def set_FIMO_thresh(self, FIMO_thresh):
try:
float_thresh = float(FIMO_thresh)
if float_thresh >= 0 and float_thresh <= 1:
self.FIMO_thresh = FIMO_thresh
else:
message = (
"Error: the following value for FIMO threshold <{FIMO_thresh}> "
"is not correct").format(FIMO_thresh=FIMO_thresh)
raise exceptions.WrongArgumentError(message)
except:
message = (
"Error: the following value for FIMO threshold <{FIMO_thresh}> "
"is not correct").format(FIMO_thresh=FIMO_thresh)
raise exceptions.WrongArgumentError(message)
def set_num_threads(self, num_threads):
"""Sets number of threads according to user input"""
try:
int_min = int(num_threads)
if int_min > 0:
self.num_threads = num_threads
else:
message = (
"Error: the following value for number of threads <{num_threads}> "
"is not correct").format(num_threads=num_threads)
raise exceptions.WrongArgumentError(message)
except:
message = (
"Error: the following value for number of threads <{num_threads}> "
"is not correct").format(num_threads=num_threads)
raise exceptions.WrongArgumentError(message)
def set_RNAseq_min_length(self, RNAseq_min_length):
"""Sets minimum length for RNAseq sequences according to user input"""
try:
int_min = int(RNAseq_min_length)
if int_min > 0:
self.RNAseq_min_length = RNAseq_min_length
else:
message = (
"Error: the following value for minimum RNAseq length <{min_len}> "
"is not correct").format(min_len=RNAseq_min_length)
raise exceptions.WrongArgumentError(message)
except:
message = (
"Error: the following value for minimum RNAseq length <{min_len}> "
"is not correct").format(min_len=RNAseq_min_length)
raise exceptions.WrongArgumentError(message)
def set_AME_scoring(self, AME_scoring):
if AME_scoring in ["max", "avg"]:
self.AME_scoring = AME_scoring
else:
message = (
"Error: the following AME scoring method <{AME_scoring}> "
"is not correct").format(AME_scoring=AME_scoring)
raise exceptions.WrongArgumentError(message)
def set_rand_sv_ratio(self, rand_sv_ratio):
try:
self.rand_sv_ratio = int(rand_sv_ratio)
except:
message = (
"Error: the following random to SV sequences ratio <{AME_scoring}> "
"is not correct").format(rand_sv_ratio=rand_sv_ratio)
raise exceptions.WrongArgumentError(message)
def set_SV_types(self, SV_types_string):
for SV_type in SV_types_string.split(","):
if SV_type not in ["inv", "dup", "tra", "del"]:
message = (
"Error: the following SV type <{SV_type}> is incorrect."
).format(SV_type=SV_type)
raise exceptions.WrongArgumentError(message)
self.SV_types = SV_types_string.split(",")
def set_sample_attr(self, sample_attr_string):
dict_attr = {}
for pair in sample_attr_string.split(","):
if ":" not in pair:
message = "Error: please use the correct format for attribute listing"
raise exceptions.WrongArgumentError(message)
if pair.split(":")[0] in dict_attr.keys():
dict_attr[pair.split(":")[0]].append(pair.split(":")[1])
else:
dict_attr[pair.split(":")[0]] = [pair.split(":")[1]]
self.sample_attr = dict_attr
def set_population(self, population):
"""Sets population origin of sample according to user input"""
if population in [
"asian_pacific_islander", "black", "caucasian", "hispanic",
"native_american"
]:
self.population = population
else:
message = ("Error: the following population <{population}> "
"is not correct").format(population=population)
raise exceptions.WrongArgumentError(message)
def main():
"""
The main function:
- parses through all the command line arguments
- creates the hla_pipeline class
- verifies there are no missing arguments
-runs the program and analysis
"""
try:
opts, args = getopt.getopt(
sys.argv[1:], "g:e:r:G:l:p:o:t:H:s:K:a:P:L:c:h", [
"input_WGS=", "input_WES=", "input_RNAseq=", "genome_dir=",
"RNAseq_min_length=", "population=", "output_dir=",
"num_threads=", "dir_HLA_HD=", "dir_seq2HLA=", "dir_Kourami=",
"dir_arcasHLA", "dir_picard=", "dir_HLA_LA=", "correct_HLA",
"help"
])
except getopt.GetoptError as e:
print(e)
sys.exit(2)
if len(args) > 0:
message = "Error: non-paired arguments are not allowed."
