def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Set the score column of each bed interval in input to "
"(MODE, BINNED) average value of the intersection region in another track). "
"Can be used, for instance, to assign a copy number of each RepeatModeler "
"prediction...")
parser.add_argument("tracksInfo",
help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("inBed", help="BED file to annotate")
parser.add_argument("track", help="Track to use for annotation")
parser.add_argument("outBed", help="Path for output, annotated BED file")
parser.add_argument("--name",
help="Set ID field (column 4 instead of 5)",
action="store_true",
default=False)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
# read the tracks list
trackList = TrackList(args.tracksInfo)
track = trackList.getTrackByName(args.track)
if track is None:
raise RuntimeError("Can't find track %s" % args.track)
# make temporary tracks list with just our track so we can keep using
# tracks list interface but not read unecessary crap.
singleListPath = getLocalTempPath("Temp_secScore", ".bed")
trackList.trackList = [track]
trackList.saveXML(singleListPath)
obFile = open(args.outBed, "w")
# trackData interface not so great at cherry picking intervals.
# need to merge them up and use segmentation interface
filledIntervals, mergedIntervals = fillGaps(args.inBed)
# read track into trackData
trackData = TrackData()
logger.info("loading track %s" % singleListPath)
trackData.loadTrackData(singleListPath,
mergedIntervals,
segmentIntervals=filledIntervals,
applyMasking=False)
# finally, write the annotation
writeAnnotatedIntervals(trackData, filledIntervals, mergedIntervals,
obFile, args)
runShellCommand("rm -f %s" % singleListPath)
obFile.close()
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Automatically set the scale attributes of numeric tracks"
" within a given tracks.xml function using some simple heuristics. ")
parser.add_argument("tracksInfo",
help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("chromSizes",
help="2-column chrom sizes file as needed"
" by bedGraphToBigWig")
parser.add_argument("queryBed", help="Region(s) to apply scaling to")
parser.add_argument("outputDir", help="Output directory")
parser.add_argument("--tracks",
help="Comma-separated list of tracks "
"to process. If not set, all tracks with a scaling"
" attribute are processed",
default=None)
parser.add_argument("--skip",
help="Comma-separated list of tracks to "
"skip.",
default=None)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
if not os.path.exists(args.outputDir):
os.makedirs(args.outputDir)
trackNames = []
if args.tracks is not None:
trackNames = args.tracks.split(",")
skipNames = []
if args.skip is not None:
skipNames = args.skip.split(",")
mergedIntervals = getMergedBedIntervals(args.queryBed)
trackData = TrackData()
trackData.loadTrackData(args.tracksInfo, mergedIntervals)
trackList = trackData.getTrackList()
for track in trackList:
if track.getName() not in skipNames and\
(track.getName() in trackNames or len(trackNames) == 0):
if track.getScale() is not None or\
track.getLogScale() is not None or\
track.getShift() is not None or\
track.getDelta() is True:
logger.info("Writing scaled track %s" % track.getName())
writeScaledTrack(trackData, track, args)
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Set the score column of each bed interval in input to "
"(MODE, BINNED) average value of the intersection region in another track). "
"Can be used, for instance, to assign a copy number of each RepeatModeler "
"prediction...")
parser.add_argument("tracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("inBed", help="BED file to annotate")
parser.add_argument("track", help="Track to use for annotation")
parser.add_argument("outBed", help="Path for output, annotated BED file")
parser.add_argument("--name", help="Set ID field (column 4 instead of 5)",
action="store_true", default=False)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
# read the tracks list
trackList = TrackList(args.tracksInfo)
track = trackList.getTrackByName(args.track)
if track is None:
raise RuntimeError("Can't find track %s" % args.track)
# make temporary tracks list with just our track so we can keep using
# tracks list interface but not read unecessary crap.
singleListPath = getLocalTempPath("Temp_secScore", ".bed")
trackList.trackList = [track]
trackList.saveXML(singleListPath)
obFile = open(args.outBed, "w")
# trackData interface not so great at cherry picking intervals.
# need to merge them up and use segmentation interface
filledIntervals, mergedIntervals = fillGaps(args.inBed)
# read track into trackData
trackData = TrackData()
logger.info("loading track %s" % singleListPath)
trackData.loadTrackData(singleListPath, mergedIntervals,
segmentIntervals=filledIntervals,
applyMasking=False)
# finally, write the annotation
writeAnnotatedIntervals(trackData, filledIntervals, mergedIntervals, obFile,
args)
runShellCommand("rm -f %s" % singleListPath)
obFile.close()
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Automatically set the scale attributes of numeric tracks"
" within a given tracks.xml function using some simple heuristics. ")
parser.add_argument("tracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("chromSizes", help="2-column chrom sizes file as needed"
" by bedGraphToBigWig")
parser.add_argument("queryBed", help="Region(s) to apply scaling to")
parser.add_argument("outputDir", help="Output directory")
parser.add_argument("--tracks", help="Comma-separated list of tracks "
"to process. If not set, all tracks with a scaling"
" attribute are processed", default=None)
parser.add_argument("--skip", help="Comma-separated list of tracks to "
"skip.", default=None)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
if not os.path.exists(args.outputDir):
os.makedirs(args.outputDir)
trackNames = []
if args.tracks is not None:
trackNames = args.tracks.split(",")
skipNames = []
if args.skip is not None:
skipNames = args.skip.split(",")
mergedIntervals = getMergedBedIntervals(args.queryBed)
trackData = TrackData()
trackData.loadTrackData(args.tracksInfo, mergedIntervals)
trackList = trackData.getTrackList()
for track in trackList:
if track.getName() not in skipNames and\
(track.getName() in trackNames or len(trackNames) == 0):
if track.getScale() is not None or\
track.getLogScale() is not None or\
track.getShift() is not None or\
track.getDelta() is True:
logger.info("Writing scaled track %s" % track.getName())
writeScaledTrack(trackData, track, args)
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Run unit tests")
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
suite = allSuites()
runner = unittest.TextTestRunner()
i = runner.run(suite)
return len(i.failures) + len(i.errors)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Automatically set the scale attributes of numeric tracks"
" within a given tracks.xml function using some simple heuristics. ")
parser.add_argument("tracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("allBed", help="Bed file spanning entire genome")
parser.add_argument("outputTracks", help="Path to write modified tracks XML"
" to.")
parser.add_argument("--numBins", help="Maximum number of bins after scaling",
default=10, type=int)
parser.add_argument("--tracks", help="Comma-separated list of tracks "
"to process. If not set, all"
" tracks listed as having a multinomial distribution"
" (since this is the default value, this includes "
"tracks with no distribution attribute) or gaussian"
" distribution will be processed.", default=None)
parser.add_argument("--skip", help="Comma-separated list of tracks to "
"skip.", default=None)
parser.add_argument("--noLog", help="Never use log scaling",
action="store_true", default=False)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
trackNames = []
if args.tracks is not None:
trackNames = args.tracks.split(",")
skipNames = []
if args.skip is not None:
skipNames = args.skip.split(",")
trackList = TrackList(args.tracksInfo)
outTrackList = copy.deepcopy(trackList)
allIntervals = getMergedBedIntervals(args.allBed)
for track in trackList:
trackExt = os.path.splitext(track.getPath())[1]
isFasta = len(trackExt) >= 3 and trackExt[:3].lower() == ".fa"
if track.getName() not in skipNames and\
(track.getName() in trackNames or len(trackNames) == 0) and\
(track.getDist() == "multinomial" or
track.getDist() == "sparse_multinomial" or
track.getDist() == "gaussian") and\
not isFasta:
try:
setTrackScale(track, args.numBins, allIntervals, args.noLog)
except ValueError as e:
logger.warning("Skipping (non-numeric?) track %s due to: %s" % (
track.getName(), str(e)))
trackList.saveXML(args.outputTracks)
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Fill in masked intervals of an hmm prediction "
"(from teHmmEval.py) with state corresponding to surrounding"
" intervals.")
parser.add_argument("tracksXML", help="XML track list (used to id masking"
" tracks")
parser.add_argument("allBed", help="Target scope. Masked intervals outside"
" of these regions will not be included")
parser.add_argument("inBed", help="TE prediction BED file. State labels"
" should probably be mapped (ie with fitStateNames.py)")
parser.add_argument("outBed", help="Output BED. Will be equivalent to"
" the input bed except all gaps corresponding to "
"masked intervals will be filled")
parser.add_argument("--maxLen", help="Maximum length of a masked interval"
" to fill (inclusive). Use --delMask option with same value"
"if running compareBedStates.py after.",
type=int, default=sys.maxint)
parser.add_argument("--default", help="Default label to give to masked "
"region if no label can be determined", default="0")
parser.add_argument("--tgts", help="Only relabel gaps that "
"are flanked on both sides by the same state, and this state"
" is in this comma- separated list. --default used for other"
" gaps. If not targetst specified then all states checked.",
default=None)
parser.add_argument("--oneSidedTgts", help="Only relabel gaps that "
"are flanked on at least one side by a state in this comma-"
"separated list --default used for other gaps",
default=None)
parser.add_argument("--onlyDefault", help="Add the default state (--default) no"
" no all masked gaps no matter what. ie ignoring all other "
"logic", action="store_true", default=False)
parser.add_argument("--cut", help="Cut out gaps for masked tracks from the input."
" By default, the input is expected to come from the HMM "
"with mask intervals already absent, and will crash on with"
" an assertion error if an overlap is detected.",
action="store_true", default=False)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
# make sets
tgtSet = set()
if args.tgts is not None:
tgtSet = set(args.tgts.split(","))
oneSidedTgtSet = set()
if args.oneSidedTgts is not None:
oneSidedTgtSet = set(args.oneSidedTgts.split(","))
assert len(tgtSet.intersection(oneSidedTgtSet)) == 0
# read the track list
trackList = TrackList(args.tracksXML)
maskTracks = trackList.getMaskTracks()
# read the input bed
inBed = args.inBed
if args.cut is True:
inBed = cutOutMaskIntervals(inBed, -1, args.maxLen + 1, args.tracksXML)
inputIntervals = readBedIntervals(inBed, ncol = 4, sort = True)
if args.cut is True:
runShellCommand("rm -f %s" % inBed)
if len(maskTracks) == 0 or len(inputIntervals) == 0:
runShellCommand("cp %s %s" % (args.inBed, args.outBed))
logger.warning("No mask tracks located in %s or"
" %s empty" % (args.tracksXML, args.inBed))
return 0
# make a temporary, combined, merged masking bed file
tempMaskBed = getLocalTempPath("Temp_mb", ".bed")
for maskTrack in maskTracks:
assert os.path.isfile(maskTrack.getPath())
runShellCommand("cat %s | setBedCol.py 3 mask | awk \'{print $1\"\t\"$2\"\t\"$3}\'>> %s" % (
maskTrack.getPath(), tempMaskBed))
maskedIntervals = getMergedBedIntervals(tempMaskBed, sort = True)
resolvedMasks = 0
if len(inputIntervals) == 0:
logger.warning("No mask tracks located in %s" % args.tracksXML)
return
inputIdx = 0
rightFlank = inputIntervals[inputIdx]
tempOutMask = getLocalTempPath("Temp_om", ".bed")
tempOutMaskFile = open(tempOutMask, "w")
for maskIdx, maskInterval in enumerate(maskedIntervals):
if maskInterval[2] - maskInterval[1] > args.maxLen:
continue
# find candidate right flank
while rightFlank < maskInterval:
if inputIdx == len(inputIntervals) - 1:
rightFlank = None
break
else:
inputIdx += 1
rightFlank = inputIntervals[inputIdx]
# candidate left flank
leftFlank = None
if inputIdx > 0:
leftFlank = inputIntervals[inputIdx - 1]
# identify flanking states if the intervals perfectly abut
leftState = None
if leftFlank is not None:
if leftFlank[0] == maskInterval[0] and leftFlank[2] == maskInterval[1]:
leftState = str(leftFlank[3])
else:
assert intersectSize(leftFlank, maskInterval) == 0
rightState = None
if rightFlank is not None:
if rightFlank[0] == maskInterval[0] and rightFlank[1] == maskInterval[2]:
rightState = str(rightFlank[3])
else:
assert intersectSize(rightFlank, maskInterval) == 0
# choose a state for the mask interval
maskState = str(args.default)
if args.onlyDefault is True:
pass
elif leftState is not None and leftState == rightState:
if len(tgtSet) == 0 or leftState in tgtSet:
maskState = leftState
elif leftState in oneSidedTgtSet:
maskState = leftState
elif rightState in oneSidedTgtSet:
maskState = rightState
# write our mask interval
tempOutMaskFile.write("%s\t%d\t%d\t%s\n" % (maskInterval[0], maskInterval[1],
maskInterval[2], maskState))
tempOutMaskFile.close()
tempMergePath1 = getLocalTempPath("Temp_mp", ".bed")
tempMergePath2 = getLocalTempPath("Temp_mp", ".bed")
runShellCommand("cp %s %s ; cat %s >> %s" % (args.inBed, tempMergePath1,
tempOutMask, tempMergePath1))
runShellCommand("cat %s | sortBed > %s" % (tempMergePath1, tempMergePath2))
tempScopePath = getLocalTempPath("temp_all", ".bed")
runShellCommand("mergeBed -i %s |sortBed > %s" % (args.allBed, tempScopePath))
runShellCommand("intersectBed -a %s -b %s > %s" % (tempMergePath2, tempScopePath,
args.outBed))
runShellCommand("rm -f %s" % " ".join([tempMaskBed, tempOutMask, tempMergePath1,
tempMergePath2, tempScopePath]))
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Add a TSD track (or modify an existing one) based on a "
"given track")
parser.add_argument("tracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("tsdTrackDir", help="Directory to write cleaned BED"
" tracks to")
parser.add_argument("outTracksInfo", help="Path to write modified tracks XML"
" to.")
parser.add_argument("inputTrack", help="Name of track to createTSDs from")
parser.add_argument("fastaTrack", help="Name of track for fasta sequence")
parser.add_argument("outputTrack", help="Name of tsd track to add. Will"
" overwrite if it already exists (or append with"
" --append option)")
parser.add_argument("--append", help="Add onto existing TSD track if exists",
default=False, action="store_true")
parser.add_argument("--inPath", help="Use given file instead of inputTrack"
" path to generate TSD", default=None)
############ TSDFINDER OPTIONS ##############
parser.add_argument("--min", help="Minimum length of a TSD",
default=None, type=int)
parser.add_argument("--max", help="Maximum length of a TSD",
default=None, type=int)
parser.add_argument("--all", help="Report all matches in region (as opposed"
" to only the nearest to the BED element which is the "
"default behaviour", action="store_true", default=False)
parser.add_argument("--maxScore", help="Only report matches with given "
"score or smaller. The score is definied as the "
"maximum distance between the (two) TSD intervals and "
"the query interval",
default=None, type=int)
parser.add_argument("--left", help="Number of bases immediately left of the "
"BED element to search for the left TSD",
default=None, type=int)
parser.add_argument("--right", help="Number of bases immediately right of "
"the BED element to search for the right TSD",
default=None, type=int)
parser.add_argument("--overlap", help="Number of bases overlapping the "
"BED element to include in search (so total space "
"on each side will be --left + overlap, and --right + "
"--overlap", default=None, type=int)
parser.add_argument("--leftName", help="Name of left TSDs in output Bed",
default=None)
parser.add_argument("--rightName", help="Name of right TSDs in output Bed",
default=None)
parser.add_argument("--id", help="Assign left/right pairs of TSDs a unique"
" matching ID", action="store_true", default=False)
parser.add_argument("--names", help="Only apply to bed interval whose "
"name is in (comma-separated) list. If not specified"
" then all intervals are processed", default=None)
parser.add_argument("--numProc", help="Number of jobs to run in parallel."
" (parallization done on different sequences in FASTA"
"file", type=int, default=1)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
# copy out all options for call to tsd finder
args.tsdFinderOptions = "--logLevel %s" % getLogLevelString()
if args.logFile is not None:
args.tsdFinderOptions += " --logFile %s" % args.logFile
for option in ["min", "max", "all", "maxScore", "left", "right", "overlap",
"leftName", "rightName", "id", "names", "numProc"]:
val = getattr(args, option)
if val is True:
args.tsdFinderOptions += " --%s" % option
elif val is not None and val is not False:
args.tsdFinderOptions += " --%s %s" % (option, val)
try:
os.makedirs(args.tsdTrackDir)
except:
pass
if not os.path.isdir(args.tsdTrackDir):
raise RuntimeError("Unable to find or create tsdTrack dir %s" %
args.tsdTrackDir)
trackList = TrackList(args.tracksInfo)
outTrackList = copy.deepcopy(trackList)
inputTrack = trackList.getTrackByName(args.inputTrack)
if inputTrack is None:
raise RuntimeError("Track %s not found" % args.inputTrack)
if args.inPath is not None:
assert os.path.isfile(args.inPath)
inputTrack.setPath(args.inPath)
inTrackExt = os.path.splitext(inputTrack.getPath())[1].lower()
if inTrackExt != ".bb" and inTrackExt != ".bed":
raise RuntimeError("Track %s has non-bed extension %s" % (
args.inputTrack, inTrackExt))
fastaTrack = trackList.getTrackByName(args.fastaTrack)
if fastaTrack is None:
raise RuntimeError("Fasta Track %s not found" % args.fastaTrack)
faTrackExt = os.path.splitext(fastaTrack.getPath())[1].lower()
if faTrackExt[:3] != ".fa":
raise RuntimeError("Fasta Track %s has non-fasta extension %s" % (
args.fastaTrack, faTrackExt))
tsdTrack = outTrackList.getTrackByName(args.outputTrack)
if tsdTrack is None:
if args.append is True:
raise RuntimeError("TSD track %s not found. Cannot append" % (
args.outputTrack))
tsdTrack = Track()
tsdTrack.name = args.outputTrack
tsdTrack.path = os.path.join(args.tsdTrackDir, args.inputTrack + "_" +
args.outputTrack + ".bed")
runTsdFinder(fastaTrack.getPath(), inputTrack.getPath(),
tsdTrack.getPath(), args)
if outTrackList.getTrackByName(tsdTrack.getName()) is None:
outTrackList.addTrack(tsdTrack)
outTrackList.saveXML(args.outTracksInfo)
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Filter overlapping intervals out")
parser.add_argument("inputBed", help="Bed file to filter")
parser.add_argument("--bed12", help="Use bed12 exons instead of start/end"
" if present (equivalent to running bed12ToBed6 on"
" input first).", action="store_true", default=False)
parser.add_argument("--rm", help="Make sure intervals that are labeled as TE "
"by rm2State.sh script are never cut by ones that are not",
default=False, action='store_true')
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
assert os.path.isfile(args.inputBed)
tempBedToolPath = initBedTool()
# do the --rm filter. by splitting into TE / non-TE
# then removing everything in non-TE that overlaps
# TE. The adding the remainder back to TE.
inputPath = args.inputBed
if args.rm is True:
tempPath = getLocalTempPath("Temp_", ".bed")
tePath = getLocalTempPath("Temp_te_", ".bed")
runShellCommand("rm2State.sh %s |grep TE | sortBed > %s" % (
args.inputBed, tempPath))
runShellCommand("intersectBed -a %s -b %s | sortBed > %s" %(
args.inputBed, tempPath, tePath))
otherPath = getLocalTempPath("Temp_other_", ".bed")
runShellCommand("rm2State.sh %s |grep -v TE | sortBed > %s" % (
args.inputBed, tempPath))
runShellCommand("intersectBed -a %s -b %s | sortBed > %s" %(
args.inputBed, tempPath, otherPath))
if os.path.getsize(tePath) > 0 and\
os.path.getsize(otherPath) > 0:
filterPath = getLocalTempPath("Temp_filter_", ".bed")
runShellCommand("subtractBed -a %s -b %s | sortBed > %s" % (
otherPath, tePath, filterPath))
inputPath = getLocalTempPath("Temp_input_", ".bed")
runShellCommand("cat %s %s | sortBed > %s" % (
tePath, filterPath, inputPath))
runShellCommand("rm -f %s" % filterPath)
runShellCommand("rm -f %s %s %s" % (tePath, otherPath, tempPath))
bedIntervals = BedTool(inputPath).sort()
if args.bed12 is True:
bedIntervals = bedIntervals.bed6()
prevInterval = None
# this code has been way to buggy for something so simple
# keep extra list to check for sure even though it's a waste of
# time and space
sanity = []
for interval in bedIntervals:
if (prevInterval is not None and
interval.chrom == prevInterval.chrom and
interval.start < prevInterval.end):
logger.debug("Replace %d bases of \n%s with\n%s" % (
prevInterval.end - interval.start,
str(interval), str(prevInterval)))
interval.start = prevInterval.end
if interval.end > interval.start:
sys.stdout.write("%s" % str(interval))
sanity.append(interval)
prevInterval = interval
for i in xrange(len(sanity) - 1):
if sanity[i].chrom == sanity[i+1].chrom:
assert sanity[i+1].start >= sanity[i].end
cleanBedTool(tempBedToolPath)
if args.inputBed != inputPath:
runShellCommand("rm -f %s" % inputPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="fix up track names and sort alphabetically. easier to do here on xml than at end for pape\
r.")
parser.add_argument("tracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("outTracksInfo", help="Path to write modified tracks XML")
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
args.logOpString = "--logLevel %s" % getLogLevelString()
if args.logFile is not None:
args.logOpString += " --logFile %s" % args.logFile
nm = dict()
nm["hollister"] = "RM-RepBase-Hollister"
nm["chaux"] = "RM-RepBase-deLaChaux"
nm["repeat_modeler"] = "RM-RepeatModeler"
nm["repbase"] = "RM-RepBase"
nm["repet"] = "REPET"
nm["ltr_finder"] = "LTR_FINDER"
nm["ltr_harvest"] = "LTR_Harvest"
nm["ltr_termini"] = "lastz-Termini"
nm["lastz-Termini"] = "lastz-LTRTermini"
nm["tir_termini"] = "lastz-InvTermini"
nm["irf"] = "IRF"
nm["palindrome"] = "lastz-Palindrome"
nm["overlap"] = "lastz-Overlap"
nm["mitehunter"] = "MITE-Hunter"
nm["helitronscanner"] = "HelitronScanner"
nm["cov_80-"] = "lastz-SelfLowId"
nm["cov_80-90"] = "lastz-SelfMedId"
nm["cov_90+"] = "lastz-SelfHighId"
nm["left_peak_80-"] = "lastz-SelfPeakLeftLow"
nm["lastz-SelfLowLeftPeak"] = nm["left_peak_80-"]
nm["left_peak_80-90"] = "lastz-SelfPeakLeftMed"
nm["lastz-SelfMedLeftPeak"] = nm["left_peak_80-90"]
nm["left_peak_90+"] = "lastz-SelfPeakLeftHigh"
nm["lastz-SelfHighLeftPeak"] = nm["left_peak_90+"]
nm["right_peak_80-"] = "lastz-SelfPeakRightLow"
nm["lastz-SelfLowRightPeak"] = nm["right_peak_80-"]
nm["right_peak_80-90"] = "lastz-SelfPeakRightMed"
nm["lastz-SelfMedRightPeak"] = nm["right_peak_80-90"]
nm["right_peak_90+"] = "lastz-SelfPeakRightHigh"
nm["lastz-SelfHighRightPeak"] = nm["right_peak_90+"]
nm["cov_maxPId"] = "lastz-SelfPctMaxId"
nm["lastz-SelfMaxPctId"] = nm["cov_maxPId"]
nm["te_domains"] = "TE-Domains"
nm["fgenesh"] = "Genes"
nm["genes"] = nm["fgenesh"]
nm["refseq"] = nm["fgenesh"]
nm["mrna"] = "mRNA"
nm["srna"] = "sRNA"
nm["ortho_depth"] = "Alignment-Depth"
nm["orthology"] = nm["ortho_depth"]
nm["chain_depth"] = nm["ortho_depth"]
nm["alignment_depth"] = nm["ortho_depth"]
nm["gcpct"] = "GC"
nm["trf"] = "TRF"
nm["windowmasker"] = "WindowMasker"
nm["polyN"] = "Ns"
nm["phastcons_ce"] = "Conservation"
nm["phastcons"] = nm["phastcons_ce"]
nm["PhastCons"] = nm["phastcons_ce"]
nm["phyloP"] = nm["phastcons_ce"]
nm["phylop"] = nm["phastcons_ce"]
rtracks = dict()
rtracks["tantan"] = True
rtracks["polyA"] = True
rtracks["transposon_psi"] = True
rtracks["transposonpsi"] = True
rtracks["repbase_censor"] = True
rtracks["tsd"] = True
rtracks["repbase_default"] = True
rtracks["dustmasker"] = True
inTracks = TrackList(args.tracksInfo)
outTracks = TrackList()
outList = []
for track in itertools.chain(inTracks.trackList, inTracks.maskTrackList):
if not os.path.exists(track.path):
raise RuntimeError("Track DNE %s" % track.path)
if track.name not in rtracks:
if track.name in nm:
track.name = nm[track.name]
else:
logger.warning("Did not map track %s" % track.name)
outList.append(track)
else:
logger.warning("Deleted track %s" % track.name)
# sort the list
def sortComp(x):
lname = x.name.lower()
if x.name == "RM-RepeatModeler":
return "aaaaa" + lname
elif "RM" in x.name:
return "aaaa" + lname
elif "REPET" in x.name:
return "aaa" + lname
elif "softmask" in lname or "tigr" in lname or "te-domains" in lname:
return "aa" + lname
elif x.getDist == "mask":
return "zzzz" + lname
else:
return lname
outList = sorted(outList, key = lambda track : sortComp(track))
for track in outList:
outTracks.addTrack(track)
outTracks.saveXML(args.outTracksInfo)
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Create a teHMM")
parser.add_argument("tracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("trainingBed", help="Path of BED file containing"
" genome regions to train model on. If --supervised "
"is used, the names in this bed file will be treated "
"as the true annotation (otherwise it is only used for "
"interval coordinates)")
parser.add_argument("outputModel", help="Path of output hmm")
parser.add_argument("--numStates", help="Number of states in model",
type = int, default=2)
parser.add_argument("--iter", help="Number of EM iterations",
type = int, default=100)
parser.add_argument("--supervised", help="Use name (4th) column of "
"<traingingBed> for the true hidden states of the"
" model. Transition parameters will be estimated"
" directly from this information rather than EM."
" NOTE: The number of states will be determined "
"from the bed.",
action = "store_true", default = False)
parser.add_argument("--cfg", help="Use Context Free Grammar insead of "
"HMM. Only works with --supervised for now",
action = "store_true", default = False)
parser.add_argument("--saPrior", help="Confidence in self alignment "
"track for CFG. Probability of pair emission "
"is multiplied by this number if the bases are aligned"
" and its complement if bases are not aligned. Must"
" be between [0,1].", default=0.95, type=float)
parser.add_argument("--pairStates", help="Comma-separated list of states"
" (from trainingBed) that are treated as pair-emitors"
" for the CFG", default=None)
parser.add_argument("--emFac", help="Normalization factor for weighting"
" emission probabilities because when there are "
"many tracks, the transition probabilities can get "
"totally lost. 0 = no normalization. 1 ="
" divide by number of tracks. k = divide by number "
"of tracks / k", type=int, default=0)
parser.add_argument("--initTransProbs", help="Path of text file where each "
"line has three entries: FromState ToState Probability"
". This file (all other transitions get probability 0)"
" is used to specifiy the initial transition model."
" The names and number of states will be initialized "
"according to this file (overriding --numStates)",
default = None)
parser.add_argument("--fixTrans", help="Do not learn transition parameters"
" (best used with --initTransProbs)",
action="store_true", default=False)
parser.add_argument("--initEmProbs", help="Path of text file where each "
"line has four entries: State Track Symbol Probability"
". This file (all other emissions get probability 0)"
" is used to specifiy the initial emission model. All "
"states specified in this file must appear in the file"
" specified with --initTransProbs (but not vice versa).",
default = None)
parser.add_argument("--fixEm", help="Do not learn emission parameters"
" (best used with --initEmProbs)",
action="store_true", default=False)
parser.add_argument("--initStartProbs", help="Path of text file where each "
"line has two entries: State Probability"
". This file (all other start probs get probability 0)"
" is used to specifiy the initial start dist. All "
"states specified in this file must appear in the file"
" specified with --initTransProbs (but not vice versa).",
default = None)
parser.add_argument("--fixStart", help="Do not learn start parameters"
" (best used with --initStartProbs)",
action="store_true", default=False)
parser.add_argument("--forceTransProbs",
help="Path of text file where each "
"line has three entries: FromState ToState Probability"
". These transition probabilities will override any "
" learned probabilities after each training iteration"
" (unspecified "
"will not be set to 0 in this case. the learned values"
" will be kept, but normalized as needed)" ,
default=None)
parser.add_argument("--forceEmProbs", help="Path of text file where each "
"line has four entries: State Track Symbol Probability"
". These "
"emission probabilities will override any learned"
" probabilities after each training iteration "
"(unspecified "
"will not be set to 0 in this case. the learned values"
" will be kept, but normalized as needed.)" ,
default = None)
parser.add_argument("--flatEm", help="Use a flat emission distribution as "
"a baseline. If not specified, the initial emission "
"distribution will be randomized by default. Emission"
" probabilities specified with --initEmpProbs or "
"--forceEmProbs will never be affected by randomizaiton"
". The randomization is important for Baum Welch "
"training, since if two states dont have at least one"
" different emission or transition probability to begin"
" with, they will never learn to be different.",
action="store_true", default=False)
parser.add_argument("--emRandRange", help="When randomly initialzing an"
" emission distribution, constrain"
" the values to the given range (pair of "
"comma-separated numbers). Overridden by "
"--initEmProbs and --forceEmProbs when applicable."
" Completely overridden by --flatEm (which is equivalent"
" to --emRandRange .5,.5.). Actual values used will"
" always be normalized.", default="0.2,0.8")
parser.add_argument("--segment", help="Bed file of segments to treat as "
"single columns for HMM (ie as created with "
"segmentTracks.py). IMPORTANT: this file must cover "
"the same regions as the traininBed file. Unless in "
"supervised mode, probably best to use same bed file "
" as both traingBed and --segment argument. Otherwise"
" use intersectBed to make sure the overlap is exact",
default=None)
parser.add_argument("--segLen", help="Effective segment length used for"
" normalizing input segments (specifying 0 means no"
" normalization applied)", type=int, default=0)
parser.add_argument("--seed", help="Seed for random number generator"
" which will be used to initialize emissions "
"(if --flatEM and --supervised not specified)",
default=None, type=int)
parser.add_argument("--reps", help="Number of replicates (with different"
" random initializations) to run. The replicate"
" with the highest likelihood will be chosen for the"
" output", default=1, type=int)
parser.add_argument("--numThreads", help="Number of threads to use when"
" running replicates (see --rep) in parallel.",
type=int, default=1)
parser.add_argument("--emThresh", help="Threshold used for convergence"
" in baum welch training. IE delta log likelihood"
" must be bigger than this number (which should be"
" positive) for convergence", type=float,
default=0.001)
parser.add_argument("--saveAllReps", help="Save all replicates (--reps)"
" models to disk, instead of just the best one"
". Format is <outputModel>.repN. There will be "
" --reps -1 such models saved as the best output"
" counts as a replicate",
action="store_true", default=False)
parser.add_argument("--maxProb", help="Gaussian distributions and/or"
" segment length corrections can cause probability"
" to *decrease* during BW iteration. Use this option"
" to remember the parameters with the highest probability"
" rather than returning the parameters after the final "
"iteration.", action="store_true", default=False)
parser.add_argument("--maxProbCut", help="Use with --maxProb option to stop"
" training if a given number of iterations go by without"
" hitting a new maxProb", default=None, type=int)
parser.add_argument("--transMatEpsilons", help="By default, epsilons are"
" added to all transition probabilities to prevent "
"converging on 0 due to rounding error only for fully"
" unsupervised training. Use this option to force this"
" behaviour for supervised and semisupervised modes",
action="store_true", default=False)
addLoggingOptions(parser)
args = parser.parse_args()
if args.cfg is True:
assert args.supervised is True
assert args.saPrior >= 0. and args.saPrior <= 1.
if args.pairStates is not None:
assert args.cfg is True
if args.initTransProbs is not None or args.fixTrans is True or\
args.initEmProbs is not None or args.fixEm is not None:
if args.cfg is True:
raise RuntimeError("--transProbs, --fixTrans, --emProbs, --fixEm "
"are not currently compatible with --cfg.")
if args.fixTrans is True and args.supervised is True:
raise RuntimeError("--fixTrans option not compatible with --supervised")
if args.fixEm is True and args.supervised is True:
raise RuntimeError("--fixEm option not compatible with --supervised")
if (args.forceTransProbs is not None or args.forceEmProbs is not None) \
and args.cfg is True:
raise RuntimeError("--forceTransProbs and --forceEmProbs are not "
"currently compatible with --cfg")
if args.flatEm is True and args.supervised is False and\
args.initEmProbs is None and args.initTransProbs is None:
raise RuntimeError("--flatEm must be used with --initEmProbs and or"
" --initTransProbs")
if args.initEmProbs is not None and args.initTransProbs is None:
raise RuntimeError("--initEmProbs can only be used in conjunction with"
" --initTransProbs")
if args.emRandRange is not None:
args.emRandRange = args.emRandRange.split(",")
try:
assert len(args.emRandRange) == 2
args.emRandRange = (float(args.emRandRange[0]),
float(args.emRandRange[1]))
except:
raise RuntimeError("Invalid --emRandRange specified")
if args.transMatEpsilons is False:
# old logic here. now overriden with above options
args.transMatEpsilons = (args.supervised is False and
args.initTransProbs is None and
args.forceTransProbs is None)
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
# read training intervals from the bed file
logger.info("loading training intervals from %s" % args.trainingBed)
mergedIntervals = getMergedBedIntervals(args.trainingBed, ncol=4)
if mergedIntervals is None or len(mergedIntervals) < 1:
raise RuntimeError("Could not read any intervals from %s" %
args.trainingBed)
# read segment intervals
segIntervals = None
if args.segment is not None:
logger.info("loading segment intervals from %s" % args.segment)
try:
checkExactOverlap(args.trainingBed, args.segment)
except:
raise RuntimeError("bed file passed with --segments option"
" must exactly overlap trainingBed")
segIntervals = readBedIntervals(args.segment, sort=True)
elif args.segLen > 0:
raise RuntimeError("--segLen can only be used with --segment")
if args.segLen <= 0:
args.segLen = None
if args.segLen > 0 and args.segLen != 1:
logger.warning("--segLen should be 0 (no correction) or 1 (base"
" correction). Values > 1 may cause bias.")
