Loading .travis.yml +1 −0 Original line number Diff line number Diff line Loading @@ -20,6 +20,7 @@ install: - conda install -c omnia keras - conda install seaborn - conda install six - conda install -c https://conda.anaconda.org/groakat pathos - python setup.py install script: - nosetests -v deepchem Loading deepchem/featurizers/coulomb_matrices.py +57 −0 Original line number Diff line number Diff line Loading @@ -155,3 +155,60 @@ class CoulombMatrix(Featurizer): else: continue return d class CoulombMatrixEig(CoulombMatrix): """ Calculate the eigenvales of Coulomb matrices for molecules. Parameters ---------- max_atoms : int Maximum number of atoms for any molecule in the dataset. Used to pad the Coulomb matrix. remove_hydrogens : bool, optional (default False) Whether to remove hydrogens before constructing Coulomb matrix. randomize : bool, optional (default False) Whether to randomize Coulomb matrices to remove dependence on atom index order. n_samples : int, optional (default 1) Number of random Coulomb matrices to generate if randomize is True. seed : int, optional Random seed. """ conformers = True name = 'coulomb_matrix' def __init__(self, max_atoms, remove_hydrogens=False, randomize=False, n_samples=1, seed=None): self.max_atoms = int(max_atoms) self.remove_hydrogens = remove_hydrogens self.randomize = randomize self.n_samples = n_samples if seed is not None: seed = int(seed) self.seed = seed def _featurize(self, mol): """ Calculate eigenvalues of Coulomb matrix for molecules. Eigenvalues are returned sorted by absolute value in descending order and padded by max_atoms. Parameters ---------- mol : RDKit Mol Molecule. """ cmat = self.coulomb_matrix(mol) features = [] for f in cmat: w, v = np.linalg.eig(f) w_abs = np.abs(w) sortidx = np.argsort(w_abs) sortidx = sortidx[::-1] w = w[sortidx] f = pad_array(w, self.max_atoms) features.append(f) features = np.asarray(features) return features deepchem/scripts/controller.sh +5 −3 Original line number Diff line number Diff line Loading @@ -2,9 +2,11 @@ #SBATCH --job-name=controller #SBATCH --output=controller_%A_%a.out #SBATCH --error=controller_%A_%a.err #SBATCH --time=24:00:00 #SBATCH --partition=normal #SBATCH -n 1 #SBATCH --time=12:00:00 ##SBATCH --partition=normal #SBATCH --partition=bigmem #SBATCH --qos=bigmem #SBATCH -n 4 ipcontroller --ip='*' --log-to-file=False & for i in {0..90}; do echo $i; Loading deepchem/scripts/featurize_pdbbind.py +3 −1 Original line number Diff line number Diff line Loading @@ -5,8 +5,10 @@ from deepchem.featurizers.basic import RDKitDescriptors from deepchem.featurizers.nnscore import NNScoreComplexFeaturizer from deepchem.featurizers.grid_featurizer import GridFeaturizer dataset_file = "../../datasets/pdbbind_core_df.pkl.gz" dataset_file = "../../../datasets/pdbbind_full_df.pkl.gz" print("About to load dataset form disk.") dataset = load_from_disk(dataset_file) print("Loaded dataset.") grid_featurizer = GridFeaturizer(voxel_width=16.0, feature_types="voxel_combined", voxel_feature_types=["ecfp", "splif", "hbond", "pi_stack", "cation_pi", "salt_bridge"], ecfp_power=9, splif_power=9, Loading Loading
.travis.yml +1 −0 Original line number Diff line number Diff line Loading @@ -20,6 +20,7 @@ install: - conda install -c omnia keras - conda install seaborn - conda install six - conda install -c https://conda.anaconda.org/groakat pathos - python setup.py install script: - nosetests -v deepchem Loading
deepchem/featurizers/coulomb_matrices.py +57 −0 Original line number Diff line number Diff line Loading @@ -155,3 +155,60 @@ class CoulombMatrix(Featurizer): else: continue return d class CoulombMatrixEig(CoulombMatrix): """ Calculate the eigenvales of Coulomb matrices for molecules. Parameters ---------- max_atoms : int Maximum number of atoms for any molecule in the dataset. Used to pad the Coulomb matrix. remove_hydrogens : bool, optional (default False) Whether to remove hydrogens before constructing Coulomb matrix. randomize : bool, optional (default False) Whether to randomize Coulomb matrices to remove dependence on atom index order. n_samples : int, optional (default 1) Number of random Coulomb matrices to generate if randomize is True. seed : int, optional Random seed. """ conformers = True name = 'coulomb_matrix' def __init__(self, max_atoms, remove_hydrogens=False, randomize=False, n_samples=1, seed=None): self.max_atoms = int(max_atoms) self.remove_hydrogens = remove_hydrogens self.randomize = randomize self.n_samples = n_samples if seed is not None: seed = int(seed) self.seed = seed def _featurize(self, mol): """ Calculate eigenvalues of Coulomb matrix for molecules. Eigenvalues are returned sorted by absolute value in descending order and padded by max_atoms. Parameters ---------- mol : RDKit Mol Molecule. """ cmat = self.coulomb_matrix(mol) features = [] for f in cmat: w, v = np.linalg.eig(f) w_abs = np.abs(w) sortidx = np.argsort(w_abs) sortidx = sortidx[::-1] w = w[sortidx] f = pad_array(w, self.max_atoms) features.append(f) features = np.asarray(features) return features
deepchem/scripts/controller.sh +5 −3 Original line number Diff line number Diff line Loading @@ -2,9 +2,11 @@ #SBATCH --job-name=controller #SBATCH --output=controller_%A_%a.out #SBATCH --error=controller_%A_%a.err #SBATCH --time=24:00:00 #SBATCH --partition=normal #SBATCH -n 1 #SBATCH --time=12:00:00 ##SBATCH --partition=normal #SBATCH --partition=bigmem #SBATCH --qos=bigmem #SBATCH -n 4 ipcontroller --ip='*' --log-to-file=False & for i in {0..90}; do echo $i; Loading
deepchem/scripts/featurize_pdbbind.py +3 −1 Original line number Diff line number Diff line Loading @@ -5,8 +5,10 @@ from deepchem.featurizers.basic import RDKitDescriptors from deepchem.featurizers.nnscore import NNScoreComplexFeaturizer from deepchem.featurizers.grid_featurizer import GridFeaturizer dataset_file = "../../datasets/pdbbind_core_df.pkl.gz" dataset_file = "../../../datasets/pdbbind_full_df.pkl.gz" print("About to load dataset form disk.") dataset = load_from_disk(dataset_file) print("Loaded dataset.") grid_featurizer = GridFeaturizer(voxel_width=16.0, feature_types="voxel_combined", voxel_feature_types=["ecfp", "splif", "hbond", "pi_stack", "cation_pi", "salt_bridge"], ecfp_power=9, splif_power=9, Loading
