def main():
args = _parse_arguments()
_check_blastplus_dependencies(args)
print(str(args), end='\n\n')
db_fpath = _create_database(args)
args.set_database_path(db_fpath)
print('{} - Start.'.format(getwt()))
result_status = _clean_reads(args)
_cleanup(args)
if result_status == 0:
print('\n{} - Completed.'.format(getwt()))
print(' Output directory: `{}`'.format(args.outdir_path))
else:
print_err('\n\a{} - Completed with errors.'.format(getwt()))
# end if
return result_status
def _parse_primers(self):
sep = ','
primer_pairs = list()
n_lines = sum(1 for _ in open(self.primers_fpath, 'rt'))
n_lines_is_even = n_lines % 2 == 0
if not n_lines_is_even:
error_msg = '\nError: Cannot parse primers from file `{}`.\n' \
'There are {} lines in this file.\n' \
'There must be even number of lines ' \
'(and therefore even number of primers), though.' \
.format(self.primers_fpath, self.primers_fpath)
raise FatalError(error_msg)
# end if
print('{} - Parsing primers...'.format(getwt()))
reference_seq = src.fasta.read_fasta_sequence(self.reference_fpath)
find_start_pos = 0
with open(self.primers_fpath, 'rt') as primers_file:
for _ in range(n_lines // 2):
try:
left_primer_seq, right_primer_seq = self._parse_primer_pair(
primers_file, sep)
self.max_primer_len = max(self.max_primer_len,
len(left_primer_seq),
len(right_primer_seq))
left_start, left_end = self._find_primer_anneal_coords(
left_primer_seq,
reference_seq,
Orientation.LEFT,
beg=find_start_pos)
find_start_pos = left_start
right_start, right_end = self._find_primer_anneal_coords(
src.sequences.reverse_complement(right_primer_seq),
reference_seq,
Orientation.RIGHT,
beg=find_start_pos)
primer_pairs.append(
PrimerPair(
Primer(left_start, left_end),
Primer(right_start, right_end),
))
except ValueError as err:
error_msg = '\nError: cannot parse a line in file `{}`.\n{}' \
.format(self.primers_fpath, err)
raise FatalError(error_msg)
# end try
# end for
# end with
print('{} - Primers: found annealing coordinates'.format(getwt()))
return primer_pairs
def print_status_bar(self):
curr_num_done_reads = self.get_num_done_reads()
bar_len = self._get_status_bar_len()
ratio_done = curr_num_done_reads / self.NUM_READS_TOTAL
percent_done = ratio_done * 100
progress_line_len = round(bar_len * ratio_done)
print_arrow = progress_line_len != bar_len
if print_arrow:
arrow = '>'
else:
arrow = ''
progress_line_len += 1
# end if
sys.stdout.write(
'\r{} - [{}{}{}] {}/{} ({}%)'.format(
getwt(),
'=' * progress_line_len,
arrow,
' ' * (bar_len - progress_line_len),
curr_num_done_reads,
self.NUM_READS_TOTAL,
round(percent_done)
)
)
sys.stdout.flush()
def create_reference_database(kromsatel_args):
db_dirpath = os.path.join(kromsatel_args.outdir_path, 'blast_database')
fs.create_dir(db_dirpath)
db_fpath = os.path.join(db_dirpath, 'kromsatel_blast_database')
print('{} - Creating a reference database for BLAST:\n `{}`...'.format(
getwt(), db_fpath))
_make_blast_db(kromsatel_args.reference_fpath, db_fpath)
print('{} - Database: created'.format(getwt()))
if kromsatel_args.use_index:
print('{} - Indexing the database...'.format(getwt()))
_index_database(db_fpath)
print('{} - Index: created'.format(getwt()))
else:
print('Index will not be created for the database.')
# end if
return db_fpath
def _count_paired_reads_verbosely(frw_fastq_fpath):
print('{} - Counting reads...'.format(getwt()))
num_reads_total = src.fastq.count_reads(frw_fastq_fpath)
print('{} - {} read pairs.'.format(getwt(), num_reads_total))
return num_reads_total