def __init__(self, data, motifs, row_indices=None, background=None):
data = numpy.array(data)
row_sum = data.sum(axis=1)
# are we dealing with counts data?
if 0 <= data.min() and 1 < data.max():
# convert to freqs data
data = data / numpy.vstack(row_sum)
row_sum = data.sum(axis=1)
# are we dealing with freqs data?
if (data >= 0).all() and numpy.allclose(
row_sum[numpy.isnan(row_sum) == False], 1
):
# standard PSSM object creation
if background is None:
background = numpy.ones(len(motifs), dtype=float) / len(motifs)
self._background = numpy.array(background)
assert len(background) == len(
motifs
), "Mismatch between number of motifs and the background"
validate_freqs_array(self._background)
pssm = safe_log(data) - safe_log(self._background)
super(PSSM, self).__init__(
pssm, motifs, row_indices=row_indices, dtype=float
)
self._indices = numpy.arange(self.shape[0]) # used for scoring
return
if not (data.min() < 0 < data.max()):
raise ValueError("PSSM has been supplied invalid data")
# we dealing with pssm data
super(PSSM, self).__init__(data, motifs, row_indices=row_indices, dtype=float)
self._indices = numpy.arange(self.shape[0]) # used for scoring
def test_write_tabular_pssm(self):
"""correctly writes tabular data for PSSM"""
# data from test_profile
data = numpy.array([
[0.1, 0.3, 0.5, 0.1],
[0.25, 0.25, 0.25, 0.25],
[0.05, 0.8, 0.05, 0.1],
[0.7, 0.1, 0.1, 0.1],
[0.6, 0.15, 0.05, 0.2],
])
pssm = PSSM(data, "ACTG")
loader = io_app.load_tabular(sep="\t")
with TemporaryDirectory(dir=".") as dirname:
writer = io_app.write_tabular(data_path=dirname, format="tsv")
outpath = join(dirname, "delme.tsv")
writer.write(pssm, identifier=outpath)
new = loader(outpath)
expected = safe_log(data) - safe_log(
numpy.array([0.25, 0.25, 0.25, 0.25]))
for i in range(len(expected)):
j = i // 4
self.assertTrue(
numpy.isclose(new.array[i][2],
expected[j][i - j],
atol=0.0001))
def relative_entropy_terms(self, background=None):
"""
Computes a row-wise relative entropy terms per motif and stores them in a DictArray.
Parameters
----------
background : dict
{motif_1: prob_1, motif_2: prob_2, ...} is the specified background distribution.
Returns
-------
DictArray
Notes
-----
If background is type None, it defaults to equifrequent.
"""
if background is None:
num_motifs = len(self.motifs)
background = array([1 / num_motifs] * num_motifs)
else:
background = array([background.get(m, 0) for m in self.motifs])
validate_freqs_array(background)
ret = background * (safe_log(background) - safe_log(self.array))
return self.template.wrap(ret)
def test_safe_log(self):
"""safe_log: should handle pos/neg/zero/empty arrays"""
# normal valid array
a = array([[4, 0, 8], [2, 16, 4]])
assert_equal(safe_log(a), array([[2, 0, 3], [1, 4, 2]]))
# input integers, output floats
assert_allclose(safe_log(array([1, 2, 3])), array([0, 1, 1.5849625]))
# just zeros
a = array([[0, 0], [0, 0]])
assert_equal(safe_log(a), array([[0, 0], [0, 0]]))
# negative number
with self.assertRaises(FloatingPointError):
safe_log(array([0, 3, -4]))
# empty array
assert_equal(safe_log(array([])), array([]))
# double empty array
assert_equal(safe_log(array([[]])), array([[]]))
