def test_roundtrip(f_hm, f_cool):
chromsizes = cooler.read_chromsizes(
"http://genome.ucsc.edu/goldenpath/help/hg19.chrom.sizes",
name_patterns=(r"^chr[0-9]+$", r"chrX$"),
)
binsize = 2000000
bintable = cooler.binnify(chromsizes, binsize)
heatmap = np.load(f_hm)
reader = cooler.create.ArrayLoader(bintable, heatmap, 100000)
cooler.create.create(f_cool, bintable, reader, assembly="hg19")
h5 = h5py.File(f_cool, "r")
new_chromtable = cooler.api.chroms(h5)
assert np.all(chromsizes.index == new_chromtable["name"])
new_bintable = cooler.api.bins(h5)
assert np.all(bintable == new_bintable)
info = cooler.api.info(h5)
assert info["genome-assembly"] == "hg19"
assert info["bin-type"] == "fixed"
assert info["bin-size"] == binsize
mat = cooler.api.matrix(h5, 0, 100, 0, 100, "count", balance=False)
assert mat.shape == (100, 100)
assert np.allclose(heatmap[:100, :100], mat)
mat = cooler.Cooler(h5).matrix("count", balance=False)[:100, :100]
assert mat.shape == (100, 100)
assert np.allclose(heatmap[:100, :100], mat)
mat = cooler.api.matrix(h5, 100, 200, 100, 200, "count", balance=False)
assert mat.shape == (100, 100)
assert np.allclose(heatmap[100:200, 100:200], mat)
mat = cooler.Cooler(h5).matrix("count", balance=False)[100:200, 100:200]
assert mat.shape == (100, 100)
assert np.allclose(heatmap[100:200, 100:200], mat)
try:
os.remove(f_cool)
except OSError:
pass
def test_roundtrip(f_hm, f_cool):
chromsizes = cooler.read_chromsizes(
'https://genome.ucsc.edu/goldenpath/help/hg19.chrom.sizes',
name_patterns=(r'^chr[0-9]+$', r'chrX$'))
binsize = 2000000
bintable = cooler.binnify(chromsizes, binsize)
heatmap = np.load(f_hm)
reader = cooler.create.ArrayLoader(bintable, heatmap, 100000)
cooler.create.create(f_cool, bintable, reader, assembly='hg19')
h5 = h5py.File(f_cool, 'r')
new_chromtable = cooler.api.chroms(h5)
assert np.all(chromsizes.index == new_chromtable['name'])
new_bintable = cooler.api.bins(h5)
assert np.all(bintable == new_bintable)
info = cooler.api.info(h5)
assert info['genome-assembly'] == 'hg19'
assert info['bin-type'] == 'fixed'
assert info['bin-size'] == binsize
mat = cooler.api.matrix(h5, 0, 100, 0, 100, 'count', balance=False)
assert mat.shape == (100, 100)
assert np.allclose(heatmap[:100, :100], mat)
mat = cooler.Cooler(h5).matrix('count', balance=False)[:100, :100]
assert mat.shape == (100, 100)
assert np.allclose(heatmap[:100, :100], mat)
mat = cooler.api.matrix(h5, 100, 200, 100, 200, 'count', balance=False)
assert mat.shape == (100, 100)
assert np.allclose(heatmap[100:200, 100:200], mat)
mat = cooler.Cooler(h5).matrix('count', balance=False)[100:200, 100:200]
assert mat.shape == (100, 100)
assert np.allclose(heatmap[100:200, 100:200], mat)
try:
os.remove(f_cool)
except OSError:
pass
def test_roundtrip():
chromsizes = cooler.read_chromsizes(
'https://genome.ucsc.edu/goldenpath/help/hg19.chrom.sizes',
name_patterns=(r'^chr[0-9]+$', r'chrX$'))
binsize = 2000000
bintable = cooler.binnify(chromsizes, binsize)
heatmap = np.load(
os.path.join(testdir, 'data', 'IMR90-MboI-matrix.2000kb.npy'))
reader = cooler.io.DenseLoader(heatmap)
cooler.io.create(testfile_path,
chromsizes,
bintable,
reader,
assembly='hg19')
h5 = h5py.File(testfile_path, 'r')
new_chromtable = cooler.chroms(h5)
assert np.all(chromsizes.index == new_chromtable['name'])
new_bintable = cooler.bins(h5)
assert np.all(bintable == new_bintable)
info = cooler.info(h5)
assert info['genome-assembly'] == 'hg19'
assert info['bin-type'] == 'fixed'
assert info['bin-size'] == binsize
mat = cooler.matrix(h5, 0, 100, 0, 100, 'count', balance=False)
assert mat.shape == (100, 100)
assert np.allclose(heatmap[:100, :100], mat)
mat = cooler.Cooler(h5).matrix('count', balance=False)[:100, :100]
assert mat.shape == (100, 100)
assert np.allclose(heatmap[:100, :100], mat)
mat = cooler.matrix(h5, 100, 200, 100, 200, 'count', balance=False)
assert mat.shape == (100, 100)
assert np.allclose(heatmap[100:200, 100:200], mat)
mat = cooler.Cooler(h5).matrix('count', balance=False)[100:200, 100:200]
assert mat.shape == (100, 100)
