def _write_vcf_header_with_sample_names(sample_names, vcf_fixed_columns,
representative_header_file, file_path):
# type: (List[str], List[str], str, str) -> None
"""Writes VCF header containing meta info and header line with sample names.
It writes all meta-information starting with `##` extracted from
`representative_header_file`, followed by one data header line with
` vcf_fixed_columns`, and sample names in `sample_names`. Example:
##INFO=<ID=CGA_SDO,Number=1,Type=Integer,Description="Number">
##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
#CHROM POS ID REF ALT QUAL FILTER INFO SAMPLE1 SAMPLE2
Args:
sample_names: The sample names appended to `vcf_fixed_columns`.
vcf_fixed_columns: The VCF fixed columns.
representative_header_file: The location of the file that provides the
meta-information.
file_path: The location where the VCF headers is saved.
"""
# pylint: disable=redefined-outer-name,reimported
from apache_beam.io import filesystems
from gcp_variant_transforms.libs import vcf_header_parser
metadata_header_lines = vcf_header_parser.get_metadata_header_lines(
representative_header_file)
with filesystems.FileSystems.create(file_path) as file_to_write:
file_to_write.write(''.join(metadata_header_lines))
file_to_write.write(str('\t'.join(vcf_fixed_columns + sample_names)))
file_to_write.write('\n')
def _read_variants(
all_patterns, # type: List[str]
pipeline, # type: beam.Pipeline
known_args, # type: argparse.Namespace
pipeline_mode, # type: int
pre_infer_headers=False, # type: bool
keep_raw_sample_names=False, # type: bool
use_1_based_coordinate=True # type: bool
):
# type: (...) -> pvalue.PCollection
"""Helper method for returning a PCollection of Variants from VCFs."""
representative_header_lines = None
if known_args.representative_header_file:
representative_header_lines = vcf_header_parser.get_metadata_header_lines(
known_args.representative_header_file)
return pipeline_common.read_variants(
pipeline,
all_patterns,
pipeline_mode,
known_args.allow_malformed_records,
representative_header_lines,
pre_infer_headers=pre_infer_headers,
sample_name_encoding=(
SampleNameEncoding.NONE if keep_raw_sample_names else
SampleNameEncoding[known_args.sample_name_encoding]),
use_1_based_coordinate=use_1_based_coordinate)
def _read_variants(
all_patterns, # type: List[str]
pipeline, # type: beam.Pipeline
known_args, # type: argparse.Namespace
pipeline_mode # type: int
):
# type: (...) -> pvalue.PCollection
"""Helper method for returning a PCollection of Variants from VCFs."""
representative_header_lines = None
if known_args.representative_header_file:
representative_header_lines = vcf_header_parser.get_metadata_header_lines(
known_args.representative_header_file)
if pipeline_mode == pipeline_common.PipelineModes.LARGE:
variants = (
pipeline
| 'InputFilePattern' >> beam.Create(all_patterns)
| 'ReadAllFromVcf' >> vcfio.ReadAllFromVcf(
representative_header_lines=representative_header_lines,
allow_malformed_records=(known_args.allow_malformed_records)))
else:
variants = pipeline | 'ReadFromVcf' >> vcfio.ReadFromVcf(
all_patterns[0],
representative_header_lines=representative_header_lines,
allow_malformed_records=known_args.allow_malformed_records,
vcf_parser_type=vcfio.VcfParserType[known_args.vcf_parser])
return variants
def test_get_metadata_header_lines(self):
lines = [
'##fileformat=VCFv4.2\n',
'##INFO=<ID=NS,Number=1,Type=Integer,Description="Number samples">\n',
'##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency">\n',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n',
'##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="GQ">\n',
'#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT Sample1 Sample2\n',
'19 1234567 mi1 G T 50 PASS NS=3 GT:GQ:DP 0/1:35:4 0/2:17:2',]
with temp_dir.TempDir() as tempdir:
file_path = self._create_temp_vcf_file(lines, tempdir)
header_lines = vcf_header_parser.get_metadata_header_lines(file_path)
self.assertEqual(header_lines, lines[:-2])
def _read_variants(all_patterns, # type: List[str]
pipeline, # type: beam.Pipeline
known_args, # type: argparse.Namespace
pipeline_mode # type: int
):
# type: (...) -> pvalue.PCollection
"""Helper method for returning a PCollection of Variants from VCFs."""
representative_header_lines = None
if known_args.representative_header_file:
representative_header_lines = vcf_header_parser.get_metadata_header_lines(
known_args.representative_header_file)
return pipeline_common.read_variants(
pipeline,
all_patterns,
pipeline_mode,
known_args.allow_malformed_records,
representative_header_lines,
vcfio.VcfParserType[known_args.vcf_parser])
def _read_variants(pipeline, known_args):
# type: (beam.Pipeline, argparse.Namespace) -> pvalue.PCollection
"""Helper method for returning a PCollection of Variants from VCFs."""
representative_header_lines = None
if known_args.representative_header_file:
representative_header_lines = vcf_header_parser.get_metadata_header_lines(
known_args.representative_header_file)
if known_args.optimize_for_large_inputs:
variants = (
pipeline
| 'InputFilePattern' >> beam.Create([known_args.input_pattern])
| 'ReadAllFromVcf' >> vcfio.ReadAllFromVcf(
representative_header_lines=representative_header_lines,
allow_malformed_records=(known_args.allow_malformed_records)))
else:
variants = pipeline | 'ReadFromVcf' >> vcfio.ReadFromVcf(
known_args.input_pattern,
representative_header_lines=representative_header_lines,
allow_malformed_records=known_args.allow_malformed_records)
return variants
