def load_deepblue_files(regionsFileName, scoreFileName):
deepBlueFiles = []
for idx, fname in enumerate(scoreFileName):
if db.isDeepBlue(fname):
deepBlueFiles.append([fname, idx])
if len(deepBlueFiles) > 0:
sys.stderr.write(
"Preloading the following deepBlue files: {}\n".format(",".join(
[x[0] for x in deepBlueFiles])))
regs = db.makeRegions(regionsFileName, args)
for x in deepBlueFiles:
x.extend([args, regs])
if len(deepBlueFiles) > 1 and args.numberOfProcessors > 1:
pool = multiprocessing.Pool(args.numberOfProcessors)
res = pool.map_async(db.preloadWrapper, deepBlueFiles).get(9999999)
else:
res = list(map(db.preloadWrapper, deepBlueFiles))
# substitute the file names with the temp files
for (ftuple, r) in zip(deepBlueFiles, res):
scoreFileName[ftuple[1]] = r
deepBlueFiles = [[x[0], x[1]] for x in deepBlueFiles]
del regs
return deepBlueFiles
def main(args=None):
"""
1. get read counts at different positions either
all of same length or from genomic regions from the BED file
2. compute the scores
"""
args = process_args(args)
if 'BED' in args:
bed_regions = args.BED
else:
bed_regions = None
if len(args.bwfiles) == 1 and not args.outRawCounts:
sys.stderr.write("You've input a single bigWig file and not specified "
"--outRawCounts. The resulting output will NOT be "
"useful with any deepTools program!\n")
# Preload deepBlue files, which need to then be deleted
deepBlueFiles = []
for idx, fname in enumerate(args.bwfiles):
if db.isDeepBlue(fname):
deepBlueFiles.append([fname, idx])
if len(deepBlueFiles) > 0:
sys.stderr.write(
"Preloading the following deepBlue files: {}\n".format(",".join(
[x[0] for x in deepBlueFiles])))
if 'BED' in args:
regs = db.makeRegions(args.BED, args)
else:
foo = db.deepBlue(deepBlueFiles[0][0],
url=args.deepBlueURL,
userKey=args.userKey)
regs = db.makeTiles(foo, args)
del foo
for x in deepBlueFiles:
x.extend([args, regs])
if len(deepBlueFiles) > 1 and args.numberOfProcessors > 1:
pool = multiprocessing.Pool(args.numberOfProcessors)
res = pool.map_async(db.preloadWrapper, deepBlueFiles).get(9999999)
else:
res = list(map(db.preloadWrapper, deepBlueFiles))
# substitute the file names with the temp files
for (ftuple, r) in zip(deepBlueFiles, res):
args.bwfiles[ftuple[1]] = r
deepBlueFiles = [[x[0], x[1]] for x in deepBlueFiles]
del regs
num_reads_per_bin = score_bw.getScorePerBin(
args.bwfiles,
args.binSize,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
stepSize=args.binSize + args.distanceBetweenBins,
verbose=args.verbose,
region=args.region,
bedFile=bed_regions,
chrsToSkip=args.chromosomesToSkip,
out_file_for_raw_data=args.outRawCounts,
allArgs=args)
sys.stderr.write("Number of bins "
"found: {}\n".format(num_reads_per_bin.shape[0]))
if num_reads_per_bin.shape[0] < 2:
exit("ERROR: too few non zero bins found.\n"
"If using --region please check that this "
"region is covered by reads.\n")
f = open(args.outFileName, "wb")
np.savez_compressed(f, matrix=num_reads_per_bin, labels=args.labels)
f.close()
if args.outRawCounts:
# append to the generated file the
# labels
header = "#'chr'\t'start'\t'end'\t"
header += "'" + "'\t'".join(args.labels) + "'\n"
f = open(args.outRawCounts, "r+")
content = f.read()
f.seek(0, 0)
f.write(header + content)
"""
if bed_regions:
bed_regions.seek(0)
reg_list = bed_regions.readlines()
args.outRawCounts.write("#'chr'\t'start'\t'end'\t")
args.outRawCounts.write("'" + "'\t'".join(args.labels) + "'\n")
fmt = "\t".join(np.repeat('%s', num_reads_per_bin.shape[1])) + "\n"
for idx, row in enumerate(num_reads_per_bin):
args.outRawCounts.write("{}\t{}\t{}\t".format(*reg_list[idx].strip().split("\t")[0:3]))
