def test_load_counts():
module_path = dirname(__file__)
counts_filename = os.path.join(
module_path,
"../../datasets/data/duan2009/duan.SC.10000.raw_sub.matrix")
counts = io.load_counts(counts_filename)
assert counts is not None
def run_nmds(directory):
if os.path.exists(os.path.join(directory, "config.ini")):
config_file = os.path.join(directory, "config.ini")
else:
config_file = None
options = parse(config_file)
random_state = np.random.RandomState(seed=options["seed"])
# First, compute MDS
if options["lengths"].endswith(".bed"):
lengths = load_lengths(os.path.join(directory, options["lengths"]))
else:
lengths = None
if options["counts"].endswith("npy"):
counts = np.load(os.path.join(directory, options["counts"]))
elif options["counts"].endswith(".matrix"):
counts = load_counts(os.path.join(directory, options["counts"]),
lengths=lengths)
if options["normalize"]:
counts = iced.filter.filter_low_counts(counts,
sparsity=False,
percentage=0.04)
counts = iced.normalization.ICE_normalization(counts, max_iter=300)
if not sparse.issparse(counts):
counts = sparse.coo_matrix(counts)
else:
counts = counts.tocsr()
counts.eliminate_zeros()
counts = counts.tocoo()
torm = np.array((counts.sum(axis=0) == 0)).flatten()
nmds = NMDS(alpha=options["alpha"],
beta=options["beta"],
random_state=random_state,
max_iter=options["max_iter"],
verbose=options["verbose"])
X = nmds.fit(counts)
X[torm] = np.nan
np.savetxt(os.path.join(directory, "NMDS." + options["output_name"]), X)
# PDB file
pdbfilename = os.path.join(directory,
"NMDS." + options["output_name"] + ".pdb")
# pdbfilename = "test.pdb"
writePDB(X, pdbfilename)
return True
def load_sample_yeast():
"""
Load and return a sample of S. cerevisiae contact count matrix from duan
et al, Nature, 2009
Returns
-------
counts, lengths:
tuple of two elements, the first a contact count matrix, the
second an ndarray containing the lengths of the chromosomes.
"""
module_path = dirname(__file__)
lengths = io.load_lengths(
os.path.join(module_path, "data/duan2009/duan.SC.10000.raw_sub.bed"))
counts = io.load_counts(
os.path.join(module_path,
"data/duan2009/duan.SC.10000.raw_sub.matrix"),
lengths=lengths)
counts = counts.toarray()
counts = counts.T + counts
return counts, lengths
def _get_counts(counts, lengths):
"""Load counts from file, or reformat counts object.
"""
if not isinstance(counts, list):
counts = [counts]
lengths = _get_lengths(lengths)
output = []
for f in counts:
if isinstance(f, np.ndarray) or sparse.issparse(f):
counts_maps = f
elif f.endswith(".npy"):
counts_maps = np.load(f)
elif f.endswith(".matrix"):
counts_maps = load_counts(f, lengths=lengths)
else:
raise ValueError("Counts file must end with .npy (for numpy array)"
" or .matrix (for hiclib / iced format)")
if sparse.issparse(counts_maps):
counts_maps = counts_maps.toarray()
counts_maps[np.isnan(counts_maps)] = 0
output.append(sparse.coo_matrix(counts_maps))
return output
sys.exit(1)
if args.perchr is True and args.bins is None:
print "--bins parameter is required when --perchr is specified"
sys.exit(1)
## bin option
if args.bins is not None:
chr_lengths = load_lengths_perchr(args.bins)
lengths = chr_lengths[0]
chrnames = chr_lengths[1]
else:
lengths = None
## Load counts in sparse format
counts = io.load_counts(args.filename, lengths=lengths)
## transform to integer if possible
if counts.data[0].is_integer():
counts.data = counts.data.astype(int)
## di/is option
if args.di is True or args.ins is True:
bins = load_bed(args.bins)
if len(bins) != counts.shape[1]:
print "Error - number of rows in BED and matrix files are not equal"
sys.exit(1)
if args.ins is True:
def myfunc( x, idx, org):
return "bin" + str(idx) + "|" + org + "|" + x[0] + ":" + x[1] + "-" + x[2]
