def retrieve(self):
if os.path.exists(self.reference_dir):
print("Warning! The reference path exists: '{}'".format(
self.reference_dir))
os.makedirs(self.reference_dir, exist_ok=True)
chromosomes_dir = os.path.join(self.reference_dir, "chromosomes")
os.makedirs(chromosomes_dir, exist_ok=True)
# UCSC returns HTTP 530 when attempting to download in multi-thread
compressed_chromosomes = Utilities.single_core_queue(
self._dl_wrapper, [{
"chromosome": i,
"chromosomes_dir": chromosomes_dir
} for i in self.CHROMOSOMES])
# Process sequence
self.parsed_records = Utilities.flatten_2d_array(
Utilities.single_core_queue(self._parse_gzip_fna,
compressed_chromosomes))
self.nfasta_file = os.path.join(self.reference_dir, "hg19.fasta")
SeqIO.write(self.parsed_records, self.nfasta_file, "fasta")
# Process annotation
self.index_dir = self.describer.get_index_guide(self.nfasta_file)
def generate_keywords_dict(keywords: list, split_words: bool = False):
keywords = [j for j in [i.strip() for i in keywords if isinstance(i, str)] if len(j) > 0]
if split_words:
keywords = Utilities.flatten_2d_array([i.split(" ") for i in keywords])
return {j: () for j in sorted([i.strip() for i in set(keywords)]) if len(j) > 0}
