def parse_onename(onename):
np.random.seed()
#Parsing individual files
if parseInMemory == True:
finalname = onename + "_parsed.frag"
#if not os.path.exists(finalname):
if True:
#create dataset in memory, parse and then save to destination
TR = HiCdataset("bla" + str(np.random.randint(100000000000)), genome=getGenome(workingGenome),
maximumMoleculeLength=500,enzymeName = enzyme,tmpFolder = "tmp",
inMemory=True) # remove inMemory if you don't have enough RAM
TR.parseInputData(dictLike=onename)
folder = os.path.split(onename)[0]
print(onename)
TR.save(ensure(finalname))
folder, fname = os.path.split(onename)
statSubFolder = os.path.join(statFolder, folder)
TR.printMetadata(saveTo=ensure(os.path.join(statSubFolder, fname + ".stat")))
else:
print("skipping parsed: ", onename)
else:
#Create dataset at destination, parse on HDD, then no need to save.
TR = HiCdataset(ensure(onename + "_parsed.frag"),
genome=getGenome(workingGenome),enzymeName = enzyme,tmpFolder = "tmp",
maximumMoleculeLength=500, mode='w')
TR.parseInputData(dictLike=onename, enzymeToFillRsites=enzyme)
TR.printMetadata(saveTo=ensure(os.path.join(statFolder, onename + ".stat")))
) # a prefix preceeding .fastq.gz, which will be used to distinguish side 1 and side 2
genomeName = "hg19"
#genomeName = "/home/ubuntu/data3/HiCdata/DM_DpnII_Oct18/dm3"
threads = 8
bowtieIndex = "/home/ubuntu/rDNA_data/index/hg19/hg19mannual"
#bowtiePath = "/usr/bin/bowtie2"
bowtiePath = "/home/ubuntu/tools/miniconda2/envs/main/bin/bowtie2"
bowtieFlags = "--very-sensitive"
#bowtieFlags = "-D 20 -R 3 -N 0 -L 7 -i S,1,0.10"
bowtieFlags = "--very-sensitive --n-ceil L,0,0.1"
seqSkipStart = 0 # skip first 2 bp of the read, if you want
#minMapLen = 25 # start mapping at this length
genome_db = getGenome(genomeName)
if not os.path.exists(bowtiePath): raise
if mode == "sra":
iterList = 2 * GEOids
elif mode == "fastq":
iterList = sorted(os.listdir(inFastqDir))
print iterList
for i in iterList:
if mode == "sra":
sraNum = i
expName = "SRR{0}".format(i)
i = expName
def refineDataset(filenames, create=True, delete=False, parseInMemory=True):
"""
Parameters
----------
filenames[0] is a list of filenames of incoming files
filenames[1] is a folder for outgoing file
filenames[2] is a working genome, that is output directory
filenames[3] is an enzyme for a given experiment
create : bool, optional
If True, parse each file.
If False, assume that files were already parsed
(e.g. if you are just playing around with filtering parameters)
delete : bool, optional
If True, delete parsed files after merging.
Man, these files may be huge... if you don't have a 10TB RAID, this may be useful.
parseInMemory : bool, optional
Perform parsing input files in memory.
"""
in_files = filenames[0]
out_file = filenames[1]
statFolder = os.path.join("statistics", out_file)
workingGenome = filenames[2]
enzyme = filenames[3]
if create == True: # if we need to parse the input files (.hdf5 from mapping).
def parse_onename(onename):
np.random.seed()
#Parsing individual files
if parseInMemory == True:
finalname = onename + "_parsed.frag"
#if not os.path.exists(finalname):
if True:
#create dataset in memory, parse and then save to destination
TR = HiCdataset(
"bla" + str(np.random.randint(100000000000)),
genome=getGenome(workingGenome),
maximumMoleculeLength=500,
enzymeName=enzyme,
tmpFolder="tmp",
inMemory=True
) # remove inMemory if you don't have enough RAM
TR.parseInputData(dictLike=onename)
folder = os.path.split(onename)[0]
print(onename)
TR.save(ensure(finalname))
folder, fname = os.path.split(onename)
statSubFolder = os.path.join(statFolder, folder)
TR.printMetadata(saveTo=ensure(
os.path.join(statSubFolder, fname + ".stat")))
else:
print("skipping parsed: ", onename)
else:
#Create dataset at destination, parse on HDD, then no need to save.