from __future__ import print_function
import numpy as np
from glob import glob
from iced import io
from iced import utils
filenames = glob("data/ay2013/*10000_raw.matrix") + \
glob("data/lemieux2013/25kb/*.matrix")
filenames.sort()
for filename in filenames:
lengths = io.load_lengths(filename.replace(".matrix", ".bed"))
counts = io.load_counts(filename, lengths=lengths)
counts = counts.toarray()
counts = counts.T + counts
mask = utils.get_intra_mask(lengths)
# Just making sure there is no interaction counted in teh diag
counts[np.diag_indices_from(counts)] = 0
print(filename)
print("Total number of counts", counts.sum())
print("%% of intra", counts[mask].sum()/counts.sum() * 100)
print("%% of inter", counts[np.invert(mask)].sum()/counts.sum() * 100)
print()
def run_pm2(directory):
if os.path.exists(os.path.join(directory, "config.ini")):
config_file = os.path.join(directory, "config.ini")
else:
config_file = None
options = parse(config_file)
random_state = np.random.RandomState(seed=options["seed"])
options = parse(config_file)
if options["lengths"].endswith(".bed"):
lengths = load_lengths(os.path.join(directory, options["lengths"]))
else:
lengths = None
if options["counts"].endswith("npy"):
counts = np.load(os.path.join(directory, options["counts"]))
counts[np.arange(len(counts)), np.arange(len(counts))] = 0
elif options["counts"].endswith(".matrix"):
counts = load_counts(os.path.join(directory, options["counts"]),
lengths=lengths)
if options["normalize"]:
counts = iced.filter.filter_low_counts(counts,
sparsity=False,
percentage=0.04)
_, bias = iced.normalization.ICE_normalization(counts,
max_iter=300,
output_bias=True)
else:
bias = None
if not sparse.issparse(counts):
counts[np.isnan(counts)] = 0
counts = sparse.coo_matrix(counts)
else:
counts = counts.tocsr()
counts.eliminate_zeros()
counts = counts.tocoo()
pm2 = PM2(alpha=options["alpha"],
beta=options["beta"],
random_state=random_state,
max_iter=options["max_iter"],
bias=bias,
verbose=options["verbose"])
X = pm2.fit(counts)
torm = np.array(((counts + counts.transpose()).sum(axis=0) == 0)).flatten()
X[torm] = np.nan
np.savetxt(os.path.join(directory, "PM2." + options["output_name"]), X)
# PDB file
pdbfilename = os.path.join(directory,
"PM2." + options["output_name"] + ".pdb")
# pdbfilename = "test.pdb"
writePDB(X, pdbfilename)
return True
from __future__ import print_function
from iced import io
import numpy as np
print("Checking the normalized matrix can be re-loaded")
counts = io.load_counts("/tmp/iced_matrix.matrix")
# Load with np.loadtxt and check that the shape makes sense
print("Checking the shape of the written matrix makes sense")
t = np.loadtxt("/tmp/iced_matrix.matrix")
if t.shape[1] != 3:
raise ValueError("The shape of the written matrix doesn't make sense")
import numpy as np
from iced import io
from iced import filter
from iced import normalization
from iced import utils
from matplotlib.colors import LogNorm
import matplotlib.pyplot as plt
lengths = io.load_lengths("data/trophozoites_10000_raw.bed")
counts = io.load_counts("data/trophozoites_10000_raw.matrix", lengths=lengths)
counts = utils.from_sparse_to_dense(counts)
normed = filter.filter_low_counts(counts, remove_all_zeros_loci=True,
sparsity=False)
normed = normalization.ICE_normalization(normed)
normed, l = utils.extract_sub_contact_map(normed, lengths, [6, 7])
to_rm = normed.sum(axis=0) == 0
normed[to_rm] = np.nan
normed[:, to_rm] = np.nan
fig, ax = plt.subplots()
m = ax.matshow(np.log(normed+1), cmap="RdYlBu_r", vmax=5)
ax.set_xticks([])
ax.set_yticks([])
l = np.concatenate([[0], l])
[ax.axhline(i, color="0", linestyle="--") for i in l.cumsum()]
[ax.axvline(i, color="0", linestyle="--") for i in l.cumsum()]
