Python BedTool.cat方法代码示例

# 需要导入模块: from pybedtools import BedTool [as 别名]
# 或者: from pybedtools.BedTool import cat [as 别名]
def generate_remainder(whole_bed, bed_prefix, bed_list):
    """
    Calculate the remaining regions that are not included in the truth set
    :param whole_bed: path to the truth regions for the whole panel
    :param bed_prefix: prefix used for all the bed files
    :param bed_list: list of all the bed files for that panel
    :return: BEDTool containing any regions that are completely missing from the truth regions
    """

    whole_truth = BedTool(whole_bed)
    whole_truth.saveas()
    whole = BedTool()

    for bed in bed_list:
        print bed
        tool = BedTool(bed)
        tool.saveas()
        if bed == bed_list[0]:
            whole = tool
        else:
            whole = whole.cat(tool)
            whole.saveas()

    whole_sorted = whole.sort()
    whole_merged = whole_sorted.merge()
    whole_merged.saveas()

    remainder = whole_merged.subtract(whole_truth)
    remainder.moveto('/results/Analysis/MiSeq/MasterBED/GIAB/' + bed_prefix + '.remainder.bed')
    missing_regions = whole_merged.subtract(whole_truth, A=True)
    return missing_regions

# 需要导入模块: from pybedtools import BedTool [as 别名]
# 或者: from pybedtools.BedTool import cat [as 别名]
class GenomicSubset(object):
    def __init__(self, name, path=paths.genome_subsets, assembly='hg19'):
        self.assembly = assembly
        self.name = name
        self.bedtool = BedTool(path + name + '.bed').sort()

        # Intersect the pathway with the appropriate genome build
        # TODO: this step should be unnecessary if the pathways are correct
        if name != self.assembly:
            self.bedtool = GenomicSubset.reference_genome(
                    self.assembly).bedtool.intersect(self.bedtool).sort().saveas()

    def expand_by(self, expansion_in_each_direction_Mb):
        window_size_str = str(expansion_in_each_direction_Mb) + 'Mb'
        print('total size before window addition:', self.bedtool.total_coverage(), 'bp')

        # compute the flanks
        # TODO: use 1cM instead of 1Mb
        print('computing flanks')
        flanks = self.bedtool.flank(
            genome=self.assembly,
            b=expansion_in_each_direction_Mb*1000000).sort().merge().saveas()

        # compute the union of the flanks and the pathway
        print('computing union')
        union = self.bedtool.cat(flanks, postmerge=False).sort()
        merged = union.merge().saveas()
        print('total size after window addition:', merged.total_coverage(), 'bp')
        self.bedtool = merged

    def restricted_to_chrom_bedtool(self, chrnum):
        return self.bedtool.filter(
                lambda x : x[0] == 'chr' + str(int(chrnum))).saveas()

    @classmethod
    def reference_genome(cls, assembly='hg19'):
        return GenomicSubset(assembly, path=paths.reference, assembly=assembly)

    @classmethod
    def reference_chrom_bedtool(cls, chrnum, assembly='hg19'):
        return cls.reference_genome(assembly=assembly).restricted_to_chrom_bedtool(chrnum)

    @classmethod
    def whole_genome(cls, assembly='hg19'):
        return cls(assembly, path=paths.reference)

# 需要导入模块: from pybedtools import BedTool [as 别名]
# 或者: from pybedtools.BedTool import cat [as 别名]
def generate_remainder(whole_bed, out_dir, bed_list):
    """
    Calculate the remaining regions that are not included in the truth set

    :param whole_bed: Path to the truth regions for the whole panel
    :type whole_bed: String
    :param out_dir: Prefix used for all the bed files
    :type out_dir: String
    :param bed_list: List of all the bed files for that panel
    :type bed_list: List of String
    :return: BEDTool containing any regions that are completely missing from the truth regions
    :rtype: BedTool
    """
    try:
        whole_truth = BedTool(whole_bed)
        whole_truth.saveas()
        whole = BedTool()

        for bed in bed_list:
            print(bed)
            tool = BedTool(bed)
            tool.saveas()
            if bed == bed_list[0]:
                whole = tool
            else:
                whole = whole.cat(tool)
                whole.saveas()

        whole_sorted = whole.sort()
        whole_merged = whole_sorted.merge()
        whole_merged.saveas()

        remainder = whole_merged.subtract(whole_truth)
        remainder.moveto(out_dir + '/remainder.bed')
        missing_regions = whole_merged.subtract(whole_truth, A=True)
    except UnicodeDecodeError:
        missing_regions = None
    return missing_regions

# 需要导入模块: from pybedtools import BedTool [as 别名]
# 或者: from pybedtools.BedTool import cat [as 别名]
 def merge(regulators):
     """Merge a list of regulators using BedTool.cat"""
     if len(regulators) > 1:
         return BedTool.cat(*regulators, postmerge=False)
     else:
         return regulators[0]

# 需要导入模块: from pybedtools import BedTool [as 别名]
# 或者: from pybedtools.BedTool import cat [as 别名]
		sorting.wait()
	return(0)

def newber(binner,factor):
	"""Returns bed record with all binding for a factor merged and renamed."""
	newbie = BedTool(binner).sort().merge(nms=True).each(featurefuncs.midpoint)
	newbie = newbie.each(featurefuncs.rename,factor)
	return(newbie)

print "Loading bed files..."
tssbed = BedTool(tsss)
jacker = BedTool(jacked)
chiper = BedTool(chiped)

print "Combining binding files..."
comber = chiper.cat(jacker,force_truncate=False,postmerge=False).moveto('./combtemp.bed')

#print "Generating oldstyle bed file..."
#oldstyle = comber.each(featurefuncs.midpoint)
#oldstyle2 = bedmaker(oldstyle,tssbed,oldout)

print "Generating newstyle bed files..."
for factor in sorted(pwmlist.keys()):
	print factor
	for model in pwmlist[factor]:
		print model
		grepper = 'grep ' + model + ' ./combtemp.bed >> ./temp1.bed'
		grepping = subprocess.Popen(grepper,shell=True)
		grepping.wait()
	newbie = newber('./temp1.bed',factor)
	newbie2 = bedmaker(newbie,tssbed,outdir + factor + '_midpoint_sorted.bed',unmatched=False)