def load(parser, args):
if (args.db is None or args.vcf is None):
parser.print_help()
exit("ERROR: load needs both a VCF file and a database file\n")
annos = annotations.get_anno_files( args )
# force skipping CADD and GERP if the data files have not been installed
if args.skip_cadd is False:
if 'cadd_score' not in annos:
sys.stderr.write("\nCADD scores are not being loaded because the"
" annotation file could not be found.\n"
"`Run gemini update --dataonly --extra cadd_score`"
" to install the annotation file.\n\n")
args.skip_cadd = True
else:
sys.stderr.write("CADD scores are being loaded (to skip use:--skip-cadd).\n")
if args.skip_gerp_bp is False:
if 'gerp_bp' not in annos:
sys.stderr.write("\nGERP per bp is not being loaded because the annotation file"
" could not be found.\n Run `gemini update --dataonly --extra gerp_bp`"
" to install the annotation file.\n\n")
args.skip_gerp_bp = True
else:
sys.stderr.write("GERP per bp is being loaded (to skip use:--skip-gerp-bp).\n")
# collect of the the add'l annotation files
annotations.load_annos( args )
if args.scheduler:
load_ipython(args)
elif args.cores > 1:
load_multicore(args)
else:
load_singlecore(args)
def load(parser, args):
if (args.db is None or args.vcf is None):
parser.print_help()
exit("ERROR: load needs both a VCF file and a database file\n")
annos = annotations.get_anno_files(args)
# force skipping CADD and GERP if the data files have not been installed
if args.skip_cadd is False:
if 'cadd_score' not in annos:
sys.stderr.write("\nCADD scores are not being loaded because the"
" annotation file could not be found.\n"
"`Run gemini update --dataonly --extra cadd_score`"
" to install the annotation file.\n\n")
args.skip_cadd = True
else:
sys.stderr.write("CADD scores are being loaded (to skip use:--skip-cadd).\n")
if args.skip_gerp_bp is False:
if 'gerp_bp' not in annos:
sys.stderr.write("\nGERP per bp is not being loaded because the annotation file"
" could not be found.\n Run `gemini update --dataonly --extra gerp_bp`"
" to install the annotation file.\n\n")
args.skip_gerp_bp = True
else:
sys.stderr.write("GERP per bp is being loaded (to skip use:--skip-gerp-bp).\n")
# collect of the the add'l annotation files
annotations.load_annos(args)
if args.scheduler:
load_ipython(args)
elif args.cores > 1:
load_multicore(args)
else:
load_singlecore(args)
def load(parser, args):
#if (args.db is None or args.vcf is None):
if args.vcf is None:
parser.print_help()
exit("ERROR: load needs both a VCF file\n")
start_time = time.time()
annos = annotations.get_anno_files( args )
# force skipping CADD and GERP if the data files have not been installed
if args.skip_cadd is False:
if 'cadd_score' not in annos:
sys.stderr.write("\nCADD scores are not being loaded because the"
" annotation file could not be found.\n"
"`Run geminicassandra update --dataonly --extra cadd_score`"
" to install the annotation file.\n\n")
args.skip_cadd = True
else:
sys.stderr.write("CADD scores are being loaded (to skip use:--skip-cadd).\n")
if args.skip_gerp_bp is False:
if 'gerp_bp' not in annos:
sys.stderr.write("\nGERP per bp is not being loaded because the annotation file"
" could not be found.\n Run `geminicassandra update --dataonly --extra gerp_bp`"
" to install the annotation file.\n\n")
args.skip_gerp_bp = True
else:
sys.stderr.write("GERP per bp is being loaded (to skip use:--skip-gerp-bp).\n")
# collect of the the add'l annotation files
annotations.load_annos( args )
time_2 = start_time
time_3 = start_time
if(args.node_num == 1):
gemini_loader = GeminiLoader(args)
gemini_loader.setup_db()
time_2 = time.time()
gemini_loader.single_core_stuff()
time_3 = time.time()
n_variants = 0
if args.cores > 1:
n_variants = load_multicore(args)
else:
n_variants = load_singlecore(args)
insert_n_variants(map(strip, args.contact_points.split(',')), args.keyspace, n_variants)
end_time = time.time()
total_time = str(end_time - start_time)
db_creation_time = str(time_2 - start_time)
single_core_time = str(time_3 - time_2)
parallel_time = str(end_time - time_3)
print "Finished loading in %s s" % total_time
if args.timing_log != None:
with open(args.timing_log, "a") as myfile:
myfile.write(",".join([args.exp_id, total_time, db_creation_time, single_core_time, parallel_time]) + "\n")
def __init__(self, args, buffer_size=10000, prepare_db=True):
self.args = args
self.seen_multi = False
# create the gemini database
# create a reader for the VCF file
self.vcf_reader = self._get_vcf_reader()
# load sample information
expected = "consequence,codons,amino_acids,gene,symbol,feature,exon,polyphen,sift,protein_position,biotype,warning".split(
",")
if self.args.anno_type == "VEP":
self._effect_fields = self._get_vep_csq(self.vcf_reader)
# tuples of (db_column, CSQ name)
self._extra_effect_fields = [("vep_%s" % x.lower(), x)
for x in self._effect_fields
if not x.lower() in expected]
else:
self._effect_fields = []
self._extra_effect_fields = []
if not prepare_db:
return
self._create_db([x[0] for x in self._extra_effect_fields])
if not self.args.no_genotypes and not self.args.no_load_genotypes:
