def validate_all_human_genes():
# runs all genes through the validator
# and generates a log file
coll = MongoClient().wikidata_src.mygene
metadata_coll = MongoClient().wikidata_src.mygene_sources
metadata = metadata_coll.find_one()
doc_filter = {'taxid': 9606, 'entrezgene': {'$exists': True}}
docs = coll.find(doc_filter)
print("total number of records: {}".format(coll.find(doc_filter).count()))
validate_type = 'eukaryotic'
docs = HelperBot.validate_docs(docs, validate_type, 'P351')
records = HelperBot.tag_mygene_docs(docs, metadata)
_ = list(records)
评论列表
文章目录