def export(self):
sampledatas_2d_array = [i for i in self._queue if i[0] in self._no_coverages_df["sample_name"].values.tolist()]
if len(sampledatas_2d_array) == 0:
print("All files have correct number of lines. No files to process")
else:
os.makedirs(os.path.dirname(mainInitializer.output), exist_ok=True)
Utilities.dump_2d_array(sampledatas_2d_array, file=mainInitializer.output)
print("Files to process: {}\nDumped sample data: '{}'".format(len(self._no_coverages_df), mainInitializer.output))
if mainInitializer.debugging_bool:
debug_table = "{}_debug.tsv".format(mainInitializer.output)
self._verified_df.to_csv(debug_table, sep='\t', header=True, index=False)
print("Dumped debug table: '{}'".format(debug_table))
def ___fai2genome(self):
"""Process existing fasta index, depends from 'samtools_faidx' function"""
def ____parse_fai_line(split_line: list):
if len(split_line) >= 2:
return split_line[:2]
print("Bad FAI file line: {}".format("\t".join(split_line)))
fai_2d_array = Utilities.load_2d_array("{}_samtools.fai".format(self._reference_mask))
genome_2d_array = []
for line in fai_2d_array:
genome_2d_array.append(____parse_fai_line(line))
out = "{}_samtools.genome".format(self._reference_mask)
Utilities.dump_2d_array(array=Utilities.remove_empty_values(genome_2d_array), file=out)
print("Created BEDTools genome index: '{}'".format(out))
def dump_annotation(self, file: str):
Utilities.dump_2d_array(array=self._annotations_2d_array, file=file)
print("Created annotation file: '{}'".format(file))