updates

from __future__ import division

from __future__ import unicode_literals

__version__ = '2.0.0'

__version__ = '2.1.0'

import deepchem.data

import deepchem.feat

"""Evaluation Metrics for Genomics Datasets."""

import numpy as np

from deepchem.data import NumpyDataset

from deepchem.utils.genomics import loaded_motifs

from scipy.signal import correlate2d

  # take max of fwd and reverse scores at each position

  scores = np.maximum(fwd_scores, rc_scores)

  return scores

def in_silico_mutagenesis(model, X):

  """Computes in-silico-mutagenesis scores

    Parameters

    ----------

    model: TensorGraph

      SequenceDNN?

    X: array...

      What shape?

    Returns

    -------

    #(num_task, N_sequences, 1, N_letters, sequence_length) ISM score array.

    (num_task, N_sequences, N_letters, sequence_length) ISM score array.

    """

  mutagenesis_scores = np.empty(X.shape + (model.num_tasks,), dtype=np.float32)

  wild_type_predictions = model.predict(NumpyDataset(X))

  wild_type_predictions = wild_type_predictions[:, np.newaxis, np.newaxis,

                                                np.newaxis]

  for sequence_index, (

      sequence,

      wild_type_prediction) in enumerate(zip(X, wild_type_predictions)):

    mutated_sequences = np.repeat(

        sequence[np.newaxis], np.prod(sequence.shape), axis=0)

    # remove wild-type

    arange = np.arange(len(mutated_sequences))

    horizontal_cycle = np.tile(

        np.arange(sequence.shape[-1]), sequence.shape[-2])

    mutated_sequences[arange, :, :, horizontal_cycle] = 0

    # add mutant

    vertical_repeat = np.repeat(

        np.arange(sequence.shape[-2]), sequence.shape[-1])

    mutated_sequences[arange, :, vertical_repeat, horizontal_cycle] = 1

    # make mutant predictions

    mutated_predictions = model.predict(NumpyDataset(mutated_sequences))

    mutated_predictions = mutated_predictions.reshape(sequence.shape +

                                                      (model.num_tasks,))

    mutagenesis_scores[

        sequence_index] = wild_type_prediction - mutated_predictions

  return np.rollaxis(mutagenesis_scores, -1)

from deepchem.metrics.genomic_metrics import get_motif_scores

from deepchem.metrics.genomic_metrics import get_pssm_scores

from deepchem.metrics.genomic_metrics import in_silico_mutagenesis

class TestGenomicMetrics(unittest.TestCase):

    pssm_scores = get_pssm_scores(sequences, pssm)

    self.assertEqual(pssm_scores.shape, (3, 5))

  def test_in_silico_mutagenesis(self):

    """Test in-silico mutagenesis returns correct shape."""

    # Construct and train SequenceDNN model

    X = np.random.rand(10, 1, 4, 50)

    y = np.random.randint(0, 2, size=(10, 1))

    dataset = dc.data.NumpyDataset(X, y)

    model = dc.models.SequenceDNN(

        50, "binary_crossentropy", num_filters=[1, 1], kernel_size=[15, 15])

    model.fit(dataset, nb_epoch=1)

    # Call in-silico mutagenesis

    mutagenesis_scores = in_silico_mutagenesis(model, X)

    print("mutagenesis_scores.shape")

    print(mutagenesis_scores.shape)

[metadata]

name = deepchem

author = Bharath Ramsundar, Evan Feinberg, Pande Lab Stanford

summary = Deep-learning models for drug discovery and quantum chemistry

home-page = https://github.com/pandegroup/deepchem

author = DeepChem contributors 

summary = Deep-learning models for drug discovery, quantum chemistry, and the life sciences.

home-page = https://github.com/deepchem/deepchem

license = MIT

version = 2.0.1

version = 2.1.0

classifier =

    Development Status :: 4 - Beta

    Environment :: Console