def main(open_name_file, dir_path,l):
DNA.generate_kmer_hash(1)
groups = read_parsed_taxonomy_file(open_name_file)
# Read in the FASTA files for each genome
read_FASTA_files(groups,dir_path)
# For each bin, generate a number of contigs,
all_scores = []
id_generator = Uniq_id(1000)
for group_index,group in enumerate(groups):
for genome in group.genomes:
parts = genome.split_seq(l)
print_parts(parts,sys.stdout, id_generator, genome)
def test_print_parts(self):
cur_dir = os.path.dirname(__file__)
parsed_file_name = os.path.join(cur_dir,"fixtures/parsed_gen_2_2_test.txt")
open_file = open(parsed_file_name, 'r')
groups = read_parsed_taxonomy_file(open_file)
dir_path = os.path.join(cur_dir,"fixtures/reference_genomes")
read_FASTA_files(groups, dir_path)
uniq_id = Uniq_id(10)
with tempfile.NamedTemporaryFile() as tmp_file:
for group_index, group in enumerate(groups):
for genome in group.genomes:
parts = genome.split_seq(10000)
print_parts(parts,tmp_file,uniq_id, genome)
tmp_file.seek(0)
genome_parts = list(SeqIO.parse(tmp_file,"fasta"))
assert_equal(len(genome_parts),1788)
assert_equal(genome_parts[0].id,"Ehrlichia_canis_Jake_uid58071_10_0")