raise exceptions.WrongArgumentError(message)
HLA_pipeline = pipeline.HLAPipeline()
for opt, arg in opts:
if opt in ("-h", "--help"):
description()
sys.exit()
elif opt in ("-g", "--input_WGS"):
HLA_pipeline.set_path_WGS(arg)
elif opt in ("-e", "--input_WES"):
HLA_pipeline.set_path_WES(arg)
elif opt in ("-r", "--input_RNAseq"):
HLA_pipeline.set_path_RNAseq(arg)
elif opt in ("-G", "--dir_genome"):
HLA_pipeline.set_dir_genome(arg)
elif opt in ("-l", "--RNAseq_min_length"):
HLA_pipeline.set_RNAseq_min_length(arg)
elif opt in ("-p", "--population"):
HLA_pipeline.set_population(arg)
elif opt in ("-o", "--output_dir"):
HLA_pipeline.set_output_dir(arg)
elif opt in ("-t", "--num_threads"):
HLA_pipeline.set_num_threads(arg)
elif opt in ("-H", "--dir_HLA_HD"):
HLA_pipeline.set_dir_HLA_HD(arg)
elif opt in ("-s", "--dir_seq2HLA"):
HLA_pipeline.set_dir_seq2HLA(arg)
elif opt in ("-K", "--dir_Kourami"):
HLA_pipeline.set_dir_Kourami(arg)
elif opt in ("-a", "--dir_arcasHLA"):
HLA_pipeline.set_dir_arcasHLA(arg)
elif opt in ("-P", "--dir_picard"):
HLA_pipeline.set_dir_picard(arg)
elif opt in ("-L", "--dir_HLA_LA"):
HLA_pipeline.set_dir_HLA_LA(arg)
elif opt in ("-c", "--correct_HLA"):
HLA_pipeline.set_path_correct_HLA(arg)
else:
message = "Error: {opt} is not a valid option".format(opt=opt)
raise exceptions.WrongArgumentError(message)
for pipeline_attr in [
"input_WGS", "input_WES", "input_RNAseq", "RNAseq_min_length",
"population", "output_dir", "dir_genome", "dir_HLA_HD",
"dir_arcasHLA", "dir_seq2HLA", "dir_Kourami", "dir_picard",
"dir_HLA_LA"
]:
if not hasattr(HLA_pipeline, pipeline_attr):
message = ("Error: you must indicate --{attr}.").format(
attr=pipeline_attr)
raise exceptions.MissingArgumentError(message)
for path in (HLA_pipeline.path_WGS, HLA_pipeline.path_WES):
runprogram.Kourami(HLA_pipeline, path)
runprogram.HLA_LA(HLA_pipeline, path)
runprogram.seq2HLA(HLA_pipeline)
runprogram.HLA_HD(HLA_pipeline)
runprogram.arcasHLA(HLA_pipeline)
analysis.extract_results(HLA_pipeline)
analysis.calculate_accuracy(HLA_pipeline)
def main():
'''Reads input from terminal and coordinates pipeline'''
try:
opts, args = getopt.getopt(
sys.argv[1:], "i:o:f:l:e:m:a:t:s:r:F:A:c:p:h", [
"input_dir=", "output_dir=", "genome_fasta=", "genome_len=",
"genome_include=", "motif_path=", "sample_attr=",
"sampleinfo_table=", "SV_types=", "rand_sv_ratio=",
"FIMO_thresh=", "AME_scoring=", "config=", "prefix=", "help"
])
except getopt.GetoptError as e:
print(e)
sys.exit(2)
if len(args) > 0:
message = "Error: non-paired arguments are not allowed."
