args = parser.parse_args()
seq_run = args.run
adaIDs = args.adaIDs
VERBOSE = args.verbose
submit = args.submit
threads = args.threads
refname = args.reference
summary = args.summary
use_trimmed = args.trimmed
maxreads = args.maxreads
subsrate = args.subsrate
gapopen = args.gapopen
gapextend = args.gapextend
# Specify the dataset
dataset = load_sequencing_run(seq_run)
data_folder = dataset.folder
# If the script is called with no adaID, iterate over all
samples = dataset.samples
if adaIDs is not None:
samples = samples.loc[samples.adapter.isin(adaIDs)]
if VERBOSE >= 2:
print samples.index.tolist()
# Iterate over all adaIDs
for samplename, sample in samples.iterrows():
adaID = str(sample.adapter)
# Submit to the cluster self if requested
if submit:
parser.add_argument('--test', action='store_true',
help='Include sanity checks on mapped reads (slow)')
parser.add_argument('--no-summary', action='store_false', dest='summary',
help='Do not save results in a summary file')
args = parser.parse_args()
seq_run = args.run
adaIDs = args.adaIDs
VERBOSE = args.verbose
maxreads = args.maxreads
minisize = args.minisize
submit = args.submit
include_tests = args.test
summary = args.summary
dataset = load_sequencing_run(seq_run)
data_folder = dataset.folder
# Set the number of cycles of the kit (for trimming adapters in short inserts)
n_cycles = dataset['cycles']
# If the script is called with no adaID, iterate over all
samples = dataset.samples
if adaIDs is not None:
samples = samples.loc[samples.adapter.isin(adaIDs)]
for (samplename, sample) in samples.iterrows():
if str(sample.PCR) == 'nan':
if VERBOSE:
print samplename+': PCR type not found, skipping'
continue