assert np.allclose(heatmap[100:200, 100:200], mat)
def test_roundtrip():
chromsizes = cooler.read_chromsizes(
'https://genome.ucsc.edu/goldenpath/help/hg19.chrom.sizes',
name_patterns=(r'^chr[0-9]+$', r'chrX$'))
chroms, lengths = zip(*iteritems(chromsizes))
binsize = 2000000
bintable = cooler.binnify(chromsizes, binsize)
heatmap = np.load(os.path.join(testdir, 'data', 'IMR90-MboI-matrix.2000kb.npy'))
with h5py.File(testfile_path, 'w') as h5:
reader = cooler.io.DenseLoader(heatmap)
cooler.io.create(h5, chroms, lengths, bintable, reader, assembly='hg19')
h5 = h5py.File(testfile_path, 'r')
new_chromtable = cooler.chroms(h5)
assert np.all(chromsizes.index == new_chromtable['name'])
new_bintable = cooler.bins(h5)
assert np.all(bintable == new_bintable)
info = cooler.info(h5)
assert info['genome-assembly'] == 'hg19'
assert info['bin-type'] == 'fixed'
assert info['bin-size'] == binsize
mat = cooler.matrix(h5, 0, 100, 0, 100, 'count')
assert mat.shape == (100, 100)
assert np.allclose(heatmap[:100,:100], mat.toarray())
mat = cooler.Cooler(h5).matrix('count')[:100, :100]
assert mat.shape == (100, 100)
assert np.allclose(heatmap[:100,:100], mat.toarray())
mat = cooler.matrix(h5, 100, 200, 100, 200, 'count')
assert mat.shape == (100, 100)
assert np.allclose(heatmap[100:200,100:200], mat.toarray())
mat = cooler.Cooler(h5).matrix('count')[100:200, 100:200]
assert mat.shape == (100, 100)
assert np.allclose(heatmap[100:200,100:200], mat.toarray())
from __future__ import division, print_function
import json
import numpy as np
import pandas as pd
import cooler
import h5py
import time
TILESIZE = 256
where = np.flatnonzero
chromsizes = cooler.read_chromsizes(
"http://s3.amazonaws.com/pkerp/data/mm9/chromInfo.txt"
) # defaults to reading chr#,X,Y,M
chromosomes = list(chromsizes.keys())
chromid_map = dict(zip(chromosomes, range(len(chromosomes))))
cumul_lengths = np.r_[0, np.cumsum(chromsizes)]
def absCoord2bin(c, pos):
try:
cid = where(cumul_lengths > pos)[0] - 1
except IndexError:
return c.info["nbins"]
chrom = chromosomes[cid]
relPos = pos - cumul_lengths[cid]
return c.offset((chrom, relPos, chromsizes[chrom]))
def getData(FILEPATH, zoomLevel, startPos1, endPos1, startPos2, endPos2):
description="Output a genome segmentation of restriction fragments as a BED file.")
parser.add_argument(
"chromsizes",
help="UCSC-like chromsizes file, with chromosomes in desired order",
metavar="CHROMSIZES_PATH")
parser.add_argument(
"binsize",
help="Resolution (bin size) in base pairs <int>",
metavar="BINSIZE")
parser.add_argument(
"--out", "-o",
help="Output file (defaults to stdout)")
args = vars(parser.parse_args())
binsize = int(args['binsize'])
chromsizes = cooler.read_chromsizes(args['chromsizes'])
bins = cooler.binnify(chromsizes, binsize)
# Write output
out = args['out']
try:
if out is None:
f = sys.stdout
else:
f = open(out, 'wt')
bins.to_csv(f, sep='\t', index=False, header=False)
except OSError:
pass
finally:
f.close()
def main():
parser = argparse.ArgumentParser(description="""python matrix_storage_benchmark.py matrix_tsv""")
parser.add_argument('matrix_tsv')
parser.add_argument(
'-s', '--square',
default=256,
type=int,
help="The size of the square within which to return values")
parser.add_argument(
'-i', '--iterations',
default=100,
type=int,
help="The number of times to run the range query")
args = vars(parser.parse_args())
binsize = 5000
infilepath = args['matrix_tsv']
outfilepath = op.join(op.dirname(infilepath), 'chrX.{}kb.cool'.format(binsize//1000))
# Build "index"
t1 = time.time()
chromsizes = cooler.read_chromsizes('test/data/hg19.chrom.sizes')
chroms = ['chrX']
lengths = [chromsizes['chrX']]
bins = cooler.binnify(chromsizes.loc['chrX':'chrX'], binsize)
chunksize = int(100e6)
reader = cooler.io.SparseLoader(infilepath, chunksize)
h5opts = dict(compression='gzip', compression_opts=6)
with h5py.File(outfilepath, 'w') as h5:
cooler.io.create(h5, chroms, lengths, bins, reader, binsize, h5opts=h5opts)
c = cooler.Cooler(outfilepath)
print("Time creating index: {:.3f} seconds".format(time.time() - t1))
# Normalization
t15 = time.time()
N_CPUS = 8
chunksize = int(100e6)
with h5py.File(outfilepath, 'r+') as h5, Pool(N_CPUS) as pool:
bias = ice.iterative_correction(
h5, chunksize=chunksize, tol=1e-05, mad_max=3,
cis_only=False, ignore_diags=3, map=pool.map)
h5opts = dict(compression='gzip', compression_opts=6)
h5['bins'].create_dataset('weight', data=bias, **h5opts)
print("Time for normalization (cis and trans): {:.3f} seconds".format(time.time() - t15))
# The bounds of the contact coordinates
c = cooler.Cooler(outfilepath)
matrix = c.matrix()
min_x = 0
min_y = 0
max_x = c.shape[0]
max_y = c.shape[1]
print("max_x:", max_x)
print("max_y:", max_y)
# Range queries
square_size = args['square']
t2 = time.time()
for i in range(args['iterations']):
point1 = random.randint(min_x, max_x - square_size)
point2 = random.randint(min_y, max_y - square_size)
mat = matrix[point1 : point1+square_size, point2 : point2+square_size]
selected_points = list(zip(mat.row, mat.col, mat.data))
t25 = time.time()
print("Time performing range queries (256x256): {:.3f} seconds (per query): {:.3f} seconds".format(t25 - t2, (t25 - t2) / args['iterations']))
weights = c.bins()['weight'][:].values
for i in range(args['iterations']):
point1 = random.randint(min_x, max_x - square_size)
point2 = random.randint(min_y, max_y - square_size)
mat = matrix[point1 : point1+square_size, point2 : point2+square_size]
bias1 = weights[point1:point1+square_size]
bias2 = weights[point2:point2+square_size]
mat.data = bias1[mat.row] * bias2[mat.col] * mat.data
selected_points = list(zip(mat.row, mat.col, mat.data))
t26 = time.time()
print("Time performing range queries (256x256) with balancing: {:.3f} seconds (per query): {:.3f} seconds".format(t26 - t25, (t26 - t25) / args['iterations']))
for i in range(args['iterations']):
point1 = random.randint(min_x, max_x - square_size * 8)
point2 = random.randint(min_y, max_y - square_size * 8)
mat = matrix[point1 : point1+square_size*8, point2 : point2+square_size*8]
selected_points = list(zip(mat.row, mat.col, mat.data))
t3 = time.time()
print("Time performing range queries (2048 x 2048): {:.3f} seconds (per query): {:.3f} seconds".format(t3 - t26, (t3 - t26) / args['iterations']))
weights = c.bins()['weight'][:].values
for i in range(args['iterations']):
point1 = random.randint(min_x, max_x - square_size * 8)
point2 = random.randint(min_y, max_y - square_size * 8)
mat = matrix[point1 : point1+square_size*8, point2 : point2+square_size*8]
selected_points = list(zip(mat.row, mat.col, mat.data))
t35 = time.time()
print("Time performing range queries (2048 x 2048) with balancing: {:.3f} seconds (per query): {:.3f} seconds".format(t35 - t3, (t35 - t3) / args['iterations']))
for i in range(args['iterations']):
point1 = random.randint(min_x, max_x - square_size)
mat = matrix[point1, :]
selected_points = list(zip(mat.row, mat.col, mat.data))
t4 = time.time()
print("Time slicing across first dimension: {:.3f} seconds (per query): {:.3f} seconds".format(t4 - t35, (t4 - t35) / args['iterations']))
for i in range(args['iterations']):
point2 = random.randint(min_y, max_y - square_size)
mat = matrix[:, point2]
selected_points = list(zip(mat.row, mat.col, mat.data))
t5 = time.time()
print("Time slicing across second dimension: {:.3f} seconds (per query): {:.3f} seconds".format(t5 - t4, (t5 - t4) / args['iterations']))
selected_points = []
for i in range(args['iterations']):
for pix in c.pixels().iterchunks(size=1000000):
diag = pix[pix.bin1_id == pix.bin2_id]
selected_points.extend( list(zip(diag['bin1_id'], diag['bin2_id'], diag['count'])) )
t6 = time.time()
print("Time slicing across the diagonal: {:.3f} seconds (per query): {:.3f} seconds".format(t6 - t5, (t6 - t5) / args['iterations']))
# Dump
print("Size of index: {} bytes".format(op.getsize(outfilepath)))
with open('/tmp/tmp.tsv', 'wt') as f:
for pix in c.pixels().iterchunks(size=100000):
pix.to_csv(f, sep='\t', index=False, header=False)
print("Time outputting the index: {:.3f}".format(time.time() - t6))
print("Size of output: {} bytes".format(op.getsize('/tmp/tmp.tsv')))