args.outRawCounts.write(fmt % tuple(row))
else:
args.outRawCounts.write("'" + "'\t'".join(args.labels) + "'\n")
fmt = "\t".join(np.repeat('{}', num_reads_per_bin.shape[1])) + "\n"
for row in num_reads_per_bin:
args.outRawCounts.write(fmt.format(*tuple(row)))
"""
f.close()
# Clean up temporary bigWig files, if applicable
if not args.deepBlueKeepTemp:
for k, v in deepBlueFiles:
os.remove(args.bwfiles[v])
else:
for k, v in deepBlueFiles:
print("{} is stored in {}".format(k, args.bwfiles[v]))
def main(args=None):
args = parse_arguments().parse_args(args)
if args.scaleFactors:
scaleFactors = [float(x) for x in args.scaleFactors.split(":")]
else:
scaleFactors = [1, 1]
# the getRatio function is called and receives
# the function_args per each tile that is considered
FUNC = getRatio
function_args = {'valueType': args.ratio,
'scaleFactors': scaleFactors,
'pseudocount': args.pseudocount}
# Preload deepBlue files, which need to then be deleted
deepBlueFiles = []
for idx, fname in enumerate([args.bigwig1, args.bigwig2]):
if db.isDeepBlue(fname):
deepBlueFiles.append([fname, idx])
if len(deepBlueFiles) > 0:
sys.stderr.write("Preloading the following deepBlue files: {}\n".format(",".join([x[0] for x in deepBlueFiles])))
foo = db.deepBlue(deepBlueFiles[0][0], url=args.deepBlueURL, userKey=args.userKey)
regs = db.makeChromTiles(foo)
for x in deepBlueFiles:
x.extend([args, regs])
if len(deepBlueFiles) > 1 and args.numberOfProcessors > 1:
pool = multiprocessing.Pool(args.numberOfProcessors)
res = pool.map_async(db.preloadWrapper, deepBlueFiles).get(9999999)
else:
res = list(map(db.preloadWrapper, deepBlueFiles))
# substitute the file names with the temp files
for (ftuple, r) in zip(deepBlueFiles, res):
if ftuple[1] == 0:
args.bigwig1 = r
else:
args.bigwig2 = r
deepBlueFiles = [[x[0], x[1]] for x in deepBlueFiles]
del regs
writeBedGraph_bam_and_bw.writeBedGraph(
[(args.bigwig1, getType(args.bigwig1)),
(args.bigwig2, getType(args.bigwig2))],
args.outFileName, 0, FUNC,
function_args, tileSize=args.binSize, region=args.region,
blackListFileName=args.blackListFileName,
verbose=args.verbose,
numberOfProcessors=args.numberOfProcessors,
format=args.outFileFormat,
smoothLength=False,
missingDataAsZero=not args.skipNonCoveredRegions,
extendPairedEnds=False)
# Clean up temporary bigWig files, if applicable
if not args.deepBlueKeepTemp:
for k, v in deepBlueFiles:
if v == 0:
os.remove(args.bigwig1)
else:
os.remove(args.bigwig2)
else:
for k, v in deepBlueFiles:
foo = args.bigwig1
if v == 1:
foo = args.bigwig2
print("{} is stored in {}".format(k, foo))
def main(args=None):
args = process_args(args)
parameters = {'upstream': args.beforeRegionStartLength,
'downstream': args.afterRegionStartLength,
'body': args.regionBodyLength,
'bin size': args.binSize,
'ref point': args.referencePoint,
'verbose': args.verbose,
'bin avg type': args.averageTypeBins,
'missing data as zero': args.missingDataAsZero,
'min threshold': args.minThreshold,
'max threshold': args.maxThreshold,
'scale': args.scale,
'skip zeros': args.skipZeros,
'nan after end': args.nanAfterEnd,
'proc number': args.numberOfProcessors,
'sort regions': args.sortRegions,
'sort using': args.sortUsing,
'unscaled 5 prime': args.unscaled5prime,
'unscaled 3 prime': args.unscaled3prime
}
hm = heatmapper.heatmapper()
# Preload deepBlue files, which need to then be deleted
deepBlueFiles = []
for idx, fname in enumerate(args.scoreFileName):
if db.isDeepBlue(fname):
deepBlueFiles.append([fname, idx])
if len(deepBlueFiles) > 0:
sys.stderr.write("Preloading the following deepBlue files: {}\n".format(",".join([x[0] for x in deepBlueFiles])))
regs = db.makeRegions(args.regionsFileName, args)
