def Run(self):
self.__CheckInputExistance()
command_line = "%s %s %s --limit=%d" % (IgRepConConfig().run_report_supernodes,
self.__params.io.compressed_final_clusters_fa,
self.__params.io.final_stripped_clusters_fa,
self.__params.min_cluster_size)
support.sys_call(command_line, self._log)
def Run(self):
self.__CheckInputExistance()
command_line = "%s %s %s %s" % (IgRepConConfig().run_pair_reads_merger,
self.__params.left_reads,
self.__params.right_reads,
self.__params.single_reads)
support.sys_call(command_line, self._log)
def compress_dataset_files(dataset_data, ext_python_modules_home, max_threads, log):
log.info("\n== Compressing corrected reads (with gzip)")
to_compress = []
for reads_library in dataset_data:
for key, value in reads_library.items():
if key.endswith('reads'):
compressed_reads_filenames = []
for reads_file in value:
if not os.path.isfile(reads_file):
support.error('something went wrong and file with corrected reads (' + reads_file + ') is missing!', log)
to_compress.append(reads_file)
compressed_reads_filenames.append(reads_file + ".gz")
reads_library[key] = compressed_reads_filenames
if len(to_compress):
pigz_path = support.which('pigz')
if pigz_path:
for reads_file in to_compress:
support.sys_call([pigz_path, '-f', '-7', '-p', str(max_threads), reads_file], log)
else:
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
from joblib2 import Parallel, delayed
elif sys.version.startswith('3.'):
from joblib3 import Parallel, delayed
n_jobs = min(len(to_compress), max_threads)
outputs = Parallel(n_jobs=n_jobs)(delayed(support.sys_call)(['gzip', '-f', '-7', reads_file]) for reads_file in to_compress)
for output in outputs:
if output:
log.info(output)
def run_corrector(configs_dir, execution_home, cfg,
ext_python_modules_home, log, to_correct, result):
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
import pyyaml2 as pyyaml
elif sys.version.startswith('3.'):
import pyyaml3 as pyyaml
dst_configs = os.path.join(cfg.output_dir, "configs")
if os.path.exists(dst_configs):
shutil.rmtree(dst_configs)
dir_util.copy_tree(os.path.join(configs_dir, "corrector"), dst_configs, preserve_times=False)
cfg_file_name = os.path.join(dst_configs, "corrector.info")
cfg.tmp_dir = support.get_tmp_dir(prefix="corrector_")
prepare_config_corr(cfg_file_name, cfg, ext_python_modules_home)
binary_name = "corrector"
command = [os.path.join(execution_home, binary_name),
os.path.abspath(cfg_file_name), os.path.abspath(to_correct)]
log.info("\n== Running contig polishing tool: " + ' '.join(command) + "\n")
log.info("\n== Dataset description file was created: " + cfg_file_name + "\n")
support.sys_call(command, log)
if not os.path.isfile(result):
support.error("Mismatch correction finished abnormally: " + result + " not found!")
if os.path.isdir(cfg.tmp_dir):
shutil.rmtree(cfg.tmp_dir)
def run_scaffold_correction(configs_dir, execution_home, cfg, log, latest, K):
data_dir = os.path.join(cfg.output_dir, "SCC", "K%d" % K)
saves_dir = os.path.join(data_dir, 'saves')
dst_configs = os.path.join(data_dir, "configs")
cfg_file_name = os.path.join(dst_configs, "config.info")
if os.path.exists(data_dir):
shutil.rmtree(data_dir)
os.makedirs(data_dir)
dir_util.copy_tree(os.path.join(configs_dir, "debruijn"),
dst_configs,
preserve_times=False)
log.info("\n== Running scaffold correction \n")
scaffolds_file = os.path.join(latest, "scaffolds.fasta")
if not os.path.isfile(scaffolds_file):
support.error("Scaffodls were not found in " + scaffolds_file, log)
if "read_buffer_size" in cfg.__dict__:
construction_cfg_file_name = os.path.join(dst_configs,
"construction.info")
process_cfg.substitute_params(
construction_cfg_file_name,
{"read_buffer_size": cfg.read_buffer_size}, log)
process_cfg.substitute_params(
os.path.join(dst_configs, "moleculo_mode.info"),
{"scaffolds_file": scaffolds_file}, log)
prepare_config_scaffold_correction(cfg_file_name, cfg, log, saves_dir, K)
command = [
os.path.join(execution_home, "spades-truseq-scfcorrection"),
cfg_file_name
]
add_configs(command, dst_configs)
log.info(str(command))
support.sys_call(command, log)
def run_iteration(configs_dir, execution_home, cfg, log, K, use_additional_contigs, last_one):
data_dir = os.path.join(cfg.output_dir, "K%d" % (K))
if os.path.exists(data_dir):
shutil.rmtree(data_dir)
os.makedirs(data_dir)
bin_reads_dir = os.path.join(cfg.output_dir, ".bin_reads")
dst_configs = os.path.join(data_dir, "configs")
shutil.copytree(os.path.join(configs_dir, "debruijn"), dst_configs)
cfg_file_name = os.path.join(dst_configs, "config.info")
# removing template configs
for root, dirs, files in os.walk(dst_configs):
for cfg_file in files:
cfg_file = os.path.join(root, cfg_file)
if cfg_file.endswith('.info.template'):
if os.path.isfile(cfg_file.split('.template')[0]):
os.remove(cfg_file)
else:
os.rename(cfg_file, cfg_file.split('.template')[0])
prepare_config_spades(cfg_file_name, cfg, log, use_additional_contigs, K, last_one)
prev_K = K
command = os.path.join(execution_home, "spades") + " " +\
os.path.abspath(cfg_file_name)
if os.path.isdir(bin_reads_dir):
if glob.glob(os.path.join(bin_reads_dir, "*_cor*")):
for cor_filename in glob.glob(os.path.join(bin_reads_dir, "*_cor*")):
cor_index = cor_filename.rfind("_cor")
new_bin_filename = cor_filename[:cor_index] + cor_filename[cor_index + 4:]
shutil.move(cor_filename, new_bin_filename)
log.info("\n== Running assembler: " + ("K%d" % (K)) + "\n")
support.sys_call(command, log)
def run_scaffold_correction(configs_dir, execution_home, cfg, log, K):
data_dir = os.path.join(cfg.output_dir, "SCC")
saves_dir = os.path.join(data_dir, 'saves')
dst_configs = os.path.join(data_dir, "configs")
cfg_file_name = os.path.join(dst_configs, "config.info")
if os.path.exists(data_dir):
shutil.rmtree(data_dir)
os.makedirs(data_dir)
dir_util.copy_tree(os.path.join(configs_dir, "debruijn"), dst_configs, preserve_times=False)
# removing template configs
for root, dirs, files in os.walk(dst_configs):
for cfg_file in files:
cfg_file = os.path.join(root, cfg_file)
if cfg_file.endswith('.info.template'):
if os.path.isfile(cfg_file.split('.template')[0]):
os.remove(cfg_file)
else:
os.rename(cfg_file, cfg_file.split('.template')[0])
log.info("\n== Running scaffold correction \n")
latest = os.path.join(cfg.output_dir, "K%d" % K)
scaffolds_file = os.path.join(latest, "scaffolds.fasta")
if not os.path.isfile(scaffolds_file):
support.error("Scaffodls were not found in " + scaffolds_file, log)
if "read_buffer_size" in cfg.__dict__:
construction_cfg_file_name = os.path.join(dst_configs, "construction.info")
process_cfg.substitute_params(construction_cfg_file_name, {"read_buffer_size": cfg.read_buffer_size}, log)
prepare_config_scaffold_correction(cfg_file_name, cfg, log, saves_dir, scaffolds_file)
command = [os.path.join(execution_home, "scaffold_correction"), cfg_file_name]
log.info(str(command))
support.sys_call(command, log)
def run_igrec(input_file,
output_dir,
log=None,
tau=4,
min_fillin=0.6,
loci="all",
threads=16,
additional_args="",
min_sread_size=5,
remove_tmp=True):
if log is None:
log = FakeLog()
args = {
"path": path_to_igrec,
"tau": tau,
"min_fillin": min_fillin,
"loci": loci,
"threads": threads,
"input_file": input_file,
"output_dir": output_dir,
"min_sread_size": min_sread_size,
"additional_args": additional_args
}
timer = Timer()
support.sys_call(
"%(path)s/igrec.py --tau=%(tau)d --min-fillin=%(min_fillin)f -t %(threads)d --loci %(loci)s -s %(input_file)s -o %(output_dir)s --min-sread-size %(min_sread_size)d %(additional_args)s"
% args,
log=log)
timer.stamp(output_dir + "/time.txt")
if remove_tmp:
rmdir(output_dir + "/vj_finder")
def run_scaffold_correction(configs_dir, execution_home, cfg, log, latest, K):
data_dir = os.path.join(cfg.output_dir, "SCC", "K%d" % K)
saves_dir = os.path.join(data_dir, 'saves')
dst_configs = os.path.join(data_dir, "configs")
cfg_file_name = os.path.join(dst_configs, "config.info")
if os.path.exists(data_dir):
shutil.rmtree(data_dir)
os.makedirs(data_dir)
dir_util.copy_tree(os.path.join(configs_dir, "debruijn"), dst_configs, preserve_times=False)
