def antiSMASH_to_dataFrame(content):
""" Extract an antiSMASH file as a pandas.DataFrame
"""
parsed = parse_antiSMASH(content)
output = pd.DataFrame()
for cs in parsed['SignificantHits']:
clusterSubject = parsed['SignificantHits'][cs].copy()
df = pd.merge(
pd.DataFrame(clusterSubject['BlastHit']),
pd.DataFrame(clusterSubject['TableGenes']),
on='subject_gene', how='outer')
del(clusterSubject['BlastHit'])
del(clusterSubject['TableGenes'])
for v in clusterSubject:
df[v] = clusterSubject[v]
output = output.append(df, ignore_index=True)
return output
评论列表
文章目录