def genomeID2Bio(genome_IDs):
"""
bio include BioSample and corresponding BioProject
"""
tqdm.write("with genome ID, start to retrieve genome information")
convertor = NCBI_convertor(genome_IDs, db='assembly')
convertor.get_GI()
convertor.get_db_summary()
aid2info = convertor.dbsummary
bs_list = list(
set([
_.get('BioSampleAccn') for _ in aid2info.values()
if _.get('BioSampleAccn')
]))
bp_list = list(
set([
_.get('BioprojectAccn') for _ in aid2info.values()
if _.get('BioprojectAccn')
]))
tqdm.write("retrieving relative Bioproject and its Biosample info")
bp2info = get_bioproject(bp_list)
bs2info = get_biosample(bs_list)
return aid2info, bp2info, bs2info
from bin.ncbi_convertor import NCBI_convertor
if __name__ == "__main__":
# test
pids = open('./protein_ids').read().split('\n')
convertor = NCBI_convertor(pids, db='protein')
# convertor.check_cache(suffix=suffix, redo=redo)
convertor.get_taxons_from_tid()
pid2assembly_dict = convertor.pid2assembly()
aids = open('./assembly_ids').read().split('\n')
convertor = NCBI_convertor(aids, db='assembly')
# convertor.check_cache(suffix=suffix, redo=redo)
convertor.get_taxons_from_tid()
nids = open('./nucleotide_ids').read().split('\n')
convertor = NCBI_convertor(nids, db='nuccore')
convertor.get_GI()
convertor.get_db_summary()
# convertor.check_cache(suffix=suffix, redo=redo)
convertor.get_taxons_from_tid()