def pool_func(filename):
curr_DIR = DIR + filename
os.chdir(curr_DIR)
reads = parser.parse_fasta(filename)
scores = computealignment.compute_scores(reads, filename)
computealignment.write_align_file(filename, scores)
createtsp.write_full_atsp(filename, len(reads), scores)
def write_fasta_stat(fasta_file, ref_file):
with open(ref_file, 'r') as f:
ref_seq = f.read()
ref_length = len(ref_seq)
reads = parse_fasta(fasta_file)
read_lengths = [len(read) for read in reads]
with open(fasta_file.split('reads.fasta')[0] + "fasta.stat", "w") as handle:
real_coverage = sum([x for x in read_lengths]) / ref_length
nr_reads = len(read_lengths)
average = sum([x for x in read_lengths]) / len(read_lengths)
median = sorted([x for x in read_lengths])[len(read_lengths) // 2]
shortest = min([x for x in read_lengths])
longest = max([x for x in read_lengths])
objective_value, actual_gaps = compute_objective_function_value_of_fasta(fasta_file)
expected_gaps = len(reads) * math.exp(-real_coverage)
unsequenced_part = math.exp(-real_coverage)
handle.write('Real Coverage: {}\n'
'Number of reads: {}\n'
'Average read length: {}\n'
# 'Median read length: {}\n'
# 'Shortest read length: {}\n'
# 'Longest read length: {}\n'
'Objective function value: {}\n'
'Expected gaps: {}\n'
'Actual gaps: {}\n'
'Unsequenced part: {}'.format(int(real_coverage), nr_reads, average, objective_value,
expected_gaps, actual_gaps,
unsequenced_part))
return (real_coverage, nr_reads, average, objective_value, expected_gaps, actual_gaps)
