Loading deepchem/molnet/check_availability.py +3 −1 Original line number Diff line number Diff line Loading @@ -178,6 +178,7 @@ CheckFeaturizer = { ('qm8', 'krr_ft'): ['CoulombMatrix', 1024], ('qm8', 'dtnn'): ['CoulombMatrix', [26, 26]], ('qm8', 'ani'): ['BPSymmetryFunction', [26, 4]], ('qm8', 'mpnn'): ['MP', [70, 8]], ('qm9', 'tf_regression'): ['ECFP', 1024], ('qm9', 'rf_regression'): ['ECFP', 1024], ('qm9', 'krr'): ['ECFP', 1024], Loading @@ -185,7 +186,8 @@ CheckFeaturizer = { ('qm9', 'tf_regression_ft'): ['CoulombMatrix', [29, 29]], ('qm9', 'krr_ft'): ['CoulombMatrix', 1024], ('qm9', 'dtnn'): ['CoulombMatrix', [29, 29]], ('qm9', 'ani'): ['BPSymmetryFunction', [29, 4]] ('qm9', 'ani'): ['BPSymmetryFunction', [29, 4]], ('qm9', 'mpnn'): ['MP', [70, 8]] } CheckSplit = { Loading deepchem/molnet/preset_hyper_parameters.py +10 −0 Original line number Diff line number Diff line Loading @@ -159,6 +159,16 @@ hps['ani'] = { 'layer_structures': [128, 128, 64], 'seed': 123 } hps['mpnn'] = { 'batch_size': 64, 'nb_epoch': 50, 'learning_rate': 0.001, 'T': 5, 'M': 10, 'n_hidden': 30, 'seed': 123 } hps['xgb_regression'] = { 'max_depth': 5, 'learning_rate': 0.05, Loading deepchem/molnet/run_benchmark_models.py +22 −2 Original line number Diff line number Diff line Loading @@ -426,7 +426,7 @@ def benchmark_regression(train_dataset, model: string, optional (default='tf_regression') choice of which model to use, should be: tf_regression, tf_regression_ft, graphconvreg, rf_regression, dtnn, dag_regression, xgb_regression, weave_regression weave_regression, krr, ani, krr_ft, mpnn test: boolean whether to calculate test_set performance hyper_parameters: dict, optional (default=None) Loading @@ -450,7 +450,7 @@ def benchmark_regression(train_dataset, assert model in [ 'tf_regression', 'tf_regression_ft', 'rf_regression', 'graphconvreg', 'dtnn', 'dag_regression', 'xgb_regression', 'weave_regression', 'krr', 'ani', 'krr_ft' 'ani', 'krr_ft', 'mpnn' ] if hyper_parameters is None: hyper_parameters = hps[model] Loading Loading @@ -697,6 +697,26 @@ def benchmark_regression(train_dataset, mode="regression", random_seed=seed) elif model_name == 'mpnn': batch_size = hyper_parameters['batch_size'] nb_epoch = hyper_parameters['nb_epoch'] learning_rate = hyper_parameters['learning_rate'] T = hyper_parameters['T'] M = hyper_parameters['M'] n_hidden = hyper_parameters['n_hidden'] model = deepchem.models.MPNNTensorGraph( len(tasks), n_atom_feat=n_features[0], n_pair_feat=n_features[1], n_hidden=n_hidden, T=T, M=M, batch_size=batch_size, learning_rate=learning_rate, use_queue=False, mode="regression") elif model_name == 'rf_regression': # Loading hyper parameters n_estimators = hyper_parameters['n_estimators'] Loading Loading
deepchem/molnet/check_availability.py +3 −1 Original line number Diff line number Diff line Loading @@ -178,6 +178,7 @@ CheckFeaturizer = { ('qm8', 'krr_ft'): ['CoulombMatrix', 1024], ('qm8', 'dtnn'): ['CoulombMatrix', [26, 26]], ('qm8', 'ani'): ['BPSymmetryFunction', [26, 4]], ('qm8', 'mpnn'): ['MP', [70, 8]], ('qm9', 'tf_regression'): ['ECFP', 1024], ('qm9', 'rf_regression'): ['ECFP', 1024], ('qm9', 'krr'): ['ECFP', 1024], Loading @@ -185,7 +186,8 @@ CheckFeaturizer = { ('qm9', 'tf_regression_ft'): ['CoulombMatrix', [29, 29]], ('qm9', 'krr_ft'): ['CoulombMatrix', 1024], ('qm9', 'dtnn'): ['CoulombMatrix', [29, 29]], ('qm9', 'ani'): ['BPSymmetryFunction', [29, 4]] ('qm9', 'ani'): ['BPSymmetryFunction', [29, 4]], ('qm9', 'mpnn'): ['MP', [70, 8]] } CheckSplit = { Loading
deepchem/molnet/preset_hyper_parameters.py +10 −0 Original line number Diff line number Diff line Loading @@ -159,6 +159,16 @@ hps['ani'] = { 'layer_structures': [128, 128, 64], 'seed': 123 } hps['mpnn'] = { 'batch_size': 64, 'nb_epoch': 50, 'learning_rate': 0.001, 'T': 5, 'M': 10, 'n_hidden': 30, 'seed': 123 } hps['xgb_regression'] = { 'max_depth': 5, 'learning_rate': 0.05, Loading
deepchem/molnet/run_benchmark_models.py +22 −2 Original line number Diff line number Diff line Loading @@ -426,7 +426,7 @@ def benchmark_regression(train_dataset, model: string, optional (default='tf_regression') choice of which model to use, should be: tf_regression, tf_regression_ft, graphconvreg, rf_regression, dtnn, dag_regression, xgb_regression, weave_regression weave_regression, krr, ani, krr_ft, mpnn test: boolean whether to calculate test_set performance hyper_parameters: dict, optional (default=None) Loading @@ -450,7 +450,7 @@ def benchmark_regression(train_dataset, assert model in [ 'tf_regression', 'tf_regression_ft', 'rf_regression', 'graphconvreg', 'dtnn', 'dag_regression', 'xgb_regression', 'weave_regression', 'krr', 'ani', 'krr_ft' 'ani', 'krr_ft', 'mpnn' ] if hyper_parameters is None: hyper_parameters = hps[model] Loading Loading @@ -697,6 +697,26 @@ def benchmark_regression(train_dataset, mode="regression", random_seed=seed) elif model_name == 'mpnn': batch_size = hyper_parameters['batch_size'] nb_epoch = hyper_parameters['nb_epoch'] learning_rate = hyper_parameters['learning_rate'] T = hyper_parameters['T'] M = hyper_parameters['M'] n_hidden = hyper_parameters['n_hidden'] model = deepchem.models.MPNNTensorGraph( len(tasks), n_atom_feat=n_features[0], n_pair_feat=n_features[1], n_hidden=n_hidden, T=T, M=M, batch_size=batch_size, learning_rate=learning_rate, use_queue=False, mode="regression") elif model_name == 'rf_regression': # Loading hyper parameters n_estimators = hyper_parameters['n_estimators'] Loading