for x in deepBlueFiles:
x.extend([args, regs])
if len(deepBlueFiles) > 1 and args.numberOfProcessors > 1:
pool = multiprocessing.Pool(args.numberOfProcessors)
res = pool.map_async(db.preloadWrapper, deepBlueFiles).get(9999999)
else:
res = list(map(db.preloadWrapper, deepBlueFiles))
# substitute the file names with the temp files
for (ftuple, r) in zip(deepBlueFiles, res):
args.scoreFileName[ftuple[1]] = r
deepBlueFiles = [[x[0], x[1]] for x in deepBlueFiles]
del regs
scores_file_list = args.scoreFileName
hm.computeMatrix(scores_file_list, args.regionsFileName, parameters, blackListFileName=args.blackListFileName, verbose=args.verbose, allArgs=args)
if args.sortRegions not in ['no', 'keep']:
sortUsingSamples = []
if args.sortUsingSamples is not None:
for i in args.sortUsingSamples:
if (i > 0 and i <= hm.matrix.get_num_samples()):
sortUsingSamples.append(i - 1)
else:
exit("The value {0} for --sortUsingSamples is not valid. Only values from 1 to {1} are allowed.".format(args.sortUsingSamples, hm.matrix.get_num_samples()))
print('Samples used for ordering within each group: ', sortUsingSamples)
hm.matrix.sort_groups(sort_using=args.sortUsing, sort_method=args.sortRegions, sample_list=sortUsingSamples)
elif args.sortRegions == 'keep':
hm.parameters['group_labels'] = hm.matrix.group_labels
hm.parameters["group_boundaries"] = hm.matrix.group_boundaries
cmo.sortMatrix(hm, args.regionsFileName, args.transcriptID, args.transcript_id_designator, verbose=not args.quiet)
hm.save_matrix(args.outFileName)
if args.outFileNameMatrix:
hm.save_matrix_values(args.outFileNameMatrix)
if args.outFileSortedRegions:
hm.save_BED(args.outFileSortedRegions)
# Clean up temporary bigWig files, if applicable
if not args.deepBlueKeepTemp:
for k, v in deepBlueFiles:
os.remove(args.scoreFileName[v])
else:
for k, v in deepBlueFiles:
print("{} is stored in {}".format(k, args.scoreFileName[v]))
def main(args=None):
args = parse_arguments().parse_args(args)
if args.scaleFactors:
scaleFactors = [float(x) for x in args.scaleFactors.split(":")]
else:
scaleFactors = [1, 1]
# the getRatio function is called and receives
# the function_args per each tile that is considered
FUNC = getRatio
function_args = {'valueType': args.ratio,
'scaleFactors': scaleFactors,
'pseudocount': args.pseudocount}
# Preload deepBlue files, which need to then be deleted
deepBlueFiles = []
for idx, fname in enumerate([args.bigwig1, args.bigwig2]):
if db.isDeepBlue(fname):
deepBlueFiles.append([fname, idx])
if len(deepBlueFiles) > 0:
sys.stderr.write("Preloading the following deepBlue files: {}\n".format(",".join([x[0] for x in deepBlueFiles])))
foo = db.deepBlue(deepBlueFiles[0][0], url=args.deepBlueURL, userKey=args.userKey)
regs = db.makeChromTiles(foo)
for x in deepBlueFiles:
x.extend([args, regs])
if len(deepBlueFiles) > 1 and args.numberOfProcessors > 1:
pool = multiprocessing.Pool(args.numberOfProcessors)
res = pool.map_async(db.preloadWrapper, deepBlueFiles).get(9999999)
else:
res = list(map(db.preloadWrapper, deepBlueFiles))
# substitute the file names with the temp files
for (ftuple, r) in zip(deepBlueFiles, res):
if ftuple[1] == 0:
args.bigwig1 = r
else:
args.bigwig2 = r
deepBlueFiles = [[x[0], x[1]] for x in deepBlueFiles]
del regs
writeBedGraph_bam_and_bw.writeBedGraph(
[(args.bigwig1, getType(args.bigwig1)),
(args.bigwig2, getType(args.bigwig2))],
args.outFileName, 0, FUNC,
function_args, tileSize=args.binSize, region=args.region,
blackListFileName=args.blackListFileName,
verbose=args.verbose,
numberOfProcessors=args.numberOfProcessors,
format=args.outFileFormat,
smoothLength=False,