log.info("\n== Running scaffold correction \n")
scaffolds_file = os.path.join(latest, "scaffolds.fasta")
if not os.path.isfile(scaffolds_file):
support.error("Scaffodls were not found in " + scaffolds_file, log)
if "read_buffer_size" in cfg.__dict__:
construction_cfg_file_name = os.path.join(dst_configs, "construction.info")
process_cfg.substitute_params(construction_cfg_file_name, {"read_buffer_size": cfg.read_buffer_size}, log)
process_cfg.substitute_params(os.path.join(dst_configs, "moleculo_mode.info"), {"scaffolds_file": scaffolds_file}, log)
prepare_config_scaffold_correction(cfg_file_name, cfg, log, saves_dir, K)
command = [os.path.join(execution_home, "scaffold_correction"), cfg_file_name]
add_configs(command, dst_configs)
log.info(str(command))
support.sys_call(command, log)
def run_ig_simulator(output_dir,
log=None,
chain="HC",
num_bases=100,
num_mutated=1000,
repertoire_size=5000,
tcr=False):
if log is None:
log = FakeLog()
assert chain in ["HC", "LC"]
args = {
"path": path_to_ig_simulator if not tcr else path_to_ig_simulator_tcr,
"output_dir": output_dir,
"chain": chain,
"num_bases": num_bases,
"num_mutated": num_mutated,
"repertoire_size": repertoire_size
}
timer = Timer()
cmd = "%(path)s/ig_simulator.py --chain-type %(chain)s --num-bases %(num_bases)d --num-mutated %(num_mutated)d --repertoire-size %(repertoire_size)d -o %(output_dir)s --skip-drawing" % args
if tcr:
vgenes = igrec_dir + "/data/germline/human/TCR/TRBV.fa"
jgenes = igrec_dir + "/data/germline/human/TCR/TRBJ.fa"
dgenes = igrec_dir + "/data/germline/human/TCR/TRBD.fa"
cmd += " --vgenes=" + vgenes + " --jgenes=" + jgenes + " --dgenes=" + dgenes
support.sys_call(cmd, log=log)
timer.stamp(output_dir + "/time.txt")
def simulate_data(input_file, output_dir, log=None, **kwargs):
import tempfile
import shutil
if log is None:
log = FakeLog()
mkdir_p(output_dir)
temp_dir = tempfile.mkdtemp()
run_igrec(input_file, temp_dir, remove_tmp=False,
tau=1) # Run IgReC for VJF output
input_file = temp_dir + "/vj_finder/cleaned_reads.fa"
simulated_repertoire_to_rcm(input_file,
"%s/final_repertoire.rcm" % output_dir)
simulated_repertoire_to_final_repertoire(
input_file, "%s/final_repertoire.fa.gz" % output_dir)
args = {
"path": igrec_dir,
"repertoire": output_dir + "/final_repertoire.fa.gz",
"rcm": output_dir + "/final_repertoire.rcm"
}
support.sys_call(
"%(path)s/py/ig_compress_equal_clusters.py %(repertoire)s %(repertoire)s -r %(rcm)s"
% args,
log=log)
# TODO factor this stage
jit_fx_file(input_file, "%s/input_reads.fa.gz" % output_dir, **kwargs)
shutil.rmtree(temp_dir)
def run_corrector(configs_dir, execution_home, cfg,
ext_python_modules_home, log, to_correct, result):
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
import pyyaml2 as pyyaml
elif sys.version.startswith('3.'):
import pyyaml3 as pyyaml
dst_configs = os.path.join(cfg.output_dir, "configs")
if os.path.exists(dst_configs):
shutil.rmtree(dst_configs)
dir_util.copy_tree(os.path.join(configs_dir, "corrector"), dst_configs, preserve_times=False)
cfg_file_name = os.path.join(dst_configs, "corrector.info")
cfg.tmp_dir = support.get_tmp_dir(prefix="corrector_")
prepare_config_corr(cfg_file_name, cfg, ext_python_modules_home)
binary_name = "corrector"
command = [os.path.join(execution_home, binary_name),
os.path.abspath(cfg_file_name), os.path.abspath(to_correct)]
log.info("\n== Running contig polishing tool: " + ' '.join(command) + "\n")
log.info("\n== Dataset description file was created: " + cfg_file_name + "\n")
support.sys_call(command, log)
if not os.path.isfile(result):
support.error("Mismatch correction finished abnormally: " + result + " not found!")
if os.path.isdir(cfg.tmp_dir):
shutil.rmtree(cfg.tmp_dir)
def run_presto(input_file, output_dir, log=None, remove_tmp=True):
if log is None:
log = FakeLog()
mkdir_p(output_dir)
# gunzip
input_file_new = "%s/input_reads.fasta" % output_dir
fastx2fastx(input_file, input_file_new)
args = {"input_file": input_file_new, "output_dir": output_dir}
timer = Timer()
support.sys_call(
"CollapseSeq.py -s %(input_file)s --outdir %(output_dir)s --outname presto"
% args,
log=log)
timer.stamp(output_dir + "/time.txt")
presto_output = output_dir + "/presto_collapse-unique.fasta"
repertoire_fa = output_dir + "/final_repertoire.fa"
with smart_open(presto_output) as fin, smart_open(repertoire_fa,
"w") as fout:
for i, record in enumerate(
SeqIO.parse(fin, idFormatByFileName(presto_output))):
id = record.description
size = parse_presto_id(id)
record.id = record.description = "cluster___%d___size___%d" % (
i, size)
SeqIO.write(record, fout, "fasta")
if remove_tmp:
os.remove(input_file_new)
os.remove(presto_output)
def run_scaffold_correction(configs_dir, execution_home, cfg, log, K):
data_dir = os.path.join(cfg.output_dir, "SCC")
saves_dir = os.path.join(data_dir, 'saves')
dst_configs = os.path.join(data_dir, "configs")
cfg_file_name = os.path.join(dst_configs, "config.info")
if os.path.exists(data_dir):
shutil.rmtree(data_dir)
os.makedirs(data_dir)
dir_util.copy_tree(os.path.join(configs_dir, "debruijn"), dst_configs, preserve_times=False)
# removing template configs
for root, dirs, files in os.walk(dst_configs):
for cfg_file in files:
cfg_file = os.path.join(root, cfg_file)
if cfg_file.endswith('.info.template'):
if os.path.isfile(cfg_file.split('.template')[0]):
os.remove(cfg_file)
else:
os.rename(cfg_file, cfg_file.split('.template')[0])
log.info("\n== Running scaffold correction \n")
latest = os.path.join(cfg.output_dir, "K%d" % K)
scaffolds_file = os.path.join(latest, "scaffolds.fasta")
if not os.path.isfile(scaffolds_file):
support.error("Scaffodls were not found in " + scaffolds_file, log)
if "read_buffer_size" in cfg.__dict__:
construction_cfg_file_name = os.path.join(dst_configs, "construction.info")
process_cfg.substitute_params(construction_cfg_file_name, {"read_buffer_size": cfg.read_buffer_size}, log)
prepare_config_scaffold_correction(cfg_file_name, cfg, log, saves_dir, scaffolds_file)
command = [os.path.join(execution_home, "scaffold_correction"), cfg_file_name]
log.info(str(command))
support.sys_call(command, log)
def compress_dataset_files(dataset_data, ext_python_modules_home, max_threads, log):
log.info("\n== Compressing corrected reads (with gzip)")
to_compress = []
for reads_library in dataset_data:
for key, value in reads_library.items():
if key.endswith('reads'):
compressed_reads_filenames = []
for reads_file in value:
if not os.path.isfile(reads_file):
support.error('something went wrong and file with corrected reads (' + reads_file + ') is missing!', log)
to_compress.append(reads_file)
compressed_reads_filenames.append(reads_file + ".gz")
reads_library[key] = compressed_reads_filenames
if len(to_compress):
pigz_path = support.which('pigz')
if pigz_path:
for reads_file in to_compress:
support.sys_call([pigz_path, '-f', '-7', '-p', str(max_threads), reads_file], log)
else:
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
from joblib2 import Parallel, delayed
elif sys.version.startswith('3.'):
from joblib3 import Parallel, delayed
n_jobs = min(len(to_compress), max_threads)
outputs = Parallel(n_jobs=n_jobs)(delayed(support.sys_call)(['gzip', '-f', '-7', reads_file]) for reads_file in to_compress)
for output in outputs:
if output:
log.info(output)
def run_iteration(configs_dir, execution_home, cfg, log, K, prev_K, last_one):
data_dir = os.path.join(cfg.output_dir, "K%d" % K)
stage = BASE_STAGE
saves_dir = os.path.join(data_dir, 'saves')
dst_configs = os.path.join(data_dir, "configs")
cfg_file_name = os.path.join(dst_configs, "config.info")
if options_storage.continue_mode:
if os.path.isfile(os.path.join(data_dir, "final_contigs.fasta")) and not (options_storage.restart_from and
(options_storage.restart_from == ("k%d" % K) or options_storage.restart_from.startswith("k%d:" % K))):
log.info("\n== Skipping assembler: " + ("K%d" % K) + " (already processed)")
return
if options_storage.restart_from and options_storage.restart_from.find(":") != -1:
stage = options_storage.restart_from[options_storage.restart_from.find(":") + 1:]
support.continue_from_here(log)
if stage != BASE_STAGE:
if not os.path.isdir(saves_dir):
support.error("Cannot restart from stage %s: saves were not found (%s)!" % (stage, saves_dir))
else:
if os.path.exists(data_dir):
shutil.rmtree(data_dir)
os.makedirs(data_dir)
shutil.copytree(os.path.join(configs_dir, "debruijn"), dst_configs)
# removing template configs
for root, dirs, files in os.walk(dst_configs):
for cfg_file in files:
cfg_file = os.path.join(root, cfg_file)
if cfg_file.endswith('.info.template'):
if os.path.isfile(cfg_file.split('.template')[0]):
os.remove(cfg_file)
else:
os.rename(cfg_file, cfg_file.split('.template')[0])
log.info("\n== Running assembler: " + ("K%d" % K) + "\n")
if prev_K:
additional_contigs_fname = os.path.join(cfg.output_dir, "K%d" % prev_K, "simplified_contigs.fasta")
if not os.path.isfile(additional_contigs_fname):
support.warning("additional contigs for K=%d were not found (%s)!" % (K, additional_contigs_fname), log)
additional_contigs_fname = None
else:
additional_contigs_fname = None
if "read_buffer_size" in cfg.__dict__:
construction_cfg_file_name = os.path.join(dst_configs, "construction.info")
process_cfg.substitute_params(construction_cfg_file_name, {"read_buffer_size": cfg.read_buffer_size}, log)
prepare_config_spades(cfg_file_name, cfg, log, additional_contigs_fname, K, stage, saves_dir, last_one)
command = [os.path.join(execution_home, "spades"), cfg_file_name]
## this code makes sense for src/debruijn/simplification.cpp: corrected_and_save_reads() function which is not used now
# bin_reads_dir = os.path.join(cfg.output_dir, ".bin_reads")
# if os.path.isdir(bin_reads_dir):
# if glob.glob(os.path.join(bin_reads_dir, "*_cor*")):
# for cor_filename in glob.glob(os.path.join(bin_reads_dir, "*_cor*")):
# cor_index = cor_filename.rfind("_cor")
# new_bin_filename = cor_filename[:cor_index] + cor_filename[cor_index + 4:]
# shutil.move(cor_filename, new_bin_filename)
support.sys_call(command, log)
def run_hammer(corrected_dataset_yaml_filename, configs_dir, execution_home, cfg,
not_used_dataset_data, ext_python_modules_home, log):
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
import pyyaml2 as pyyaml
elif sys.version.startswith('3.'):
import pyyaml3 as pyyaml
dst_configs = os.path.join(cfg.output_dir, "configs")
if os.path.exists(dst_configs):
shutil.rmtree(dst_configs)
if cfg.iontorrent:
dir_util.copy_tree(os.path.join(configs_dir, "ionhammer"), dst_configs, preserve_times=False)
cfg_file_name = os.path.join(dst_configs, "ionhammer.cfg")
else:
dir_util.copy_tree(os.path.join(configs_dir, "hammer"), dst_configs, preserve_times=False)
cfg_file_name = os.path.join(dst_configs, "config.info")
# removing template configs
for root, dirs, files in os.walk(dst_configs):
for cfg_file in files:
cfg_file = os.path.join(root, cfg_file)
if cfg_file.endswith('.template'):
if os.path.isfile(cfg_file.split('.template')[0]):
os.remove(cfg_file)
else:
os.rename(cfg_file, cfg_file.split('.template')[0])
cfg.tmp_dir = support.get_tmp_dir(prefix="hammer_")
if cfg.iontorrent:
prepare_config_ih(cfg_file_name, cfg, ext_python_modules_home)
binary_name = "ionhammer"
else:
prepare_config_bh(cfg_file_name, cfg, log)
binary_name = "hammer"
command = [os.path.join(execution_home, binary_name),
os.path.abspath(cfg_file_name)]
log.info("\n== Running read error correction tool: " + ' '.join(command) + "\n")
support.sys_call(command, log)
if not os.path.isfile(corrected_dataset_yaml_filename):
support.error("read error correction finished abnormally: " + corrected_dataset_yaml_filename + " not found!")
corrected_dataset_data = pyyaml.load(open(corrected_dataset_yaml_filename, 'r'))
remove_not_corrected_reads(cfg.output_dir)
is_changed = False
if cfg.gzip_output:
is_changed = True
compress_dataset_files(corrected_dataset_data, ext_python_modules_home, cfg.max_threads, log)
if not_used_dataset_data:
is_changed = True
corrected_dataset_data += not_used_dataset_data
if is_changed:
pyyaml.dump(corrected_dataset_data, open(corrected_dataset_yaml_filename, 'w'))
log.info("\n== Dataset description file was created: " + corrected_dataset_yaml_filename + "\n")
if os.path.isdir(cfg.tmp_dir):
shutil.rmtree(cfg.tmp_dir)
def Run(self, log):
log.info("Running %s" % self.cmdl)
try:
support.sys_call(self.cmdl, log, self.cwd)
except:
log.error("Failed to run '%s':\n%s" % (self.cmdl, sys.exc_info()))
return -1
log.info("Returned 0")
return 0
def run_hammer(corrected_dataset_yaml_filename, configs_dir, execution_home, cfg,
not_used_dataset_data, ext_python_modules_home, log):
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
import pyyaml2 as pyyaml
elif sys.version.startswith('3.'):
import pyyaml3 as pyyaml
dst_configs = os.path.join(cfg.output_dir, "configs")
if os.path.exists(dst_configs):
shutil.rmtree(dst_configs)
if cfg.iontorrent:
dir_util.copy_tree(os.path.join(configs_dir, "ionhammer"), dst_configs, preserve_times=False)
cfg_file_name = os.path.join(dst_configs, "ionhammer.cfg")
else:
dir_util.copy_tree(os.path.join(configs_dir, "hammer"), dst_configs, preserve_times=False)
cfg_file_name = os.path.join(dst_configs, "config.info")
# removing template configs
for root, dirs, files in os.walk(dst_configs):
for cfg_file in files:
cfg_file = os.path.join(root, cfg_file)
if cfg_file.endswith('.template'):
if os.path.isfile(cfg_file.split('.template')[0]):
os.remove(cfg_file)
else:
os.rename(cfg_file, cfg_file.split('.template')[0])
cfg.tmp_dir = support.get_tmp_dir(prefix="hammer_")
if cfg.iontorrent:
prepare_config_ih(cfg_file_name, cfg, ext_python_modules_home)
binary_name = "ionhammer"
else:
prepare_config_bh(cfg_file_name, cfg, log)
binary_name = "hammer"
command = [os.path.join(execution_home, binary_name),
os.path.abspath(cfg_file_name)]
log.info("\n== Running read error correction tool: " + ' '.join(command) + "\n")
support.sys_call(command, log)
if not os.path.isfile(corrected_dataset_yaml_filename):
support.error("read error correction finished abnormally: " + corrected_dataset_yaml_filename + " not found!")
corrected_dataset_data = pyyaml.load(open(corrected_dataset_yaml_filename, 'r'))
remove_not_corrected_reads(cfg.output_dir)
is_changed = False
if cfg.gzip_output:
is_changed = True
compress_dataset_files(corrected_dataset_data, ext_python_modules_home, cfg.max_threads, log)
if not_used_dataset_data:
is_changed = True
corrected_dataset_data += not_used_dataset_data
if is_changed:
pyyaml.dump(corrected_dataset_data, open(corrected_dataset_yaml_filename, 'w'))
log.info("\n== Dataset description file was created: " + corrected_dataset_yaml_filename + "\n")
if os.path.isdir(cfg.tmp_dir):
shutil.rmtree(cfg.tmp_dir)
def Run(self):
self.__CheckInputExistance()
command_line = IgRepConConfig().run_trie_compressor + " -i " + self.__params.io.cropped_reads + \
" -o " + self.__params.io.compressed_reads + " -m " + self.__params.io.map_file
support.sys_call(command_line, self._log)
command_line = "%s %s %s --limit=%d" % (
IgRepConConfig().run_report_supernodes,
self.__params.io.compressed_reads,
self.__params.io.supernodes_file, self.__params.min_cluster_size)
support.sys_call(command_line, self._log)
def Run(self):
self.__CheckInputExistance()
command_line = "%s %s %s -T %s -m %s -r %s -R %s" % (IgRepConConfig().run_compress_equal_clusters,
self.__params.io.uncompressed_final_clusters_fa,
self.__params.io.compressed_final_clusters_fa,
self.__params.io.tmp_compressed_clusters_fa,
self.__params.io.tmp_compressed_clusters_map,
self.__params.io.uncompressed_final_rcm,
self.__params.io.compressed_final_rcm)
support.sys_call(command_line, self._log)
def main():
args = parse_args()
# create logger
log = logging.getLogger("Mismatch correction " + args.assembly_type)
log.setLevel(logging.DEBUG)
console = logging.StreamHandler(sys.stdout)
console.setFormatter(logging.Formatter("%(message)s"))
console.setLevel(logging.DEBUG)
log.addHandler(console)
# moving assembled contigs (scaffolds) to misc dir
if os.path.isfile(args.corrected):
shutil.move(args.corrected, args.assembled)
# TODO can check only here, that assembled existst and may be skipping...
if not os.path.isfile(args.assembled) or os.path.getsize(
args.assembled) == 0:
log.info("\n== Skipping processing of %s (empty file)\n" %
args.assembly_type)
else:
log.info("\n== Processing of %s\n" % args.assembly_type)
tmp_dir_for_corrector = os.path.join(args.output_dir,
"mismatch_corrector",
args.assembly_type)
# correcting
result_corrected_filename = os.path.join(tmp_dir_for_corrector,
"corrected_contigs.fasta")
dst_configs = os.path.join(tmp_dir_for_corrector, "configs")
cfg_file_name = os.path.join(dst_configs, "corrector.info")
binary_name = "spades-corrector-core"
command = [
os.path.join(args.bin_home, binary_name),
os.path.abspath(cfg_file_name),
os.path.abspath(args.assembled)
]
log.info("\n== Running contig polishing tool: " + ' '.join(command) +
"\n")
log.info("\n== Dataset description file was created: " +
cfg_file_name + "\n")
log.info("Run: " + ' '.join(command))
support.sys_call(command, log)
if not os.path.isfile(result_corrected_filename):
log.error(
"mismatch correction finished abnormally: %s not found!" %
result_corrected_filename)
if os.path.isfile(result_corrected_filename):
shutil.copyfile(result_corrected_filename, args.corrected)
def move_dataset_files(dataset_data,
dst,
ext_python_modules_home,
max_threads,
log,
gzip=False):
to_compress = []
for reads_library in dataset_data:
for key, value in reads_library.items():
if key.endswith('reads'):
moved_reads_files = []
for reads_file in value:
dst_filename = os.path.join(dst,
os.path.basename(reads_file))
# TODO: fix problem with files with the same basenames in Hammer binary!
if not os.path.isfile(reads_file):
if (not gzip and os.path.isfile(dst_filename)) or (
gzip and os.path.isfile(dst_filename + '.gz')):
support.warning(
'file with corrected reads (' + reads_file +
') is the same in several libraries', log)
if gzip:
dst_filename += '.gz'
else:
support.error(
'something went wrong and file with corrected reads ('
+ reads_file + ') is missing!', log)
else:
shutil.move(reads_file, dst_filename)
if gzip:
to_compress.append(dst_filename)
dst_filename += '.gz'
moved_reads_files.append(dst_filename)
reads_library[key] = moved_reads_files
if len(to_compress):
pigz_path = support.which('pigz')
if pigz_path:
for reads_file in to_compress:
support.sys_call([
pigz_path, '-f', '-7', '-p',
str(max_threads), reads_file
], log)
else:
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
from joblib2 import Parallel, delayed
elif sys.version.startswith('3.'):
from joblib3 import Parallel, delayed
n_jobs = min(len(to_compress), max_threads)
outputs = Parallel(n_jobs=n_jobs)(
delayed(support.sys_call)(['gzip', '-f', '-7', reads_file])
for reads_file in to_compress)
for output in outputs:
if output:
log.info(output)
def run_iteration(configs_dir, execution_home, cfg, log, K, prev_K, last_one):
data_dir = os.path.join(cfg.output_dir, "K%d" % K)
stage = BASE_STAGE
saves_dir = os.path.join(data_dir, 'saves')
dst_configs = os.path.join(data_dir, "configs")
if options_storage.continue_mode:
if os.path.isfile(os.path.join(data_dir, "final_contigs.fasta")) and not (options_storage.restart_from and
(options_storage.restart_from == ("k%d" % K) or options_storage.restart_from.startswith("k%d:" % K))):
log.info("\n== Skipping assembler: " + ("K%d" % K) + " (already processed)")
return
if options_storage.restart_from and options_storage.restart_from.find(":") != -1 \
and options_storage.restart_from.startswith("k%d:" % K):
stage = options_storage.restart_from[options_storage.restart_from.find(":") + 1:]
support.continue_from_here(log)
if stage != BASE_STAGE:
if not os.path.isdir(saves_dir):
support.error("Cannot restart from stage %s: saves were not found (%s)!" % (stage, saves_dir))
else:
if os.path.exists(data_dir):
shutil.rmtree(data_dir)
os.makedirs(data_dir)
dir_util._path_created = {} # see http://stackoverflow.com/questions/9160227/dir-util-copy-tree-fails-after-shutil-rmtree
dir_util.copy_tree(os.path.join(configs_dir, "debruijn"), dst_configs, preserve_times=False)
log.info("\n== Running assembler: " + ("K%d" % K) + "\n")
if prev_K:
additional_contigs_fname = os.path.join(cfg.output_dir, "K%d" % prev_K, "simplified_contigs.fasta")
if not os.path.isfile(additional_contigs_fname):
support.warning("additional contigs for K=%d were not found (%s)!" % (K, additional_contigs_fname), log)
additional_contigs_fname = None
else:
additional_contigs_fname = None
if "read_buffer_size" in cfg.__dict__:
#FIXME why here???
process_cfg.substitute_params(os.path.join(dst_configs, "construction.info"), {"read_buffer_size": cfg.read_buffer_size}, log)
if "scaffolding_mode" in cfg.__dict__:
#FIXME why here???
process_cfg.substitute_params(os.path.join(dst_configs, "pe_params.info"), {"scaffolding_mode": cfg.scaffolding_mode}, log)
prepare_config_rnaspades(os.path.join(dst_configs, "rna_mode.info"), log)
prepare_config_construction(os.path.join(dst_configs, "construction.info"), log)
cfg_fn = os.path.join(dst_configs, "config.info")
prepare_config_spades(cfg_fn, cfg, log, additional_contigs_fname, K, stage, saves_dir, last_one, execution_home)
command = [os.path.join(execution_home, "spades-core"), cfg_fn]
add_configs(command, dst_configs)
#print("Calling: " + " ".join(command))
support.sys_call(command, log)
def run_iteration(configs_dir, execution_home, cfg, log, K, prev_K, last_one):
data_dir = os.path.join(cfg.output_dir, "K%d" % K)
stage = BASE_STAGE
saves_dir = os.path.join(data_dir, 'saves')
dst_configs = os.path.join(data_dir, "configs")
if options_storage.continue_mode:
if os.path.isfile(os.path.join(data_dir, "final_contigs.fasta")) and not (options_storage.restart_from and
(options_storage.restart_from == ("k%d" % K) or options_storage.restart_from.startswith("k%d:" % K))):
log.info("\n== Skipping assembler: " + ("K%d" % K) + " (already processed)")
return
if options_storage.restart_from and options_storage.restart_from.find(":") != -1 \
and options_storage.restart_from.startswith("k%d:" % K):
stage = options_storage.restart_from[options_storage.restart_from.find(":") + 1:]
support.continue_from_here(log)
if stage != BASE_STAGE:
if not os.path.isdir(saves_dir):
support.error("Cannot restart from stage %s: saves were not found (%s)!" % (stage, saves_dir))
else:
if os.path.exists(data_dir):
shutil.rmtree(data_dir)
os.makedirs(data_dir)
dir_util._path_created = {} # see http://stackoverflow.com/questions/9160227/dir-util-copy-tree-fails-after-shutil-rmtree
dir_util.copy_tree(os.path.join(configs_dir, "debruijn"), dst_configs, preserve_times=False)
log.info("\n== Running assembler: " + ("K%d" % K) + "\n")
if prev_K:
additional_contigs_fname = os.path.join(cfg.output_dir, "K%d" % prev_K, "simplified_contigs.fasta")
if not os.path.isfile(additional_contigs_fname):
support.warning("additional contigs for K=%d were not found (%s)!" % (K, additional_contigs_fname), log)
additional_contigs_fname = None
else:
additional_contigs_fname = None
if "read_buffer_size" in cfg.__dict__:
#FIXME why here???
process_cfg.substitute_params(os.path.join(dst_configs, "construction.info"), {"read_buffer_size": cfg.read_buffer_size}, log)
if "scaffolding_mode" in cfg.__dict__:
#FIXME why here???
process_cfg.substitute_params(os.path.join(dst_configs, "pe_params.info"), {"scaffolding_mode": cfg.scaffolding_mode}, log)
prepare_config_rnaspades(os.path.join(dst_configs, "rna_mode.info"), log)
prepare_config_construction(os.path.join(dst_configs, "construction.info"), log)
cfg_fn = os.path.join(dst_configs, "config.info")
prepare_config_spades(cfg_fn, cfg, log, additional_contigs_fname, K, stage, saves_dir, last_one, execution_home)
command = [os.path.join(execution_home, "spades-core"), cfg_fn]
add_configs(command, dst_configs)
#print("Calling: " + " ".join(command))
support.sys_call(command, log)
def run_mixcr2_alignment_only(input_file,
output_dir,
log=None,
loci="all",
enforce_fastq=False,
threads=16,
remove_tmp=True,
species="hsa"):
if log is None:
log = FakeLog()
mkdir_p(output_dir)
if enforce_fastq and idFormatByFileName(input_file) == "fasta":
input_file_fq = "%s/input_reads.fq" % output_dir
fastx2fastx(input_file, input_file_fq)
input_file = input_file_tmp = input_file_fq
elif idFormatByFileName(input_file) == "fasta":
input_file_fasta = "%s/input_reads.fasta" % output_dir
fastx2fastx(input_file, input_file_fasta)
input_file = input_file_tmp = input_file_fasta
else:
input_file_tmp = None
path = path_to_mixcr2
args = {
"path": path,
"compress_eq_clusters_cmd":
path_to_igrec + "/py/ig_compress_equal_clusters.py",
"mixcr_cmd": "java -jar %s/mixcr.jar" % path,
"threads": threads,
"input_file": input_file,
"output_dir": output_dir,
"species": species,
"loci": loci,
"loci_arg": "chains"
}
# support.sys_call("%(mixcr_cmd)s align -t %(threads)d -f -g -r %(output_dir)s/align_report.txt --%(loci_arg)s %(loci)s --noMerge --species %(species)s %(input_file)s %(output_dir)s/mixcr.vdjca" % args,
# log=log)
timer = Timer()
support.sys_call(
"%(mixcr_cmd)s align -p kaligner2 --species %(species)s -t %(threads)d -f -g -r %(output_dir)s/align_report.txt --noMerge --%(loci_arg)s %(loci)s -OreadsLayout=Collinear -OvParameters.geneFeatureToAlign=VTranscript -OallowPartialAlignments=true %(input_file)s %(output_dir)s/mixcr.vdjca"
% args,
log=log)
timer.stamp(output_dir + "/time.txt")
if remove_tmp:
if input_file_tmp is not None:
os.remove(input_file_tmp)
os.remove(output_dir + "/align_report.txt")
os.remove(output_dir + "/mixcr.vdjca")
def run_bh(result_filename, configs_dir, execution_home, cfg,
ext_python_modules_home, log):
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
import pyyaml2 as pyyaml
elif sys.version.startswith('3.'):
import pyyaml3 as pyyaml
dst_configs = os.path.join(cfg.output_dir, "configs")
if os.path.exists(dst_configs):
shutil.rmtree(dst_configs)
shutil.copytree(os.path.join(configs_dir, "hammer"), dst_configs)
cfg_file_name = os.path.join(dst_configs, "config.info")
# removing template configs
for root, dirs, files in os.walk(dst_configs):
for cfg_file in files:
cfg_file = os.path.join(root, cfg_file)
if cfg_file.endswith('.info.template'):
if os.path.isfile(cfg_file.split('.template')[0]):
os.remove(cfg_file)
else:
os.rename(cfg_file, cfg_file.split('.template')[0])
prepare_config_bh(cfg_file_name, cfg, log)
command = [
os.path.join(execution_home, "hammer"),
os.path.abspath(cfg_file_name)
]
log.info("\n== Running read error correction tool: " + ' '.join(command) +
"\n")
support.sys_call(command, log)
corrected_dataset_yaml_filename = os.path.join(cfg.tmp_dir,
"corrected.yaml")
if not os.path.isfile(corrected_dataset_yaml_filename):
support.error("read error correction finished abnormally: " +
corrected_dataset_yaml_filename + " not found!")
corrected_dataset_data = pyyaml.load(
open(corrected_dataset_yaml_filename, 'r'))
if cfg.gzip_output:
log.info("\n== Compressing corrected reads (with gzip)")
move_dataset_files(corrected_dataset_data, cfg.output_dir,
ext_python_modules_home, cfg.max_threads, log,
cfg.gzip_output)
corrected_dataset_yaml_filename = result_filename
pyyaml.dump(corrected_dataset_data,
open(corrected_dataset_yaml_filename, 'w'))
log.info("\n== Dataset description file created: " +
corrected_dataset_yaml_filename + "\n")
shutil.rmtree(cfg.tmp_dir)
def Run(self):
self.__CheckInputExistance()
self.__params.vj_finder_output = os.path.join(self.__params.output,
"vj_finder")
command_line = IgRepConConfig().run_vj_aligner + " -i " + self.__params.single_reads + \
" -o " + self.__params.io.vj_finder_output + \
" --db-directory " + IgRepConConfig().path_to_germline + \
" -t " + str(self.__params.num_threads) + \
" --loci " + self.__params.loci + \
" --organism " + self.__params.organism
if self.__params.no_pseudogenes:
command_line += " --no-pseudogenes"
support.sys_call(command_line, self._log)
def run_iteration(configs_dir, execution_home, cfg, log, K, prev_K, last_one):
data_dir = os.path.join(cfg.output_dir, "K%d" % K)
stage = BASE_STAGE
saves_dir = os.path.join(data_dir, 'saves')
dst_configs = os.path.join(data_dir, "configs")
cfg_file_name = os.path.join(dst_configs, "config.info")
if options_storage.continue_mode:
if os.path.isfile(os.path.join(data_dir, "final_contigs.fasta")) and not (options_storage.restart_from and
(options_storage.restart_from == ("k%d" % K) or options_storage.restart_from.startswith("k%d:" % K))):
log.info("\n== Skipping assembler: " + ("K%d" % K) + " (already processed)")
return
if options_storage.restart_from and options_storage.restart_from.find(":") != -1:
stage = options_storage.restart_from[options_storage.restart_from.find(":") + 1:]
support.continue_from_here(log)
if stage != BASE_STAGE:
if not os.path.isdir(saves_dir):
support.error("Cannot restart from stage %s: saves were not found (%s)!" % (stage, saves_dir))
else:
if os.path.exists(data_dir):
shutil.rmtree(data_dir)
os.makedirs(data_dir)
dir_util.copy_tree(os.path.join(configs_dir, "debruijn"), dst_configs, preserve_times=False)
# removing template configs
for root, dirs, files in os.walk(dst_configs):
for cfg_file in files:
cfg_file = os.path.join(root, cfg_file)
if cfg_file.endswith('.info.template'):
if os.path.isfile(cfg_file.split('.template')[0]):
os.remove(cfg_file)
else:
os.rename(cfg_file, cfg_file.split('.template')[0])
log.info("\n== Running assembler: " + ("K%d" % K) + "\n")
if prev_K:
additional_contigs_fname = os.path.join(cfg.output_dir, "K%d" % prev_K, "simplified_contigs.fasta")
if not os.path.isfile(additional_contigs_fname):
support.warning("additional contigs for K=%d were not found (%s)!" % (K, additional_contigs_fname), log)
additional_contigs_fname = None
else:
additional_contigs_fname = None
if "read_buffer_size" in cfg.__dict__:
construction_cfg_file_name = os.path.join(dst_configs, "construction.info")
process_cfg.substitute_params(construction_cfg_file_name, {"read_buffer_size": cfg.read_buffer_size}, log)
prepare_config_spades(cfg_file_name, cfg, log, additional_contigs_fname, K, stage, saves_dir, last_one, execution_home)
command = [os.path.join(execution_home, "spades"), cfg_file_name]
support.sys_call(command, log)
def Run(self):
self.__CheckInputExistance()
command_line = "%s -i %s -c %s -q %s -o %s" % (
IgRepConConfig().run_rcm_recoverer, self.__params.io.cropped_reads,
self.__params.io.map_file,
self.__params.io.dense_sgraph_decomposition,
self.__params.io.uncompressed_final_rcm)
support.sys_call(command_line, self._log)
command_line = IgRepConConfig().run_consensus_constructor + \
" -i " + self.__params.io.cropped_reads + \
" -R " + self.__params.io.uncompressed_final_rcm + \
" -o " + self.__params.io.uncompressed_final_clusters_fa + \
" -H " + " -t " + str(self.__params.num_threads)
support.sys_call(command_line, self._log)
def run_iteration(configs_dir, execution_home, cfg, log, K,
use_additional_contigs, last_one):
data_dir = os.path.join(cfg.output_dir, "K%d" % K)
if options_storage.continue_mode:
if os.path.isfile(os.path.join(data_dir, "final_contigs.fasta")):
log.info("\n== Skipping assembler: " + ("K%d" % K) +
" (already processed)")
return
else:
options_storage.continue_mode = False # continue from here
if os.path.exists(data_dir):
shutil.rmtree(data_dir)
os.makedirs(data_dir)
bin_reads_dir = os.path.join(cfg.output_dir, ".bin_reads")
dst_configs = os.path.join(data_dir, "configs")
shutil.copytree(os.path.join(configs_dir, "debruijn"), dst_configs)
cfg_file_name = os.path.join(dst_configs, "config.info")
# removing template configs
for root, dirs, files in os.walk(dst_configs):
for cfg_file in files:
cfg_file = os.path.join(root, cfg_file)
if cfg_file.endswith('.info.template'):
if os.path.isfile(cfg_file.split('.template')[0]):
os.remove(cfg_file)
else:
os.rename(cfg_file, cfg_file.split('.template')[0])
prepare_config_spades(cfg_file_name, cfg, log, use_additional_contigs, K,
last_one)
command = [
os.path.join(execution_home, "spades"),
os.path.abspath(cfg_file_name)
]
if os.path.isdir(bin_reads_dir):
if glob.glob(os.path.join(bin_reads_dir, "*_cor*")):
for cor_filename in glob.glob(os.path.join(bin_reads_dir,
"*_cor*")):
cor_index = cor_filename.rfind("_cor")
new_bin_filename = cor_filename[:cor_index] + cor_filename[
cor_index + 4:]
shutil.move(cor_filename, new_bin_filename)
log.info("\n== Running assembler: " + ("K%d" % K) + "\n")
support.sys_call(command, log)
def get_igblast_output(args):
args.input_hash = hash_file(args.input)
args.igblast_output = args.storage_dir + "/" + args.input_hash + ".blast"
if args.rerun_igblast or not os.path.exists(args.igblast_output + ".gz"):
log.info("IgBLAST output will be written to " + args.igblast_output + ".gz")
fq2fa(args.input, args.tmp_file)
igblast_time = time.time()
support.sys_call("bash %(workdir)s/blast.sh %(tmp_file)s %(igblast_output)s 2> /dev/null" % args.__dict__, log)
igblast_time = time.time() - igblast_time
os.unlink(args.tmp_file)
support.sys_call("gzip %s --force" % args.igblast_output, log)
log.info("IgBLAST time: %fs" % igblast_time)
blast = ParseIgBlastOutput(args.igblast_output + ".gz", log, smart_open)
# Normalize blast_blocks
return [line.hit_table for line in blast.blocks]
def main():
log = igrec.CreateLogger()
parser, params = ParseCommandLineParams(log)
CheckParamsCorrectness(parser, params, log)
try:
if not os.path.exists(params.output):
os.makedirs(params.output)
igrec.CreateFileLogger(params, log)
igrec.PrintCommandLine(log)
final_dir = InitMakeFiles(params, log)
# We need freshly compiled version to get actual build info
if not params.no_compilation:
support.sys_call(
"make -C " +
os.path.join(os.path.dirname(final_dir), "compilation"), log)
from src.build_info.build_info import BuildInfo
print "===================Build info==================="
BuildInfo().Log(log)
print "================================================"
support.sys_call("make -C " + final_dir, log)
PrintOutputFiles(params, log)
log.info("\nThank you for using BarcodedIgReC!")
except KeyboardInterrupt:
log.info("\nBarcodedIgReC was interrupted!")
except Exception:
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
log.exception(exc_value)
log.info("\nERROR: Exception caught.")
SupportInfo(log)
sys.exit(exc_value)
except BaseException:
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
log.exception(exc_value)
log.info("\nERROR: Exception caught.")
SupportInfo(log)
sys.exit(exc_value)
log.info("Log was written to " + params.log_filename)
def run_vjfinder(input_file,
output_dir,
log=None,
loci="all",
threads=16,
additional_args="",
remove_tmp=False):
if log is None:
log = FakeLog()
import os.path
import os
args = {
"path": path_to_igrec,
"loci": loci,
"threads": threads,
"input_file": input_file,
"output_dir": output_dir,
"organism": "human",
"path_to_germline": igrec_dir + "/data/germline",
"additional_args": additional_args
}
args = dict2class(args)
command_line = args.path + "/build/release/bin/vj_finder" + \
" -i " + os.path.abspath(args.input_file) + \
" -o " + os.path.abspath(args.output_dir) + \
" --db-directory " + os.path.abspath(args.path_to_germline) + \
" -t " + str(args.threads) + \
" --loci " + args.loci + \
" --organism " + args.organism + " " + args.additional_args
cwd = os.getcwd()
os.chdir(igrec_dir)
timer = Timer()
support.sys_call(command_line, log=log)
timer.stamp(output_dir + "/time.txt")
os.chdir(cwd)
if remove_tmp:
import os.path
if os.path.isfile(output_dir):
import shutil
shutil.rmtree(output_dir)
def main():
log = igrec.CreateLogger()
parser, params = ParseCommandLineParams(log)
CheckParamsCorrectness(parser, params, log)
try:
if not os.path.exists(params.output):
os.makedirs(params.output)
igrec.CreateFileLogger(params, log)
igrec.PrintCommandLine(log)
final_dir = InitMakeFiles(params, log)
# We need freshly compiled version to get actual build info
if not params.no_compilation:
support.sys_call("make -C " + os.path.join(os.path.dirname(final_dir), "compilation"), log)
print "===================Build info==================="
from py import build_info
build_info.Log(log)
print "================================================"
support.sys_call("make -C " + final_dir, log)
PrintOutputFiles(params, log)
log.info("\nThank you for using BarcodedIgReC!")
except KeyboardInterrupt:
log.info("\nBarcodedIgReC was interrupted!")
except Exception:
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
log.exception(exc_value)
log.info("\nERROR: Exception caught.")
SupportInfo(log)
sys.exit(exc_value)
except BaseException:
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
log.exception(exc_value)
log.info("\nERROR: Exception caught.")
SupportInfo(log)
sys.exit(exc_value)
log.info("Log was written to " + params.log_filename)
def run_bh(result_filename, configs_dir, execution_home, cfg, ext_python_modules_home, log):
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
import pyyaml2 as pyyaml
elif sys.version.startswith('3.'):
import pyyaml3 as pyyaml
dst_configs = os.path.join(cfg.output_dir, "configs")
if os.path.exists(dst_configs):
shutil.rmtree(dst_configs)
shutil.copytree(os.path.join(configs_dir, "hammer"), dst_configs)
cfg_file_name = os.path.join(dst_configs, "config.info")
# removing template configs
for root, dirs, files in os.walk(dst_configs):
for cfg_file in files:
cfg_file = os.path.join(root, cfg_file)
if cfg_file.endswith('.info.template'):
if os.path.isfile(cfg_file.split('.template')[0]):
os.remove(cfg_file)
else:
os.rename(cfg_file, cfg_file.split('.template')[0])
prepare_config_bh(cfg_file_name, cfg, log)
command = [os.path.join(execution_home, "hammer"),
os.path.abspath(cfg_file_name)]
log.info("\n== Running read error correction tool: " + ' '.join(command) + "\n")
support.sys_call(command, log)
corrected_dataset_yaml_filename = os.path.join(cfg.tmp_dir, "corrected.yaml")
if not os.path.isfile(corrected_dataset_yaml_filename):
support.error("read error correction finished abnormally: " + corrected_dataset_yaml_filename + " not found!")
corrected_dataset_data = pyyaml.load(open(corrected_dataset_yaml_filename, 'r'))
if cfg.gzip_output:
log.info("\n== Compressing corrected reads (with gzip)")
move_dataset_files(corrected_dataset_data, cfg.output_dir, ext_python_modules_home, cfg.max_threads, log, cfg.gzip_output)
corrected_dataset_yaml_filename = result_filename
pyyaml.dump(corrected_dataset_data, open(corrected_dataset_yaml_filename, 'w'))
log.info("\n== Dataset description file created: " + corrected_dataset_yaml_filename + "\n")
shutil.rmtree(cfg.tmp_dir)
def run_igrec_old(input_file,
output_dir,
log=None,
tau=3,
threads=16,
additional_args="",
remove_tmp=True):
if log is None:
log = FakeLog()
output_dir = os.path.abspath(output_dir)
input_file = os.path.abspath(input_file)
args = {
"path": path_to_igrec_old,
"tau": tau,
"threads": threads,
"input_file": input_file,
"output_dir": output_dir,
"additional_args": additional_args
}
timer = Timer()
cwd = os.getcwd()
os.chdir(path_to_igrec_old)
support.sys_call(
"%(path)s/ig_repertoire_constructor.py --tau=%(tau)d -t %(threads)d -s %(input_file)s -o %(output_dir)s %(additional_args)s"
% args,
log=log)
os.chdir(cwd)
timer.stamp(output_dir + "/time.txt")
# Rename output
os.rename(output_dir + "/constructed_repertoire.clusters.fa",
output_dir + "/final_repertoire.fa")
os.rename(output_dir + "/constructed_repertoire.rcm",
output_dir + "/final_repertoire.rcm")
if remove_tmp:
rmdir(output_dir + "/configs")
rmdir(output_dir + "/saves")
rmdir(output_dir + "/temp_files")
rmdir(output_dir + "/hamming_graphs_tau_%d" % tau)
def Run(self):
self.__CheckInputExistance()
if not self.__params.no_alignment:
self.__params.vj_finder_output = os.path.join(self.__params.output, "vj_finder")
command_line = os.path.abspath(IgRepConConfig().run_vj_aligner) + \
" -i " + os.path.abspath(self.__params.single_reads) + \
" -o " + os.path.abspath(self.__params.io.vj_finder_output) + \
" --db-directory " + os.path.abspath(IgRepConConfig().path_to_germline) + \
" -t " + str(self.__params.num_threads) + \
" --loci " + self.__params.loci + \
" --organism " + self.__params.organism
if self.__params.no_pseudogenes:
command_line += " --pseudogenes=off"
else:
command_line += " --pseudogenes=on"
cwd = os.getcwd()
os.chdir(home_directory)
support.sys_call(command_line, self._log)
os.chdir(cwd)
else:
self._log.info("VJ Finder stage skipped")
self.__params.io.cropped_reads = self.__params.single_reads
def RunTool(params, log):
try:
igs_command_line = ig_simulator_bin + " " + \
params.output_config_file
support.sys_call(igs_command_line, log)
log.info("\nThank you for using " + tool_name + "!\n")
except (KeyboardInterrupt):
log.info("\n" + tool_name + " was interrupted!")
except Exception:
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
log.exception(exc_value)
log.info("\nERROR: Exception caught.")
except BaseException:
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
log.exception(exc_value)
log.info("\nERROR: Exception caught.")
def move_dataset_files(dataset_data, dst, ext_python_modules_home, max_threads, log, gzip=False):
to_compress = []
for reads_library in dataset_data:
for key, value in reads_library.items():
if key.endswith('reads'):
moved_reads_files = []
for reads_file in value:
dst_filename = os.path.join(dst, os.path.basename(reads_file))
# TODO: fix problem with files with the same basenames in Hammer binary!
if not os.path.isfile(reads_file):
if (not gzip and os.path.isfile(dst_filename)) or (gzip and os.path.isfile(dst_filename + '.gz')):
support.warning('file with corrected reads (' + reads_file + ') is the same in several libraries', log)
if gzip:
dst_filename += '.gz'
else:
support.error('something went wrong and file with corrected reads (' + reads_file + ') is missing!', log)
else:
shutil.move(reads_file, dst_filename)
if gzip:
to_compress.append(dst_filename)
dst_filename += '.gz'
moved_reads_files.append(dst_filename)
reads_library[key] = moved_reads_files
if len(to_compress):
pigz_path = support.which('pigz')
if pigz_path:
for reads_file in to_compress:
support.sys_call([pigz_path, '-f', '-7', '-p', str(max_threads), reads_file], log)
else:
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
from joblib2 import Parallel, delayed
elif sys.version.startswith('3.'):
from joblib3 import Parallel, delayed
n_jobs = min(len(to_compress), max_threads)
outputs = Parallel(n_jobs=n_jobs)(delayed(support.sys_call)(['gzip', '-f', '-7', reads_file]) for reads_file in to_compress)
for output in outputs:
if output:
log.info(output)
def run_bh(configs_dir, execution_home, cfg, ext_python_modules_home, log):
addsitedir(ext_python_modules_home)
import pyyaml
dst_configs = os.path.join(cfg.output_dir, "configs")
if os.path.exists(dst_configs):
shutil.rmtree(dst_configs)
shutil.copytree(os.path.join(configs_dir, "hammer"), dst_configs)
cfg_file_name = os.path.join(dst_configs, "config.info")
# removing template configs
for root, dirs, files in os.walk(dst_configs):
for cfg_file in files:
cfg_file = os.path.join(root, cfg_file)
if cfg_file.endswith('.info.template'):
if os.path.isfile(cfg_file.split('.template')[0]):
os.remove(cfg_file)
else:
os.rename(cfg_file, cfg_file.split('.template')[0])
prepare_config_bh(cfg_file_name, cfg, log)
command = os.path.join(execution_home, "hammer") + " " +\
os.path.abspath(cfg_file_name)
log.info("\n== Running read error correction tool: " + command + "\n")
support.sys_call(command, log)
corrected_dataset_yaml_filename = os.path.join(cfg.tmp_dir, "corrected.yaml")
corrected_dataset_data = pyyaml.load(file(corrected_dataset_yaml_filename, 'r'))
if cfg.gzip_output:
log.info("\n== Compressing corrected reads (with gzip)")
support.move_dataset_files(corrected_dataset_data, cfg.output_dir, log, cfg.gzip_output)
corrected_dataset_yaml_filename = os.path.join(cfg.output_dir, "corrected.yaml")
pyyaml.dump(corrected_dataset_data, file(corrected_dataset_yaml_filename, 'w'))
log.info("\n== Dataset description file created: " + corrected_dataset_yaml_filename + "\n")
shutil.rmtree(cfg.tmp_dir)
return corrected_dataset_yaml_filename
def Run(self):
self.__CheckInputExistance()
command_line = IgRepConConfig().run_trie_compressor + " -i " + self.__params.io.cropped_reads + \
" -o " + self.__params.io.compressed_reads + " -m " + self.__params.io.map_file + " -Toff"
support.sys_call(command_line, self._log)
command_line = IgRepConConfig().run_triecmp_to_repertoire + " -i " + self.__params.io.cropped_reads + \
" -c " + self.__params.io.compressed_reads + " -m " + self.__params.io.map_file + \
" -r " + self.__params.io.supernode_repertoire + " -R " + self.__params.io.supernode_rcm
support.sys_call(command_line, self._log)
command_line = "%s %s %s --limit=%d" % (IgRepConConfig().run_report_supernodes,
self.__params.io.supernode_repertoire,
self.__params.io.supernodes_file,
self.__params.min_cluster_size)
support.sys_call(command_line, self._log)
if not self.__params.equal_compression:
command_line = IgRepConConfig().run_fake_trie_compressor + " -i " + self.__params.io.cropped_reads + \
" -o " + self.__params.io.compressed_reads + " -m " + self.__params.io.map_file
support.sys_call(command_line, self._log)
def run_hammer(corrected_dataset_yaml_filename, configs_dir, execution_home, cfg,
dataset_data, ext_python_modules_home, only_compressing_is_needed, log):
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
import pyyaml2 as pyyaml
elif sys.version.startswith('3.'):
import pyyaml3 as pyyaml
# not all reads need processing
if support.get_lib_ids_by_type(dataset_data, options_storage.LONG_READS_TYPES):
not_used_dataset_data = support.get_libs_by_type(dataset_data, options_storage.LONG_READS_TYPES)
to_correct_dataset_data = support.rm_libs_by_type(dataset_data, options_storage.LONG_READS_TYPES)
to_correct_dataset_yaml_filename = os.path.join(cfg.output_dir, "to_correct.yaml")
pyyaml.dump(to_correct_dataset_data, open(to_correct_dataset_yaml_filename, 'w'), default_flow_style = False, default_style='"', width=100500)
cfg.dataset_yaml_filename = to_correct_dataset_yaml_filename
else:
not_used_dataset_data = None
if not only_compressing_is_needed:
dst_configs = os.path.join(cfg.output_dir, "configs")
if os.path.exists(dst_configs):
shutil.rmtree(dst_configs)
if cfg.iontorrent:
dir_util.copy_tree(os.path.join(configs_dir, "ionhammer"), dst_configs, preserve_times=False)
cfg_file_name = os.path.join(dst_configs, "ionhammer.cfg")
else:
dir_util.copy_tree(os.path.join(configs_dir, "hammer"), dst_configs, preserve_times=False)
cfg_file_name = os.path.join(dst_configs, "config.info")
cfg.tmp_dir = support.get_tmp_dir(prefix="hammer_")
if cfg.iontorrent:
prepare_config_ih(cfg_file_name, cfg, ext_python_modules_home)
binary_name = "ionhammer"
else:
prepare_config_bh(cfg_file_name, cfg, log)
binary_name = "hammer"
command = [os.path.join(execution_home, binary_name),
os.path.abspath(cfg_file_name)]
log.info("\n== Running read error correction tool: " + ' '.join(command) + "\n")
support.sys_call(command, log)
if not os.path.isfile(corrected_dataset_yaml_filename):
support.error("read error correction finished abnormally: " + corrected_dataset_yaml_filename + " not found!")
else:
log.info("\n===== Skipping %s (already processed). \n" % "read error correction tool")
support.continue_from_here(log)
corrected_dataset_data = pyyaml.load(open(corrected_dataset_yaml_filename, 'r'))
remove_not_corrected_reads(cfg.output_dir)
is_changed = False
if cfg.gzip_output:
is_changed = True
compress_dataset_files(corrected_dataset_data, ext_python_modules_home, cfg.max_threads, log)
if not_used_dataset_data:
is_changed = True
corrected_dataset_data += not_used_dataset_data
if is_changed:
pyyaml.dump(corrected_dataset_data, open(corrected_dataset_yaml_filename, 'w'), default_flow_style = False, default_style='"', width=100500)
log.info("\n== Dataset description file was created: " + corrected_dataset_yaml_filename + "\n")
if os.path.isdir(cfg.tmp_dir):
shutil.rmtree(cfg.tmp_dir)
def main(argv, external_logger = ""):
from argparse import ArgumentParser
parser = ArgumentParser(description="== DSF: an algorithm for corrupted cliques search ==",
epilog="""
In case you have troubles running DSF, you can write to [email protected].
Please provide us with dense_subgraph_finder.log file from the output directory.
""",
add_help=False)
req_args = parser.add_argument_group("Input")
input_args = req_args.add_mutually_exclusive_group(required=True)
input_args.add_argument("-g", "--graph",
type=str,
default="",
dest="graph",
help="Input graph in GRAPH format")
input_args.add_argument("--test",
action="store_const",
const=os.path.join(home_directory, "test_dataset/dsf/test.graph"),
dest="graph",
help="Running test dataset")
out_args = parser.add_argument_group("Output")
out_args.add_argument("-o", "--output",
type=str,
default=os.path.join(home_directory, "dsf_test"),
help="Output directory")
optional_args = parser.add_argument_group("Optional arguments")
optional_args.add_argument("-t", "--threads",
type=int,
default=16,
dest="num_threads",
help="Threads number [default: %(default)d]")
optional_args.add_argument("-f", '--min-fillin',
type=float,
default=0.6,
dest="min_fillin",
help='Minimum fill-in of dense subgraphs [default: %(default)f]')
optional_args.add_argument("-n", "--min-snode-size",
type=int,
default=5,
dest="min_snode_size",
help="Minimum vertex weight that prevents its gluing with other heavy vertex "
"[default: %(default)d]")
optional_args.add_argument("-s", "--min-size",
type=int,
default=5,
dest="min_graph_size",
help="Minimum size of graph where dense subgraphs will be computed "
"[default: %(default)d]")
optional_args.add_argument("--create-triv-dec",
action="store_const",
const=True,
dest="create_trivial_decomposition",
help='Creating decomposition according to connected components [default: False]')
optional_args.add_argument("--save-aux-files",
action="store_const",
const=True,
dest="save_aux_files",
help="Saving auxiliary files: subgraphs in GRAPH format and their decompositions "
"[default: False]")
optional_args.add_argument("--clean-output-dir",
default=True,
dest="clean_output_dir",
action="store_true",
help="Clean output directory on start [default]")
optional_args.add_argument("--no-clean-output-dir",
default=True,
dest="clean_output_dir",
action="store_false",
help="Do not clean output directory on start")
optional_args.add_argument("-h", "--help",
action="help",
help="Help message and exit")
parser.set_defaults(config_dir="configs",
config_file="config.info")
# prepare log
log = logging.getLogger('dense_subgraph_finder')
log.setLevel(logging.DEBUG)
console = logging.StreamHandler(sys.stdout)
console.setFormatter(logging.Formatter('%(message)s'))
console.setLevel(logging.DEBUG)
log.addHandler(console)
if external_logger != "":
external_log_handler = logging.FileHandler(external_logger, mode = "a")
log.addHandler(external_log_handler)
args = [arg for arg in argv if ntpath.basename(arg) != 'dense_subgraph_finder.py']
params = parser.parse_args(args)
CheckParamsCorrectness(params, log, parser)
SetOutputParams(params, params.output)
PrepareOutputDir(params, log)
# log file
params.log_filename = os.path.join(params.output, "dense_subgraph_finder.log")
if os.path.exists(params.log_filename):
log.info("Removing %s" % params.log_filename)
os.remove(params.log_filename)
log_handler = logging.FileHandler(params.log_filename, mode='a')
log.addHandler(log_handler)
# print command line
command_line = "Command_line: "
if argv[0] != "dense_subgraph_finder.py":
command_line += "dense_subgraph_finder.py "
command_line += " ".join(argv)
log.info(command_line + "\n")
PrintParams(params, log)
log.info("Log will be written to " + params.log_filename + "\n")
PrepareConfigs(params, log)
# run dense subgraph finder
try:
dsf_command_line = init.PathToBins.run_dense_sgraph_finder + " " + params.config_file
support.sys_call(dsf_command_line, log)
Cleanup(params, log)
log.info("\nThank you for using Dense Subgraph Finder!\n")
except (KeyboardInterrupt):
log.info("\nDense subgraph finder was interrupted!")
except Exception:
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
log.exception(exc_value)
log.info("\nERROR: Exception caught.")
supportInfo(log)
except BaseException:
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
log.exception(exc_value)
log.info("\nERROR: Exception caught.")
supportInfo(log)
log.info("Log was written to " + params.log_filename)
def main(argv):
from argparse import ArgumentParser
parser = ArgumentParser(description="== " + tool_name + ": a tool for diversity analysis of full-length immunosequencing reads ==",
epilog="In case you have troubles running " + tool_name + ", you can write to [email protected]."
"Please provide us with diversity_analyzer.log file from the output directory.",
add_help=False)
req_args = parser.add_argument_group("Required params")
input_args = req_args.add_mutually_exclusive_group(required=True)
input_args.add_argument("-i", "--input",
type=str,
default="",
dest="input_reads",
help="Input reads in FASTQ/FATSA format")
input_args.add_argument("--test",
action="store_const",
const=test_reads,
dest="input_reads",
help="Running test dataset")
out_args = parser.add_argument_group("Output")
out_args.add_argument("-o", "--output",
type=str,
dest="output_dir",
default="", #os.path.join(home_directory, "cdr_test"),
help="Output directory")
optional_args = parser.add_argument_group("Optional arguments")
optional_args.add_argument("-t", "--threads",
type=int,
default=16,
dest="num_threads",
help="Threads number [default: %(default)d]")
optional_args.add_argument("-d", '--domain',
type=str,
default="imgt",
dest="domain_system",
help='Domain system for CDR search: imgt OR kabat [default: %(default)s]')
vj_finder_args= parser.add_argument_group("VJ alignment params")
optional_args.add_argument("-l", "--loci",
type=str,
default="all",
dest="loci",
help="Loci: IGH, IGK, IGL, IG (all BCRs), TRA, TRB, TRG, TRD, TR (all TCRs) or all. "
"[default: %(default)s]")
optional_args.add_argument("--org",
type=str,
default="human",
dest="organism",
help="Organism: human, mouse, rat, rabbit, rhesus-monkey [default: %(default)s]")
optional_args.add_argument('--skip-plots',
action='store_const',
const=True,
dest = "skip_plots",
help = "Skip drawing plots")
optional_args.add_argument("-h", "--help",
action="help",
help="Help message and exit")
# prepare log
log = logging.getLogger('diversity_analyzer')
log.setLevel(logging.DEBUG)
console = logging.StreamHandler(sys.stdout)
console.setFormatter(logging.Formatter('%(message)s'))
console.setLevel(logging.DEBUG)
log.addHandler(console)
params = parser.parse_args()
CheckBinariesExistance(params, log)
CheckParamsCorrectness(params, log)
SetOutputParams(params, log)
PrepareOutputDir(params)
# log file
params.log_filename = os.path.join(params.output_dir, "diversity_analyzer.log")
if os.path.exists(params.log_filename):
os.remove(params.log_filename)
log_handler = logging.FileHandler(params.log_filename, mode='a')
log.addHandler(log_handler)
# print command line
command_line = "Command_line: "
command_line += " ".join(argv)
log.info(command_line + "\n")
PrintParams(params, log)
log.info("Log will be written to " + params.log_filename + "\n")
PrepareConfigs(params, log)
try:
cdr_command_line = run_cdr_labeler + " " + params.cdr_labeler_config_file
support.sys_call(cdr_command_line, log)
if not params.skip_plots:
log.info("\n==== Visualization of diversity statistics ====")
visualize_vj_stats.main(["", os.path.join(params.output_dir, "cdr_details.txt"),
os.path.join(params.output_dir, "shm_details.txt"),
params.output_dir, log])
log.info("\n==== Annotation report creation ====")
html_report_writer.main(os.path.join(params.output_dir, "cdr_details.txt"),
os.path.join(params.output_dir, "shm_details.txt"),
os.path.join(params.output_dir, "plots"),
os.path.join(params.output_dir, "annotation_report.html"), log)
Cleanup(params, log)
log.info("\nThank you for using " + tool_name + "!\n")
except (KeyboardInterrupt):
log.info("\n" + tool_name + " was interrupted!")
except Exception:
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
log.exception(exc_value)
log.info("\nERROR: Exception caught.")
#supportInfo(log)
except BaseException:
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
log.exception(exc_value)
log.info("\nERROR: Exception caught.")
#supportInfo(log)
log.info("Log was written to " + params.log_filename)
def main(ds_args_list, general_args_list, spades_home, bin_home):
log = logging.getLogger('dipspades')
log.setLevel(logging.DEBUG)
console = logging.StreamHandler(sys.stdout)
console.setFormatter(logging.Formatter('%(message)s'))
console.setLevel(logging.DEBUG)
log.addHandler(console)
support.check_binaries(bin_home, log)
ds_args = parse_arguments(ds_args_list, log)
if not os.path.exists(ds_args.output_dir):
os.makedirs(ds_args.output_dir)
log_filename = os.path.join(ds_args.output_dir, "dipspades.log")
if os.path.exists(log_filename):
os.remove(log_filename)
log_handler = logging.FileHandler(log_filename, mode='a')
log.addHandler(log_handler)
params_filename = os.path.join(ds_args.output_dir, "params.txt")
params_handler = logging.FileHandler(params_filename, mode='a')
log.addHandler(params_handler)
log.info("\n")
log.info("General command line: " + " ".join(general_args_list) + "\n")
log.info("dipSPAdes command line: " + " ".join(ds_args_list) + "\n")
print_ds_args(ds_args, log)
log.removeHandler(params_handler)
log.info("\n======= dipSPAdes started. Log can be found here: " + log_filename + "\n")
write_haplocontigs_in_file(ds_args.haplocontigs, ds_args.haplocontigs_fnames)
config_fname = prepare_configs(os.path.join(spades_home, "configs", "dipspades"), ds_args, log)
ds_args.tmp_dir = support.get_tmp_dir(prefix="dipspades_", base_dir=ds_args.tmp_dir)
prepare_config(config_fname, ds_args, log)
try:
log.info("===== Assembling started.\n")
binary_path = os.path.join(bin_home, "dipspades")
command = [binary_path, config_fname]
support.sys_call(command, log)
log.info("\n===== Assembling finished.\n")
print_ds_output(ds_args.output_dir, log)
if os.path.isdir(ds_args.tmp_dir):
shutil.rmtree(ds_args.tmp_dir)
log.info("\n======= dipSPAdes finished.\n")
log.info("dipSPAdes log can be found here: " + log_filename + "\n")
log.info("Thank you for using dipSPAdes!")
log.removeHandler(log_handler)
except Exception:
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
if exc_type == OSError and exc_value.errno == errno.ENOEXEC: # Exec format error
support.error("It looks like you are using SPAdes binaries for another platform.\n" +
support.get_spades_binaries_info_message(), dipspades=True)
else:
log.exception(exc_value)
support.error("exception caught: %s" % exc_type, log)
except BaseException: # since python 2.5 system-exiting exceptions (e.g. KeyboardInterrupt) are derived from BaseException
exc_type, exc_value, _ = sys.exc_info()
if exc_type == SystemExit:
sys.exit(exc_value)
else:
log.exception(exc_value)
support.error("exception caught: %s" % exc_type, log, dipspades=True)
