# Make target_tf from AtRegNet.txt and from AtRegNet.csv (much bigger). # Usage: python3 make_target_tf_agris.py > ../Data/information/target_tf_agris.txt # Last modified on 16 Feb 2021 by Hui Lan import codecs, sys class GeneIdValidator: def __init__(self, organism): self.org = organism def isvalid(self, ID): if self.org == 'ath': return ID.startswith('AT') and len(ID) == 9 and ID[3] == 'G' else: return False def make_dictionary(fname, separator): sample_id = 'C0000000000001' id_validator = GeneIdValidator('ath') f = codecs.open(fname, encoding='utf-8', errors='ignore') lines = f.readlines() f.close() d = {} duplicate = 0 for line in lines[1:]: line = line.strip() lst = line.split(separator) if len(lst) >= 5: tf0 = lst[1].upper().strip() target0 = lst[4].upper().strip() tf_lst = [x.strip() for x in tf0.split('/') if id_validator.isvalid(x)] target_lst = [x.strip() for x in target0.split('/') if id_validator.isvalid(x)] for tf in tf_lst: for target in target_lst: k = target + '.' + tf if k in d: duplicate += 1 else: d[k] = [target, tf, sample_id] return duplicate, d if __name__ == '__main__': duplicate1, d = make_dictionary('../Data/information/AtRegNet.txt', '\t') # OSU AtRegNet, an older version. Most are confirmed tf target pairs??? duplicate2, d2 = make_dictionary('../Data/information/AtRegNet2.csv', ',') # OSU AtRegNet downloaded in Feb 2021. This file includes much more tf target pairs (confirmed, unconfirmed, dap-seq, etc) d.update(d2) # combine two dictionaries into one. print('pairs: %d' % len(d), file=sys.stderr) print('duplicate: %d' % (duplicate1 + duplicate2), file=sys.stderr) for k in sorted(d.keys()): print('\t'.join(d[k]))