def process_sample(sample_name, fastq_files, info, bam_files, dirs,
config, config_file):
"""Finalize processing for a sample, potentially multiplexed.
"""
config = _update_config_w_custom(config, info)
genome_build = info.get("genome_build", None)
(_, sam_ref) = get_genome_ref(genome_build, config["algorithm"]["aligner"],
dirs["galaxy"])
fastq1, fastq2 = combine_fastq_files(fastq_files, dirs["work"])
log.info("Combining and preparing wig file %s" % str(sample_name))
sort_bam = merge_bam_files(bam_files, dirs["work"], config)
(gatk_bam, vrn_file, effects_file) = ("", "", "")
if config["algorithm"]["recalibrate"]:
log.info("Recalibrating %s with GATK" % str(sample_name))
gatk_bam = recalibrate_quality(sort_bam, fastq1, fastq2, sam_ref,
dirs, config)
if config["algorithm"]["snpcall"]:
log.info("SNP genotyping %s with GATK" % str(sample_name))
vrn_file = run_genotyper(gatk_bam, sam_ref, config)
log.info("Calculating variation effects for %s" % str(sample_name))
effects_file = variation_effects(vrn_file, genome_build, config)
if config["algorithm"].get("transcript_assemble", False):
tx_file = assemble_transcripts(sort_bam, sam_ref, config)
if sam_ref is not None:
log.info("Generating summary files: %s" % str(sample_name))
generate_align_summary(sort_bam, fastq2 is not None, sam_ref,
sample_name, config, dirs)
bam_to_wig(sort_bam, config, config_file)
return [sample_name, fastq_files, info, sort_bam, gatk_bam, vrn_file,
effects_file]
def merge_sample(data):
"""Merge fastq and BAM files for multiple samples.
"""
logger.info("Combining fastq and BAM files %s" % str(data["name"]))
config = _update_config_w_custom(data["config"], data["info"])
genome_build, sam_ref = ref_genome_info(data["info"], config, data["dirs"])
fastq1, fastq2 = combine_fastq_files(data["fastq_files"], data["dirs"]["work"],
config)
sort_bam = merge_bam_files(data["bam_files"], data["dirs"]["work"], config)
return [[{"name": data["name"],
"genome_build": genome_build, "sam_ref": sam_ref,
"work_bam": sort_bam, "fastq1": fastq1, "fastq2": fastq2,
"dirs": data["dirs"], "config": config,
"config_file": data["config_file"]}]]
def merge_sample(data):
"""Merge fastq and BAM files for multiple samples.
"""
logger.info("Combining fastq and BAM files %s" % str(data["name"]))
config = _update_config_w_custom(data["config"], data["info"])
genome_build, sam_ref = ref_genome_info(data["info"], config, data["dirs"])
if config["algorithm"].get("upload_fastq", False):
fastq1, fastq2 = combine_fastq_files(data["fastq_files"], data["dirs"]["work"],
config)
else:
fastq1, fastq2 = None, None
sort_bam = merge_bam_files(data["bam_files"], data["dirs"]["work"], config)
return [[{"name": data["name"], "metadata": data["info"].get("metadata", {}),
"genome_build": genome_build, "sam_ref": sam_ref,
"work_bam": sort_bam, "fastq1": fastq1, "fastq2": fastq2,
"dirs": data["dirs"], "config": config,
"config_file": data["config_file"]}]]
def merge_sample(data):
"""Merge fastq and BAM files for multiple samples.
"""
logger.info("Combining fastq and BAM files %s" % str(data["name"]))
config = _update_config_w_custom(data["config"], data["info"])
genome_build, sam_ref = ref_genome_info(data["info"], config, data["dirs"])
if config["algorithm"].get("upload_fastq", False):
fastq1, fastq2 = combine_fastq_files(data["fastq_files"], data["dirs"]["work"],
config)
else:
fastq1, fastq2 = None, None
sort_bam = merge_bam_files(data["bam_files"], data["dirs"]["work"], config)
return [[{"name": data["name"],
"genome_build": genome_build, "sam_ref": sam_ref,
"work_bam": sort_bam, "fastq1": fastq1, "fastq2": fastq2,
"dirs": data["dirs"], "config": config,
"config_file": data["config_file"]}]]
