
'B', 'D', 'H', 'V', 'V', '-', 'K', 'Y', 'S', 'W', 'R', 'M', 'T', 'G', 'C',
'A', 'N', '.'
]
for k, v, c, n in zip(keys, values, complements, notkeys):
IUPAChash[k] = v
IUPACcomp[k] = c
IUPACnot[k] = n
#################################
# LOADING DATA FROM INPUT FILES #
#################################
genome = fu.import_genome(args.genome_FASTA, keep_case=False)
chromosomes = {}
for k, v in genome.items():
chromosomes[k] = len(v)
linecounter = 0
if __name__ == '__main__':
for line in open(args.match_file):
linecounter += 1
if line[0] == '#':
continue
try:
BED_filename, search_sequence, mismatches = line.rstrip().split(
' ')
except: