def main():
os.chdir('./bin')
dirc = sys.argv[1]
cfg = load_mirquant_config_file(sys.argv[3])
name = os.path.basename(dirc.split('./IntermediateFiles/')[0])
mirquant_output = sample_output_paths(cfg['paths']['output'], name)
logName = '{}_collectRes.log'.format(os.path.basename(dirc))
initiate_logging('{}/collect_results_logs/'.format(mirquant_output['log']),
logName)
bt = '{}.results'.format(sys.argv[1])
res_li = resource_paths(cfg['parameters']['species'], cfg['paths'],
cfg['parameters'])
mir_file, TRNAfile = res_li[1], res_li[5]
outDir = os.path.dirname(bt)
filesLib = glob.glob('{}/../*LIB.fa'.format(os.path.dirname(dirc)))[0]
print_run_info(dirc, bt, cfg['parameters']['species'], outDir, filesLib)
btWins, EM = result_file_dict(bt, dirc)
mirs = get_miR_info(mir_file)
counters = initialize_counters()
bedFile = []
for res in sorted(btWins):
bedFile, counters = mainChunk(res, counters, bedFile, dirc, EM,
TRNAfile, mirs, outDir, mirquant_output)
write_summary_to_log(counters)
write_shrimp_results_bed(sys.argv[1], bedFile)
os.system('rm {}'.format(sys.argv[2]))
def main(arg):
start = time.time()
os.chdir('./bin')
cfg = load_mirquant_config_file(arg.conf)
scfg = load_sys_config_file(arg.conf)
job = build_job(scfg['job'])
t_job = build_job(scfg['job_threaded'])
dr, dr_i, fi_base = set_up_output_folder(arg.sample,
cfg['paths']['output'])
out_di = sample_output_paths(cfg['paths']['output'], fi_base)
initiate_logging(out_di['log'], 'chainSubmission.log')
res_li = resource_paths(cfg['parameters']['species'], cfg['paths'],
cfg['parameters'])
tRNA, tmRNA, BI = res_li[4], res_li[3], res_li[7]
define_input_varibles(cfg)
lib = set_lib(dr_i, fi_base)
MINrna, MAXrna = cutadapt_cmd(arg.sample, lib, cfg['cutadapt'],
out_di['log'], arg.conf)
logging.info('cutadapt = {}'.format(time.time() - start))
separate_by_read_length(MINrna, MAXrna, lib, out_di['output'])
for length in range(MINrna, MAXrna + 1):
fi = '{}_{}.fq'.format(lib, length)
bowtie(fi, length, BI, cfg['bowtie'])
logging.info('bowtie = {}'.format(time.time() - start))
window_creation(MINrna, MAXrna, lib, BI, tRNA, tmRNA)
logging.info('window generation = {}'.format(time.time() - start))
mapping_statistics(arg.sample, lib, dr, fi_base)
run_shrimp_alignment(MINrna, MAXrna, lib, out_di['log'], out_di['temp'],
t_job, arg.conf)
bt_postProcEM.main('{}_merge.bed'.format(lib), '{}_allGS.bed'.format(lib),
out_di['temp'])
reduce_shrimp_res(out_di['temp'], dr_i, job)
logging.info('finish = {}'.format(time.time() - start))
def main():
os.chdir('./bin')
dirc = sys.argv[1]
cfg = load_mirquant_config_file(sys.argv[3])
name = os.path.basename(dirc.split('./IntermediateFiles/')[0])
mirquant_output = sample_output_paths(cfg['paths']['output'], name)
logName = '{}_collectRes.log'.format(os.path.basename(dirc))
initiate_logging('{}/collect_results_logs/'.format(mirquant_output['log']), logName)
bt = '{}.results'.format(sys.argv[1])
res_li = resource_paths(cfg['parameters']['species'], cfg['paths'], cfg['parameters'])
mir_file, TRNAfile = res_li[1], res_li[5]
outDir = os.path.dirname(bt)
filesLib = glob.glob('{}/../*LIB.fa'.format(os.path.dirname(dirc)))[0]
print_run_info(dirc, bt, cfg['parameters']['species'], outDir, filesLib)
btWins, EM = result_file_dict(bt, dirc)
mirs = get_miR_info(mir_file)
counters = initialize_counters()
bedFile = []
for res in sorted(btWins):
bedFile, counters = mainChunk(res, counters, bedFile, dirc, EM, TRNAfile, mirs, outDir, mirquant_output)
write_summary_to_log(counters)
write_shrimp_results_bed(sys.argv[1], bedFile)
os.system('rm {}'.format(sys.argv[2]))
def main(arg):
os.chdir('./bin')
cfg = load_mirquant_config_file(arg.conf)
scfg = load_sys_config_file(arg.conf)
job = build_job(scfg['job'])
dr, dr_i, fi_base = set_up_output_folder(arg.sample, cfg['paths']['output'])
out_di = sample_output_paths(cfg['paths']['output'], fi_base)
initiate_logging(out_di['log'], 'chainSubmission.log')
res_li = resource_paths(cfg['parameters']['species'], cfg['paths'], cfg['parameters'])
tRNA, tmRNA, BI = res_li[4], res_li[3], res_li[7]
define_input_varibles(cfg)
generate_adapter_files.main(arg.sample, out_di['log'], arg.conf)
MAXrna = get_maxRNA_length(arg.sample, cfg['cutadapt'])
lib = set_lib(dr_i, fi_base)
MINrna = cutadapt_cmd(arg.sample, lib, cfg['cutadapt'])
separate_by_read_length(MINrna, MAXrna, lib, out_di['output'])
for length in range(MINrna, MAXrna + 1):
fi = '{}_{}.fq'.format(lib, length)
bowtie(fi, length, BI, cfg['bowtie'])
window_creation(MINrna, MAXrna, lib, BI, tRNA, tmRNA)
mapping_statistics(arg.sample, lib, dr, fi_base)
run_shrimp_alignment(MINrna, MAXrna, lib, out_di['log'], out_di['temp'], job, arg.conf)
bt_postProcEM.main('{}_merge.bed'.format(lib), '{}_allGS.bed'.format(lib), out_di['temp'])
reduce_shrimp_res(out_di['temp'], dr_i, job)
def main(file, log_dir, conf):
check_input()
cfg = load_mirquant_config_file(conf)
dirc, name, need_adapt = check_for_adapter_file(file)
if need_adapt == True:
if not check_for_barcode_file(dirc, name, cfg):
barcode = scan_fastq_for_barcode(file, name, log_dir)
adapter = create_adapter(barcode, cfg['cutadapt']['adapter'])
write_adapter_file(dirc, name, adapter)
def main(file, log_dir, conf):
check_input()
cfg = load_mirquant_config_file(conf)
dirc, name, need_adapt = check_for_adapter_file(file)
if need_adapt == True:
if not check_for_barcode_file(dirc, name, cfg):
barcode = scan_fastq_for_barcode(file, name, log_dir)
adapter = create_adapter(barcode, cfg['cutadapt']['adapter'])
write_adapter_file(dirc, name, adapter)
def main(conf):
os.chdir('./bin')
cfg = load_mirquant_config_file(conf)
samples = return_sample_results_directories(cfg['paths']['project'])
for sample in samples:
samp_name = os.path.basename(sample[:-1])
out_di = sample_output_paths(cfg['paths']['output'], samp_name)
run_summary2Tab_clust(cfg['paths'], cfg['parameters']['species'], sample, conf)
move_files_to_out_dir(out_di, sample, samp_name)
write_summary_table(sample)
def main(size, lib, base, conf, log_dir):
cfg = load_mirquant_config_file(conf)
initiate_logging(log_dir, "SHRiMP_{}.log".format(size))
reads = "{}{}.noHit".format(base, size)
working_dir = os.getcwd()
make_out_dir(lib, size)
seedList = make_base_seed(size)
group_Name = shrimp_submission("pypath", cfg["shrimp"], seedList, lib, log_dir, reads)
shrimp_postProcGS.main(conf, os.getcwd())
def main(size, lib, base, conf, log_dir):
cfg = load_mirquant_config_file(conf)
initiate_logging(log_dir, 'SHRiMP_{}.log'.format(size))
reads = '{}{}.noHit'.format(base, size)
working_dir = os.getcwd()
make_out_dir(lib, size)
seedList = make_base_seed(size)
group_Name = shrimp_submission('pypath', cfg['shrimp'], seedList, lib,
log_dir, reads)
shrimp_postProcGS.main(conf, os.getcwd())
