for suspicion of contamination')
args = parser.parse_args()
seq_run = args.run
samplenames = args.samples
adaIDs = args.adaIDs
fragments = args.fragments
VERBOSE = args.verbose
maxreads = args.maxreads
submit = args.submit
summary = args.summary
max_mismatches = args.max_mismatches
susp_mismatches = args.susp_mismatches
if seq_run is not None:
samples = load_samples_sequenced(seq_runs=[seq_run])
if adaIDs is not None:
samples = samples.loc[samples.adapter.isin(adaIDs)]
if VERBOSE >= 3:
print 'adaIDs', samples.adapter
else:
samples = load_samples_sequenced().loc[samplenames]
for (samplename, sample) in samples.iterrows():
sample = SampleSeq(sample)
if VERBOSE >= 1:
print samplename
if str(sample.PCR) == 'nan':
if VERBOSE:
print 'PCR type not found, skipping'
parser.add_argument('--max-mismatches', type=int, default=20,
dest='max_mismatches',
help='Maximal number of mismatches to select')
args = parser.parse_args()
seq_runs = args.runs
samplenames = args.samples
adaIDs = args.adaIDs
fragments = args.fragments
use_pats = args.use_pats
VERBOSE = args.verbose
maxseqs = args.maxseqs
min_mismatches = args.min_mismatches
max_mismatches = args.max_mismatches
samples = load_samples_sequenced()
if seq_runs is not None:
samples = samples.loc[samples['seq run'].isin(seq_runs)]
if adaIDs is not None:
samples = samples.loc[samples.adapter.isin(adaIDs)]
if use_pats:
samples = samples.loc[samples['patient sample'] != 'nan']
else:
samples = samples.loc[samplenames]
if fragments is None:
fragments = ['F'+str(i+1) for i in xrange(6)]
alis = {fr: AlignIO.read(get_consensi_alignment_filename('all', fr), 'fasta')
help='Maximal number of reads to analyze')
parser.add_argument('--filtered', action='store_true',
help='Analyze filtered reads')
args = parser.parse_args()
samplenames = args.samples
seq_runs = args.runs
adaIDs = args.adaIDs
fragments = args.fragments
VERBOSE = args.verbose
maxreads = args.maxreads
use_filtered = args.filtered
# If the script is called with no adaID, iterate over all
if seq_runs is not None:
samples = load_samples_sequenced(seq_runs=seq_runs)
if adaIDs is not None:
samples = samples.loc[samples.adapter.isin(adaIDs)]
if VERBOSE >= 3:
print 'adaIDs', samples.adapter
else:
samples = load_samples_sequenced().loc[samplenames]
if len(samples) == 0:
print 'WARNING: no samples found.'
sys.exit()
hists = []
for (samplename, sample) in samples.iterrows():
if VERBOSE == 1: