def main():
parser = argparse.ArgumentParser()
parser.add_argument('-i', '--input')
parser.add_argument('-r', '--ref')
parser.add_argument('-v', dest='verbose', action='store_true')
args = parser.parse_args()
try:
len(args.input) > 0
except:
usage()
sys.exit(2)
with AlignmentSet(args.input) as peekCmpH5:
print "test"
print peekCmpH5
logging.info("Peeking at CmpH5 file %s" % (args.input))
logging.info("Input CmpH5 data: numAlnHits=%d" % len(peekCmpH5))
cmpContigNames = set(peekCmpH5.refNames)
print cmpContigNames
reference.loadFromFile(args.ref, peekCmpH5)
f = ReferenceSet(args.ref)
f.assertIndexed()
for fastaRecord in f.contigs:
refName = fastaRecord.id
print refName
def _loadReference(self, alnFile):
logging.info("Loading reference")
reference.loadFromFile(options.referenceFilename, alnFile)
# Grok the referenceWindow spec, if any.
if options.referenceWindowsAsString is None:
options.referenceWindows = ()
elif options.skipUnrecognizedContigs:
# This is a workaround for smrtpipe scatter/gather.
options.referenceWindows = []
for s in options.referenceWindowsAsString.split(","):
try:
win = reference.stringToWindow(s)
options.referenceWindows.append(win)
except Exception:
msg = traceback.format_exc()
logging.debug(msg)
pass
else:
options.referenceWindows = map(reference.stringToWindow,
options.referenceWindowsAsString.split(","))
if options.referenceWindowsFromAlignment:
options.referenceWindows = alnFile.refWindows
def _loadReference(self, alnFile):
logging.info("Loading reference")
reference.loadFromFile(options.referenceFilename, alnFile)
# Grok the referenceWindow spec, if any.
if options.referenceWindowsAsString is None:
options.referenceWindows = ()
elif options.skipUnrecognizedContigs:
# This is a workaround for smrtpipe scatter/gather.
options.referenceWindows = []
for s in options.referenceWindowsAsString.split(","):
try:
win = reference.stringToWindow(s)
options.referenceWindows.append(win)
except Exception:
msg = traceback.format_exc()
logging.debug(msg)
pass
else:
options.referenceWindows = map(
reference.stringToWindow,
options.referenceWindowsAsString.split(","))
if options.referenceWindowsFromAlignment:
options.referenceWindows = alnFile.refWindows
def _loadReference(self, cmpH5):
logging.info("Loading reference")
err = reference.loadFromFile(options.referenceFilename, cmpH5)
if err:
die("Error loading reference")
# Grok the referenceWindow spec, if any.
if options.referenceWindowsAsString is None:
options.referenceWindows = ()
elif options.skipUnrecognizedContigs:
# This is a workaround for smrtpipe scatter/gather.
options.referenceWindows = []
for s in options.referenceWindowsAsString.split(","):
try:
win = reference.stringToWindow(s)
options.referenceWindows.append(win)
except:
pass
else:
options.referenceWindows = map(reference.stringToWindow,
options.referenceWindowsAsString.split(","))
def _loadReference(self, cmpH5):
logging.info("Loading reference")
err = reference.loadFromFile(options.referenceFilename, cmpH5)
if err:
die("Error loading reference")
# Grok the referenceWindow spec, if any.
if options.referenceWindowsAsString is None:
options.referenceWindows = ()
elif options.skipUnrecognizedContigs:
# This is a workaround for smrtpipe scatter/gather.
options.referenceWindows = []
for s in options.referenceWindowsAsString.split(","):
try:
win = reference.stringToWindow(s)
options.referenceWindows.append(win)
except:
pass
else:
options.referenceWindows = map(
reference.stringToWindow,
options.referenceWindowsAsString.split(","))
import numpy as np
from pbcore.io import CmpH5Reader
from GenomicConsensus import reference
from projutils import getReads
from bqcy.bqcy import run_bqcy
cmpH5 = CmpH5Reader(
'/home/nick/workspace/btry6790_project/PXO99A_ref_wo_one_copy_212kb_repeat.cmp.h5'
)
reference.loadFromFile(
"/home/nick/workspace/btry6790_project/ref_PXO99A_genome_reference_wo_one_copy_212k_repeat/sequence/ref_PXO99A_genome_reference_wo_one_copy_212k_repeat.fasta",
cmpH5)
tmplSeq, realTmplLen, readSeqs, qvInfo = getReads(cmpH5, reference,
(146000, 146050), 64, 100)
#print(readSeqs[:, 65:])
#exit()
print("POA Consensus: " + ''.join(map(chr, tmplSeq.tolist())))
tmplSeq = np.zeros((64), dtype=np.uint8)
tmplOrds = map(ord, "A" * 50)
tmplSeq[:len(tmplOrds)] = tmplOrds
results = np.zeros(8 * tmplSeq.shape[0], dtype=np.float64)
origTmplScore, bestMutantScore, bestMutatedSeq = run_bqcy(
tmplSeq, readSeqs, qvInfo, results)
print("Polished: " + ''.join(map(chr, np.asarray(bestMutatedSeq).tolist())))
print("Fake Template: " + ''.join(map(chr, np.asarray(tmplSeq).tolist())))
print(results)
import numpy as np
from pbcore.io import CmpH5Reader
from GenomicConsensus import reference
from projutils import getReads
from bqcy.bqcy import getTemplateScore
from bqfast.bqfast import run_bqfast
cmpH5 = CmpH5Reader('/home/nick/workspace/btry6790_project/PXO99A_ref_wo_one_copy_212kb_repeat.cmp.h5')
reference.loadFromFile("/home/nick/workspace/btry6790_project/ref_PXO99A_genome_reference_wo_one_copy_212k_repeat/sequence/ref_PXO99A_genome_reference_wo_one_copy_212k_repeat.fasta", cmpH5)
#tmplSeq, realTmplLen, readSeqs, qvInfo = getReads(cmpH5, reference, (146000, 146100), 128, 100)
tmplSeq, realTmplLen, readSeqs, qvInfo = getReads(cmpH5, reference, (146000, 146050), 64, 100)
print("Real Template: " + ''.join(map(chr, tmplSeq.tolist())))
tmplSeq = np.zeros((64), dtype=np.uint8)
tmplOrds = map(ord, "A" * 50)
tmplSeq[:len(tmplOrds)] = tmplOrds
tmplScore = getTemplateScore(tmplSeq, readSeqs, qvInfo)
results, polishedTmplSeq = run_bqfast(tmplSeq, tmplSeq.shape[0], tmplScore, readSeqs, qvInfo)
print("Polished: " + ''.join(map(chr, polishedTmplSeq.tolist())))
print("Fake Template: " + ''.join(map(chr, tmplSeq.tolist())))
print(results[:tmplSeq.shape[0] * 8])