# read the tracks, while intersecting them with the training intervals
logger.info("loading tracks %s" % args.tracksInfo)
trackData = TrackData()
trackData.loadTrackData(args.tracksInfo, mergedIntervals,
segmentIntervals=segIntervals)
catMap = None
userTrans = None
if args.supervised is False and args.initTransProbs is not None:
logger.debug("initializing transition model with user data")
catMap = stateNamesFromUserTrans(args.initTransProbs)
# state number is overrided by the transProbs file
args.numStates = len(catMap)
truthIntervals = None
# state number is overrided by the input bed file in supervised mode
if args.supervised is True:
logger.info("processing supervised state names")
# we reload because we don't want to be merging them here
truthIntervals = readBedIntervals(args.trainingBed, ncol=4)
catMap = mapStateNames(truthIntervals)
args.numStates = len(catMap)
# train the model
seeds = [random.randint(0, 4294967294)]
if args.seed is not None:
seeds = [args.seed]
random.seed(args.seed)
seeds += [random.randint(0, sys.maxint) for x in xrange(1, args.reps)]
def trainClosure(randomSeed):
return trainModel(randomSeed, trackData=trackData, catMap=catMap,
userTrans=userTrans, truthIntervals=truthIntervals,
args=args)
modelList = runParallelShellCommands(argList=seeds, numProc = args.numThreads,
execFunction = trainClosure,
useThreads = True)
# select best model
logmsg = ""
bestModel = (-1, LOGZERO)
for i in xrange(len(modelList)):
curModel = (i, modelList[i].getLastLogProb())
if curModel[1] > bestModel[1]:
bestModel = curModel
if curModel[1] is not None:
logmsg += "Rep %i: TotalProb: %f\n" % curModel
if len(modelList) > 1:
logging.info("Training Replicates Statistics:\n%s" % logmsg)
logging.info("Selecting best replicate (%d, %f)" % bestModel)
model = modelList[bestModel[0]]
# write the model to a pickle
logger.info("saving trained model to %s" % args.outputModel)
saveModel(args.outputModel, model)
# write all replicates
writtenCount = 0
if args.saveAllReps is True:
for i, repModel in enumerate(modelList):
if i != bestModel[0]:
repPath = "%s.rep%d" % (args.outputModel, writtenCount)
logger.info("saving replicate model to %s" % repPath)
saveModel(repPath, repModel)
writtenCount += 1
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description=" Given two bed files: a prediction and a true (or target)"
" annotation, re-label the prediction's state names so that they "
" best match the true annotation. Usees same logic as "
" compareBedStates.py for determining accuracy")
parser.add_argument("tgtBed", help="Target bed file")
parser.add_argument("predBed", help="Predicted bed file to re-label. ")
parser.add_argument("outBed", help="Output bed (relabeling of predBed)")
parser.add_argument("--col",
help="Column of bed files to use for state"
" (currently only support 4(name) or 5(score))",
default=4,
type=int)
parser.add_argument(
"--intThresh",
help="Threshold to consider interval from"
" tgtBed covered by predBed. If not specified, then base"
" level statistics will be used. Value in range (0,1]",
type=float,
default=None)
parser.add_argument("--noFrag",
help="Dont allow fragmented interval matches ("
"see help for --frag in compareBedStates.py). Only"
" relevant with --intThresh",
action="store_true",
default=False)
parser.add_argument(
"--qualThresh",
help="Minimum match ratio between truth"
" and prediction to relabel prediction. Example, if"
" predicted state X overlaps target state LTR 25 pct of "
"the time, then qualThresh must be at least 0.25 to "
"label X as LTR in the output. Value in range (0, 1]",
type=float,
default=0.1)
parser.add_argument("--ignore",
help="Comma-separated list of stateNames to"
" ignore (in prediction)",
default=None)
parser.add_argument("--ignoreTgt",
help="Comma-separated list of stateNames to"
" ignore (int target)",
default=None)
parser.add_argument("--tgt",
help="Comma-separated list of stateNames to "
" consider (in target). All others will be ignored",
default=None)
parser.add_argument(
"--unique",
help="If more than one predicted state maps"
" to the same target state, add a unique id (numeric "
"suffix) to the output so that they can be distinguished",
action="store_true",
default=False)
parser.add_argument("--model",
help="Apply state name mapping to the model"
" in the specified path (it is strongly advised to"
" make a backup of the model first)",
default=None)
parser.add_argument("--noMerge",
help="By default, adjacent intervals"
" with the same state name in the output are "
"automatically merged into a single interval. This"
" flag disables this.",
action="store_true",
default=False)
parser.add_argument("--hm",
help="Write confusion matrix as heatmap in PDF"
" format to specified file",
default=None)
parser.add_argument("--old",
help="Use old name mapping logic which just "
"takes biggest overlap in forward confusion matrix. "
"faster than new default logic which does the greedy"
" f1 optimization",
action="store_true",
default=False)
parser.add_argument("--fdr",
help="Use FDR cutoff instead of (default)"
" greedy F1 optimization for state labeling",
type=float,
default=None)
parser.add_argument("--tl",
help="Path to tracks XML file. Used to cut "
"out mask tracks so they are removed from comparison."
" (convenience option to not have to manually run "
"subtractBed everytime...)",
default=None)
parser.add_argument(
"--colOrder",
help="List of states used to force"
" ordering in heatmap (otherwise alphabetical) columns. These"
" states will correspond to the tgtBed when --old used and"
" --predBed otherwise.",
default=None)
parser.add_argument(
"--hmCovRow",
help="Path to write 1-row heatmap of "
"state coverage (fraction of bases). only works with --hm",
default=None)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
if args.ignore is not None:
args.ignore = set(args.ignore.split(","))
else:
args.ignore = set()
if args.ignoreTgt is not None:
args.ignoreTgt = set(args.ignoreTgt.split(","))
else:
args.ignoreTgt = set()
if args.tgt is not None:
args.tgt = set(args.tgt.split(","))
if args.old is True:
raise RuntimeError("--tgt option not implemented for --old")
else:
args.tgt = set()
if args.old is True and args.fdr is not None:
raise RuntimeError("--old and --fdr options are exclusive")
assert args.col == 4 or args.col == 5
tempFiles = []
if args.tl is not None:
cutBedTgt = cutOutMaskIntervals(args.tgtBed, -1, sys.maxint, args.tl)
cutBedPred = cutOutMaskIntervals(args.predBed, -1, sys.maxint, args.tl)
if cutBedTgt is not None:
assert cutBedPred is not None
tempFiles += [cutBedTgt, cutBedPred]
args.tgtBed = cutBedTgt
args.predBed = cutBedPred
checkExactOverlap(args.tgtBed, args.predBed)
intervals1 = readBedIntervals(args.tgtBed, ncol=args.col)
intervals2 = readBedIntervals(args.predBed, ncol=args.col)
cfName = "reverse"
if args.old is True:
intervals1, intervals2 = intervals2, intervals1
cfName = "forward"
# generate confusion matrix based on accuracy comparison using
# base or interval stats as desired
if args.intThresh is not None:
logger.info("Computing interval %s confusion matrix" % cfName)
confMat = compareIntervalsOneSided(intervals2, intervals1,
args.col - 1, args.intThresh, False,
not args.noFrag)[1]
else:
logger.info("Computing base %s confusion matrix" % cfName)
confMat = compareBaseLevel(intervals2, intervals1, args.col - 1)[1]
logger.info("%s Confusion Matrix:\n%s" % (cfName, str(confMat)))
# find the best "true" match for each predicted state
if args.old is True:
intervals1, intervals2 = intervals2, intervals1
stateMap = getStateMapFromConfMatrix_simple(confMat)
else:
stateMap = getStateMapFromConfMatrix(confMat, args.tgt, args.ignoreTgt,
args.ignore, args.qualThresh,
args.fdr)
# filter the stateMap to take into account the command-line options
# notably --ignore, --ignoreTgt, --qualThresh, and --unique
filterStateMap(stateMap, args)
logger.info("State Map:\n%s", str(stateMap))
# write the model if spefied
if args.model is not None:
applyNamesToModel(stateMap, args.model)
# generate the output bed using the statemap
writeFittedBed(intervals2, stateMap, args.outBed, args.col - 1,
args.noMerge, args.ignoreTgt)
# write the confusion matrix as heatmap
if args.hm is not None:
if canPlot is False:
raise RuntimeError("Unable to write heatmap. Maybe matplotlib is "
"not installed?")
writeHeatMap(confMat, args.hm, args.colOrder, args.hmCovRow)
if len(tempFiles) > 0:
runShellCommand("rm -f %s" % " ".join(tempFiles))
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Generate HMM-usable tracklist from raw tracklist. EX "
"used to transform mustang_alyrata_tracks.xml -> "
"mustang_alyrata_clean.xml. Runs cleanRM.py cleanLtrFinder.py and "
" cleanTermini.py and addTsdTrack.py and setTrackScaling.py (also runs "
" removeBedOverlaps.py before each of the clean scripts)")
parser.add_argument("tracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("allBed", help="Bed file spanning entire genome")
parser.add_argument("cleanTrackPath", help="Directory to write cleaned BED"
" tracks to")
parser.add_argument("outTracksInfo", help="Path to write modified tracks XML"
" to.")
parser.add_argument("--numBins", help="Maximum number of bins after scaling",
default=10, type=int)
parser.add_argument("--scaleTracks", help="Comma-separated list of tracks "
"to process for scaling. If not set, all"
" tracks listed as having a multinomial distribution"
" (since this is the default value, this includes "
"tracks with no distribution attribute) or gaussian "
"distribution will be processed.", default=None)
parser.add_argument("--skipScale", help="Comma-separated list of tracks to "
"skip for scaling.", default=None)
parser.add_argument("--ltr_termini", help="Name of termini track (appy tsd)",
default="ltr_termini")
parser.add_argument("--repeat_modeler", help="Name of repeat_modeler track (appy tsd)",
default="repeat_modeler")
parser.add_argument("--sequence", help="Name of fasta sequence track",
default="sequence")
parser.add_argument("--tsd", help="Name of tsd track to generate (appy cleanTermini.py)",
default="tsd")
parser.add_argument("--tir", help="Name of tir_termini track (appy cleanTermini.py)",
default="tir_termini")
parser.add_argument("--noScale", help="Dont do any scaling", default=False,
action="store_true")
parser.add_argument("--noTsd", help="Dont generate TSD track. NOTE:"
" TSD track is hardcoded to be generated from "
"termini and (non-LTR elements of ) chaux",
default=False, action="store_true")
parser.add_argument("--numProc", help="Number of processes to use for tsdFinder.py",
default=1, type=int)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
args.logOpString = "--logLevel %s" % getLogLevelString()
if args.logFile is not None:
args.logOpString += " --logFile %s" % args.logFile
try:
os.makedirs(args.cleanTrackPath)
except:
pass
if not os.path.isdir(args.cleanTrackPath):
raise RuntimeError("Unable to find or create cleanTrack dir %s" %
args.cleanTrackPath)
tempTracksInfo = getLocalTempPath("Temp_mustang_alyrata_clean", "xml")
runCleaning(args, tempTracksInfo)
assert os.path.isfile(tempTracksInfo)
runTsd(args, tempTracksInfo)
runScaling(args, tempTracksInfo)
runShellCommand("rm -f %s" % tempTracksInfo)
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Fill in masked intervals of an hmm prediction "
"(from teHmmEval.py) with state corresponding to surrounding"
" intervals.")
parser.add_argument("tracksXML",
help="XML track list (used to id masking"
" tracks")
parser.add_argument("allBed",
help="Target scope. Masked intervals outside"
" of these regions will not be included")
parser.add_argument(
"inBed",
help="TE prediction BED file. State labels"
" should probably be mapped (ie with fitStateNames.py)")
parser.add_argument("outBed",
help="Output BED. Will be equivalent to"
" the input bed except all gaps corresponding to "
"masked intervals will be filled")
parser.add_argument(
"--maxLen",
help="Maximum length of a masked interval"
" to fill (inclusive). Use --delMask option with same value"
"if running compareBedStates.py after.",
type=int,
default=sys.maxint)
parser.add_argument("--default",
help="Default label to give to masked "
"region if no label can be determined",
default="0")
parser.add_argument(
"--tgts",
help="Only relabel gaps that "
"are flanked on both sides by the same state, and this state"
" is in this comma- separated list. --default used for other"
" gaps. If not targetst specified then all states checked.",
default=None)
parser.add_argument(
"--oneSidedTgts",
help="Only relabel gaps that "
"are flanked on at least one side by a state in this comma-"
"separated list --default used for other gaps",
default=None)
parser.add_argument(
"--onlyDefault",
help="Add the default state (--default) no"
" no all masked gaps no matter what. ie ignoring all other "
"logic",
action="store_true",
default=False)
parser.add_argument(
"--cut",
help="Cut out gaps for masked tracks from the input."
" By default, the input is expected to come from the HMM "
"with mask intervals already absent, and will crash on with"
" an assertion error if an overlap is detected.",
action="store_true",
default=False)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
# make sets
tgtSet = set()
if args.tgts is not None:
tgtSet = set(args.tgts.split(","))
oneSidedTgtSet = set()
if args.oneSidedTgts is not None:
oneSidedTgtSet = set(args.oneSidedTgts.split(","))
assert len(tgtSet.intersection(oneSidedTgtSet)) == 0
# read the track list
trackList = TrackList(args.tracksXML)
maskTracks = trackList.getMaskTracks()
# read the input bed
inBed = args.inBed
if args.cut is True:
inBed = cutOutMaskIntervals(inBed, -1, args.maxLen + 1, args.tracksXML)
inputIntervals = readBedIntervals(inBed, ncol=4, sort=True)
if args.cut is True:
runShellCommand("rm -f %s" % inBed)
if len(maskTracks) == 0 or len(inputIntervals) == 0:
runShellCommand("cp %s %s" % (args.inBed, args.outBed))
logger.warning("No mask tracks located in %s or"
" %s empty" % (args.tracksXML, args.inBed))
return 0
# make a temporary, combined, merged masking bed file
tempMaskBed = getLocalTempPath("Temp_mb", ".bed")
for maskTrack in maskTracks:
assert os.path.isfile(maskTrack.getPath())
runShellCommand(
"cat %s | setBedCol.py 3 mask | awk \'{print $1\"\t\"$2\"\t\"$3}\'>> %s"
% (maskTrack.getPath(), tempMaskBed))
maskedIntervals = getMergedBedIntervals(tempMaskBed, sort=True)
resolvedMasks = 0
if len(inputIntervals) == 0:
logger.warning("No mask tracks located in %s" % args.tracksXML)
return
inputIdx = 0
rightFlank = inputIntervals[inputIdx]
tempOutMask = getLocalTempPath("Temp_om", ".bed")
tempOutMaskFile = open(tempOutMask, "w")
for maskIdx, maskInterval in enumerate(maskedIntervals):
if maskInterval[2] - maskInterval[1] > args.maxLen:
continue
# find candidate right flank
while rightFlank < maskInterval:
if inputIdx == len(inputIntervals) - 1:
rightFlank = None
break
else:
inputIdx += 1
rightFlank = inputIntervals[inputIdx]
# candidate left flank
leftFlank = None
if inputIdx > 0:
leftFlank = inputIntervals[inputIdx - 1]
# identify flanking states if the intervals perfectly abut
leftState = None
if leftFlank is not None:
if leftFlank[0] == maskInterval[0] and leftFlank[
2] == maskInterval[1]:
leftState = str(leftFlank[3])
else:
assert intersectSize(leftFlank, maskInterval) == 0
rightState = None
if rightFlank is not None:
if rightFlank[0] == maskInterval[0] and rightFlank[
1] == maskInterval[2]:
rightState = str(rightFlank[3])
else:
assert intersectSize(rightFlank, maskInterval) == 0
# choose a state for the mask interval
maskState = str(args.default)
if args.onlyDefault is True:
pass
elif leftState is not None and leftState == rightState:
if len(tgtSet) == 0 or leftState in tgtSet:
maskState = leftState
elif leftState in oneSidedTgtSet:
maskState = leftState
elif rightState in oneSidedTgtSet:
maskState = rightState
# write our mask interval
tempOutMaskFile.write(
"%s\t%d\t%d\t%s\n" %
(maskInterval[0], maskInterval[1], maskInterval[2], maskState))
tempOutMaskFile.close()
tempMergePath1 = getLocalTempPath("Temp_mp", ".bed")
tempMergePath2 = getLocalTempPath("Temp_mp", ".bed")
runShellCommand("cp %s %s ; cat %s >> %s" %
(args.inBed, tempMergePath1, tempOutMask, tempMergePath1))
runShellCommand("cat %s | sortBed > %s" % (tempMergePath1, tempMergePath2))
tempScopePath = getLocalTempPath("temp_all", ".bed")
runShellCommand("mergeBed -i %s |sortBed > %s" %
(args.allBed, tempScopePath))
runShellCommand("intersectBed -a %s -b %s > %s" %
(tempMergePath2, tempScopePath, args.outBed))
runShellCommand("rm -f %s" % " ".join([
tempMaskBed, tempOutMask, tempMergePath1, tempMergePath2, tempScopePath
]))
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Evaluate a given data set with a trained HMM. Display"
" the log probability of the input data given the model, and "
"optionally output the most likely sequence of hidden states.")
parser.add_argument("tracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("inputModel", help="Path of hmm created with"
"teHmmTrain.py")
parser.add_argument("bedRegions", help="Intervals to process")
parser.add_argument("--bed", help="path of file to write viterbi "
"output to (most likely sequence of hidden states)",
default=None)
parser.add_argument("--numThreads", help="Number of threads to use (only"
" applies to CFG parser for the moment)",
type=int, default=1)
parser.add_argument("--slice", help="Make sure that regions are sliced"
" to a maximum length of the given value. Most "
"useful when model is a CFG to keep memory down. "
"When 0, no slicing is done",
type=int, default=0)
parser.add_argument("--segment", help="Use the intervals in bedRegions"
" as segments which each count as a single column"
" for evaluattion. Note the model should have been"
" trained with the --segment option pointing to this"
" same bed file.", action="store_true", default=False)
parser.add_argument("--segLen", help="Effective segment length used for"
" normalizing input segments (specifying 0 means no"
" normalization applied)", type=int, default=0)
parser.add_argument("--maxPost", help="Use maximum posterior decoding instead"
" of Viterbi for evaluation", action="store_true",
default=False)
parser.add_argument("--pd", help="Output BED file for posterior distribution. Must"
" be used in conjunction with --pdStates (View on the "
"browser via bedGraphToBigWig)", default=None)
parser.add_argument("--pdStates", help="comma-separated list of state names to use"
" for computing posterior distribution. For example: "
" --pdStates inside,LTR_left,LTR_right will compute the probability"
", for each observation, that the hidden state is inside OR LTR_left"
" OR LTR_right. Must be used with --pd to specify output "
"file.", default=None)
parser.add_argument("--bic", help="save Bayesian Information Criterion (BIC) score"
" in given file", default=None)
parser.add_argument("--ed", help="Output BED file for emission distribution. Must"
" be used in conjunction with --edStates (View on the "
"browser via bedGraphToBigWig)", default=None)
parser.add_argument("--edStates", help="comma-separated list of state names to use"
" for computing emission distribution. For example: "
" --edStates inside,LTR_left for each obsercation the probability "
" that inside emitted that observaiton plus the probabillity that"
" LTR_left emitted it. If more than one state is selected, this "
" is not a distribution, but a sum of distributions (and values"
" can exceed 1). Mostly for debugging purposes. Note output in LOG",
default=None)
parser.add_argument("--chroms", help="list of chromosomes, or regions, to run in parallel"
" (in BED format). input regions will be intersected with each line"
" in this file, and the result will correspsond to an individual job",
default=None)
parser.add_argument("--proc", help="number of processes (use in conjunction with --chroms)",
type=int, default=1)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
if args.slice <= 0:
args.slice = sys.maxint
elif args.segment is True:
raise RuntimeError("--slice and --segment options are not compatible at "
"this time")
if (args.pd is not None) ^ (args.pdStates is not None):
raise RuntimeError("--pd requires --pdStates and vice versa")
if (args.ed is not None) ^ (args.edStates is not None):
raise RuntimeError("--ed requires --edStates and vice versa")
if args.bed is None and (args.pd is not None or args.ed is not None):
raise RuntimeError("Both --ed and --pd only usable in conjunction with"
" --bed")
if args.chroms is not None:
# hack to allow chroms argument to chunk and rerun
parallelDispatch(argv, args)
cleanBedTool(tempBedToolPath)
return 0
# load model created with teHmmTrain.py
logger.info("loading model %s" % args.inputModel)
model = loadModel(args.inputModel)
if isinstance(model, MultitrackCfg):
if args.maxPost is True:
raise RuntimeErorr("--post not supported on CFG models")
# apply the effective segment length
if args.segLen > 0:
assert args.segment is True
model.getEmissionModel().effectiveSegmentLength = args.segLen
# read intervals from the bed file
logger.info("loading target intervals from %s" % args.bedRegions)
mergedIntervals = getMergedBedIntervals(args.bedRegions, ncol=4)
if mergedIntervals is None or len(mergedIntervals) < 1:
raise RuntimeError("Could not read any intervals from %s" %
args.bedRegions)
# slice if desired
choppedIntervals = [x for x in slicedIntervals(mergedIntervals, args.slice)]
# read segment intervals
segIntervals = None
if args.segment is True:
logger.info("loading segment intervals from %s" % args.bedRegions)
segIntervals = readBedIntervals(args.bedRegions, sort=True)
# load the input
# read the tracks, while intersecting them with the given interval
trackData = TrackData()
# note we pass in the trackList that was saved as part of the model
# because we do not want to generate a new one.
logger.info("loading tracks %s" % args.tracksInfo)
trackData.loadTrackData(args.tracksInfo, choppedIntervals,
model.getTrackList(),
segmentIntervals=segIntervals)
# do the viterbi algorithm
if isinstance(model, MultitrackHmm):
algname = "viterbi"
if args.maxPost is True:
algname = "posterior decoding"
logger.info("running %s algorithm" % algname)
elif isinstance(model, MultitrackCfg):
logger.info("running CYK algorithm")
vitOutFile = None
if args.bed is not None:
vitOutFile = open(args.bed, "w")
totalScore = 0
tableIndex = 0
totalDatapoints = 0
# Note: in general there's room to save on memory by only computing single
# track table at once (just need to add table by table interface to hmm...)
posteriors = [None] * trackData.getNumTrackTables()
posteriorsFile = None
posteriorsMask = None
if args.pd is not None:
posteriors = model.posteriorDistribution(trackData)
posteriorsFile = open(args.pd, "w")
posteriorsMask = getPosteriorsMask(args.pdStates, model)
assert len(posteriors[0][0]) == len(posteriorsMask)
emProbs = [None] * trackData.getNumTrackTables()
emissionsFile = None
emissionsMask = None
if args.ed is not None:
emProbs = model.emissionDistribution(trackData)
emissionsFile = open(args.ed, "w")
emissionsMask = getPosteriorsMask(args.edStates, model)
assert len(emProbs[0][0]) == len(emissionsMask)
decodeFunction = model.viterbi
if args.maxPost is True:
decodeFunction = model.posteriorDecode
for i, (vitLogProb, vitStates) in enumerate(decodeFunction(trackData,
numThreads=args.numThreads)):
totalScore += vitLogProb
if args.bed is not None or args.pd is not None:
if args.bed is not None:
vitOutFile.write("#Viterbi Score: %f\n" % (vitLogProb))
trackTable = trackData.getTrackTableList()[tableIndex]
tableIndex += 1
statesToBed(trackTable,
vitStates, vitOutFile, posteriors[i], posteriorsMask,
posteriorsFile, emProbs[i], emissionsMask, emissionsFile)
totalDatapoints += len(vitStates) * trackTable.getNumTracks()
print "Viterbi (log) score: %f" % totalScore
if isinstance(model, MultitrackHmm) and model.current_iteration is not None:
print "Number of EM iterations: %d" % model.current_iteration
if args.bed is not None:
vitOutFile.close()
if posteriorsFile is not None:
posteriorsFile.close()
if emissionsFile is not None:
emissionsFile.close()
if args.bic is not None:
bicFile = open(args.bic, "w")
# http://en.wikipedia.org/wiki/Bayesian_information_criterion
lnL = float(totalScore)
try:
k = float(model.getNumFreeParameters())
except:
# numFreeParameters still not done for semi-supervised
# just pass through a 0 instead of crashing for now
k = 0.0
n = float(totalDatapoints)
bic = -2.0 * lnL + k * (np.log(n) + np.log(2 * np.pi))
bicFile.write("%f\n" % bic)
bicFile.write("# = -2.0 * lnL + k * (lnN + ln(2 * np.pi))\n"
"# where lnL=%f k=%d (%d states) N=%d (%d obs * %d tracks) lnN=%f\n" % (
lnL, int(k), model.getEmissionModel().getNumStates(), int(totalDatapoints),
totalDatapoints / model.getEmissionModel().getNumTracks(),
model.getEmissionModel().getNumTracks(), np.log(n)))
bicFile.close()
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Create starting transition and emission distributions "
"from a candidate BED annotation, which can"
" be used with teHmmTrain.py using the --initTransProbs and "
"--initEmProbs options, respectively. The distributions created here"
" are extremely simple, but this can be a good shortcut to at least "
"getting the state names into the init files, which can be further "
"tweeked by hand.")
parser.add_argument("tracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("trackName", help="Name of Track to use as initial"
" annotation")
parser.add_argument("queryBed", help="Bed file with regions to query")
parser.add_argument("outTransProbs", help="File to write transition model"
" to")
parser.add_argument("outEmProbs", help="File to write emission model to")
parser.add_argument("--numOut", help="Number of \"outside\" states to add"
" to the model.", default=1, type=int)
parser.add_argument("--numTot", help="Add x \"outside\" states such "
"that total states is this. (overrieds --numOut)",
default=0, type=int)
parser.add_argument("--outName", help="Name of outside states (will have"
" numeric suffix if more than 1)", default="Outside")
parser.add_argument("--mode", help="Strategy for initializing the "
"transition graph: {\'star\': all states are connected"
" to the oustide state(s) but not each other; "
" \'data\': transitions estimated from input bed; "
" \'full\': dont write edges and let teHmmTrain.py "
"initialize as a clique}", default="star")
parser.add_argument("--selfTran", help="This script will always write all"
" the self-transition probabilities to the output file. "
"They will all be set to the specified value using this"
" option, or estimated from the data if -1", default=-1.,
type=float)
parser.add_argument("--em", help="Emission probability for input track ("
"ie probability that state emits itself)",
type=float, default=0.95)
parser.add_argument("--outEmNone", help="Add None emission probabilities"
" for target track for Outside states",
action="store_true", default=None)
addLoggingOptions(parser)
args = parser.parse_args()
if args.mode == "star" and args.numOut < 1:
raise RuntimeError("--numOut must be at least 1 if --mode star is used")
if args.mode != "star" and args.mode != "data" and args.mode != "full":
raise RuntimeError("--mode must be one of {star, data, full}")
if args.mode == "data":
raise RuntimeError("--data not implemented yet")
assert os.path.isfile(args.tracksInfo)
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
# Read the tracks info
trackList = TrackList(args.tracksInfo)
# Extract the track we want
track = trackList.getTrackByName(args.trackName)
if track is None:
raise RuntimeError("Track %s not found in tracksInfo" % args.trackName)
trackPath = track.getPath()
if track.getDist() != "multinomial" and track.getDist() != "gaussian":
raise RuntimeError("Track %s does not have multinomial or "
"gaussian distribution" % args.trackName)
if track.getScale() is not None or track.getLogScale() is not None:
raise RuntimeError("Track %s must not have scale" % args.trackName)
# read query intervals from the bed file
logger.info("loading query intervals from %s" % args.queryBed)
mergedIntervals = getMergedBedIntervals(args.queryBed, ncol=4)
if mergedIntervals is None or len(mergedIntervals) < 1:
raise RuntimeError("Could not read any intervals from %s" %
args.queryBed)
# read the track, while intersecting with query intervals
# (track is saved as temp XML file for sake not changing interface)
bedIntervals = []
for queryInterval in mergedIntervals:
bedIntervals += readBedIntervals(trackPath,
ncol = track.getValCol() + 1,
chrom=queryInterval[0],
start=queryInterval[1],
end=queryInterval[2])
# 1st pass to collect set of names
nameMap = CategoryMap(reserved = 0)
for interval in bedIntervals:
nameMap.update(interval[track.getValCol()])
outNameMap = CategoryMap(reserved = 0)
if args.numTot > 0:
args.numOut = max(0, args.numTot - len(nameMap))
for i in xrange(args.numOut):
outName = args.outName
if args.numOut > 1:
outName += str(i)
assert nameMap.has(outName) is False
outNameMap.update(outName)
# write the transition model for use with teHmmTrain.py --initTransProbs
writeTransitions(bedIntervals, nameMap, outNameMap, args)
# write the emission model for use with teHmmTrain.py --initEmProbs
writeEmissions(bedIntervals, nameMap, outNameMap, args)
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Make some tables of statistics from a BED file. All"
" output will be written in one big CSV table to be viewed in a "
"spreadsheet.")
parser.add_argument("inBed", help="Input bed file")
parser.add_argument("outCsv", help="Path to write output in CSV format")
parser.add_argument("--ignore",
help="Comma-separated list of names"
" to ignore",
default="")
parser.add_argument("--numBins",
help="Number of (linear) bins for "
"histograms",
type=int,
default=10)
parser.add_argument("--logHist",
help="Apply log-transform to data for "
"histogram",
action="store_true",
default=False)
parser.add_argument("--histRange",
help="Histogram range as comma-"
"separated pair of numbers",
default=None)
parser.add_argument("--noHist",
help="skip hisograms",
action="store_true",
default=False)
parser.add_argument("--noScore",
help="Just do length stats",
action="store_true",
default=False)
parser.add_argument("--noLen",
help="Just do score stats",
action="store_true",
default=False)
parser.add_argument("--nearness",
help="Compute nearness stats (instead "
"of normal stats) of input bed with given BED. Output"
" will be a BED instead of CSV, with nearness in the "
"score position",
default=None)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
if args.histRange is not None:
args.histRange = args.histRange.split(",")
assert len(args.histRange) == 2
args.histRange = int(args.histRange[0]), int(args.histRange[1])
outFile = open(args.outCsv, "w")
args.ignoreSet = set(args.ignore.split(","))
intervals = readBedIntervals(args.inBed,
ncol=5,
sort=args.nearness is not None)
csvStats = ""
# nearness stats
if args.nearness is not None:
args.noScore = True
csvStats = makeNearnessBED(intervals, args)
# length stats
elif args.noLen is False:
csvStats = makeCSV(intervals, args, lambda x: int(x[2]) - int(x[1]),
"Length")
# score stats
try:
if args.noScore is False:
csvStats += "\n" + makeCSV(intervals, args, lambda x: float(x[4]),
"Score")
csvStats += "\n" + makeCSV(
intervals, args, lambda x: float(x[4]) *
(float(x[2]) - float(x[1])), "Score*Length")
except Exception as e:
logger.warning("Couldn't make score stats because %s" % str(e))
outFile.write(csvStats)
outFile.write("\n")
outFile.close()
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description=" Given two bed files: a prediction and a true (or target)"
" annotation, re-label the prediction's state names so that they "
" best match the true annotation. Usees same logic as "
" compareBedStates.py for determining accuracy")
parser.add_argument("tgtBed", help="Target bed file")
parser.add_argument("predBed", help="Predicted bed file to re-label. ")
parser.add_argument("outBed", help="Output bed (relabeling of predBed)")
parser.add_argument("--col", help="Column of bed files to use for state"
" (currently only support 4(name) or 5(score))",
default = 4, type = int)
parser.add_argument("--intThresh", help="Threshold to consider interval from"
" tgtBed covered by predBed. If not specified, then base"
" level statistics will be used. Value in range (0,1]",
type=float, default=None)
parser.add_argument("--noFrag", help="Dont allow fragmented interval matches ("
"see help for --frag in compareBedStates.py). Only"
" relevant with --intThresh", action="store_true",
default=False)
parser.add_argument("--qualThresh", help="Minimum match ratio between truth"
" and prediction to relabel prediction. Example, if"
" predicted state X overlaps target state LTR 25 pct of "
"the time, then qualThresh must be at least 0.25 to "
"label X as LTR in the output. Value in range (0, 1]",
type=float, default=0.1)
parser.add_argument("--ignore", help="Comma-separated list of stateNames to"
" ignore (in prediction)", default=None)
parser.add_argument("--ignoreTgt", help="Comma-separated list of stateNames to"
" ignore (int target)", default=None)
parser.add_argument("--tgt", help="Comma-separated list of stateNames to "
" consider (in target). All others will be ignored",
default=None)
parser.add_argument("--unique", help="If more than one predicted state maps"
" to the same target state, add a unique id (numeric "
"suffix) to the output so that they can be distinguished",
action="store_true", default=False)
parser.add_argument("--model", help="Apply state name mapping to the model"
" in the specified path (it is strongly advised to"
" make a backup of the model first)", default=None)
parser.add_argument("--noMerge", help="By default, adjacent intervals"
" with the same state name in the output are "
"automatically merged into a single interval. This"
" flag disables this.", action="store_true",
default=False)
parser.add_argument("--hm", help="Write confusion matrix as heatmap in PDF"
" format to specified file", default = None)
parser.add_argument("--old", help="Use old name mapping logic which just "
"takes biggest overlap in forward confusion matrix. "
"faster than new default logic which does the greedy"
" f1 optimization", action="store_true", default=False)
parser.add_argument("--fdr", help="Use FDR cutoff instead of (default)"
" greedy F1 optimization for state labeling",
type=float, default=None)
parser.add_argument("--tl", help="Path to tracks XML file. Used to cut "
"out mask tracks so they are removed from comparison."
" (convenience option to not have to manually run "
"subtractBed everytime...)", default=None)
parser.add_argument("--colOrder", help="List of states used to force"
" ordering in heatmap (otherwise alphabetical) columns. These"
" states will correspond to the tgtBed when --old used and"
" --predBed otherwise.", default=None)
parser.add_argument("--hmCovRow", help="Path to write 1-row heatmap of "
"state coverage (fraction of bases). only works with --hm",
default=None)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
if args.ignore is not None:
args.ignore = set(args.ignore.split(","))
else:
args.ignore = set()
if args.ignoreTgt is not None:
args.ignoreTgt = set(args.ignoreTgt.split(","))
else:
args.ignoreTgt = set()
if args.tgt is not None:
args.tgt = set(args.tgt.split(","))
if args.old is True:
raise RuntimeError("--tgt option not implemented for --old")
else:
args.tgt = set()
if args.old is True and args.fdr is not None:
raise RuntimeError("--old and --fdr options are exclusive")
assert args.col == 4 or args.col == 5
tempFiles = []
if args.tl is not None:
cutBedTgt = cutOutMaskIntervals(args.tgtBed, -1, sys.maxint, args.tl)
cutBedPred = cutOutMaskIntervals(args.predBed, -1, sys.maxint, args.tl)
if cutBedTgt is not None:
assert cutBedPred is not None
tempFiles += [cutBedTgt, cutBedPred]
args.tgtBed = cutBedTgt
args.predBed = cutBedPred
checkExactOverlap(args.tgtBed, args.predBed)
intervals1 = readBedIntervals(args.tgtBed, ncol = args.col)
intervals2 = readBedIntervals(args.predBed, ncol = args.col)
cfName = "reverse"
if args.old is True:
intervals1, intervals2 = intervals2, intervals1
cfName = "forward"
# generate confusion matrix based on accuracy comparison using
# base or interval stats as desired
if args.intThresh is not None:
logger.info("Computing interval %s confusion matrix" % cfName)
confMat = compareIntervalsOneSided(intervals2, intervals1, args.col -1,
args.intThresh, False,
not args.noFrag)[1]
else:
logger.info("Computing base %s confusion matrix" % cfName)
confMat = compareBaseLevel(intervals2, intervals1, args.col - 1)[1]
logger.info("%s Confusion Matrix:\n%s" % (cfName, str(confMat)))
# find the best "true" match for each predicted state
if args.old is True:
intervals1, intervals2 = intervals2, intervals1
stateMap = getStateMapFromConfMatrix_simple(confMat)
else:
stateMap = getStateMapFromConfMatrix(confMat, args.tgt, args.ignoreTgt,
args.ignore, args.qualThresh,
args.fdr)
# filter the stateMap to take into account the command-line options
# notably --ignore, --ignoreTgt, --qualThresh, and --unique
filterStateMap(stateMap, args)
logger.info("State Map:\n%s", str(stateMap))
# write the model if spefied
if args.model is not None:
applyNamesToModel(stateMap, args.model)
# generate the output bed using the statemap
writeFittedBed(intervals2, stateMap, args.outBed, args.col-1, args.noMerge,
args.ignoreTgt)
# write the confusion matrix as heatmap
if args.hm is not None:
if canPlot is False:
raise RuntimeError("Unable to write heatmap. Maybe matplotlib is "
"not installed?")
writeHeatMap(confMat, args.hm, args.colOrder, args.hmCovRow)
if len(tempFiles) > 0:
runShellCommand("rm -f %s" % " ".join(tempFiles))
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Train, evalaute, then compare hmm model on input")
parser.add_argument("trainingTracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks used "
"for training")
parser.add_argument("outputDir", help="directory to write output")
parser.add_argument("inBeds", nargs="*", help="list of training beds")
parser.add_argument("--evalTracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks used"
" for evaluation (only need if different from"
" trainingTracksInfo", default=None)
parser.add_argument("--numProc", help="Max number of processors to use",
type=int, default=1)
parser.add_argument("--allTrackCombinations", help="Rerun with all"
" possible combinations of tracks from the input"
" tracksInfo file. Note that this number gets big"
" pretty fast.", action = "store_true", default= False)
parser.add_argument("--emStates", help="By default the supervised mode"
" of teHmmTrain is activated. This option overrides"
" that and uses the EM mode and the given number of "
"states instead", type=int, default=None)
parser.add_argument("--cross", help="Do 50/50 cross validation by training"
" on first half input and validating on second",
action="store_true", default=False)
parser.add_argument("--emFac", help="Normalization factor for weighting"
" emission probabilities because when there are "
"many tracks, the transition probabilities can get "
"totally lost. 0 = no normalization. 1 ="
" divide by number of tracks. k = divide by number "
"of tracks / k", type=int, default=0)
parser.add_argument("--mod", help="Path to trained model. This will "
"bypass the training phase that would normally be done"
" and just skip to the evaluation. Note that the user"
" must make sure that the trained model has the "
"states required to process the input data",
default = None)
parser.add_argument("--iter", help="Number of EM iterations. Needs to be"
" used in conjunction with --emStates to specify EM"
" training",
type = int, default=None)
parser.add_argument("--initTransProbs", help="Path of text file where each "
"line has three entries: FromState ToState Probability"
". This file (all other transitions get probability 0)"
" is used to specifiy the initial transition model."
" The names and number of states will be initialized "
"according to this file (overriding --numStates)",
default = None)
parser.add_argument("--fixTrans", help="Do not learn transition parameters"
" (best used with --initTransProbs)",
action="store_true", default=False)
parser.add_argument("--initEmProbs", help="Path of text file where each "
"line has four entries: State Track Symbol Probability"
". This file (all other emissions get probability 0)"
" is used to specifiy the initial emission model. All "
"states specified in this file must appear in the file"
" specified with --initTransProbs (but not vice versa).",
default = None)
parser.add_argument("--fixEm", help="Do not learn emission parameters"
" (best used with --initEmProbs)",
action="store_true", default=False)
parser.add_argument("--initStartProbs", help="Path of text file where each "
"line has two entries: State Probability"
". This file (all other start probs get probability 0)"
" is used to specifiy the initial start dist. All "
"states specified in this file must appear in the file"
" specified with --initTransProbs (but not vice versa).",
default = None)
parser.add_argument("--fixStart", help="Do not learn start parameters"
" (best used with --initStartProbs)",
action="store_true", default=False)
parser.add_argument("--forceTransProbs",
help="Path of text file where each "
"line has three entries: FromState ToState Probability"
". These transition probabilities will override any "
" learned probabilities after training (unspecified "
"will not be set to 0 in this case. the learned values"
" will be kept, but normalized as needed" ,
default=None)
parser.add_argument("--forceEmProbs", help="Path of text file where each "
"line has four entries: State Track Symbol Probability"
". These "
"emission probabilities will override any learned"
" probabilities after training (unspecified "
"will not be set to 0 in this case. the learned values"
" will be kept, but normalized as needed." ,
default = None)
parser.add_argument("--flatEm", help="Use a flat emission distribution as "
"a baseline. If not specified, the initial emission "
"distribution will be randomized by default. Emission"
" probabilities specified with --initEmpProbs or "
"--forceEmProbs will never be affected by randomizaiton"
". The randomization is important for Baum Welch "
"training, since if two states dont have at least one"
" different emission or transition probability to begin"
" with, they will never learn to be different.",
action="store_true", default=False)
parser.add_argument("--emRandRange", help="When randomly initialzing a"
" multinomial emission distribution, constrain"
" the values to the given range (pair of "
"comma-separated numbers). Overridden by "
"--initEmProbs and --forceEmProbs when applicable."
" Completely overridden by --flatEm (which is equivalent"
" to --emRandRange .5,.5.). Actual values used will"
" always be normalized.", default=None)
parser.add_argument("--mandTracks", help="Mandatory track names for use "
"with --allTrackCombinations in comma-separated list",
default=None)
parser.add_argument("--combinationRange", help="in form MIN,MAX: Only "
"explore track combination in given (closed) range. "
"A more refined version of --allTrackCombinations.",
default=None)
parser.add_argument("--supervised", help="Use name (4th) column of "
"<traingingBed> for the true hidden states of the"
" model. Transition parameters will be estimated"
" directly from this information rather than EM."
" NOTE: The number of states will be determined "
"from the bed.",
action = "store_true", default = False)
parser.add_argument("--segment", help="Input bed files are also used to "
"segment data. Ie teHmmTrain is called with --segment"
" set to the input file. Not currently working with "
" --supervised",
action = "store_true", default=False)
parser.add_argument("--segLen", help="Effective segment length used for"
" normalizing input segments (specifying 0 means no"
" normalization applied) in training", type=int,
default=None)
parser.add_argument("--truth", help="Use specifed file instead of "
"input file(s) for truth comparison. Makes sense"
" when --segment is specified and only one input"
" bed specified", default = None)
parser.add_argument("--eval", help="Bed file used for evaluation. It should"
" cover same region in same order as --truth. Option "
"exists mostly to specify segmentation of --truth",
default=None)
parser.add_argument("--seed", help="Seed for random number generator"
" which will be used to initialize emissions "
"(if --flatEM and --supervised not specified)",
default=None, type=int)
parser.add_argument("--reps", help="Number of training replicates (with "
" different"
" random initializations) to run. The replicate"
" with the highest likelihood will be chosen for the"
" output", default=None, type=int)
parser.add_argument("--numThreads", help="Number of threads to use when"
" running training replicates (see --rep) in parallel.",
type=int, default=None)
parser.add_argument("--emThresh", help="Threshold used for convergence"
" in baum welch training. IE delta log likelihood"
" must be bigger than this number (which should be"
" positive) for convergence", type=float,
default=None)
parser.add_argument("--fit", help="Run fitStateNames.py to automap names"
" before running comparison", action="store_true",
default=False)
parser.add_argument("--fitOpts", help="Options to pass to fitStateNames.py"
" (only effective if used with --fit)", default=None)
parser.add_argument("--saveAllReps", help="Save all replicates (--reps)"
" models to disk, instead of just the best one"
". Format is <outputModel>.repN. There will be "
" --reps -1 such models saved as the best output"
" counts as a replicate. Comparison statistics"
" will be generated for each rep.",
action="store_true", default=False)
parser.add_argument("--maxProb", help="Gaussian distributions and/or"
" segment length corrections can cause probability"
" to *decrease* during BW iteration. Use this option"
" to remember the parameters with the highest probability"
" rather than returning the parameters after the final "
"iteration.", action="store_true", default=False)
parser.add_argument("--maxProbCut", help="Use with --maxProb option to stop"
" training if a given number of iterations go by without"
" hitting a new maxProb", default=None, type=int)
parser.add_argument("--transMatEpsilons", help="By default, epsilons are"
" added to all transition probabilities to prevent "
"converging on 0 due to rounding error only for fully"
" unsupervised training. Use this option to force this"
" behaviour for supervised and semisupervised modes",
action="store_true", default=False)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
logOps = "--logLevel %s" % getLogLevelString()
if args.logFile is not None:
logOps += " --logFile %s" % args.logFile
if not os.path.exists(args.outputDir):
os.makedirs(args.outputDir)
if args.evalTracksInfo is None:
args.evalTracksInfo = args.trainingTracksInfo
trainingTrackList = TrackList(args.trainingTracksInfo)
evalTrackList = TrackList(args.evalTracksInfo)
checkTrackListCompatible(trainingTrackList, evalTrackList)
sizeRange = (len(trainingTrackList), len(trainingTrackList) + 1)
if args.allTrackCombinations is True:
sizeRange = (1, len(trainingTrackList) + 1)
if args.combinationRange is not None:
toks = args.combinationRange.split(",")
sizeRange = int(toks[0]),int(toks[1]) + 1
logger.debug("manual range (%d, %d) " % sizeRange)
mandTracks = set()
if args.mandTracks is not None:
mandTracks = set(args.mandTracks.split(","))
logger.debug("mandatory set %s" % str(mandTracks))
trainFlags = ""
if args.emStates is not None:
trainFlags += " --numStates %d" % args.emStates
if args.supervised is True:
trainFlags += " --supervised"
if args.segment is True:
raise RuntimeError("--supervised not currently compatible with "
"--segment")
trainFlags += " --emFac %d" % args.emFac
if args.forceEmProbs is not None:
trainFlags += " --forceEmProbs %s" % args.forceEmProbs
if args.iter is not None:
assert args.emStates is not None or args.initTransProbs is not None
trainFlags += " --iter %d" % args.iter
if args.initTransProbs is not None:
trainFlags += " --initTransProbs %s" % args.initTransProbs
if args.initEmProbs is not None:
trainFlags += " --initEmProbs %s" % args.initEmProbs
if args.fixEm is True:
trainFlags += " --fixEm"
if args.initStartProbs is not None:
trainFlags += " --initStartProbs %s" % args.initStartProbs
if args.fixStart is True:
trainFlags += " --fixStart"
if args.forceTransProbs is not None:
trainFlags += " --forceTransProbs %s" % args.forceTransProbs
if args.forceEmProbs is not None:
trainFlags += " --forceEmProbs %s" % args.forceEmProbs
if args.flatEm is True:
trainFlags += " --flatEm"
if args.emRandRange is not None:
trainFlags += " --emRandRange %s" % args.emRandRange
if args.segLen is not None:
trainFlags += " --segLen %d" % args.segLen
if args.seed is not None:
trainFlags += " --seed %d" % args.seed
if args.reps is not None:
trainFlags += " --reps %d" % args.reps
if args.numThreads is not None:
trainFlags += " --numThreads %d" % args.numThreads
if args.emThresh is not None:
trainFlags += " --emThresh %f" % args.emThresh
if args.saveAllReps is True:
trainFlags += " --saveAllReps"
if args.maxProb is True:
trainFlags += " --maxProb"
if args.transMatEpsilons is True:
trainFlags += " --transMatEpsilons"
if args.maxProbCut is not None:
trainFlags += " --maxProbCut %d" % args.maxProbCut
# write out command line for posteriorty's sake
if not os.path.exists(args.outputDir):
os.makedirs(args.outputDir)
cmdPath = os.path.join(args.outputDir, "teHmmBenchmark_cmd.txt")
cmdFile = open(cmdPath, "w")
cmdFile.write(" ".join(argv) + "\n")
cmdFile.close()
#todo: try to get timing for each command
commands = []
rows = dict()
for pn, pList in enumerate(subsetTrackList(trainingTrackList, sizeRange,
mandTracks)):
if len(pList) == len(trainingTrackList):
outDir = args.outputDir
else:
outDir = os.path.join(args.outputDir, "perm%d" % pn)
if not os.path.exists(outDir):
os.makedirs(outDir)
trainingTrackPath = os.path.join(outDir, "training_tracks.xml")
evalTrackPath = os.path.join(outDir, "eval_tracks.xml")
for maskTrack in trainingTrackList.getMaskTracks():
pList.addTrack(copy.deepcopy(maskTrack))
pList.saveXML(trainingTrackPath)
epList = TrackList()
for track in pList:
t = copy.deepcopy(evalTrackList.getTrackByName(track.getName()))
epList.addTrack(t)
for maskTrack in trainingTrackList.getMaskTracks():
epList.addTrack(copy.deepcopy(maskTrack))
epList.saveXML(evalTrackPath)
for inBed in args.inBeds:
base = os.path.basename(inBed)
truthBed = inBed
testBed = inBed
if args.cross is True:
truthBed = os.path.join(outDir,
os.path.splitext(base)[0] +
"_truth_temp.bed")
testBed = os.path.join(outDir,
os.path.splitext(base)[0] +
"_test_temp.bed")
splitBed(inBed, truthBed, testBed)
# train
if args.mod is not None:
modPath = args.mod
command = "ls %s" % modPath
else:
modPath = os.path.join(outDir,
os.path.splitext(base)[0] + ".mod")
command = "teHmmTrain.py %s %s %s %s %s" % (trainingTrackPath,
truthBed,
modPath,
logOps,
trainFlags)
if args.segment is True:
command += " --segment %s" % truthBed
# view
viewPath = os.path.join(outDir,
os.path.splitext(base)[0] + "_view.txt")
command += " && teHmmView.py %s > %s" % (modPath, viewPath)
# evaluate
numReps = 1
if args.reps is not None and args.saveAllReps is True:
numReps = args.reps
assert numReps > 0
missed = 0
# little hack to repeat evaluation for each training replicate
for repNum in xrange(-1, numReps-1):
if repNum == -1:
repSuffix = ""
else:
repSuffix = ".rep%d" % repNum
evalBed = os.path.join(outDir,
os.path.splitext(base)[0] + "_eval.bed" +
repSuffix)
hmmEvalInputBed = testBed
if args.eval is not None:
hmmEvalInputBed = args.eval
bicPath = os.path.join(outDir,
os.path.splitext(base)[0] + "_bic.txt" +
repSuffix)
command += " && teHmmEval.py %s %s %s --bed %s %s --bic %s" % (
evalTrackPath,
modPath + repSuffix,
hmmEvalInputBed,
evalBed,
logOps,
bicPath)
zin = True
if args.segment is True:
command += " --segment"
# fit
compTruth = testBed
if args.truth is not None:
compTruth = args.truth
compareInputBed = evalBed
if args.fit is True:
fitBed = os.path.join(outDir,
os.path.splitext(base)[0] + "_eval_fit.bed" +
repSuffix)
command += " && fitStateNames.py %s %s %s --tl %s" % (compTruth,
evalBed,
fitBed,
evalTrackPath)
if args.fitOpts is not None:
command += " " + args.fitOpts
compareInputBed = fitBed
# compare
compPath = os.path.join(outDir,
os.path.splitext(base)[0] + "_comp.txt" +
repSuffix)
command += " && compareBedStates.py %s %s --tl %s > %s" % (
compTruth,
compareInputBed,
evalTrackPath,
compPath)
# make table row
if repSuffix == "":
rowPath = os.path.join(outDir,
os.path.splitext(base)[0] + "_row.txt")
if inBed in rows:
rows[inBed].append(rowPath)
else:
rows[inBed] = [rowPath]
command += " && scrapeBenchmarkRow.py %s %s %s %s %s" % (
args.trainingTracksInfo,
trainingTrackPath,
evalBed,
compPath,
rowPath)
# remember command
inCmdPath = os.path.join(outDir,
os.path.splitext(base)[0] + "_cmd.txt")
inCmdFile = open(inCmdPath, "w")
inCmdFile.write(command + "\n")
inCmdFile.close()
commands.append(command)
runParallelShellCommands(commands, args.numProc)
writeTables(args.outputDir, rows)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Find candidate TSDs (exact forward matches) flanking given"
"BED intervals. Score is distance between TSD and bed interval.")
parser.add_argument("fastaSequence", help="DNA sequence in FASTA format")
parser.add_argument("inBed", help="BED file with TEs whose flanking regions "
"we wish to search")
parser.add_argument("outBed", help="BED file containing (only) output TSDs")
parser.add_argument("--min", help="Minimum length of a TSD",
default=4, type=int)
parser.add_argument("--max", help="Maximum length of a TSD",
default=6, type=int)
parser.add_argument("--all", help="Report all matches in region (as opposed"
" to only the nearest to the BED element which is the "
"default behaviour", action="store_true", default=False)
parser.add_argument("--maxScore", help="Only report matches with given "
"score or smaller. The score is definied as the "
"maximum distance between the (two) TSD intervals and "
"the query interval",
default=None, type=int)
parser.add_argument("--left", help="Number of bases immediately left of the "
"BED element to search for the left TSD",
default=7, type=int)
parser.add_argument("--right", help="Number of bases immediately right of "
"the BED element to search for the right TSD",
default=7, type=int)
parser.add_argument("--overlap", help="Number of bases overlapping the "
"BED element to include in search (so total space "
"on each side will be --left + overlap, and --right + "
"--overlap", default=3, type=int)
parser.add_argument("--leftName", help="Name of left TSDs in output Bed",
default="L_TSD")
parser.add_argument("--rightName", help="Name of right TSDs in output Bed",
default="R_TSD")
parser.add_argument("--id", help="Assign left/right pairs of TSDs a unique"
" matching ID", action="store_true", default=False)
parser.add_argument("--names", help="Only apply to bed interval whose "
"name is in (comma-separated) list. If not specified"
" then all intervals are processed", default=None)
parser.add_argument("--numProc", help="Number of jobs to run in parallel."