raise exceptions.WrongArgumentError(message)
motif_pipeline = pipeline.MotifPipeline()
sample_attr_path = None
genome_fasta = None
genome_len = None
genome_include = None
prefix = None
config_name = "local"
for opt, arg in opts:
if opt in ("-h", "--help"):
description()
sys.exit()
elif opt in ("-i", "--input_dir"):
motif_pipeline.set_input_dir(arg)
elif opt in ("-o", "--output_dir"):
motif_pipeline.set_output_dir(arg)
elif opt in ("-f", "--genome_fasta"):
genome_fasta = arg
elif opt in ("-l", "--genome_len"):
genome_len = arg
elif opt in ("-e", "--genome_include"):
genome_include = arg
elif opt in ("-m", "--motif_path"):
motif_pipeline.set_motif_path(arg)
elif opt in ("-a", "--sample_attr"):
motif_pipeline.set_sample_attr(arg)
elif opt in ("-t", "--sampleinfo_table"):
sample_attr_path = arg
elif opt in ("-s", "--SV_types"):
motif_pipeline.set_SV_types(arg)
elif opt in ("-r", "--rand_sv_ratio"):
motif_pipeline.set_rand_sv_ratio(arg)
elif opt in ("-F", "--FIMO_thresh"):
motif_pipeline.set_FIMO_thresh(arg)
elif opt in ("-A", "--AME_scoring"):
motif_pipeline.set_AME_scoring(arg)
elif opt in ("-c", "--config"):
config_name = arg
elif opt in ("-p", "--prefix"):
prefix = arg
else:
message = "Error: {opt} is not a valid option".format(opt=opt)
raise exceptions.WrongArgumentError(message)
if ((sample_attr_path is None and not motif_pipeline.sample_attr == "all")
or (sample_attr_path is not None
and motif_pipeline.sample_attr == "all")):
message = "Error: you must indicate both --sampleinfo_table and --sample_attr, or neither."
raise exceptions.MissingArgumentError(message)
if genome_fasta is None:
message = "Error: you must indicate --genome_fasta."
raise exceptions.MissingArgumentError(message)
if genome_len is None:
message = "Error: you must indicate --genome_len."
raise exceptions.MissingArgumentError(message)
if genome_include is None:
message = "Error: you must indicate --genome_include."
raise exceptions.MissingArgumentError(message)
for pipeline_attr in ["input_dir", "output_dir", "motif_path"]:
if not hasattr(motif_pipeline, pipeline_attr):
message = ("Error: you must indicate --{attr}.").format(
attr=pipeline_attr)
raise exceptions.MissingArgumentError(message)
motif_pipeline.set_subdir_name(prefix)
motif_pipeline.write_description()
motif_pipeline.set_list_bedpe(sample_attr_path)
reference_genome = refgenome.ReferenceGenome(genome_fasta, genome_len,
genome_include)
base_dir = '/'.join(os.path.abspath(__file__).split('/')[:-1])
try:
config = os.path.join(base_dir, 'configs', '{}.py'.format(config_name))
spec = importlib.util.spec_from_file_location('', config)
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
parsl.load(module.config)
except:
raise exceptions.IncorrectPathError(
"Cannot find the config file <{config_name}>.".format(
config_name=config_name))
if not os.path.isdir(motif_pipeline.output_dir + "bed_files"):
os.mkdir(motif_pipeline.output_dir + "bed_files")
for file_name in motif_pipeline.list_bedpe:
sv_types_to_run = get_SV_types(motif_pipeline, file_name)
if sv_types_to_run:
extractdata.bedpe_to_bed(reference_genome, motif_pipeline,
file_name, sv_types_to_run)
parsl.wait_for_current_tasks()
runprogram.merge(motif_pipeline)
motif_pipeline.set_num_SV_breakpoints()
runprogram.bedtools(motif_pipeline, reference_genome)
runprogram.FIMO(motif_pipeline)
runprogram.AME(motif_pipeline)
extractdata.extract_list_sequences_AME(motif_pipeline)
extractdata.extract_output_FIMO(motif_pipeline)
extractdata.extract_output_AME(motif_pipeline)
graphs.generate_histogram(motif_pipeline)