def main(conf):
os.chdir('./bin')
cfg = load_mirquant_config_file(conf)
samples = return_sample_results_directories(cfg['paths']['project'])
for sample in samples:
print '\nProcessing sample {}...'.format(sample)
samp_name = os.path.basename(sample[:-1])
out_di = sample_output_paths(cfg['paths']['output'], samp_name)
run_summary2Tab_clust(cfg['paths'], cfg['parameters']['species'],
sample, conf)
move_files_to_out_dir(out_di, sample, samp_name)
write_summary_table(sample)
def main(conf, shrimp_dir):
check_input()
cfg = load_mirquant_config_file(conf)
res_li = resource_paths(cfg['parameters']['species'], cfg['paths'], cfg['parameters'])
sample = os.path.basename(shrimp_dir.split('./IntermediateFiles/')[0])
out_di = sample_output_paths(cfg['paths']['output'], sample)
logging.info('\n\n### Processing SHRiMP results ###\n')
mir_fi = res_li[1]
mirList, mirStrand = load_mir_info(mir_fi)
tagCount, hits, maps = load_SHRiMP_res(shrimp_dir)
hits, tags, pCount = get_best_alignments(hits, maps)
write_processed_shrimp_output(hits, tags, mirList, mirStrand, shrimp_dir)
remove_temp_file(os.path.basename(shrimp_dir).split('_')[1], out_di['temp'])
logging.info('Total SHRiMP alignments = {}; proportional count = {}'.format(tagCount, pCount))
def main(conf, shrimp_dir):
print 'Shrimp post-processing'
check_input()
cfg = load_mirquant_config_file(conf)
res_li = resource_paths(cfg['parameters']['species'], cfg['paths'], cfg['parameters'])
sample = os.path.basename(shrimp_dir.split('./IntermediateFiles/')[0])
out_di = sample_output_paths(cfg['paths']['output'], sample)
logging.info('\n\n### Processing SHRiMP results ###\n')
mir_fi = res_li[1]
mirList, mirStrand = load_mir_info(mir_fi)
tagCount, hits, maps = load_SHRiMP_res(shrimp_dir)
hits, tags, pCount = get_best_alignments(hits, maps)
write_processed_shrimp_output(hits, tags, mirList, mirStrand, shrimp_dir)
remove_temp_file(os.path.basename(shrimp_dir).split('_')[1], out_di['temp'])
logging.info('Total SHRiMP alignments = {}; proportional count = {}'.format(tagCount, pCount))
dictionary. Add the all the counts together in a total counts
dictionary. Add the counts to the counts dictionary as well.
'''
for item in res_line[1:]:
L, V = item.split(':')
if N not in features:
features[N] = {}
features[N][L] = V
try:
tot[L] += float(features[N][L])
except KeyError:
tot[L] = float(features[N][L])
return features, tot
cfg = load_mirquant_config_file(sys.argv[2])
res = sys.argv[1]
SPEC = cfg['parameters']['species']
res_li = resource_paths(SPEC, cfg['paths'], cfg['parameters'])
genome, mmuFile, tRNAFile, refAnn = res_li[0], res_li[2], res_li[4], res_li[6]
CODE = SPEC
bedInfo = mirANDtrna_to_bed(mmuFile, tRNAFile)
expression = {}
baseExp = {}
'''
for item in res_line[1:]:
L, V = item.split(':')
if N not in features:
features[N] = {}
features[N][L] = V
try:
tot[L] += float(features[N][L])
except KeyError:
tot[L] = float(features[N][L])
return features, tot
res = sys.argv[1]
cfg = load_mirquant_config_file(sys.argv[2])
species = cfg['parameters']['species']
res_li = resource_paths(species, cfg['paths'], cfg['parameters'])
genome, mmuFile, tRNAFile, refAnn = res_li[0], res_li[2], res_li[4], res_li[6]
bedInfo = mirANDtrna_to_bed(mmuFile, tRNAFile)
expression = {}
baseExp = {}
baseKeys = {}
bedLine = {}
features = {}
Novelarr = {}
tot = {}
tmp = res
tfile_name = 'mktemp'