antismash_products.py

import json
z=set()
with open("/media/socialgene_nvme/v0.2.3/refseq/socialgene_neo4j/import/antismash_results.jsonl", "r") as h:
    for line in h:
        for record in json.loads(line)['records']:
            for k,v in record.items():
                for i in v:
                    for ii in i['products']:
                        z.add(ii)





# {'siderophore', 'thioamide-NRP', 'lanthipeptide-class-ii', 'furan', 'tropodithietic-acid', 'lipolanthine', 'epipeptide', 'amglyccycl', 'other', 'pyrrolidine', 'transAT-PKS-like', 'lanthipeptide-class-iv', 'proteusin', 'terpene', 'sactipeptide', 'NRPS', 'NAPAA', 'resorcinol', 'thiopeptide', 'lassopeptide', 'phenazine', 'T1PKS', 'acyl_amino_acids', 'bottromycin', 'blactam', 'redox-cofactor', 'glycocin', 'PpyS-KS', 'thioamitides', 'prodigiosin', 'melanin', 'nucleoside', 'lanthipeptide-class-iii', 'T2PKS', 'aminocoumarin', 'arylpolyene', 'guanidinotides', 'PBDE', 'hglE-KS', 'RRE-containing', 'fungal-RiPP', 'spliceotide', 'RaS-RiPP', 'oligosaccharide', 'indole', 'hserlactone', 'NRPS-like', 'phosphoglycolipid', 'linaridin', 'microviridin', 'PKS-like', 'betalactone', 'cyclic-lactone-autoinducer', 'PUFA', 'NAGGN', 'ectoine', 'butyrolactone', 'phosphonate', 'cyanobactin', 'T3PKS', 'RiPP-like', 'ranthipeptide', 'ladderane', 'transAT-PKS', 'lanthipeptide-class-v', 'lanthipeptide-class-i', 'LAP', 'CDPS'}