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"])
# 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["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"])["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, 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 _create_validate_config(vrn_file, rm_file, rm_interval_file, rm_genome,
base_dir, data):
"""Create a bcbio.variation configuration input for validation.
"""
if rm_genome:
rm_genome = genome.get_refs(rm_genome, None, data["dirs"]["galaxy"])[-1]
if rm_genome != data["sam_ref"]:
eval_genome = data["sam_ref"]
else:
eval_genome = None
else:
eval_genome = None
rm_genome = data["sam_ref"]
ref_call = {"file": str(rm_file), "name": "ref", "type": "grading-ref",
"preclean": True, "prep": True, "remove-refcalls": True}
a_intervals = get_analysis_intervals(data)
if rm_interval_file:
ref_call["intervals"] = rm_interval_file
eval_call = {"file": vrn_file, "name": "eval", "remove-refcalls": True}
if eval_genome:
eval_call["ref"] = eval_genome
eval_call["preclean"] = True
eval_call["prep"] = True
if a_intervals and eval_genome:
eval_call["intervals"] = os.path.abspath(a_intervals)
exp = {"sample": data["name"][-1],
"ref": rm_genome,
"approach": "grade",
"calls": [ref_call, eval_call]}
if a_intervals and not eval_genome:
exp["intervals"] = os.path.abspath(a_intervals)
if data.get("callable_bam") and not eval_genome:
exp["align"] = data["callable_bam"]
return {"dir": {"base": base_dir, "out": "work", "prep": "work/prep"},
"experiments": [exp]}
def _add_reference_resources(data):
"""Add genome reference information to the item to process.
"""
aligner = data["config"]["algorithm"].get("aligner", None)
align_ref, sam_ref = genome.get_refs(data["genome_build"], aligner, data["dirs"]["galaxy"])
data["align_ref"] = align_ref
data["sam_ref"] = sam_ref
data["genome_resources"] = genome.get_resources(data["genome_build"], sam_ref)
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"])
# 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["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"])["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)
align_ref, sam_ref = genome.get_refs(data["genome_build"], aligner,
data["dirs"]["galaxy"])
data["align_ref"] = align_ref
data["sam_ref"] = sam_ref
data["genome_resources"] = genome.get_resources(data["genome_build"],
sam_ref)
return data
def get_genome_dir(gid, galaxy_dir, data):
"""Return standard location of genome directories.
"""
if galaxy_dir:
refs = genome.get_refs(gid, None, galaxy_dir, data)
seq_file = tz.get_in(["fasta", "base"], refs)
if seq_file and os.path.exists(seq_file):
return os.path.dirname(os.path.dirname(seq_file))
else:
gdirs = glob.glob(os.path.join(_get_data_dir(), "genomes", "*", gid))
if len(gdirs) == 1 and os.path.exists(gdirs[0]):
return gdirs[0]
def get_genome_dir(gid, galaxy_dir, data):
"""Return standard location of genome directories.
"""
if galaxy_dir:
refs = genome.get_refs(gid, None, galaxy_dir, data)
seq_file = tz.get_in(["fasta", "base"], refs)
if seq_file and os.path.exists(seq_file):
return os.path.dirname(os.path.dirname(seq_file))
else:
gdirs = glob.glob(os.path.join(_get_data_dir(), "genomes", "*", gid))
if len(gdirs) == 1 and os.path.exists(gdirs[0]):
return gdirs[0]
def _create_validate_config(vrn_file, rm_file, rm_interval_file, rm_genome,
base_dir, data):
"""Create a bcbio.variation configuration input for validation.
"""
if rm_genome:
rm_genome = genome.get_refs(rm_genome, None,
data["dirs"]["galaxy"])[-1]
if rm_genome != data["sam_ref"]:
eval_genome = data["sam_ref"]
else:
eval_genome = None
else:
eval_genome = None
rm_genome = data["sam_ref"]
ref_call = {
"file": rm_file,
"name": "ref",
"type": "grading-ref",
"preclean": True,
"prep": True,
"remove-refcalls": True
}
if rm_interval_file:
ref_call["intervals"] = rm_interval_file
eval_call = {"file": vrn_file, "name": "eval", "remove-refcalls": True}
if eval_genome:
eval_call["ref"] = eval_genome
eval_call["preclean"] = True
eval_call["prep"] = True
exp = {
"sample": data["name"][-1],
"ref": rm_genome,
"approach": "grade",
"calls": [ref_call, eval_call]
}
if data.get("callable_bam"):
exp["align"] = data["callable_bam"]
intervals = ensemble.get_analysis_intervals(data)
if intervals:
exp["intervals"] = os.path.abspath(intervals)
return {
"dir": {
"base": base_dir,
"out": "work",
"prep": "work/prep"
},
"experiments": [exp]
}