Loading README.md +4 −4 Original line number Diff line number Diff line Loading @@ -263,14 +263,14 @@ Scaffold splitting |chembl |MT-NN regression |Index |0.443 |0.427 | | |MT-NN regression |Random |0.464 |0.434 | | |MT-NN regression |Scaffold |0.484 |0.361 | |gdb7 |MT-NN regression |Index |0.961 |0.011 | | |MT-NN regression |Random |0.742 |0.732 | |gdb7 |MT-NN regression |Index |0.994 |0.010 | | |MT-NN regression |Random |0.860 |0.773 | |kaggle |MT-NN regression |User-defined|0.748 |0.452 | |Dataset |Model |Splitting |Train score/MAE(kcal/mol)|Valid score/MAE(kcal/mol)| |----------------|--------------------|------------|-------------------------|-------------------------| |gdb7 |MT-NN regression |Index |44.5 |185.6 | | |MT-NN regression |Random |86.1 |92.2 | |gdb7 |MT-NN regression |Index |18.3 |172.0 | | |MT-NN regression |Random |44.3 |59.1 | * General features Loading examples/gdb7/gdb7_tf_model.py +10 −8 Original line number Diff line number Diff line Loading @@ -11,18 +11,20 @@ import numpy as np from gdb7_datasets import load_gdb7 np.random.seed(123) gdb7_tasks, datasets, transformers = load_gdb7(featurizer=dc.feat.CoulombMatrix(23)) split="random" num_atoms=23 gdb7_tasks, datasets, transformers = load_gdb7(featurizer=dc.feat.CoulombMatrix(num_atoms), split=split) train_dataset, valid_dataset, test_dataset = datasets #fit_transformers = [dc.trans.CoulombRandomizationFitTransformer(), dc.trans.NormalizationFitTransformer()] X = train_dataset.X fit_transformers = [dc.trans.CoulombFitTransformer(X, num_atoms=23)] fit_transformers = [dc.trans.CoulombFitTransformer(X, num_atoms)] regression_metric = dc.metrics.Metric(dc.metrics.mean_absolute_error, mode="regression") regression_metric = [dc.metrics.Metric(dc.metrics.mean_absolute_error, mode="regression"), dc.metrics.Metric(dc.metrics.pearson_r2_score, mode="regression")] model = dc.models.TensorflowMultiTaskFitTransformRegressor( n_tasks=len(gdb7_tasks), n_features=23, learning_rate=.001, momentum=.8, batch_size=512, learning_rate=.0002, momentum=.8, batch_size=512, weight_init_stddevs=[1/np.sqrt(2000),1/np.sqrt(800),1/np.sqrt(800),1/np.sqrt(1000)], bias_init_consts=[0.,0.,0.,0.], layer_sizes=[2000,800,800,1000], dropouts=[0.1,0.1,0.1,0.1], fit_transformers=fit_transformers, n_random_samples=10, seed=123) Loading @@ -31,10 +33,10 @@ model = dc.models.TensorflowMultiTaskFitTransformRegressor( model.fit(train_dataset, nb_epoch=50) model.save() train_scores = model.evaluate(train_dataset, [regression_metric], transformers) train_scores = model.evaluate(train_dataset, regression_metric, transformers) print("Train scores [kcal/mol]") print(train_scores) valid_scores = model.evaluate(valid_dataset, [regression_metric], transformers) valid_scores = model.evaluate(valid_dataset, regression_metric, transformers) print("Validation scores [kcal/mol]") print(valid_scores) Loading
README.md +4 −4 Original line number Diff line number Diff line Loading @@ -263,14 +263,14 @@ Scaffold splitting |chembl |MT-NN regression |Index |0.443 |0.427 | | |MT-NN regression |Random |0.464 |0.434 | | |MT-NN regression |Scaffold |0.484 |0.361 | |gdb7 |MT-NN regression |Index |0.961 |0.011 | | |MT-NN regression |Random |0.742 |0.732 | |gdb7 |MT-NN regression |Index |0.994 |0.010 | | |MT-NN regression |Random |0.860 |0.773 | |kaggle |MT-NN regression |User-defined|0.748 |0.452 | |Dataset |Model |Splitting |Train score/MAE(kcal/mol)|Valid score/MAE(kcal/mol)| |----------------|--------------------|------------|-------------------------|-------------------------| |gdb7 |MT-NN regression |Index |44.5 |185.6 | | |MT-NN regression |Random |86.1 |92.2 | |gdb7 |MT-NN regression |Index |18.3 |172.0 | | |MT-NN regression |Random |44.3 |59.1 | * General features Loading
examples/gdb7/gdb7_tf_model.py +10 −8 Original line number Diff line number Diff line Loading @@ -11,18 +11,20 @@ import numpy as np from gdb7_datasets import load_gdb7 np.random.seed(123) gdb7_tasks, datasets, transformers = load_gdb7(featurizer=dc.feat.CoulombMatrix(23)) split="random" num_atoms=23 gdb7_tasks, datasets, transformers = load_gdb7(featurizer=dc.feat.CoulombMatrix(num_atoms), split=split) train_dataset, valid_dataset, test_dataset = datasets #fit_transformers = [dc.trans.CoulombRandomizationFitTransformer(), dc.trans.NormalizationFitTransformer()] X = train_dataset.X fit_transformers = [dc.trans.CoulombFitTransformer(X, num_atoms=23)] fit_transformers = [dc.trans.CoulombFitTransformer(X, num_atoms)] regression_metric = dc.metrics.Metric(dc.metrics.mean_absolute_error, mode="regression") regression_metric = [dc.metrics.Metric(dc.metrics.mean_absolute_error, mode="regression"), dc.metrics.Metric(dc.metrics.pearson_r2_score, mode="regression")] model = dc.models.TensorflowMultiTaskFitTransformRegressor( n_tasks=len(gdb7_tasks), n_features=23, learning_rate=.001, momentum=.8, batch_size=512, learning_rate=.0002, momentum=.8, batch_size=512, weight_init_stddevs=[1/np.sqrt(2000),1/np.sqrt(800),1/np.sqrt(800),1/np.sqrt(1000)], bias_init_consts=[0.,0.,0.,0.], layer_sizes=[2000,800,800,1000], dropouts=[0.1,0.1,0.1,0.1], fit_transformers=fit_transformers, n_random_samples=10, seed=123) Loading @@ -31,10 +33,10 @@ model = dc.models.TensorflowMultiTaskFitTransformRegressor( model.fit(train_dataset, nb_epoch=50) model.save() train_scores = model.evaluate(train_dataset, [regression_metric], transformers) train_scores = model.evaluate(train_dataset, regression_metric, transformers) print("Train scores [kcal/mol]") print(train_scores) valid_scores = model.evaluate(valid_dataset, [regression_metric], transformers) valid_scores = model.evaluate(valid_dataset, regression_metric, transformers) print("Validation scores [kcal/mol]") print(valid_scores)
