def encl_sam_genotype(sam_path, arg_dict):
exp_dir = arg_dict['exp_dir']
read_len = arg_dict['read_len']
motif = arg_dict['motif']
score_dict = { 'match': 3, \
'mismatch': -1, \
'gap': -3}
verbose = False
pre, post = extract_pre_post_flank(exp_dir, read_len)
nCopy_dict = {}
total_count = 0
with open(sam_path, 'r') as encl_handle:
for record in csv.reader(encl_handle, dialect='excel-tab'):
if record[0][0] != '@':
sample = record[9]
nCopy, pos, score = expansion_aware_realign(
sample, pre, post, motif, score_dict, verbose)
if nCopy not in nCopy_dict:
nCopy_dict[nCopy] = 1
else:
nCopy_dict[nCopy] = nCopy_dict[nCopy] + 1
total_count = total_count + 1
nCopy_list = nCopy_dict.keys()
freq_list = []
for nCopy in nCopy_list:
freq_list.append(float(nCopy_dict[nCopy]) / float(total_count))
return nCopy_list, freq_list
parser.add_argument('--exp-dir', type=str, required=True)
args = parser.parse_args()
out_pref = args.out_pref
in_pref = args.in_pref
exp_dir = args.exp_dir
arg_dict = load_profile(exp_dir)
read_len = arg_dict['read_len']
locus = arg_dict['locus']
motif = arg_dict['motif']
chrom, locus_start, locus_end = extract_locus_info(locus)
pre, post = extract_pre_post_flank(exp_dir, read_len)
score_dict = { 'match': 3, \
'mismatch': -1, \
'gap': -3}
verbose = False
margin = 2
in_sam = in_pref + '.sam'
out_sam = out_pref + '.sam'
out_sam_handle = open(out_sam, 'w')
print 'Filtering ' + in_pref + '.sam'
with open(in_sam, 'r') as in_sam_handle:
for record in in_sam_handle:
if record[0] == '@':
out_sam_handle.write(record)