def test_wavefrontify(self, decorator, b):
l1, l2, s = 14, 37, 9
minval_open, maxval_open = 10.5, 11.5
minval_extend, maxval_extend = 0.8, 1.2
sim_mat = random_sim_mat(b, l1=l1, l2=l2, emb_dim=3)
gap_open = random_gap_penalty(minval_open, maxval_open, b, l1, l2)
gap_extend = random_gap_penalty(minval_extend, maxval_extend, b, l1,
l2)
w = alignment.weights_from_sim_mat(sim_mat, gap_open, gap_extend)
wavefrontify_fn = tf_ops.wavefrontify
unwavefrontify_fn = tf_ops.unwavefrontify
if decorator is not None:
wavefrontify_fn = decorator(wavefrontify_fn)
unwavefrontify_fn = decorator(unwavefrontify_fn)
w_wavefrontified = wavefrontify_fn(w)
w_unwavefrontified = unwavefrontify_fn(w_wavefrontified)
self.assertEqual(w_wavefrontified.shape, (l1 + l2 - 1, s, l1, b))
self.assertAllEqual(w_unwavefrontified, w)
for n in tf.range(b):
for a in tf.range(s):
for i in tf.range(l1):
for j in tf.range(l2):
self.assertEqual(w_wavefrontified[i + j, a, i, n],
w[n, i, j, a])
def forward(sw_params):
# Perturbs the Smith-Waterman LP parameters.
sim_mat, gap_open, gap_extend = sw_params[0], sw_params[1], sw_params[2]
sw_params = alignment.weights_from_sim_mat(sim_mat, gap_open, gap_extend)
shape, dtype = tf.shape(sw_params), sw_params.dtype
pert_shape = tf.concat([[num_samples], shape], axis=0)
noise, noise_grad = tf.nest.map_structure(
lambda t: tf.cast(t, dtype), noise_sampler(pert_shape))
pert_sw_params = tf.expand_dims(sw_params, 0) + sigma * noise
pert_sw_params = tf.reshape(pert_sw_params,
tf.concat([[-1], shape[1:]], axis=0))
# Computes optimal Smith-Waterman scores and alignments.
scores, paths = hard_sw_affine(pert_sw_params)
# Average scores and outputs over random perturbations
def perturbation_reshape(t):
new_shape = tf.concat([[num_samples], [-1], tf.shape(t)[1:]], 0)
return tf.reshape(t, new_shape)
scores = perturbation_reshape(scores) # [num_samples, batch]
paths = perturbation_reshape(paths) # [num_samples, batch, len1, len2, 9]
pert_scores = tf.reduce_mean(scores, axis=0)
pert_paths = tf.reduce_mean(paths, axis=0)
if stop_paths_gradient:
pert_paths = tf.stop_gradient(pert_paths)
def grad(ds, dp):
# Computes grad of scores w.r.t. (packed) sw_params.
grad_scores = pert_paths * tf.reshape(ds, [tf.shape(ds)[0], 1, 1, 1])
# Computes grad of scores w.r.t. sim_mat, gap_open and gap_extend.
grad_scores = alignment.adjoint_weights_from_sim_mat(
grad_scores, gap_open.shape, gap_extend.shape)
if stop_paths_gradient:
gradients = grad_scores
else:
# Flattens paths to shape [num_samples, batch, len1 * len2 * 9].
flat_paths = tf.reshape(
paths, [num_samples, tf.shape(paths)[1], -1])
flat_noise_grad = tf.reshape(
noise_grad, [num_samples, tf.shape(noise_grad)[1], -1])
# Flattens dp to shape [num_samples, len1 * len2 * 9]
flat_dp = tf.reshape(dp, [tf.shape(dp)[0], -1])
