def run(argv):
print argv
args = parseArgs(argv)
if args.m4.endswith("m5"):
aligns = M5File(args.m4)
else:
aligns = M4File(args.m4)
if args.reads.endswith("fasta"):
reads = FastaFile(args.reads)
elif args.reads.endswith("fastq"):
temp = FastqFile(args.reads)
reads = {}
for i in temp:
reads[i] = temp[i].seq
del (temp)
else:
logging.error("Expected Fasta or Fastq for READS (%s)" % args.reads)
exit(1)
logging.info("Extracting tails")
tailfastq = tempfile.NamedTemporaryFile(suffix=".fasta",
delete=False,
dir=args.temp)
tailfastq.close()
tailfastq = tailfastq.name
logging.debug("Tail read tmp file %s " % (tailfastq))
r, t, m = extractTails(aligns,
reads,
outFq=tailfastq,
minLength=args.minTail)
logging.info("Parsed %d reads" % (r))
logging.info("Found %d tails" % (t))
logging.info("%d reads had double tails" % (m))
if t == 0:
logging.info("No tails -- Exiting")
exit(0)
logging.info("Mapping Tails")
tailmap = tempfile.NamedTemporaryFile(suffix=".m4",
delete=False,
dir=args.temp)
tailmap.close()
tailmap = tailmap.name
logging.debug("Read map tmp file %s " % (tailmap))
mapTails(tailfastq,
args.ref,
nproc=args.nproc,
out=tailmap,
useSa=args.noSa)
logging.info("Consolidating alignments")
logging.debug("Final file %s " % (args.output))
n = uniteTails(aligns, tailmap, args.output, args.inplace)
logging.info("%d tails mapped" % (n))
class NullDevice():
def write(self, s):
pass
if __name__ == '__main__':
args = parseArgs()
alignFile = args.outname+".m5"
consensusFile = args.outname+".fasta"
#extract the read I'm looking for
if args.target is not None:#Name
tempOut = open("temp.fasta",'w')
fasta = FastaFile(args.reads)
tempOut.write(">%s\n%s\n" % (args.target, fasta[args.target]))
tempOut.write
blasr(args.reads, tempOut.name, nproc=args.nproc, outName=alignFile)
aligns = M5File(alignFile)
fout = open(consensusFile, 'w')
results = consensus(aligns)
fout.write(">pbjpolish_%d_vote_%d_len\n" % (results.contribBases,\
results.fillBases, results.sequence))
#fout.write(">\n%s\n" % consensus(aligns))
fout.close()
elif args.Target is not None:#File
blasr(args.reads, args.Target, nproc=args.nproc, outName=alignFile)
#!/usr/bin/python
import argparse, json
from pbsuite.jelly.Jelly import JellyProtocol
from pbsuite.utils.FileHandlers import FastaFile, FastqFile
from pbsuite.utils.summarizeAssembly import getStats
USAGE = """Get statistics on fasta/fastq sequences recorded in a Protocol.xml"""
if __name__ == '__main__':
parser = argparse.ArgumentParser(description=USAGE, \
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("xml", metavar="XML", type=str, \
help="Protocol.xml with inputs listed")
args = parser.parse_args()
protocol = JellyProtocol(args.xml)
seqLengths = []
for i in protocol.inputs:
if i.endswith(".fasta"):
f = FastaFile(i)
for j in f.values():
seqLengths.append(len(j))
if i.endswith(".fastq"):
f = FastqFile(i)
for j in f.values():
seqLengths.append(len(j.seq))
print "Read Stats", json.dumps(getStats(seqLengths), indent=4)
#!/usr/bin/env python
import argparse, json
from pbsuite.jelly.Jelly import JellyProtocol
from pbsuite.utils.FileHandlers import FastaFile, FastqFile
from pbsuite.utils.summarizeAssembly import getStats
USAGE = """Get statistics on fasta/fastq sequences recorded in a Protocol.xml"""
if __name__ == '__main__':
parser = argparse.ArgumentParser(description=USAGE, \
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("xml", metavar="XML", type=str, \
help="Protocol.xml with inputs listed")
args = parser.parse_args()
protocol = JellyProtocol(args.xml)
seqLengths = []
for i in protocol.inputs:
if i.endswith(".fasta"):
f = FastaFile(i)
for j in f.values():
seqLengths.append(len(j))
if i.endswith(".fastq"):
f = FastqFile(i)
for j in f.values():
seqLengths.append(len(j.seq))
print "Read Stats", json.dumps(getStats(seqLengths), indent=4)
def run(self):
#Fasta Ref Output
scaffTempName = self.scaffInput + ".tempFasta"
scaffOutput = open(scaffTempName, 'w')
#Qual Ref Output
if self.qualInput is not None:
qualTempName = self.qualInput + ".tempQual"
qualOutput = open(qualTempName, 'w')
#Gaps Output
if self.opts.gapOutput is not None:
gapTableOut = open(self.opts.gapOutput, 'w')
else:
gapTableOut = False
logging.info(
"Creating reference sequence index names and identifying gaps")
refTemplate = "ref%07d"
refId = 1
#Read References
reference = FastaFile(self.scaffInput)
if self.qualInput is not None:
qualReference = QualFile(self.qualInput)
for key in reference:
scaffIndex = refTemplate % refId
scaffName = key.replace(' ', '_')
refId += 1
scaffName = scaffName + "|" + scaffIndex
scaffOutput.write(">" + scaffName + "\n" + wrap(reference[key]) +
"\n")
if self.qualInput is not None:
qualOutput.write(">" + scaffName + "\n" +
qwrap(qualReference[key]) + "\n")
gapCoords = []
for gap in re.finditer("[^Nn]([Nn]{%d,%s})[^Nn]" % \
(self.opts.minGap, self.opts.maxGap), reference[key]):
gapCoords.append([gap.start() + 1, gap.end() - 1])
if len(gapCoords) == 0: #no Gaps
gapTableOut.write("\t".join(
[scaffName, 'na', 'na', scaffIndex + "_0_0", '3']) + '\n')
logging.debug("Scaffold %s is empty" % scaffName)
continue
#Consolidate gaps that are too close -- indicating LQ regions.
