Loading README.md +63 −52 Original line number Diff line number Diff line Loading @@ -244,7 +244,7 @@ Scaffold splitting * Regression |Dataset |Model |Splitting |Train score/R2|Valid score/R2| |-----------|--------------------|------------|--------------|--------------| |----------------|--------------------|------------|--------------|--------------| |delaney |MT-NN regression |Index |0.773 |0.574 | | |graphconv regression|Index |0.991 |0.825 | | |MT-NN regression |Random |0.769 |0.591 | Loading @@ -257,6 +257,9 @@ Scaffold splitting | |graphconv regression|Random |0.117 |0.076 | | |MT-NN regression |Scaffold |0.180 |0.052 | | |graphconv regression|Scaffold |0.131 |0.046 | |pdbbind(core) |MT-NN regression |Random |0.973 |0.494 | |pdbbind(refined)|MT-NN regression |Random |0.987 |0.503 | |pdbbind(full) |MT-NN regression |Random |0.983 |0.528 | |kaggle |MT-NN regression |User-defined|0.748 |0.452 | * General features Loading @@ -264,7 +267,7 @@ Scaffold splitting Number of tasks and examples in the datasets |Dataset |N(tasks) |N(samples) | |-----------|-----------|-----------| |----------------|-----------|-----------| |tox21 |12 |8014 | |muv |17 |93127 | |pcba |128 |439863 | Loading @@ -273,11 +276,16 @@ Number of tasks and examples in the datasets |delaney |1 |1128 | |kaggle |15 |173065 | |nci |60 |19127 | |pdbbind(core) |1 |195 | |pdbbind(refined)|1 |3706 | |pdbbind(full) |1 |11908 | Time needed for benchmark test(~20h in total) |Dataset |Model |Time(loading)/s |Time(running)/s| |-----------|--------------------|----------------|---------------| |----------------|--------------------|----------------|---------------| |tox21 |logistic regression |30 |60 | | |Multitask network |30 |60 | | |robust MT-NN |30 |90 | Loading @@ -302,6 +310,9 @@ Time needed for benchmark test(~20h in total) | |graphconv regression|10 |40 | |nci |MT-NN regression |400 |1200 | | |graphconv regression|400 |2500 | |pdbbind(core) |MT-NN regression |0(featurized) |30 | |pdbbind(refined)|MT-NN regression |0(featurized) |40 | |pdbbind(full) |MT-NN regression |0(featurized) |60 | |kaggle |MT-NN regression |2200 |3200 | Loading deepchem/splits/splitters.py +2 −1 Original line number Diff line number Diff line Loading @@ -269,6 +269,7 @@ class MolecularWeightSplitter(Splitter): """ np.testing.assert_almost_equal(frac_train + frac_valid + frac_test, 1.) if not seed is None: np.random.seed(seed) mws = [] Loading examples/benchmark.py +2 −2 Original line number Diff line number Diff line Loading @@ -101,8 +101,8 @@ def benchmark_loading_datasets(hyper_parameters, if dataset in ['pdbbind']: featurizer = 'grid' #pdbbind use grid featurizer if split in ['scaffold']: return #skip the scaffold splitting of pdbbind if split in ['scaffold', 'index']: return #skip the scaffold and index splitting of pdbbind if not model in ['tf_regression']: return Loading examples/stable_results.csv +1 −0 Original line number Diff line number Diff line Loading @@ -48,6 +48,7 @@ 0,delaney,random,regression,train,graphconvreg,0.9951851944,valid,graphconvreg,0.8397307618,time_for_running,102.9403319359 0,nci,random,regression,train,tf_regression,0.167724376,valid,tf_regression,0.0846994662,time_for_running,1255.847104311 0,nci,random,regression,train,graphconvreg,0.1173603957,valid,graphconvreg,0.0762376225,time_for_running,2608.3014204502 0,pdbbind,random,regression,train,tf_regression,0.9826504619,valid,tf_regression,0.5282495192,time_for_running,59.4712688923 0,tox21,scaffold,classification,train,tf,0.8626085326,valid,tf,0.7030201614,time_for_running,63.5685660839 0,tox21,scaffold,classification,train,tf_robust,0.8608722489,valid,tf_robust,0.7100530015,time_for_running,101.614424944 0,tox21,scaffold,classification,train,logreg,0.9004137009,valid,logreg,0.650190286,time_for_running,60.018599987 Loading Loading
README.md +63 −52 Original line number Diff line number Diff line Loading @@ -244,7 +244,7 @@ Scaffold splitting * Regression |Dataset |Model |Splitting |Train score/R2|Valid score/R2| |-----------|--------------------|------------|--------------|--------------| |----------------|--------------------|------------|--------------|--------------| |delaney |MT-NN regression |Index |0.773 |0.574 | | |graphconv regression|Index |0.991 |0.825 | | |MT-NN regression |Random |0.769 |0.591 | Loading @@ -257,6 +257,9 @@ Scaffold splitting | |graphconv regression|Random |0.117 |0.076 | | |MT-NN regression |Scaffold |0.180 |0.052 | | |graphconv regression|Scaffold |0.131 |0.046 | |pdbbind(core) |MT-NN regression |Random |0.973 |0.494 | |pdbbind(refined)|MT-NN regression |Random |0.987 |0.503 | |pdbbind(full) |MT-NN regression |Random |0.983 |0.528 | |kaggle |MT-NN regression |User-defined|0.748 |0.452 | * General features Loading @@ -264,7 +267,7 @@ Scaffold splitting Number of tasks and examples in the datasets |Dataset |N(tasks) |N(samples) | |-----------|-----------|-----------| |----------------|-----------|-----------| |tox21 |12 |8014 | |muv |17 |93127 | |pcba |128 |439863 | Loading @@ -273,11 +276,16 @@ Number of tasks and examples in the datasets |delaney |1 |1128 | |kaggle |15 |173065 | |nci |60 |19127 | |pdbbind(core) |1 |195 | |pdbbind(refined)|1 |3706 | |pdbbind(full) |1 |11908 | Time needed for benchmark test(~20h in total) |Dataset |Model |Time(loading)/s |Time(running)/s| |-----------|--------------------|----------------|---------------| |----------------|--------------------|----------------|---------------| |tox21 |logistic regression |30 |60 | | |Multitask network |30 |60 | | |robust MT-NN |30 |90 | Loading @@ -302,6 +310,9 @@ Time needed for benchmark test(~20h in total) | |graphconv regression|10 |40 | |nci |MT-NN regression |400 |1200 | | |graphconv regression|400 |2500 | |pdbbind(core) |MT-NN regression |0(featurized) |30 | |pdbbind(refined)|MT-NN regression |0(featurized) |40 | |pdbbind(full) |MT-NN regression |0(featurized) |60 | |kaggle |MT-NN regression |2200 |3200 | Loading
deepchem/splits/splitters.py +2 −1 Original line number Diff line number Diff line Loading @@ -269,6 +269,7 @@ class MolecularWeightSplitter(Splitter): """ np.testing.assert_almost_equal(frac_train + frac_valid + frac_test, 1.) if not seed is None: np.random.seed(seed) mws = [] