def main(argv):
if len(argv) == 0:
print(
"[Error] - Expected call format:\n python post_process_results.py [ -o <outdir> | -c <config> ]"
)
sys.exit(2)
try:
opts, args = getopt.getopt(argv, "ho:c:", ["outdir=", "config="])
except getopt.GetoptError:
print(
"[Error] - Expected call format:\n python post_process_results.py [ -o <outdir> | -c <config> ]"
)
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print(
"python post_process_results.py [ -o <outdir> | -c <config> ]")
sys.exit()
elif opt in ('-o', '--outdir'):
out_dir = arg
elif opt in ('-c', '--config'):
config_file = arg
out_dir = create_out_dir(config_file)
return out_dir
def init_ouput_dirs(self):
# Init output dir structure
self.out_dir = custom_utils.create_out_dir(self.config_file)
self.ml_data_dir = self.out_dir + '/ml_data'
self.clinvar_feature_table_dir = self.ml_data_dir + '/clinvar_feature_tables'
self.out_models_dir = self.ml_data_dir + '/models'
def init_ouput_dirs(self): # Init output dir structure self.out_dir = custom_utils.create_out_dir(self.config_file) self.ml_data_dir = self.out_dir + '/ml_data' self.clinvar_feature_table_dir = self.ml_data_dir + '/clinvar_feature_tables' self.out_models_dir = self.ml_data_dir + '/models' self.raw_seq_dir = self.ml_data_dir + '/raw_seq' if not os.path.exists(self.raw_seq_dir): os.makedirs(self.raw_seq_dir)
def __init__(self, config_file, input_features, chrom, NTHREADS=20):
print("Initialising new JarvisDataPreprocessing object...")
self.input_features = input_features
self.chrom = chrom
self.NTHREADS = NTHREADS
# ==== Read config parameters ====
config_params = custom_utils.get_config_params(config_file)
self.hg_version = config_params['hg_version']
print('\n\nhg_version:', self.hg_version)
self.grch = {'hg19': '37', 'hg38': '38'}
pathogenic_set = config_params['pathogenic_set']
benign_set = config_params['benign_set']
self.patho_benign_sets = pathogenic_set + '_' + benign_set
self.win_len = config_params['win_len']
#self.win_len = int(config_params['win_len'] / 2)
self.Y_label = config_params['Y_label']
# ==== Define dir structure ====
out_dir = custom_utils.create_out_dir(config_file)
self.ml_data_dir = out_dir + '/ml_data'
if not os.path.exists(self.ml_data_dir):
os.makedirs(self.ml_data_dir)
self.seq_out_dir = self.ml_data_dir + '/raw_seq'
if not os.path.exists(self.seq_out_dir):
os.makedirs(self.seq_out_dir)
self.feature_tables_dir = self.ml_data_dir + '/clinvar_feature_tables'
if not os.path.exists(self.feature_tables_dir):
os.makedirs(self.feature_tables_dir)
self.jarvis_predictions_dir = self.ml_data_dir + '/jarvis_predictions'
if not os.path.exists(self.jarvis_predictions_dir):
os.makedirs(self.jarvis_predictions_dir)
self.jarvis_predictions_per_chr_dir = self.jarvis_predictions_dir + '/chr' + str(
self.chrom)
if not os.path.exists(self.jarvis_predictions_per_chr_dir):
os.makedirs(self.jarvis_predictions_per_chr_dir)
# Specificy input (static) files
self.human_ref_genome_2bit = '../' + self.hg_version + '/homo_sapiens_GRCh' + self.grch[
self.hg_version] + '_FASTA/hsa' + self.grch[
self.hg_version] + '.2bit'
def init_dirs(self):
"""
Dir Initialisation
"""
self.out_dir = create_out_dir(self.config_file, create_dirs=False)
self.ml_data_dir = self.out_dir + '/ml_data'