i = 0
while i < len(gapCoords) - 1:
if gapCoords[i + 1][0] - gapCoords[i][1] < 25:
gapCoords[i + 1][0] = gapCoords[i][0]
del (gapCoords[i])
else:
i += 1
prevEnd = 0 #Contig Start Tracking
idx = 0
#Make the first gap
prevEnd = gapCoords[0][1]
gapCoords[0][1] - gapCoords[0][0]
flag = Gap.BEGIN
if len(gapCoords) == 1:
flag += Gap.END
if gapTableOut:
gapTableOut.write("%s\t%i\t%i\t%s_%i_%i\t%d\n" \
% (scaffName, gapCoords[0][0], gapCoords[0][1], scaffIndex, idx, idx+1, flag))
#Now Go Through the rest of the gaps
for i in range(1, len(gapCoords)):
idx += 1
prevEnd = gapCoords[i][1]
gapCoords[i][1] - gapCoords[i][0]
if gapTableOut:
if i == len(gapCoords) - 1:
flag = Gap.END
else:
flag = 0
gapTableOut.write("%s\t%i\t%i\t%s_%i_%i\t%d\n" \
% (scaffName, gapCoords[i][0], gapCoords[i][1], scaffIndex, idx, idx+1, flag))
#Close shop
scaffOutput.close()
os.rename(self.scaffInput, self.scaffInput + ".original")
os.rename(scaffTempName, self.scaffInput)
if self.qualInput is not None:
qualOutput.close()
os.rename(self.qualInput, self.qualInput + ".original")
os.rename(qualTempName, self.qualInput)
if gapTableOut:
gapTableOut.close()
if self.opts.index:
logging.info("Creating .sa indexes for references")
r, o, e = exe("sawriter %s.sa %s" %
(self.scaffInput, self.scaffInput))
if r != 0:
logging.error("sawriter returned %d" % r)
logging.error("Ensure it's in your path")
exit(1)
logging.debug(str(o) + ' ' + str(e))
logging.info("Finished!")
from pbsuite.utils.FileHandlers import FastaFile
import json, re, sys
"""
## Arguments
1 - reference.fasta -- input reference created by Setup.py
2 - liftOverTable.json - created at end of Jelly run
3 - jelly.out.fasta -- new reference created by Jelly
"""
fasta = FastaFile(sys.argv[1])
nameLookup = {}
for entry in fasta:
data = entry.split('|')
refKey = data[-1]
origName = "|".join(data[:-1])
nameLookup[refKey] = origName
liftOver = json.load(open(sys.argv[2], 'r'))
jellyFasta = FastaFile(sys.argv[3])
regex = re.compile("ref\d{7}")
for key in liftOver:
myRefs = set()
for id, strand, size in liftOver[key]:
myRefs.update(regex.findall(id))
newName = []
for refId in myRefs:
newName.append(nameLookup[refId])
sys.stdout.write(">%s\n%s\n" % ("_".join(newName), jellyFasta[key]))
used.append(node)
next = getStrongestEdge(node, direction, used)
if next is None:
break
path.append(next)
if next.qstrand == '-':
if direction == SUPPORTFLAGS.left:
direction = SUPPORTFLAGS.right
elif direction == SUPPORTFLAGS.right:
direction = SUPPORTFLAGS.left
node = next.qname
paths.append(path)
for p in paths:
if len(p) == 0:
continue
for i in p:
if not i.tname.startswith("ref"):
sys.stdout.write(i.tname.split('/')[1], i.tstrand, "\t")
else:
sys.stdout.write(i.tname, i.tstrand, "\t")
sys.stdout.write('\n')
if __name__ == '__main__':
reads = sys.argv[1]
fasta = FastaFile(reads)
#blasr(reads, reads, 4)
ovl = m5ToOvlGraph(fasta.keys(), "out.m5")
ovlSimplify(ovl)
nx.write_gml(ovl, "ovl.gml")
import sys, random
from pbsuite.utils.FileHandlers import FastaFile, revComp, wrap
def getRandomSeq(length):
return "".join([random.choice(['A', 'T', 'C', 'G']) for i in xrange(length)])
if __name__ == '__main__':
fasta = FastaFile(sys.argv[1])
key = fasta.keys()[0]
ref = list(fasta[key])
#800bp insertion in the sample (deletion in the reference)
ref[5000:5800] = ""
#5000 Insertion
#Inversion in the sample (inversion in the reference) tails
ref[9000:12000] = list("".join(ref[10000:13000]).translate(revComp)[::-1])
#9000-12000 - INversion
#1kb deletion in sample (insert into the reference) tails
seq = getRandomSeq(1000)
ref[20000:20000] = list(seq)
#20000-21000 -- Deletion
#100bp insertion in sample (deletion in the reference) spots
ref[30000:30100] = ""
#30000 - Insertion
#200bp deletion in sample (insert into the reference) spots
seq = getRandomSeq(200)
ref[35000:35000] = list(seq)