def build_hash_and_pickle(ref_fn, key_length, force_rebuild=False):
reference_hash_pkl_fn = '{}_hash_keylength_{}.pkl'.format(
splitext(ref_fn)[0], key_length)
if exists(reference_hash_pkl_fn) and not force_rebuild:
ref_genome_hash = pickle.load(open(reference_hash_pkl_fn, 'rb'))
if max(map(len, ref_genome_hash)) == key_length:
return ref_genome_hash
else:
pass
else:
pass
reference = read_reference(ref_fn)
ref_genome_hash = make_genome_hash(reference, key_length)
pickle.dump(ref_genome_hash, open(reference_hash_pkl_fn, 'wb'))
return ref_genome_hash
help='File containing a reference genome.')
parser.add_argument('-r',
'--reads',
required=True,
dest='reads_file',
help='File containg sequencing reads.')
parser.add_argument('-o',
'--outputFile',
required=True,
dest='output_file',
help='Output file name.')
args = parser.parse_args()
reference_fn = args.reference_file
reads_fn = args.reads_file
output_fn = args.output_file
input_reads = read_reads(reads_fn)
# This will take a while; you can use an array slice for example:
#
# input_reads = reads[:300]
#
# to generate some data quickly.
reference = read_reference(reference_fn)
alignments, reads = trivial_algorithm(input_reads, reference)
output_str = pretty_print_aligned_reads_with_ref(reads, alignments,
reference)
with (open(output_fn, 'w')) as output_file:
output_file.write(output_str)