missingDataAsZero=not args.skipNonCoveredRegions,
extendPairedEnds=False)
# Clean up temporary bigWig files, if applicable
if not args.deepBlueKeepTemp:
for k, v in deepBlueFiles:
if v == 0:
os.remove(args.bigwig1)
else:
os.remove(args.bigwig2)
else:
for k, v in deepBlueFiles:
foo = args.bigwig1
if v == 1:
foo = args.bigwig2
print("{} is stored in {}".format(k, foo))
def main(args=None):
"""
1. get read counts at different positions either
all of same length or from genomic regions from the BED file
2. compute the scores
"""
args = process_args(args)
if 'BED' in args:
bed_regions = args.BED
else:
bed_regions = None
if len(args.bwfiles) == 1 and not args.outRawCounts:
sys.stderr.write("You've input a single bigWig file and not specified "
"--outRawCounts. The resulting output will NOT be "
"useful with any deepTools program!\n")
# Preload deepBlue files, which need to then be deleted
deepBlueFiles = []
for idx, fname in enumerate(args.bwfiles):
if db.isDeepBlue(fname):
deepBlueFiles.append([fname, idx])
if len(deepBlueFiles) > 0:
sys.stderr.write("Preloading the following deepBlue files: {}\n".format(",".join([x[0] for x in deepBlueFiles])))
if 'BED' in args:
regs = db.makeRegions(args.BED, args)
else:
foo = db.deepBlue(deepBlueFiles[0][0], url=args.deepBlueURL, userKey=args.userKey)
regs = db.makeTiles(foo, args)
del foo
for x in deepBlueFiles:
x.extend([args, regs])
if len(deepBlueFiles) > 1 and args.numberOfProcessors > 1:
pool = multiprocessing.Pool(args.numberOfProcessors)
res = pool.map_async(db.preloadWrapper, deepBlueFiles).get(9999999)
else:
res = list(map(db.preloadWrapper, deepBlueFiles))
# substitute the file names with the temp files
for (ftuple, r) in zip(deepBlueFiles, res):
args.bwfiles[ftuple[1]] = r
deepBlueFiles = [[x[0], x[1]] for x in deepBlueFiles]
del regs
num_reads_per_bin = score_bw.getScorePerBin(
args.bwfiles,
args.binSize,
blackListFileName=args.blackListFileName,
numberOfProcessors=args.numberOfProcessors,
stepSize=args.binSize + args.distanceBetweenBins,
verbose=args.verbose,
region=args.region,
bedFile=bed_regions,
chrsToSkip=args.chromosomesToSkip,
out_file_for_raw_data=args.outRawCounts,
allArgs=args)
sys.stderr.write("Number of bins "
"found: {}\n".format(num_reads_per_bin.shape[0]))
if num_reads_per_bin.shape[0] < 2:
exit("ERROR: too few non zero bins found.\n"
"If using --region please check that this "
"region is covered by reads.\n")
f = open(args.outFileName, "wb")
np.savez_compressed(f,
matrix=num_reads_per_bin,
labels=args.labels)
f.close()
if args.outRawCounts:
# append to the generated file the
# labels
header = "#'chr'\t'start'\t'end'\t"
header += "'" + "'\t'".join(args.labels) + "'\n"
f = open(args.outRawCounts, "r+")
content = f.read()
f.seek(0, 0)
f.write(header + content)
"""
if bed_regions:
bed_regions.seek(0)
reg_list = bed_regions.readlines()
args.outRawCounts.write("#'chr'\t'start'\t'end'\t")
args.outRawCounts.write("'" + "'\t'".join(args.labels) + "'\n")
fmt = "\t".join(np.repeat('%s', num_reads_per_bin.shape[1])) + "\n"
for idx, row in enumerate(num_reads_per_bin):
args.outRawCounts.write("{}\t{}\t{}\t".format(*reg_list[idx].strip().split("\t")[0:3]))
args.outRawCounts.write(fmt % tuple(row))
else:
args.outRawCounts.write("'" + "'\t'".join(args.labels) + "'\n")
fmt = "\t".join(np.repeat('{}', num_reads_per_bin.shape[1])) + "\n"
for row in num_reads_per_bin:
args.outRawCounts.write(fmt.format(*tuple(row)))
"""
f.close()
# Clean up temporary bigWig files, if applicable
if not args.deepBlueKeepTemp:
for k, v in deepBlueFiles:
os.remove(args.bwfiles[v])
else:
for k, v in deepBlueFiles:
print("{} is stored in {}".format(k, args.bwfiles[v]))