# Purpose: check what are the newly added run ids, and how many. # Usage: python3 get_new_runs.py # 23 Apr 2025, zjnu, hui import os, glob, gzip from configure import MAPPED_RDATA_DIR, TPM_FILE, UPDATE_NETWORK_LOG_FILE from log import write_log_file def convert_to_ena_run_id(x): ''' Check section Sample ID naming convention from ../brain.documentation/QUICKSTART.rst ''' index = max(x.find('DRR'), x.find('ERR'), x.find('SRR')) if index > 0: return x[index:].rstrip('X') else: return x def get_run_ids_from_quant_file_names(path_to_quant_files): result = set() quant_files = glob.glob(os.path.join(path_to_quant_files, '*_quant.txt')) for filepath in quant_files: fname = os.path.basename(filepath) result.add(fname.strip('_quant.txt')) return result def get_run_ids_from_tpm_files(path_to_tpm_files): tpm_files = glob.glob(os.path.join(path_to_tpm_files, 'TPM*')) run_ids = set() for filename in tpm_files: if filename.endswith('txt'): with open(filename) as f: line = f.readlines()[0] line = line.strip() lst = line.split('\t') for runid in lst[1:]: run_ids.add(convert_to_ena_run_id(runid)) elif filename.endswith('gz'): with gzip.open(filename, 'rt') as f: line = f.readlines()[0] line = line.strip() lst = line.split('\t') for runid in lst[1:]: run_ids.add(convert_to_ena_run_id(runid)) return run_ids if __name__ == '__main__': # Get all run IDs in MAPPED_RDATA_DIR new_run_ids = get_run_ids_from_quant_file_names(MAPPED_RDATA_DIR) # Get all run IDs in PATH_TO_TPM PATH_TO_TPM = os.path.dirname(TPM_FILE) existing_run_ids = get_run_ids_from_tpm_files(PATH_TO_TPM) set_diff = new_run_ids.difference(existing_run_ids) print('Total new run IDs in the quant files from %s: %d' % (MAPPED_RDATA_DIR, len(new_run_ids))) print('Total existing run IDs in the TPM files from %s: %d' % (PATH_TO_TPM, len(existing_run_ids))) print('Diff: %d' % (len(set_diff))) write_log_file('[get_new_runs.py] %d new RNA-seq downloaded and mapped.' % (len(set_diff)), UPDATE_NETWORK_LOG_FILE)