# load the sample info from the VCF file.
self._prepare_samples()
# initialize genotype counts for each sample
self._init_sample_gt_counts()
self.num_samples = len(self.samples)
else:
self.num_samples = 0
self.clinvar_chrom_gene_lookup = load_clinvar(
annotations.get_anno_files(self.args)['clinvar'])
self.buffer_size = buffer_size
self._get_anno_version()
if not args.skip_gene_tables:
self._get_gene_detailed()
self._get_gene_summary()
def __init__(self, args, buffer_size=10000, prepare_db=True):
self.args = args
self.seen_multi = False
# create the gemini database
# create a reader for the VCF file
self.vcf_reader = self._get_vcf_reader()
# load sample information
expected = "consequence,codons,amino_acids,gene,symbol,feature,exon,polyphen,sift,protein_position,biotype,warning".split(",")
if self.args.anno_type == "VEP":
self._effect_fields = self._get_vep_csq(self.vcf_reader)
# tuples of (db_column, CSQ name)
self._extra_effect_fields = [("vep_%s" % x.lower(), x) for x in self._effect_fields if not x.lower() in expected]
else:
self._effect_fields = []
self._extra_effect_fields = []
if not prepare_db:
return
self._create_db([x[0] for x in self._extra_effect_fields])
if not self.args.no_genotypes and not self.args.no_load_genotypes:
# load the sample info from the VCF file.
self._prepare_samples()
# initialize genotype counts for each sample
self._init_sample_gt_counts()
self.num_samples = len(self.samples)
else:
self.num_samples = 0
self.clinvar_chrom_gene_lookup = load_clinvar(annotations.get_anno_files(self.args)['clinvar'])
self.buffer_size = buffer_size
self._get_anno_version()
if not args.skip_gene_tables:
self._get_gene_detailed()
self._get_gene_summary()
def load(parser, args):
#if (args.db is None or args.vcf is None):
if args.vcf is None:
parser.print_help()
exit("ERROR: load needs both a VCF file\n")
start_time = time.time()
annos = annotations.get_anno_files(args)
# force skipping CADD and GERP if the data files have not been installed
if args.skip_cadd is False:
if 'cadd_score' not in annos:
sys.stderr.write(
"\nCADD scores are not being loaded because the"
" annotation file could not be found.\n"
"`Run geminicassandra update --dataonly --extra cadd_score`"
" to install the annotation file.\n\n")
args.skip_cadd = True
else:
sys.stderr.write(
"CADD scores are being loaded (to skip use:--skip-cadd).\n")
if args.skip_gerp_bp is False:
if 'gerp_bp' not in annos:
sys.stderr.write(
"\nGERP per bp is not being loaded because the annotation file"
" could not be found.\n Run `geminicassandra update --dataonly --extra gerp_bp`"
" to install the annotation file.\n\n")
args.skip_gerp_bp = True
else:
sys.stderr.write(
"GERP per bp is being loaded (to skip use:--skip-gerp-bp).\n")
# collect of the the add'l annotation files
annotations.load_annos(args)
time_2 = start_time
time_3 = start_time
if (args.node_num == 1):
gemini_loader = GeminiLoader(args)
gemini_loader.setup_db()
time_2 = time.time()
gemini_loader.single_core_stuff()
time_3 = time.time()
n_variants = 0
if args.cores > 1:
n_variants = load_multicore(args)
else:
n_variants = load_singlecore(args)
insert_n_variants(map(strip, args.contact_points.split(',')),
args.keyspace, n_variants)
end_time = time.time()
total_time = str(end_time - start_time)
db_creation_time = str(time_2 - start_time)
single_core_time = str(time_3 - time_2)
parallel_time = str(end_time - time_3)
print "Finished loading in %s s" % total_time
if args.timing_log != None:
with open(args.timing_log, "a") as myfile:
myfile.write(",".join([
args.exp_id, total_time, db_creation_time, single_core_time,
parallel_time
]) + "\n")
