def get_mutation_rep_time(mutation_file, sample_name):
""" Returns list with replication timings of mutated nucleotides
with given sample name, mutation motif and final nucleotide"""
sys.stdout.write("\nConsidering {0} sample: ".format(sample_name))
mutation_rep_time = []
# We consider chromosomes separately to avoid memory overflow:
# All genome in str format ~ 3.1 GB - too much for RAM in my PC
genome_file_names = core.get_genome_file_names()
for chromosome in genome_file_names:
sys.stdout.write(chromosome + ', ')
sys.stdout.flush()
mutations_list = core.read_mutations(mutation_file,
mutation_type='subs',
chromosome=chromosome,
sample_names=[sample_name],
final_nucleotides=core.FINAL_NUCL)
with open(genome_file_names[chromosome]) as genome_file:
genom = genome_file.read()
for index, mutation in mutations_list.iterrows():
# FIXME: Considering mutations_list 20 times - unefficient
position = mutation['positionFrom']
motif = genome[position - 2: position + 1]
if motif in core.MOTIFS:
rep_time = core.calculate_replication_timing(chromosome,
position)
if rep_time == -1:
print '\nuncalculatable replication time at\
{0}:{1}'.format(chromosome, position)
mutation_rep_time.append(rep_time)
del genome
return mutation_rep_time
def get_motif_rep_time(chromosome):
""" Returns list of replication timings of positions in genome
with particular motif and given chromosome"""
motif_rep_time = []
genome_file_names = core.get_genome_file_names()
with open(genome_file_names[chromosome], 'r') as f:
genome = f.read()
for motif in core.MOTIFS:
# First occurence of beginning of motif
first_occurence = genome.find(motif, 0)
while first_occurence >= 0:
# One +1 because str.find finds start of motif, but we want center
# Second +1 because str begins with 0th element
replication_timing = core.calculate_replication_timing(chromosome,
first_occurence + 2)
if replication_timing == -1:
print '\nuncalculatable replication time at {0}:{1}'\
.format(chromosome, first_occurence + 2)
motif_rep_time.append(replication_timing)
first_occurence = genome.find(motif, first_occurence + 1)
del genome
return motif_rep_time
for motif in core.MOTIFS:
# First occurence of beginning of motif
first_occurence = genome.find(motif, 0)
while first_occurence >= 0:
# One +1 because str.find finds start of motif, but we want center
# Second +1 because str begins with 0th element
replication_timing = core.calculate_replication_timing(chromosome,
first_occurence + 2)
if replication_timing == -1:
print '\nuncalculatable replication time at {0}:{1}'\
.format(chromosome, first_occurence + 2)
motif_rep_time.append(replication_timing)
first_occurence = genome.find(motif, first_occurence + 1)
del genome
return motif_rep_time
if __name__ == '__main__':
if len(sys.argv) != 2:
sys.exit("Usage {0} outDir".format(sys.argv[0]))
genome_file_names = core.get_genome_file_names()
for chromosome in genome_file_names:
motifReplicationTiming = get_motif_rep_time(chromosome)
print "Chromosome #{0} motifs has been considered\n".format(chromosome)
outFileName = os.path.join(sys.argv[1], chromosome)
with open(outFileName, 'w') as fout:
for time in motifReplicationTiming:
fout.write(str(time) + '\n')
del motifReplicationTiming