def seg_count_file(self):
"""
This function parses the tab delimited SegCopy file into a complex dictionary.
:return:
"""
prior_ploidy = {
} # This is essentially a tracking dictionary that I make here because the keys are available.
bin_tracking_dict = Tool_Box.VivifiedDictionary()
line_num = 0
seg_copy_array = self.array_builder()
seg_count = list(csv.reader(open(self.input_file), delimiter='\t'))
for line in seg_count:
if line_num > 0:
bin_tracking_dict[line[0]][line_num] = (line[1], line[2])
elif line_num == 0: # First line is the header.
label_list = line
for i in range(len(label_list)):
if i > 2:
prior_ploidy[label_list[i]] = [-1, False, 0, 0, 0]
line_num += 1
if not eval(self.chrY):
with suppress(KeyError):
bin_tracking_dict.pop("chrY")
return prior_ploidy, bin_tracking_dict, seg_copy_array
def quality_check(data_bundle, fastq_files):
"""
Called by the multiprocessor pool. Examines the indices and determines the mismatches and N counts.
:param data_bundle:
:param fastq_files:
:return:
"""
prog_check = data_bundle[0]
index_list = data_bundle[1]
file1_anchor_seq = data_bundle[2]
file2_anchor_seq = data_bundle[3]
fastq1 = FASTQ_Reader(fastq_files[0])
fastq2 = FASTQ_Reader(fastq_files[1])
umt_dict = collections.defaultdict(
lambda: collections.defaultdict(int))
anchor_dict = Tool_Box.VivifiedDictionary()
read_count = 0
try:
while True:
fastq1_read = next(fastq1.seq_read())
fastq2_read = next(fastq2.seq_read())
read_count += 1
if read_count % int(prog_check) == 0:
print(" -->Processed {0} reads in file {1} and {2}.".
format(read_count, fastq_files[0], fastq_files[1]))
# Get read index and UMT.
umt = "{0}{1}".format(
fastq1_read.name.split("|")[0],
fastq2_read.name.split("|")[1].split(":")[0])
read_index = fastq1_read.name.split(":")[-1]
# Quantify anchor lengths.
unknown_anchor1 = fastq1_read.seq[7:18]
unknown_anchor2 = fastq2_read.seq[7:18]
match1 = Levenshtein.distance(file1_anchor_seq,
unknown_anchor1)
match2 = Levenshtein.distance(file2_anchor_seq,
unknown_anchor2)
for index in index_list:
index_match = Levenshtein.distance(read_index,
index[0][:6])
# Add anchor and UMT data to dictionaries.
if index[0] in anchor_dict and index_match < 2:
anchor_dict[index[0]]["R1"][match1] += 1
anchor_dict[index[0]]["R2"][match2] += 1
umt_dict[index[0]][umt] += 1
# if umt in umt_dict[index[0]]:
# umt_dict[index[0]][umt] += 1
# else:
# umt_dict[index[0]][umt] = 1
elif index_match < 2:
anchor_dict[
index[0]]["R1"] = [0] * len(file1_anchor_seq)
anchor_dict[
index[0]]["R2"] = [0] * len(file2_anchor_seq)
anchor_dict[index[0]]["R1"][match1] += 1
anchor_dict[index[0]]["R2"][match2] += 1
umt_dict[index[0]][umt] = 1
except StopIteration:
return anchor_dict, umt_dict