" (parallization done on different sequences in FASTA"
"file", type=int, default=1)
parser.add_argument("--sequences", help="Only process given sequences of input"
" FASTA file (comma-separated list).", default=None)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
assert os.path.exists(args.inBed)
assert os.path.exists(args.fastaSequence)
assert args.min <= args.max
args.nextId = 0
if args.sequences is not None:
args.sequences = set(args.sequences.split(","))
# read intervals from the bed file
logger.info("loading target intervals from %s" % args.inBed)
bedIntervals = readBedIntervals(args.inBed, ncol=4, sort=True)
if bedIntervals is None or len(bedIntervals) < 1:
raise RuntimeError("Could not read any intervals from %s" %
args.inBed)
if args.numProc > 1:
runParallel(args, bedIntervals)
return 0
tsds = findTsds(args, bedIntervals)
writeBedIntervals(tsds, args.outBed)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Produce a bed file of genome segments which are atomic"
" elements with resepect to the hmm. ie each segment emits a single"
" state. Mask tracks always cut. "
"Output intervals are assigned name 0 1 0 1 etc.")
parser.add_argument("tracksInfo",
help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("allBed", help="Bed file spanning entire genome")
parser.add_argument("outBed", help="Output segments")
parser.add_argument("--thresh",
help="Number of tracks that can change "
"before a new segment formed. Increasing this value"
" increases the expected lengths of output segments",
type=int,
default=1)
parser.add_argument("--cutTracks",
help="Create a new segment if something"
" changes in one of these tracks (as specified by "
"comman-separated list), overriding --thresh options"
" if necessary. For example, --cutTracks tsd,chaux"
" would invoke a new segment everytime the value at"
"either of these tracks changed",
default=None)
parser.add_argument("--cutUnscaled",
help="Cut on all unscaled (used as "
"a proxy for non-numeric) tracks",
default=False,
action="store_true")
parser.add_argument("--cutMultinomial",
help="Cut non-gaussian, non-binary"
" tracks everytime",
default=False,
action="store_true")
parser.add_argument("--cutNonGaussian",
help="Cut all but guassian tracks",
default=False,
action="store_true")
parser.add_argument("--comp",
help="Strategy for comparing columns for the "
"threshold cutoff. Options are [first, prev], where"
" first compares with first column of segment and "
"prev compares with column immediately left",
default="first")
parser.add_argument("--ignore",
help="Comma-separated list of tracks to "
"ignore (the FASTA DNA sequence would be a good "
"candidate",
default="sequence")
parser.add_argument("--maxLen",
help="Maximum length of a segment (<= 0 means"
" no max length applied",
type=int,
default=0)
parser.add_argument(
"--fixLen",
help="Just make segments of specifed fixed "
"length ignoring other parameters and logic (<= 0 means"
" no fixed length applied",
type=int,
default=0)
parser.add_argument("--stats",
help="Write some statistics to specified "
"file. Of the form <trackName> <Diff> <DiffPct> "
" where <Diff> is the number of times a track differs"
" between two consecutive segments, and <DiffPct> "
" is the average perecentage of all such differences "
"accounted for by the track",
default=None)
parser.add_argument(
"--delMask",
help="Entirely remove intervals from "
"mask tracks that are > given length (otherwise "
"they would just be ignored by HMM tools). The difference"
" here is that removed intervals will break contiguity.",
type=int,
default=None)
parser.add_argument(
"--chroms",
help="list of chromosomes, or regions, to run in parallel"
" (in BED format). input regions will be intersected with each line"
" in this file, and the result will correspsond to an individual job",
default=None)
parser.add_argument(
"--proc",
help="number of processes (use in conjunction with --chroms)",
type=int,
default=1)
parser.add_argument(
"--co",
help="count offset for segment labels. only used internally",
type=int,
default=0)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
if args.comp != "first" and args.comp != "prev":
raise RuntimeError("--comp must be either first or prev")
if args.chroms is not None:
# hack to allow chroms argument to chunk and rerun
parallelDispatch(argv, args)
cleanBedTool(tempBedToolPath)
return 0
# read query intervals from the bed file
tempFiles = []
if args.delMask is not None:
cutBed = cutOutMaskIntervals(args.allBed, args.delMask, sys.maxint,
args.tracksInfo)
if cutBed is not None:
tempFiles.append(cutBed)
args.allBed = cutBed
logger.info("loading segment region intervals from %s" % args.allBed)
mergedIntervals = getMergedBedIntervals(args.allBed, ncol=4)
if mergedIntervals is None or len(mergedIntervals) < 1:
raise RuntimeError("Could not read any intervals from %s" %
args.allBed)
# read the tracks, while intersecting them with the query intervals
logger.info("loading tracks %s" % args.tracksInfo)
trackData = TrackData()
trackData.loadTrackData(args.tracksInfo,
mergedIntervals,
treatMaskAsBinary=True)
# process the --cutTracks option
trackList = trackData.getTrackList()
cutList = np.zeros((len(trackList)), np.int)
if args.cutTracks is not None:
cutNames = args.cutTracks.split(",")
for name in cutNames:
track = trackList.getTrackByName(name)
if track is None:
raise RuntimeError("cutTrack %s not found" % name)
trackNo = track.getNumber()
assert trackNo < len(cutList)
cutList[trackNo] = 1
args.cutList = cutList
# make sure mask tracks count as cut tracks
for track in trackList:
if track.getDist() == 'mask':
args.cutList[track.getNumber()] = 1
# process the --ignore option
ignoreList = np.zeros((len(trackList)), np.int)
if args.ignore is not None:
ignoreNames = args.ignore.split(",")
for name in ignoreNames:
track = trackList.getTrackByName(name)
if track is None:
if name is not "sequence":
logger.warning("ignore track %s not found" % name)
continue
trackNo = track.getNumber()
assert trackNo < len(ignoreList)
ignoreList[trackNo] = 1
if args.cutList[trackNo] == 1:
raise RuntimeError("Same track (%s) cant be cut and ignored" %
name)
args.ignoreList = ignoreList
#process the --cutUnscaled option
if args.cutUnscaled is True:
for track in trackList:
trackNo = track.getNumber()
if track.scale is None and track.shift is None and\
track.logScale is None and\
args.ignoreList[trackNo] == 0:
assert trackNo < len(cutList)
cutList[trackNo] = 1
#process the --cutMultinomial option
if args.cutMultinomial is True:
for track in trackList:
trackNo = track.getNumber()
if track.dist == "multinomial" and\
args.ignoreList[trackNo] == 0:
assert trackNo < len(cutList)
cutList[trackNo] = 1
#process the --cutNonGaussian option
if args.cutNonGaussian is True:
for track in trackList:
trackNo = track.getNumber()
if track.dist != "gaussian" and\
args.ignoreList[trackNo] == 0:
assert trackNo < len(cutList)
cutList[trackNo] = 1
# segment the tracks
stats = dict()
segmentTracks(trackData, args, stats)
writeStats(trackData, args, stats)
if len(tempFiles) > 0:
runShellCommand("rm -f %s" % " ".join(tempFiles))
cleanBedTool(tempBedToolPath)
def main(argv=None):
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Combine a bunch of non-numeric BED tracks into"
" single file using fitStateNames.py to try to keep names "
"consistent. Idea is to be used as baseline to compare"
" hmm to (via base-by-base statistics, primarily, since"
" this procedure could induce some fragmentation)")
parser.add_argument("tracksXML", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("regionBed", help="BED file representing "
"target region (best if whole genome)")
parser.add_argument("outBed", help="Output bed")
parser.add_argument("--tracks", help="Comma-separated list of "
"track names to use. All tracks will be"
" used by default", default=None)
parser.add_argument("--outside", help="Name to give non-annotated"
"regions", default="Outside")
parser.add_argument("--fitThresh", help="Min map percentage (0,1)"
" in order to rename (see --qualThresh option"
"of fitStateNames.py", type=float,
default=0.5)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
inputTrackList = TrackList(args.tracksXML)
iter = 0
# get regionBed where all intervals are merged when possible
regionIntervals = getMergedBedIntervals(args.regionBed, sort=True)
tempRegionPath = getLocalTempPath("Temp", "_reg.bed")
tempRegionFile = open(tempRegionPath, "w")
for interval in regionIntervals:
tempRegionFile.write("\t".join([str(x) for x in interval]) + "\n")
tempRegionFile.close()
# accumulate tracks in temp file
tempOutPath = getLocalTempPath("Temp", "_out.bed")
for track in inputTrackList:
if track.shift is not None or track.scale is not None or\
track.logScale is not None or track.dist == "gaussian" or\
os.path.splitext(track.getPath())[1].lower() != ".bed":
logger.warning("Skipping numeric track %s" % track.getName())
elif args.tracks is None or track.getName() in args.tracks.split(","):
combineTrack(track, tempOutPath, tempRegionPath, iter, args)
iter += 1
# nothing got written, make everything outside
if iter == 0:
tempOutFile = open(tempOutPath, "w")
for interval in regionIntervals:
tempOutFile.write("%s\t%s\t%s\t%s\n" % (interval[0], interval[1],
interval[2], args.outside))
tempOutFile.close()
runShellCommand("mv %s %s" % (tempOutPath, args.outBed))
runShellCommand("rm -f %s" % (tempRegionPath))
cleanBedTool(tempBedToolPath)
def main(argv=None):
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description=" Thin wrapper of teHmmTrain.py and teHmmEval.py "
"to generate a table of Number-of-HMM-states VS BIC. Lower BIC"
" is better")
parser.add_argument("tracks", help="tracks xml used for training and eval")
parser.add_argument("trainingBeds", help="comma-separated list of training regions"
" (training region size will be a variable in output table). "
"if segmentation is activated, these must also be the "
"segmented beds...")
parser.add_argument("evalBed", help="eval region")
parser.add_argument("trainOpts", help="all teHmmTrain options in quotes")
parser.add_argument("evalOpts", help="all teHmmEval options in quotes")
parser.add_argument("states", help="comma separated-list of numbers of states"
" to try")
parser.add_argument("outDir", help="output directory")
parser.add_argument("--reps", help="number of replicates", type = int,
default=1)
parser.add_argument("--proc", help="maximum number of processors to use"
" in parallel", type = int, default = 1)
parser.add_argument("--resume", help="try not to rewrite existing files",
action="store_true", default=False)
parser.add_argument("--initTrans", help="the states argument is overridden"
" to specify a list of transition initialization files "
"instead of state numbers", action="store_true",
default=False)
parser.add_argument("--numReps", help="the states argument is overridden"
" to specifiy a list of replicate numbers (--reps)"
" arguments", action="store_true", default=False)
parser.add_argument("--numIter", help="the states argument is overridden"
" to specifiy a list of iteration counts (--iter)"
" arugments", action="store_true", default=False)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
if sum([int(i) for i in [args.initTrans, args.numReps, args.numIter]]) > 1:
raise RuntimeError("only one of {--initTrans, --numReps, --numIter} "
"can be used at a time")
if not os.path.isdir(args.outDir):
runShellCommand("mkdir %s" % args.outDir)
# get the sizes of the trianing beds
trainingSizes = []
trainingBeds = []
for tb in args.trainingBeds.split(","):
if len(tb) > 0:
trainingBeds.append(tb)
for bed in trainingBeds:
assert os.path.isfile(bed)
bedLen = 0
for interval in readBedIntervals(bed):
bedLen += interval[2] - interval[1]
trainingSizes.append(bedLen)
# make sure --bed not in teHmmEval options and --numStates not in train
# options
trainOpts = args.trainOpts.split()
if "--numStates" in args.trainOpts and not args.numReps and not args.numIter:
nsIdx = trainOpts.index("--numStates")
assert nsIdx < len(trainOpts) - 1
del trainOpts[nsIdx]
del trainOpts[nsIdx]
if "--initTransProbs" in args.trainOpts:
tpIdx = trainOpts.index("--initTransProbs")
assert tpIdx < len(trainOpts) - 1
del trainOpts[tpIdx]
del trianOpts[tpIdx]
trainProcs = 1
if "--numThreads" in args.trainOpts:
npIdx = trainOpts.index("--numThreads")
assert npIdx < len(trainOpts) - 1
trainProcs = int(trainOpts[npIdx + 1])
segOptIdx = -1
if "--segment" in args.trainOpts:
segIdx = trainOpts.index("--segment")
assert segIdx < len(trainOpts) - 1
segOptIdx = segIdx + 1
if args.numReps and "--reps" in args.trainOpts:
repsIdx = trainOpts.index("--reps")
assert repsIdx < len(trainOpts) - 1
del trainOpts[repsIdx]
del trainOpts[repsIdx]
if args.numIter and "--iter" in args.trainOpts:
iterIdx = trainOpts.index("--iter")
assert iterIdx < len(trainOpts) - 1
del trainOpts[iterIdx]
del trainOpts[iterIdx]
evalOpts = args.evalOpts.split()
if "--bed" in args.evalOpts:
bedIdx = evalOpts.index("--bed")
assert bedIdx < len(evalOpts) - 1
del evalOpts[bedIdx]
del evalOpts[bedIdx]
if "--bic" in args.evalOpts:
bicIdx = evalOpts.index("--bic")
assert bicIdx < len(evalOpts) - 1
del evalOpts[bicIdx]
del evalOpts[bicIdx]
# hack in support for --initTrans option by munging out model sizes
# from the text files
if args.initTrans is True:
transFiles = args.states.split(",")
states = []
for tf in transFiles:
stateSet = set()
with open(tf) as f:
for line in f:
toks = line.split()
print toks
if len(toks) > 1 and toks[0][0] != "#":
stateSet.add(toks[0])
stateSet.add(toks[1])
states.append(len(stateSet))
else:
states = args.states.split(",")
trainCmds = []
evalCmds = []
prevSize = -1
sameSizeCount = 0
for trainingSize, trainingBed in zip(trainingSizes, trainingBeds):
# hack to take into account we may have different inputs with same
# same size, so their corresponding results need unique filenames
if trainingSize == prevSize:
sameSizeCount += 1
else:
sameSizeCount = 0
prevSize = trainingSize
print prevSize, trainingSize, sameSizeCount
for numStates in states:
for rep in xrange(args.reps):
outMod = os.path.join(args.outDir, "hmm_%d.%d.%d.%d.mod" % (
trainingSize, sameSizeCount, int(numStates), int(rep)))
if segOptIdx != -1:
trainOpts[segOptIdx] = trainingBed
if args.initTrans is True:
statesOpt = "--initTransProbs %s" % transFiles[states.index(numStates)]
elif args.numIter is True:
# states argument overridden by iterations
statesOpt = "--iter %d" % int(numStates)
elif args.numReps is True:
# states argument overridden by reps
statesOpt = "--reps %d" % int(numStates)
else:
statesOpt = "--numStates %d" % int(numStates)
trainCmd = "teHmmTrain.py %s %s %s %s %s" % (
args.tracks, trainingBed, outMod, " ".join(trainOpts),
statesOpt)
if not args.resume or not os.path.isfile(outMod) or \
os.path.getsize(outMod) < 100:
trainCmds.append(trainCmd)
outBic = outMod.replace(".mod", ".bic")
outBed = outMod.replace(".mod", "_eval.bed")
evalCmd = "teHmmEval.py %s %s %s --bed %s --bic %s %s" % (
args.tracks, outMod, args.evalBed, outBed, outBic,
" ".join(evalOpts))
if not args.resume or not os.path.isfile(outBic) or \
os.path.getsize(outBic) < 2:
evalCmds.append(evalCmd)
# run the training
runParallelShellCommands(trainCmds, max(1, args.proc / trainProcs))
# run the eval
runParallelShellCommands(evalCmds, args.proc)
# make the table header
tableFile = open(os.path.join(args.outDir, "bictable.csv"), "w")
stateColName = "states"
if args.numIter is True:
statesColName = "iter"
elif args.numReps is True:
stateColName = "reps"
tableFile.write("trainFile, trainSize, %s, meanBic, minBic, maxBic" % stateColName)
for i in xrange(args.reps):
tableFile.write(", bic.%d" % i)
tableFile.write("\n")
# make the table body
prevSize = -1
sameSizeCount = 0
for (trainingSize,trainingBed) in zip(trainingSizes, trainingBeds):
# hack to take into account we may have different inputs with same
# same size, so their corresponding results need unique filenames
if trainingSize == prevSize:
sameSizeCount += 1
else:
sameSizeCount = 0
prevSize = trainingSize
for numStates in states:
bics = []
printBics = []
for rep in xrange(args.reps):
outMod = os.path.join(args.outDir, "hmm_%d.%d.%d.%d.mod" % (
trainingSize, sameSizeCount, int(numStates), int(rep)))
outBic = outMod.replace(".mod", ".bic")
try:
with open(outBic, "r") as obFile:
for line in obFile:
bic = float(line.split()[0])
break
bics.append(bic)
printBics.append(bic)
except:
logger.warning("Coudn't find bic %s" % outBic)
printBics.append("ERROR")
# write row
tableFile.write("%s, %d, %d" % (trainingBed, int(trainingSize), int(numStates)))
if len(bics) > 0:
tableFile.write(", %f, %f, %f" % (np.mean(bics), np.min(bics),
np.max(bics)))
else:
tableFile.write(", ERROR, ERROR, ERROR")
for pb in printBics:
tableFile.write(", %s" % pb)
tableFile.write("\n")
tableFile.close()
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description=
"fix up track names and sort alphabetically. easier to do here on xml than at end for pape\
r.")