# Computes grad of paths w.r.t. (packed) sw_params.
grad_paths = tf.einsum('nbd,nb->bd', flat_noise_grad,
tf.einsum('nbd,bd->nb', flat_paths, flat_dp))
grad_paths /= sigma * num_samples
grad_paths = tf.reshape(grad_paths, shape) # [batch, len1, len2, 9]
# Computes grad of paths w.r.t. sim_mat, gap_open and gap_extend.
grad_paths = alignment.adjoint_weights_from_sim_mat(
grad_paths, gap_open.shape, gap_extend.shape)
# Adds gradients w.r.t. scores and gradients w.r.t. paths.
gradients = tf.nest.map_structure(
lambda x, y: x + y, grad_scores, grad_paths)
return gradients
return (pert_scores, pert_paths), grad
def test_smith_waterman_empty(self, decorator):
smith_waterman_fn = tf_ops.hard_sw_affine
if decorator is not None:
smith_waterman_fn = decorator(smith_waterman_fn)
tol = 1e-6
single_sub = - 5*tf.ones((5, 5))
toy_sub = tf.expand_dims(single_sub, 0)
toy_gap_open = 0.03 * tf.ones((toy_sub.shape[0],))
toy_gap_extend = 0.02 * tf.ones((toy_sub.shape[0],))
w = alignment.weights_from_sim_mat(toy_sub, toy_gap_open, toy_gap_extend)
values, paths = smith_waterman_fn(w, tol=tol)
paths_squeeze = alignment.path_label_squeeze(paths)
self.assertAllClose(values, [0.0], atol=2 * tol)
self.assertAllEqual(paths_squeeze, tf.zeros([1, 5, 5], tf.float32))
def setUp(self):
super().setUp()
single_sub = 6*tf.eye(5) - 5*tf.ones((5, 5))
second_sub = tf.tensor_scatter_nd_update(single_sub,
indices=[[0, 0], [1, 1]],
updates=[-5, -5])
third_sub = tf.tensor_scatter_nd_update(single_sub,
indices=[[0, 0], [2, 2]],
updates=[-5, -5])
fourth_sub = tf.tensor_scatter_nd_update(single_sub,
indices=[[0, 0], [4, 4]],
updates=[-5, -5])
self._toy_sub = tf.stack([single_sub, second_sub, third_sub, fourth_sub])
self._toy_gap_open = 0.03 * tf.ones((self._toy_sub.shape[0],))
self._toy_gap_extend = 0.02 * tf.ones((self._toy_sub.shape[0],))
self._weights = alignment.weights_from_sim_mat(self._toy_sub,
self._toy_gap_open,
self._toy_gap_extend)
def test_smith_waterman_termination(self, decorator):
smith_waterman_fn = tf_ops.hard_sw_affine
if decorator is not None:
smith_waterman_fn = decorator(smith_waterman_fn)
tol = 1e-6
single_sub = tf.concat([- 5*tf.ones((3, 1)),
6*tf.eye(3) - 5*tf.ones((3, 3))], 1)
toy_sub = tf.expand_dims(single_sub, 0)
toy_gap_open = 0.03 * tf.ones((toy_sub.shape[0],))
toy_gap_extend = 0.02 * tf.ones((toy_sub.shape[0],))
w = alignment.weights_from_sim_mat(toy_sub, toy_gap_open, toy_gap_extend)
values, paths = smith_waterman_fn(w, tol=tol)
paths_squeeze = alignment.path_label_squeeze(paths)
self.assertAllClose(values, [3.0], atol=2 * tol)
paths_squeeze_test = tf.convert_to_tensor([[[0., 1., 0., 0.],
[0., 0., 2., 0.],
[0., 0., 0., 2.]]], tf.float32)
self.assertAllEqual(paths_squeeze, paths_squeeze_test)
def unperturbed_alignment_score(sim_mat,
gap_open,
gap_extend):
"""Noiseless alignment score and paths from Smith-Waterman parameters."""
sw_params = alignment.weights_from_sim_mat(sim_mat, gap_open, gap_extend)
return hard_sw_affine(sw_params)