TR = HiCdataset(ensure(onename + "_parsed.frag"),
genome=getGenome(workingGenome),
enzymeName=enzyme,
tmpFolder="tmp",
maximumMoleculeLength=500,
mode='w')
TR.parseInputData(dictLike=onename, enzymeToFillRsites=enzyme)
TR.printMetadata(
saveTo=ensure(os.path.join(statFolder, onename + ".stat")))
list(map(parse_onename, in_files))
"Merging files alltogether, applying filters"
TR = HiCdataset(ensure(out_file + "_merged.frag"),
genome=getGenome(workingGenome),
enzymeName=enzyme,
tmpFolder="tmp",
dictToStoreIDs="h5dict",
mode="w")
TR.merge([i + "_parsed.frag" for i in in_files])
#Merge in all parsed files from one experiment
if delete == True: # cleaning up parsed files
for delFile in [i + "_parsed.frag" for i in in_files]:
os.remove(delFile)
"Now opening new dataset for refined data, and performing all the filtering "
TR = HiCdataset(out_file + "_refined.frag",
enzymeName=enzyme,
genome=getGenome(workingGenome),
tmpFolder="tmp",
dictToStoreIDs="h5dict",
mode='w')
TR.load(out_file + "_merged.frag")
#----------------------------Set of filters applied -------------
TR.filterDuplicates()
#TR.save(out_file+".dat")
#TR.filterExtreme(cutH=0.0001, cutL=0)
#TR.filterRsiteStart()
#TR.filterLarge()
TR.writeFilteringStats()
TR.printMetadata(saveTo=statFolder + ".stat")
#------------------------End set of filters applied----------
else:
#If merging & filters has already been done, just load files
TR = HiCdataset(out_file + "_working.frag",
enzymeName=enzyme,
mode='w',
genome=getGenome(workingGenome))
TR.load(out_file + "_refined.frag")
TR.printMetadata(saveTo=statFolder + ".stat")
print("----->Building Raw heatmap at different resolutions")
TR.printStats()
for res in coolerResolutions:
TR.saveCooler(out_file + ".{0}.cool".format(res), res)
pass
#Now merging different experiments alltogether
#note that the first column is not here, as it is a replica
experiments = set([(i[0], i[2], i[3]) for i in combinedExperimentNames])
print(experiments)
for experiment in experiments:
workingGenome = experiment[1]
myExperimentNames = [i[1] + "_refined.frag" for i in combinedExperimentNames if (i[0], i[2], i[3]) == (experiment[0], experiment[1],experiment[2])]
assert len(myExperimentNames) > 0
if len(myExperimentNames) > 0:
#If we have more than one experiment (replica) for the same data, we can combine.
TR = HiCdataset(os.path.join(workingGenome, "%s-all-%s_refined.frag" %
(experiment[0],experiment[2])), genome=getGenome(workingGenome),
enzymeName = experiment[2],tmpFolder = "tmp",dictToStoreIDs="h5dict")
statSaveName = os.path.join("statistics", workingGenome, "%s-all-%s_refined.stat" % (experiment[0], experiment[2]))
TR.merge(myExperimentNames)
TR.printMetadata(saveTo=statSaveName)
for res in wholeGenomeResolutionsKb:
TR.saveHeatmap(os.path.join(workingGenome, "%s-all-%s-{0}k.hm" % (experiment[0], experiment[2])).format(res), res*1000)
for res in byChromosomeResolutionsKb:
TR.saveByChromosomeHeatmap(os.path.join(workingGenome, "%s-all-%s-{0}k.byChr" % (experiment[0], experiment[2])).format(res), res*1000)
for res in HiResWithOverlapResolutionsKb:
TR.saveHiResHeatmapWithOverlaps(os.path.join(workingGenome, "%s-all-%s-{0}k_HighRes.byChr" % (experiment[0], experiment[2])).format(res), res*1000)
for res in SuperHiResWithOverlapResolutionsKb:
TR.saveSuperHighResMapWithOverlaps(os.path.join(workingGenome, "%s-all-%s-{0}k_SuperHighRes.byChr" % (experiment[0], experiment[2])).format(res), res*1000)
except:
raise ValueError("Cannot create directory")
return f
path = "/home/ubuntu/RNAdata/Golov/hic/mapped-hg19/35_AGAGGCCT_reads_merged_len_adj/"
f1 = h5py.File(path + "chunk0001.hdf5" ,'r+')
f1 = mirnylib.h5dict.h5dict(path + "chunk0001.hdf5" ,'r+')
print f1["misc"]["genome"]["idx2label"]
chrm_conversion_table = f1["misc"]["genome"]["idx2label"]
genome_db = getGenome("hg19")
workingGenome = "hg19"
for key in genome_db.idx2label:
print key ,
print genome_db.idx2label[key] ,
print("Keys: %s" % f1.keys())
chrms1_key = list(f1.keys())[0]
chrms2_key = list(f1.keys())[1]
cuts1_key = list(f1.keys())[2]
cuts2_key = list(f1.keys())[3]
misc_key = list(f1.keys())[4]