parser.add_argument("tracksInfo",
help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("outTracksInfo",
help="Path to write modified tracks XML")
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
args.logOpString = "--logLevel %s" % getLogLevelString()
if args.logFile is not None:
args.logOpString += " --logFile %s" % args.logFile
nm = dict()
nm["hollister"] = "RM-RepBase-Hollister"
nm["chaux"] = "RM-RepBase-deLaChaux"
nm["repeat_modeler"] = "RM-RepeatModeler"
nm["repbase"] = "RM-RepBase"
nm["repet"] = "REPET"
nm["ltr_finder"] = "LTR_FINDER"
nm["ltr_harvest"] = "LTR_Harvest"
nm["ltr_termini"] = "lastz-Termini"
nm["lastz-Termini"] = "lastz-LTRTermini"
nm["tir_termini"] = "lastz-InvTermini"
nm["irf"] = "IRF"
nm["palindrome"] = "lastz-Palindrome"
nm["overlap"] = "lastz-Overlap"
nm["mitehunter"] = "MITE-Hunter"
nm["helitronscanner"] = "HelitronScanner"
nm["cov_80-"] = "lastz-SelfLowId"
nm["cov_80-90"] = "lastz-SelfMedId"
nm["cov_90+"] = "lastz-SelfHighId"
nm["left_peak_80-"] = "lastz-SelfPeakLeftLow"
nm["lastz-SelfLowLeftPeak"] = nm["left_peak_80-"]
nm["left_peak_80-90"] = "lastz-SelfPeakLeftMed"
nm["lastz-SelfMedLeftPeak"] = nm["left_peak_80-90"]
nm["left_peak_90+"] = "lastz-SelfPeakLeftHigh"
nm["lastz-SelfHighLeftPeak"] = nm["left_peak_90+"]
nm["right_peak_80-"] = "lastz-SelfPeakRightLow"
nm["lastz-SelfLowRightPeak"] = nm["right_peak_80-"]
nm["right_peak_80-90"] = "lastz-SelfPeakRightMed"
nm["lastz-SelfMedRightPeak"] = nm["right_peak_80-90"]
nm["right_peak_90+"] = "lastz-SelfPeakRightHigh"
nm["lastz-SelfHighRightPeak"] = nm["right_peak_90+"]
nm["cov_maxPId"] = "lastz-SelfPctMaxId"
nm["lastz-SelfMaxPctId"] = nm["cov_maxPId"]
nm["te_domains"] = "TE-Domains"
nm["fgenesh"] = "Genes"
nm["genes"] = nm["fgenesh"]
nm["refseq"] = nm["fgenesh"]
nm["mrna"] = "mRNA"
nm["srna"] = "sRNA"
nm["ortho_depth"] = "Alignment-Depth"
nm["orthology"] = nm["ortho_depth"]
nm["chain_depth"] = nm["ortho_depth"]
nm["alignment_depth"] = nm["ortho_depth"]
nm["gcpct"] = "GC"
nm["trf"] = "TRF"
nm["windowmasker"] = "WindowMasker"
nm["polyN"] = "Ns"
nm["phastcons_ce"] = "Conservation"
nm["phastcons"] = nm["phastcons_ce"]
nm["PhastCons"] = nm["phastcons_ce"]
nm["phyloP"] = nm["phastcons_ce"]
nm["phylop"] = nm["phastcons_ce"]
rtracks = dict()
rtracks["tantan"] = True
rtracks["polyA"] = True
rtracks["transposon_psi"] = True
rtracks["transposonpsi"] = True
rtracks["repbase_censor"] = True
rtracks["tsd"] = True
rtracks["repbase_default"] = True
rtracks["dustmasker"] = True
inTracks = TrackList(args.tracksInfo)
outTracks = TrackList()
outList = []
for track in itertools.chain(inTracks.trackList, inTracks.maskTrackList):
if not os.path.exists(track.path):
raise RuntimeError("Track DNE %s" % track.path)
if track.name not in rtracks:
if track.name in nm:
track.name = nm[track.name]
else:
logger.warning("Did not map track %s" % track.name)
outList.append(track)
else:
logger.warning("Deleted track %s" % track.name)
# sort the list
def sortComp(x):
lname = x.name.lower()
if x.name == "RM-RepeatModeler":
return "aaaaa" + lname
elif "RM" in x.name:
return "aaaa" + lname
elif "REPET" in x.name:
return "aaa" + lname
elif "softmask" in lname or "tigr" in lname or "te-domains" in lname:
return "aa" + lname
elif x.getDist == "mask":
return "zzzz" + lname
else:
return lname
outList = sorted(outList, key=lambda track: sortComp(track))
for track in outList:
outTracks.addTrack(track)
outTracks.saveXML(args.outTracksInfo)
cleanBedTool(tempBedToolPath)
def main(argv=None):
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Helper script to rank a list of tracks based on how well "
"they improve some measure of HMM accuracy, by wrapping "
"teHmmBenchmark.py")
parser.add_argument("tracks", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("training", help="BED Training regions"
"teHmmTrain.py")
parser.add_argument("truth", help="BED Truth used for scoring")
parser.add_argument("states", help="States (in truth) to use for"
" average F1 score (comma-separated")
parser.add_argument("outDir", help="Directory to place all results")
parser.add_argument("--benchOpts", help="Options to pass to "
"teHmmBenchmark.py (wrap in double quotes)",
default="")
parser.add_argument("--startTracks", help="comma-separated list of "
"tracks to start off with", default = None)
parser.add_argument("--segOpts", help="Options to pass to "
"segmentTracks.py (wrap in double quotes)",
default="--comp first --thresh 1 --cutUnscaled")
parser.add_argument("--fullSegment", help="Only use segmentation"
" based on entire track list for each iteration"
" rather than compute segmentation each time (as"
" done by default)", action="store_true",
default=False)
parser.add_argument("--bic", help="rank by BIC instead of score "
" (both always present in output table though)",
action="store_true", default=False)
parser.add_argument("--base", help="use base-level F1 instead of "
"interval-level", default=False, action="store_true")
parser.add_argument("--naive", help="rank by \"naive\" score",
action="store_true", default=False)
parser.add_argument("--doNaive", help="compute naive stats. will be "
"turned on by default if --naive is used", default=False,
action="store_true")
parser.add_argument("--segTracks", help="tracks XML to use for segmentation"
" (by default will be same as tracks))", default=None)
parser.add_argument("--recallSkew", help="when computing f1, multiply recall"
" by this number (hack to favour larger recall)",
default=1., type=float)
parser.add_argument("--score", help="accuracy score to use from "
"{f1, prec, rec}", default="f1")
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
# make sure no no-no options in benchOpts
if "--eval" in args.benchOpts or "--truth" in args.benchOpts:
raise RuntimeError("--eval and --truth cannot be passed through to "
"teHmmBenchmark.py as they are generated from "
"<training> and <truth> args from this script")
# don't want to keep track of extra logic required for not segmenting
if "--segment" not in args.benchOpts:
args.benchOpts += " --segment"
logger.warning("Adding --segment to teHmmBenchmark.py options")
if args.bic is True and args.naive is True:
raise RuntimeError("--bic and --naive are mutually incompatible")
if args.naive is True:
args.doNaive = True
if args.segTracks is None:
args.segTracks = args.tracks
if not os.path.exists(args.outDir):
os.makedirs(args.outDir)
greedyRank(args)
def main(argv=None):
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description=" Thin wrapper of teHmmTrain.py and teHmmEval.py "
"to generate a table of Number-of-HMM-states VS BIC. Lower BIC"
" is better")
parser.add_argument("tracks", help="tracks xml used for training and eval")
parser.add_argument(
"trainingBeds",
help="comma-separated list of training regions"
" (training region size will be a variable in output table). "
"if segmentation is activated, these must also be the "
"segmented beds...")
parser.add_argument("evalBed", help="eval region")
parser.add_argument("trainOpts", help="all teHmmTrain options in quotes")
parser.add_argument("evalOpts", help="all teHmmEval options in quotes")
parser.add_argument("states",
help="comma separated-list of numbers of states"
" to try")
parser.add_argument("outDir", help="output directory")
parser.add_argument("--reps",
help="number of replicates",
type=int,
default=1)
parser.add_argument("--proc",
help="maximum number of processors to use"
" in parallel",
type=int,
default=1)
parser.add_argument("--resume",
help="try not to rewrite existing files",
action="store_true",
default=False)
parser.add_argument(
"--initTrans",
help="the states argument is overridden"
" to specify a list of transition initialization files "
"instead of state numbers",
action="store_true",
default=False)
parser.add_argument("--numReps",
help="the states argument is overridden"
" to specifiy a list of replicate numbers (--reps)"
" arguments",
action="store_true",
default=False)
parser.add_argument("--numIter",
help="the states argument is overridden"
" to specifiy a list of iteration counts (--iter)"
" arugments",
action="store_true",
default=False)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
if sum([int(i) for i in [args.initTrans, args.numReps, args.numIter]]) > 1:
raise RuntimeError("only one of {--initTrans, --numReps, --numIter} "
"can be used at a time")
if not os.path.isdir(args.outDir):
runShellCommand("mkdir %s" % args.outDir)
# get the sizes of the trianing beds
trainingSizes = []
trainingBeds = []
for tb in args.trainingBeds.split(","):
if len(tb) > 0:
trainingBeds.append(tb)
for bed in trainingBeds:
assert os.path.isfile(bed)
bedLen = 0
for interval in readBedIntervals(bed):
bedLen += interval[2] - interval[1]
trainingSizes.append(bedLen)
# make sure --bed not in teHmmEval options and --numStates not in train
# options
trainOpts = args.trainOpts.split()
if "--numStates" in args.trainOpts and not args.numReps and not args.numIter:
nsIdx = trainOpts.index("--numStates")
assert nsIdx < len(trainOpts) - 1
del trainOpts[nsIdx]
del trainOpts[nsIdx]
if "--initTransProbs" in args.trainOpts:
tpIdx = trainOpts.index("--initTransProbs")
assert tpIdx < len(trainOpts) - 1
del trainOpts[tpIdx]
del trianOpts[tpIdx]
trainProcs = 1
if "--numThreads" in args.trainOpts:
npIdx = trainOpts.index("--numThreads")
assert npIdx < len(trainOpts) - 1
trainProcs = int(trainOpts[npIdx + 1])
segOptIdx = -1
if "--segment" in args.trainOpts:
segIdx = trainOpts.index("--segment")
assert segIdx < len(trainOpts) - 1
segOptIdx = segIdx + 1
if args.numReps and "--reps" in args.trainOpts:
repsIdx = trainOpts.index("--reps")
assert repsIdx < len(trainOpts) - 1
del trainOpts[repsIdx]
del trainOpts[repsIdx]
if args.numIter and "--iter" in args.trainOpts:
iterIdx = trainOpts.index("--iter")
assert iterIdx < len(trainOpts) - 1
del trainOpts[iterIdx]
del trainOpts[iterIdx]
evalOpts = args.evalOpts.split()
if "--bed" in args.evalOpts:
bedIdx = evalOpts.index("--bed")
assert bedIdx < len(evalOpts) - 1
del evalOpts[bedIdx]
del evalOpts[bedIdx]
if "--bic" in args.evalOpts:
bicIdx = evalOpts.index("--bic")
assert bicIdx < len(evalOpts) - 1
del evalOpts[bicIdx]
del evalOpts[bicIdx]
# hack in support for --initTrans option by munging out model sizes
# from the text files
if args.initTrans is True:
transFiles = args.states.split(",")
states = []
for tf in transFiles:
stateSet = set()
with open(tf) as f:
for line in f:
toks = line.split()
print toks
if len(toks) > 1 and toks[0][0] != "#":
stateSet.add(toks[0])
stateSet.add(toks[1])
states.append(len(stateSet))
else:
states = args.states.split(",")
trainCmds = []
evalCmds = []
prevSize = -1
sameSizeCount = 0
for trainingSize, trainingBed in zip(trainingSizes, trainingBeds):
# hack to take into account we may have different inputs with same
# same size, so their corresponding results need unique filenames
if trainingSize == prevSize:
sameSizeCount += 1
else:
sameSizeCount = 0
prevSize = trainingSize
print prevSize, trainingSize, sameSizeCount
for numStates in states:
for rep in xrange(args.reps):
outMod = os.path.join(
args.outDir, "hmm_%d.%d.%d.%d.mod" %
(trainingSize, sameSizeCount, int(numStates), int(rep)))
if segOptIdx != -1:
trainOpts[segOptIdx] = trainingBed
if args.initTrans is True:
statesOpt = "--initTransProbs %s" % transFiles[
states.index(numStates)]
elif args.numIter is True:
# states argument overridden by iterations
statesOpt = "--iter %d" % int(numStates)
elif args.numReps is True:
# states argument overridden by reps
statesOpt = "--reps %d" % int(numStates)
else:
statesOpt = "--numStates %d" % int(numStates)
trainCmd = "teHmmTrain.py %s %s %s %s %s" % (
args.tracks, trainingBed, outMod, " ".join(trainOpts),
statesOpt)
if not args.resume or not os.path.isfile(outMod) or \
os.path.getsize(outMod) < 100:
trainCmds.append(trainCmd)
outBic = outMod.replace(".mod", ".bic")
outBed = outMod.replace(".mod", "_eval.bed")
evalCmd = "teHmmEval.py %s %s %s --bed %s --bic %s %s" % (
args.tracks, outMod, args.evalBed, outBed, outBic,
" ".join(evalOpts))
if not args.resume or not os.path.isfile(outBic) or \
os.path.getsize(outBic) < 2:
evalCmds.append(evalCmd)
# run the training
runParallelShellCommands(trainCmds, max(1, args.proc / trainProcs))
# run the eval
runParallelShellCommands(evalCmds, args.proc)
# make the table header
tableFile = open(os.path.join(args.outDir, "bictable.csv"), "w")
stateColName = "states"
if args.numIter is True:
statesColName = "iter"
elif args.numReps is True:
stateColName = "reps"
tableFile.write("trainFile, trainSize, %s, meanBic, minBic, maxBic" %
stateColName)
for i in xrange(args.reps):
tableFile.write(", bic.%d" % i)
tableFile.write("\n")
# make the table body
prevSize = -1
sameSizeCount = 0
for (trainingSize, trainingBed) in zip(trainingSizes, trainingBeds):
# hack to take into account we may have different inputs with same
# same size, so their corresponding results need unique filenames
if trainingSize == prevSize:
sameSizeCount += 1
else:
sameSizeCount = 0
prevSize = trainingSize
for numStates in states:
bics = []
printBics = []
for rep in xrange(args.reps):
outMod = os.path.join(
args.outDir, "hmm_%d.%d.%d.%d.mod" %
(trainingSize, sameSizeCount, int(numStates), int(rep)))
outBic = outMod.replace(".mod", ".bic")
try:
with open(outBic, "r") as obFile:
for line in obFile:
bic = float(line.split()[0])
break
bics.append(bic)
printBics.append(bic)
except:
logger.warning("Coudn't find bic %s" % outBic)
printBics.append("ERROR")
# write row
tableFile.write("%s, %d, %d" %
(trainingBed, int(trainingSize), int(numStates)))
if len(bics) > 0:
tableFile.write(", %f, %f, %f" %
(np.mean(bics), np.min(bics), np.max(bics)))
else:
tableFile.write(", ERROR, ERROR, ERROR")
for pb in printBics:
tableFile.write(", %s" % pb)
tableFile.write("\n")
tableFile.close()
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Add a TSD track (or modify an existing one) based on a "
"given track")
parser.add_argument("tracksInfo",
help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("tsdTrackDir",
help="Directory to write cleaned BED"
" tracks to")
parser.add_argument("outTracksInfo",
help="Path to write modified tracks XML"
" to.")
parser.add_argument("inputTrack", help="Name of track to createTSDs from")
parser.add_argument("fastaTrack", help="Name of track for fasta sequence")
parser.add_argument("outputTrack",
help="Name of tsd track to add. Will"
" overwrite if it already exists (or append with"
" --append option)")
parser.add_argument("--append",
help="Add onto existing TSD track if exists",
default=False,
action="store_true")
parser.add_argument("--inPath",
help="Use given file instead of inputTrack"
" path to generate TSD",
default=None)
############ TSDFINDER OPTIONS ##############
parser.add_argument("--min",
help="Minimum length of a TSD",
default=None,
type=int)
parser.add_argument("--max",
help="Maximum length of a TSD",
default=None,
type=int)
parser.add_argument("--all",
help="Report all matches in region (as opposed"
" to only the nearest to the BED element which is the "
"default behaviour",
action="store_true",
default=False)
parser.add_argument("--maxScore",
help="Only report matches with given "
"score or smaller. The score is definied as the "
"maximum distance between the (two) TSD intervals and "
"the query interval",
default=None,
type=int)
parser.add_argument("--left",
help="Number of bases immediately left of the "
"BED element to search for the left TSD",
default=None,
type=int)
parser.add_argument("--right",
help="Number of bases immediately right of "
"the BED element to search for the right TSD",
default=None,
type=int)
parser.add_argument("--overlap",
help="Number of bases overlapping the "
"BED element to include in search (so total space "
"on each side will be --left + overlap, and --right + "
"--overlap",
default=None,
type=int)
parser.add_argument("--leftName",
help="Name of left TSDs in output Bed",
default=None)
parser.add_argument("--rightName",
help="Name of right TSDs in output Bed",
default=None)
parser.add_argument("--id",
help="Assign left/right pairs of TSDs a unique"
" matching ID",
action="store_true",
default=False)
parser.add_argument("--names",
help="Only apply to bed interval whose "
"name is in (comma-separated) list. If not specified"
" then all intervals are processed",
default=None)
parser.add_argument("--numProc",
help="Number of jobs to run in parallel."
