def create_bed_file(bed_txt_path, bed_coordinates):
with bed_txt_path.open("w") as bed_file:
for bed_coordinate in bed_coordinates:
print(*bed_coordinate, sep="\t", file=bed_file)
bed_gz_path = compress_using_bgzip(bed_txt_path)
_ = index_using_tabix(bed_gz_path)
def _prepare_annotation(self) -> Tuple[Path, Path]:
log.print_progress(
"Data preprocessing to prepare CWAS annotation step")
with self.bed_key_list_path.open() as bed_key_list_file:
bed_key_list = yaml.safe_load(bed_key_list_file)
bed_file_and_keys = []
for bed_filename, bed_key in bed_key_list.items():
bed_file_path = self.annot_data_dir / bed_filename
bed_file_and_keys.append((bed_file_path, bed_key))
log.print_progress(
"Merge all of your annotation BED files into one BED file")
merge_bed_path = self.workspace / "merged_annotation.bed"
merge_bed_files(
merge_bed_path,
bed_file_and_keys,
self.num_proc,
self.force_overwrite,
)
log.print_progress("Compress your BED file.")
bed_gz_path = compress_using_bgzip(merge_bed_path,
self.force_overwrite)
log.print_progress("Make an index of your BED file.")
bed_idx_path = index_using_tabix(bed_gz_path, self.force_overwrite)
return bed_gz_path, bed_idx_path
def create_bed_files(bed_txt_paths, input_coordinates):
for bed_txt_path, coordinates_per_file in zip(bed_txt_paths,
input_coordinates):
create_bed_file(bed_txt_path, bed_entries(coordinates_per_file))
bed_gz_path = compress_using_bgzip(bed_txt_path)
_ = index_using_tabix(bed_gz_path)
def process_vep_vcf(self):
print_progress("Compress the VEP output using bgzip")
vcf_gz_path = compress_using_bgzip(self.vep_output_vcf_path)
print_progress("Create an index of the VEP output using tabix")
index_using_tabix(vcf_gz_path)