def _get_vector(self, bp):
bed = read_bed(bp)
divide_bed(bed, self.bin_size)
merge_bed(bed)
try:
vector = bed2vector(bed, self.chromosome_len)
except:
print bp
raise
return vector
def __init__(self, beds_path, chromosome_len_path, dhs_path, bin_size):
self.beds_path = beds_path
self.bin_size = bin_size
self.dhs_path = dhs_path
with open(chromosome_len_path) as clp:
self.chromosome_len = read_chromosome_len(clp)
divide_bed(self.chromosome_len, self.bin_size)
self.genome_len = 0
for chromosome in self.chromosome_len:
self.genome_len += self.chromosome_len[chromosome][0]["end"] + 1
def init_dhs_extraction(self):
with open(self.dhs_path) as dp:
dhs = read_bed(dp)
divide_bed(dhs, self.bin_size)
merge_bed(dhs)
self.dhs_vector = bed2vector(dhs, self.chromosome_len)
coverage = len(nonzero(self.dhs_vector)[0])
print coverage,"coverage"
ret = empty((coverage, len(self.beds_path)), dtype="int8")
current_col = 0
for bed_path in self.beds_path:
with open(bed_path) as bp:
ret[:,current_col] = self._bed2extracted_vector(bp)
current_col += 1
self.sparse = csr_matrix(ret,dtype="int16")
print "init DHS extraction finished"
def setUp(self):
with open("./utest/test1.len") as tl:
self.len_obj = read_chromosome_len(tl)
divide_bed(self.len_obj, 100)
def testMerge2(self):
divide_bed(self.bed_obj, 100)
merge_bed(self.bed_obj)
with open("./utest/test1_divided_merged.bed") as dmd:
self.bed_dmer = read_bed(dmd)
self.assertEqual(self.bed_obj, self.bed_dmer)
def testDivide(self):
divide_bed(self.bed_obj, 100)
with open("./utest/test1_divided.bed") as dd:
self.bed_div = read_bed(dd)
self.assertEqual(self.bed_div, self.bed_obj)