" (parallization done on different sequences in FASTA"
"file",
type=int,
default=1)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
# copy out all options for call to tsd finder
args.tsdFinderOptions = "--logLevel %s" % getLogLevelString()
if args.logFile is not None:
args.tsdFinderOptions += " --logFile %s" % args.logFile
for option in [
"min", "max", "all", "maxScore", "left", "right", "overlap",
"leftName", "rightName", "id", "names", "numProc"
]:
val = getattr(args, option)
if val is True:
args.tsdFinderOptions += " --%s" % option
elif val is not None and val is not False:
args.tsdFinderOptions += " --%s %s" % (option, val)
try:
os.makedirs(args.tsdTrackDir)
except:
pass
if not os.path.isdir(args.tsdTrackDir):
raise RuntimeError("Unable to find or create tsdTrack dir %s" %
args.tsdTrackDir)
trackList = TrackList(args.tracksInfo)
outTrackList = copy.deepcopy(trackList)
inputTrack = trackList.getTrackByName(args.inputTrack)
if inputTrack is None:
raise RuntimeError("Track %s not found" % args.inputTrack)
if args.inPath is not None:
assert os.path.isfile(args.inPath)
inputTrack.setPath(args.inPath)
inTrackExt = os.path.splitext(inputTrack.getPath())[1].lower()
if inTrackExt != ".bb" and inTrackExt != ".bed":
raise RuntimeError("Track %s has non-bed extension %s" %
(args.inputTrack, inTrackExt))
fastaTrack = trackList.getTrackByName(args.fastaTrack)
if fastaTrack is None:
raise RuntimeError("Fasta Track %s not found" % args.fastaTrack)
faTrackExt = os.path.splitext(fastaTrack.getPath())[1].lower()
if faTrackExt[:3] != ".fa":
raise RuntimeError("Fasta Track %s has non-fasta extension %s" %
(args.fastaTrack, faTrackExt))
tsdTrack = outTrackList.getTrackByName(args.outputTrack)
if tsdTrack is None:
if args.append is True:
raise RuntimeError("TSD track %s not found. Cannot append" %
(args.outputTrack))
tsdTrack = Track()
tsdTrack.name = args.outputTrack
tsdTrack.path = os.path.join(
args.tsdTrackDir,
args.inputTrack + "_" + args.outputTrack + ".bed")
runTsdFinder(fastaTrack.getPath(), inputTrack.getPath(),
tsdTrack.getPath(), args)
if outTrackList.getTrackByName(tsdTrack.getName()) is None:
outTrackList.addTrack(tsdTrack)
outTrackList.saveXML(args.outTracksInfo)
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Produce a bed file of genome segments which are atomic"
" elements with resepect to the hmm. ie each segment emits a single"
" state. Mask tracks always cut. "
"Output intervals are assigned name 0 1 0 1 etc.")
parser.add_argument("tracksInfo", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("allBed", help="Bed file spanning entire genome")
parser.add_argument("outBed", help="Output segments")
parser.add_argument("--thresh", help="Number of tracks that can change "
"before a new segment formed. Increasing this value"
" increases the expected lengths of output segments",
type=int, default=1)
parser.add_argument("--cutTracks", help="Create a new segment if something"
" changes in one of these tracks (as specified by "
"comman-separated list), overriding --thresh options"
" if necessary. For example, --cutTracks tsd,chaux"
" would invoke a new segment everytime the value at"
"either of these tracks changed", default=None)
parser.add_argument("--cutUnscaled", help="Cut on all unscaled (used as "
"a proxy for non-numeric) tracks", default=False,
action="store_true")
parser.add_argument("--cutMultinomial", help="Cut non-gaussian, non-binary"
" tracks everytime", default=False, action="store_true")
parser.add_argument("--cutNonGaussian", help="Cut all but guassian tracks",
default=False, action="store_true")
parser.add_argument("--comp", help="Strategy for comparing columns for the "
"threshold cutoff. Options are [first, prev], where"
" first compares with first column of segment and "
"prev compares with column immediately left",
default="first")
parser.add_argument("--ignore", help="Comma-separated list of tracks to "
"ignore (the FASTA DNA sequence would be a good "
"candidate", default="sequence")
parser.add_argument("--maxLen", help="Maximum length of a segment (<= 0 means"
" no max length applied",
type=int, default=0)
parser.add_argument("--fixLen", help="Just make segments of specifed fixed "
"length ignoring other parameters and logic (<= 0 means"
" no fixed length applied",
type=int, default=0)
parser.add_argument("--stats", help="Write some statistics to specified "
"file. Of the form <trackName> <Diff> <DiffPct> "
" where <Diff> is the number of times a track differs"
" between two consecutive segments, and <DiffPct> "
" is the average perecentage of all such differences "
"accounted for by the track", default=None)
parser.add_argument("--delMask", help="Entirely remove intervals from "
"mask tracks that are > given length (otherwise "
"they would just be ignored by HMM tools). The difference"
" here is that removed intervals will break contiguity.",
type=int, default=None)
parser.add_argument("--chroms", help="list of chromosomes, or regions, to run in parallel"
" (in BED format). input regions will be intersected with each line"
" in this file, and the result will correspsond to an individual job",
default=None)
parser.add_argument("--proc", help="number of processes (use in conjunction with --chroms)",
type=int, default=1)
parser.add_argument("--co", help="count offset for segment labels. only used internally",
type=int, default=0)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
if args.comp != "first" and args.comp != "prev":
raise RuntimeError("--comp must be either first or prev")
if args.chroms is not None:
# hack to allow chroms argument to chunk and rerun
parallelDispatch(argv, args)
cleanBedTool(tempBedToolPath)
return 0
# read query intervals from the bed file
tempFiles = []
if args.delMask is not None:
cutBed = cutOutMaskIntervals(args.allBed, args.delMask, sys.maxint,
args.tracksInfo)
if cutBed is not None:
tempFiles.append(cutBed)
args.allBed = cutBed
logger.info("loading segment region intervals from %s" % args.allBed)
mergedIntervals = getMergedBedIntervals(args.allBed, ncol=4)
if mergedIntervals is None or len(mergedIntervals) < 1:
raise RuntimeError("Could not read any intervals from %s" %
args.allBed)
# read the tracks, while intersecting them with the query intervals
logger.info("loading tracks %s" % args.tracksInfo)
trackData = TrackData()
trackData.loadTrackData(args.tracksInfo, mergedIntervals,
treatMaskAsBinary=True)
# process the --cutTracks option
trackList = trackData.getTrackList()
cutList = np.zeros((len(trackList)), np.int)
if args.cutTracks is not None:
cutNames = args.cutTracks.split(",")
for name in cutNames:
track = trackList.getTrackByName(name)
if track is None:
raise RuntimeError("cutTrack %s not found" % name)
trackNo = track.getNumber()
assert trackNo < len(cutList)
cutList[trackNo] = 1
args.cutList = cutList
# make sure mask tracks count as cut tracks
for track in trackList:
if track.getDist() == 'mask':
args.cutList[track.getNumber()] = 1
# process the --ignore option
ignoreList = np.zeros((len(trackList)), np.int)
if args.ignore is not None:
ignoreNames = args.ignore.split(",")
for name in ignoreNames:
track = trackList.getTrackByName(name)
if track is None:
if name is not "sequence":
logger.warning("ignore track %s not found" % name)
continue
trackNo = track.getNumber()
assert trackNo < len(ignoreList)
ignoreList[trackNo] = 1
if args.cutList[trackNo] == 1:
raise RuntimeError("Same track (%s) cant be cut and ignored" %
name)
args.ignoreList = ignoreList
#process the --cutUnscaled option
if args.cutUnscaled is True:
for track in trackList:
trackNo = track.getNumber()
if track.scale is None and track.shift is None and\
track.logScale is None and\
args.ignoreList[trackNo] == 0:
assert trackNo < len(cutList)
cutList[trackNo] = 1
#process the --cutMultinomial option
if args.cutMultinomial is True:
for track in trackList:
trackNo = track.getNumber()
if track.dist == "multinomial" and\
args.ignoreList[trackNo] == 0:
assert trackNo < len(cutList)
cutList[trackNo] = 1
#process the --cutNonGaussian option
if args.cutNonGaussian is True:
for track in trackList:
trackNo = track.getNumber()
if track.dist != "gaussian" and\
args.ignoreList[trackNo] == 0:
assert trackNo < len(cutList)
cutList[trackNo] = 1
# segment the tracks
stats = dict()
segmentTracks(trackData, args, stats)
writeStats(trackData, args, stats)
if len(tempFiles) > 0:
runShellCommand("rm -f %s" % " ".join(tempFiles))
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Make some tables of statistics from a BED file. All"
" output will be written in one big CSV table to be viewed in a "
"spreadsheet.")
parser.add_argument("inBed", help="Input bed file")
parser.add_argument("outCsv", help="Path to write output in CSV format")
parser.add_argument("--ignore", help="Comma-separated list of names"
" to ignore", default="")
parser.add_argument("--numBins", help="Number of (linear) bins for "
"histograms", type=int, default=10)
parser.add_argument("--logHist", help="Apply log-transform to data for "
"histogram", action="store_true", default=False)
parser.add_argument("--histRange", help="Histogram range as comma-"
"separated pair of numbers", default=None)
parser.add_argument("--noHist", help="skip hisograms", action="store_true",
default=False)
parser.add_argument("--noScore", help="Just do length stats",
action="store_true", default=False)
parser.add_argument("--noLen", help="Just do score stats",
action="store_true", default=False)
parser.add_argument("--nearness", help="Compute nearness stats (instead "
"of normal stats) of input bed with given BED. Output"
" will be a BED instead of CSV, with nearness in the "
"score position", default=None)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
if args.histRange is not None:
args.histRange = args.histRange.split(",")
assert len(args.histRange) == 2
args.histRange = int(args.histRange[0]), int(args.histRange[1])
outFile = open(args.outCsv, "w")
args.ignoreSet = set(args.ignore.split(","))
intervals = readBedIntervals(args.inBed, ncol = 5, sort = args.nearness is not None)
csvStats = ""
# nearness stats
if args.nearness is not None:
args.noScore = True
csvStats = makeNearnessBED(intervals, args)
# length stats
elif args.noLen is False:
csvStats = makeCSV(intervals, args, lambda x : int(x[2])-int(x[1]),
"Length")
# score stats
try:
if args.noScore is False:
csvStats += "\n" + makeCSV(intervals, args, lambda x : float(x[4]),
"Score")
csvStats += "\n" + makeCSV(intervals, args, lambda x : float(x[4]) * (
float(x[2]) - float(x[1])), "Score*Length")
except Exception as e:
logger.warning("Couldn't make score stats because %s" % str(e))
outFile.write(csvStats)
outFile.write("\n")
outFile.close()
cleanBedTool(tempBedToolPath)
def main(argv=None):
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Write track data into ASCII dump. Row i corresponds"
" to the ith position found when scanning query BED IN SORTED ORDER."
"Column j corresponds to the jth track in the XML file. --map option"
" used to write internal integer format used by HMM. Unobserved values"
" written as \"None\" if default attribute not specified or track not"
" binary. Rounding can occur if scaling parameters present.\n\n"
"IMPORTANT: values stored in 8bit integers internally. Any track with"
" more than 256 different values will get clamped (with a warning)")
parser.add_argument("tracks", help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("query", help="BED region(s) to dump. SCANNED IN"
" SORTED ORDER")
parser.add_argument("output", help="Path of file to write output to")
parser.add_argument("--map", help="Apply name mapping, including"
" transformation specified in scale, logScale"
", etc. attributes, that HMM uses internally"
". Important to note that resulting integers"
" are just unique IDs. ID_1 > ID_2 does not"
" mean anything", action="store_true",
default=False)
parser.add_argument("--segment", help="Treat each interval in query"
" as a single segment (ie with only one data point)"
". In this case, query should probably have been"
" generated with segmentTracks.py",
action="store_true",
default=False)
parser.add_argument("--noPos", help="Do not print genomic position"
" (first 2 columnts)", action="store_true",
default=False)
parser.add_argument("--noMask", help="Ignore mask tracks",
default=False, action="store_true")
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
# make sure output writeable
outFile = open(args.output, "w")
# need to remember to fix this, disable as precaution for now
assert args.noMask is True or args.segment is False
# read query intervals from the bed file
logger.info("loading query intervals from %s" % args.query)
mergedIntervals = getMergedBedIntervals(args.query, ncol=3)
if mergedIntervals is None or len(mergedIntervals) < 1:
raise RuntimeError("Could not read any intervals from %s" %
args.query)
# read the segment intervals from the (same) bed file
segIntervals = None
if args.segment is True:
logger.info("loading segment intervals from %s" % args.query)
segIntervals = readBedIntervals(args.query, sort=True)
# read all data from track xml
logger.info("loading tracks %s" % args.tracks)
trackData = TrackData()
trackData.loadTrackData(args.tracks, mergedIntervals,
segmentIntervals=segIntervals,
applyMasking = not args.noMask)
# dump the data to output
dumpTrackData(trackData, outFile, args.map, not args.noPos)
outFile.close()
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Generate HMM-usable tracklist from raw tracklist. EX "
"used to transform mustang_alyrata_tracks.xml -> "
"mustang_alyrata_clean.xml. Runs cleanRM.py cleanLtrFinder.py and "
" cleanTermini.py and addTsdTrack.py and setTrackScaling.py (also runs "
" removeBedOverlaps.py before each of the clean scripts)")
parser.add_argument("tracksInfo",
help="Path of Tracks Info file "
"containing paths to genome annotation tracks")
parser.add_argument("allBed", help="Bed file spanning entire genome")
parser.add_argument("cleanTrackPath",
help="Directory to write cleaned BED"
" tracks to")
parser.add_argument("outTracksInfo",
help="Path to write modified tracks XML"
" to.")
parser.add_argument("--numBins",
help="Maximum number of bins after scaling",
default=10,
type=int)
parser.add_argument("--scaleTracks",
help="Comma-separated list of tracks "
"to process for scaling. If not set, all"
" tracks listed as having a multinomial distribution"
" (since this is the default value, this includes "
"tracks with no distribution attribute) or gaussian "
"distribution will be processed.",
default=None)
parser.add_argument("--skipScale",
help="Comma-separated list of tracks to "
"skip for scaling.",
default=None)
parser.add_argument("--ltr_termini",
help="Name of termini track (appy tsd)",
default="ltr_termini")
parser.add_argument("--repeat_modeler",
help="Name of repeat_modeler track (appy tsd)",
default="repeat_modeler")
parser.add_argument("--sequence",
help="Name of fasta sequence track",
default="sequence")
parser.add_argument(
"--tsd",
help="Name of tsd track to generate (appy cleanTermini.py)",
default="tsd")
parser.add_argument(
"--tir",
help="Name of tir_termini track (appy cleanTermini.py)",
default="tir_termini")
parser.add_argument("--noScale",
help="Dont do any scaling",
default=False,
action="store_true")
parser.add_argument("--noTsd",
help="Dont generate TSD track. NOTE:"
" TSD track is hardcoded to be generated from "
"termini and (non-LTR elements of ) chaux",
default=False,
action="store_true")
parser.add_argument("--numProc",
help="Number of processes to use for tsdFinder.py",
default=1,
type=int)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
tempBedToolPath = initBedTool()
args.logOpString = "--logLevel %s" % getLogLevelString()
if args.logFile is not None:
args.logOpString += " --logFile %s" % args.logFile
try:
os.makedirs(args.cleanTrackPath)
except:
pass
if not os.path.isdir(args.cleanTrackPath):
raise RuntimeError("Unable to find or create cleanTrack dir %s" %
args.cleanTrackPath)
tempTracksInfo = getLocalTempPath("Temp_mustang_alyrata_clean", "xml")
runCleaning(args, tempTracksInfo)
assert os.path.isfile(tempTracksInfo)
runTsd(args, tempTracksInfo)
runScaling(args, tempTracksInfo)
runShellCommand("rm -f %s" % tempTracksInfo)
cleanBedTool(tempBedToolPath)
def main(argv=None):
if argv is None:
argv = sys.argv
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Find candidate TSDs (exact forward matches) flanking given"
"BED intervals. Score is distance between TSD and bed interval.")
parser.add_argument("fastaSequence", help="DNA sequence in FASTA format")
parser.add_argument("inBed",
help="BED file with TEs whose flanking regions "
"we wish to search")
parser.add_argument("outBed",
help="BED file containing (only) output TSDs")
parser.add_argument("--min",
help="Minimum length of a TSD",
default=4,
type=int)
parser.add_argument("--max",
help="Maximum length of a TSD",
default=6,
type=int)
parser.add_argument("--all",
help="Report all matches in region (as opposed"
" to only the nearest to the BED element which is the "
"default behaviour",
action="store_true",
default=False)
parser.add_argument("--maxScore",
help="Only report matches with given "
"score or smaller. The score is definied as the "
"maximum distance between the (two) TSD intervals and "
"the query interval",
default=None,
type=int)
parser.add_argument("--left",
help="Number of bases immediately left of the "
"BED element to search for the left TSD",
default=7,
type=int)
parser.add_argument("--right",
help="Number of bases immediately right of "
"the BED element to search for the right TSD",
default=7,
type=int)
parser.add_argument("--overlap",
help="Number of bases overlapping the "
"BED element to include in search (so total space "
"on each side will be --left + overlap, and --right + "
"--overlap",
default=3,
type=int)
parser.add_argument("--leftName",
help="Name of left TSDs in output Bed",
default="L_TSD")
parser.add_argument("--rightName",
help="Name of right TSDs in output Bed",
default="R_TSD")
parser.add_argument("--id",
help="Assign left/right pairs of TSDs a unique"
" matching ID",
action="store_true",
default=False)
parser.add_argument("--names",
help="Only apply to bed interval whose "
"name is in (comma-separated) list. If not specified"
" then all intervals are processed",
default=None)
parser.add_argument("--numProc",
help="Number of jobs to run in parallel."
" (parallization done on different sequences in FASTA"
"file",
type=int,
default=1)
parser.add_argument("--sequences",
help="Only process given sequences of input"
" FASTA file (comma-separated list).",
default=None)
addLoggingOptions(parser)
args = parser.parse_args()
setLoggingFromOptions(args)
assert os.path.exists(args.inBed)
assert os.path.exists(args.fastaSequence)
assert args.min <= args.max
args.nextId = 0
if args.sequences is not None:
args.sequences = set(args.sequences.split(","))
# read intervals from the bed file
logger.info("loading target intervals from %s" % args.inBed)
bedIntervals = readBedIntervals(args.inBed, ncol=4, sort=True)
if bedIntervals is None or len(bedIntervals) < 1:
raise RuntimeError("Could not read any intervals from %s" % args.inBed)
if args.numProc > 1:
runParallel(args, bedIntervals)
return 0
tsds = findTsds(args, bedIntervals)
writeBedIntervals(tsds, args.outBed)