def __init__(self, config_file, include_vcf_features=False):
self.config_file = config_file
self.include_vcf_features = include_vcf_features
config_params = custom_utils.get_config_params(config_file)
self.win_len = config_params['win_len']
#self.win_len = int(config_params['win_len'] / 2)
self.init_ouput_dirs()
print(self.out_dir)
jarvis_pkl_file = self.ml_data_dir + '/jarvis_data.pkl'
if predict_on_test_set:
jarvis_pkl_file = self.ml_data_dir + '/jarvis_data.' + str(test_indexes[0]) + '_' + str(test_indexes[1]) + '.pkl'
self.data_dict_file = jarvis_pkl_file
# @anchor -- REUNDANT check: already calling the prepara_data.py module prior to training
if not os.path.exists(self.data_dict_file):
print("\nPreparing training data - calling JarvisDataPreprocessing object...")
data_preprocessor = JarvisDataPreprocessing(config_file, predict_on_test_set=predict_on_test_set, test_indexes=test_indexes)
# Extract raw sequences from input variant windows and combine with original feature set
additional_features_df, filtered_onehot_seqs = data_preprocessor.compile_feature_table_incl_raw_seqs()
# Merge data, transform into form appropriate for DNN training and save into file
self.data_dict_file = data_preprocessor.transform_and_save_data(additional_features_df, filtered_onehot_seqs)
print(self.data_dict_file)
def __init__(self, config_file, genomic_class):
config_params = custom_utils.get_config_params(config_file)
self.genomic_class = genomic_class
self.tables_per_metric = {}
self.current_palette = sns.color_palette() + sns.color_palette("Paired")
self.hex_colors = [matplotlib.colors.to_hex(x) for x in self.current_palette]
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'
if __name__ == '__main__':
startTime = datetime.now()
args = sys.argv
chrom = args[1]
config_file = args[2] #'config.yaml'
single_nt_offset = int(args[3]) # 1 to (win_len-1)
# Read run parameters from config file and store into a dictionary
config_params = get_config_params(config_file)
print(config_params)
hg_version = config_params['hg_version']
grch = {'hg19': '37', 'hg38': '38'}
genomic_classes_files = {}
print('cwd:', os.getcwd())
with open(config_params['genomic_classes']) as fh:
for line in fh:
line = line.rstrip()
genomic_class, cur_path, _ = line.split('\t')
genomic_classes_files[genomic_class] = cur_path
# ==================== Initialisation ====================
config_file = sys.argv[1]
input_features = sys.argv[2]
genomic_classes = sys.argv[3] # comma-separated
genomic_classes = genomic_classes.split(',')
use_fixed_cv_batches = bool(int(sys.argv[4]))
cv_repeats = int(sys.argv[5])
include_vcf_features = False
test_indexes = []
# ----------------------
train_with_cv = False # get generalised performance with cross-validation
config_suffix = re.split("\.", config_file.split('/')[-1])[1]
print('config_suffix:', config_suffix)
run_params = custom_utils.get_config_params(config_file)
# [Note]: predict_on_test_set is __redundant__ and __deprecated__
#predict_on_test_set = bool(run_params['predict_on_test_set'])
predict_on_test_set = False
# -- Compatible only with: train_with_cv = True
# *************************************
use_pathogenicity_trained_model = True
use_conservation_trained_model = False
# *************************************
# sanity check
if use_pathogenicity_trained_model:
train_with_cv = True