from pyproto.utils import parse_iter_sdf, rlen
path_fn = '../../tmp/ChEBI_complete.sdf'
i = 0
v_card = []
pc = set()
for me in parse_iter_sdf(path_fn):
attr = 'PubChem Database Links'
if attr in me:
pubchem_id = list(filter(lambda x: x.startswith('CID:'), me[attr]))
if rlen(pubchem_id) > 1:
v_card.append([me['ChEBI ID'], pubchem_id])
i += 1
if i % 5000 == 0:
print(i)
print("CHEBI SDF")
print(v_card)
print(pc)
i += 1
if i % 100 ==0:
print(i)
if r.content is None:
continue
data, refs = parse_KEGG(kegg_id, r.content.decode('utf-8'))
if data is None or refs is None:
continue
for attr, val in list(data.items())+list(refs.items()):
c = rlen(val)
if c > card[attr]:
card[attr] = c
if c > 1:
count[attr] += 1
if isinstance(val, str):
nc = len(val)
else:
nc = max([len(f) for f in val])
if nc > nchar[attr]:
nchar[attr] = nc
print("kegg:")
print(dict(card))
print(dict(count))
print(dict(nchar))