def postprocess_variants(data):
"""Provide post-processing of variant calls: filtering and effects annotation.
"""
cur_name = "%s, %s" % (data["name"][-1], get_variantcaller(data))
logger.info("Finalizing variant calls: %s" % cur_name)
if data.get("align_bam") and data.get("vrn_file"):
logger.info("Calculating variation effects for %s" % cur_name)
effect_todo = effects.get_type(data)
if effect_todo:
if effect_todo == "snpeff":
ann_vrn_file = effects.snpeff_effects(data)
elif effect_todo == "vep":
ann_vrn_file = effects.run_vep(data)
else:
raise ValueError(
"Unexpected variant effects configuration: %s" %
effect_todo)
if ann_vrn_file:
data["vrn_file"] = ann_vrn_file
logger.info("Filtering for %s" % cur_name)
data["vrn_file"] = variant_filtration(
data["vrn_file"], data["sam_ref"],
tz.get_in(("genome_resources", "variation"), data, {}), data)
logger.info("Prioritization for %s" % cur_name)
data["vrn_file"] = prioritize.handle_vcf_calls(data["vrn_file"], data)
return [[data]]
def add_reference_resources(data, remote_retriever=None):
"""Add genome reference information to the item to process.
"""
aligner = data["config"]["algorithm"].get("aligner", None)
if remote_retriever:
data["reference"] = remote_retriever.get_refs(data["genome_build"],
aligner, data["config"])
else:
data["reference"] = genome.get_refs(data["genome_build"], aligner,
data["dirs"]["galaxy"], data)
_check_ref_files(data["reference"], data)
# back compatible `sam_ref` target
data["sam_ref"] = utils.get_in(data, ("reference", "fasta", "base"))
ref_loc = utils.get_in(data, ("config", "resources", "species", "dir"),
utils.get_in(data, ("reference", "fasta", "base")))
if remote_retriever:
data = remote_retriever.get_resources(data["genome_build"], ref_loc,
data)
else:
data["genome_resources"] = genome.get_resources(
data["genome_build"], ref_loc, data)
if effects.get_type(
data) == "snpeff" and "snpeff" not in data["reference"]:
data["reference"]["snpeff"] = effects.get_snpeff_files(data)
data = _fill_validation_targets(data)
data = _fill_prioritization_targets(data)
# Re-enable when we have ability to re-define gemini configuration directory
if False:
if population.do_db_build([data], need_bam=False):
data["reference"]["gemini"] = population.get_gemini_files(data)
return data
def add_reference_resources(data, remote_retriever=None):
"""Add genome reference information to the item to process.
"""
aligner = data["config"]["algorithm"].get("aligner", None)
if remote_retriever:
data["reference"] = remote_retriever.get_refs(data["genome_build"], aligner, data["config"])
else:
data["reference"] = genome.get_refs(data["genome_build"], aligner, data["dirs"]["galaxy"], data)
_check_ref_files(data["reference"], data)
# back compatible `sam_ref` target
data["sam_ref"] = utils.get_in(data, ("reference", "fasta", "base"))
ref_loc = utils.get_in(data, ("config", "resources", "species", "dir"),
utils.get_in(data, ("reference", "fasta", "base")))
if remote_retriever:
data = remote_retriever.get_resources(data["genome_build"], ref_loc, data)
else:
data["genome_resources"] = genome.get_resources(data["genome_build"], ref_loc, data)
if effects.get_type(data) == "snpeff" and "snpeff" not in data["reference"]:
data["reference"]["snpeff"] = effects.get_snpeff_files(data)
data = _fill_validation_targets(data)
data = _fill_prioritization_targets(data)
# Re-enable when we have ability to re-define gemini configuration directory
if False:
if population.do_db_build([data], need_bam=False):
data["reference"]["gemini"] = population.get_gemini_files(data)
return data
def add_reference_resources(data):
"""Add genome reference information to the item to process.
"""
aligner = data["config"]["algorithm"].get("aligner", None)
data["reference"] = genome.get_refs(data["genome_build"], aligner,
data["dirs"]["galaxy"], data)
# back compatible `sam_ref` target
data["sam_ref"] = utils.get_in(data, ("reference", "fasta", "base"))
ref_loc = utils.get_in(data, ("config", "resources", "species", "dir"),
utils.get_in(data, ("reference", "fasta", "base")))
data["genome_resources"] = genome.get_resources(data["genome_build"],
ref_loc)
if effects.get_type(data) == "snpeff":
data["reference"]["snpeff"] = effects.get_snpeff_files(data)
alt_genome = utils.get_in(data,
("config", "algorithm", "validate_genome_build"))
if alt_genome:
data["reference"]["alt"] = {
alt_genome:
genome.get_refs(alt_genome, None, data["dirs"]["galaxy"],
data)["fasta"]
}
# Re-enable when we have ability to re-define gemini configuration directory
if False:
if population.do_db_build([data], check_gemini=False, need_bam=False):
data["reference"]["gemini"] = population.get_gemini_files(data)
return data
def add_reference_resources(data):
"""Add genome reference information to the item to process.
"""
aligner = data["config"]["algorithm"].get("aligner", None)
data["reference"] = genome.get_refs(data["genome_build"], aligner, data["dirs"]["galaxy"], data)
# back compatible `sam_ref` target
data["sam_ref"] = utils.get_in(data, ("reference", "fasta", "base"))
ref_loc = utils.get_in(data, ("config", "resources", "species", "dir"),
utils.get_in(data, ("reference", "fasta", "base")))
data["genome_resources"] = genome.get_resources(data["genome_build"], ref_loc, data)
if effects.get_type(data) == "snpeff":
data["reference"]["snpeff"] = effects.get_snpeff_files(data)
alt_genome = utils.get_in(data, ("config", "algorithm", "validate_genome_build"))
if alt_genome:
data["reference"]["alt"] = {alt_genome:
genome.get_refs(alt_genome, None, data["dirs"]["galaxy"], data)["fasta"]}
# Re-enable when we have ability to re-define gemini configuration directory
if False:
if population.do_db_build([data], check_gemini=False, need_bam=False):
data["reference"]["gemini"] = population.get_gemini_files(data)
return data
def postprocess_variants(data):
"""Provide post-processing of variant calls: filtering and effects annotation.
"""
cur_name = "%s, %s" % (data["name"][-1], get_variantcaller(data))
logger.info("Finalizing variant calls: %s" % cur_name)
if data.get("align_bam") and data.get("vrn_file"):
logger.info("Calculating variation effects for %s" % cur_name)
effect_todo = effects.get_type(data)
if effect_todo:
if effect_todo == "snpeff":
ann_vrn_file = effects.snpeff_effects(data)
elif effect_todo == "vep":
ann_vrn_file = effects.run_vep(data)
else:
raise ValueError("Unexpected variant effects configuration: %s" % effect_todo)
if ann_vrn_file:
data["vrn_file"] = ann_vrn_file
logger.info("Filtering for %s" % cur_name)
data["vrn_file"] = variant_filtration(data["vrn_file"], data["sam_ref"],
tz.get_in(("genome_resources", "variation"), data, {}),
data)
logger.info("Prioritization for %s" % cur_name)
data["vrn_file"] = prioritize.handle_vcf_calls(data["vrn_file"], data)
return [[data]]