self.clinvar_feature_table_dir = self.ml_data_dir + '/clinvar_feature_tables'
self.clinvar_ml_out_dir = self.ml_data_dir + '/clinvar-out'
if not os.path.exists(self.clinvar_ml_out_dir):
os.makedirs(self.clinvar_ml_out_dir)
self.base_out_models_dir = self.ml_data_dir + '/models'
if not os.path.exists(self.base_out_models_dir):
os.makedirs(self.base_out_models_dir)
kmer = config_params['kmer'] # 7 or 3
all_variants_upper_thres = config_params['all_variants_upper_thres'] # e.g. 200 (filter out windows with more than 200 variants before fitting regression)
MAF_thres = config_params['MAF_thres'] # e.g. 0.0001 (Minor Allele Frequency)
variants_table_dir = config_params['variants_table_dir'] # gnomad-filtered_variant_tables-all-PASS_ONLY-NO_SEGDUP-NO_LCR-high_conf_regions
# ----------------------
human_ref_genome_2bit = '../' + hg_version + '/homo_sapiens_GRCh' + grch[hg_version] + '_FASTA/hsa' + grch[hg_version] +'.2bit'
data_dir = '../' + dataset + '/out/' + variants_table_dir
print('> data_dir: ' + data_dir)
filtered_vcf = data_dir + '/chr' + chrom + '_' + dataset + '_table.' + population + '.txt.filtered'
# ----------------------
# Create out_MAF{threshold} dir to store output results (plots and gwRVIS csv files)
out_dir = create_out_dir(config_file)
print('> out_dir: ' + out_dir)
var_ratios_dir = out_dir + '/var_ratios'
if not os.path.exists(var_ratios_dir):
os.makedirs(var_ratios_dir, exist_ok=True)
gwrvis_dir = out_dir + '/gwrvis_scores'
if not os.path.exists(gwrvis_dir):
os.makedirs(gwrvis_dir, exist_ok=True)
gwrvis_nt_offset_dir = gwrvis_dir + '/single_nt_offset_' + str(single_nt_offset)
if not os.path.exists(gwrvis_nt_offset_dir):
os.makedirs(gwrvis_nt_offset_dir, exist_ok=True)
plots_dir = out_dir + '/plots_per_chrom'
pp = PdfPages(full_genome_out + "/Whole_genome_gwRVIS_Boxplots.pdf")
pp.savefig(boxplot_fig)
pp.close()
if __name__ == '__main__':
config_file = sys.argv[1] # 'config.log'
input_classes_file = sys.argv[2] # 'input_classes.txt'
# ----- Init directories and global variables -----
out_dir = create_out_dir(config_file) # get output dir - already generated
print('Output dir: ' + out_dir)
gwrvis_distr_data_dir = out_dir + '/gwrvis_distribution/data'
full_genome_out = out_dir + '/full_genome_out'
ucne_dir = '../UCNEbase'
chroms = [str(ch) for ch in list(range(1,23))]
# ---- Read run parameters from config file and store into a dictionary -----
run_params = get_config_params(config_file)
genomic_classes_log = run_params['genomic_classes']
filter_plot_outliers = run_params['filter_plot_outliers']
genomic_classes.append(vals[-2])
#genomic_classes = ['intergenic', 'utr', 'intergenic_utr_lincrna_ucne_vista']
return genomic_classes
if __name__ == '__main__':
config_file = sys.argv[1]
DL_MODELS = bool(int(sys.argv[2]))
# Read dir structure
out_dir = custom_utils.create_out_dir(config_file)
ml_data_dir = out_dir + '/ml_data'
clinvar_feature_table_dir = ml_data_dir + '/clinvar_feature_tables'
clinvar_out_dir = ml_data_dir + '/clinvar-out'
# Infer available genomic classes
genomic_classes = infer_avail_genomic_classes()
for genomic_class in genomic_classes:
print('\n> Genomic class:', genomic_class)
bench = MetricsBenchmark(config_file, genomic_class)
ret = bench.read_metrics_from_saved_files()
if ret == -1:
continue
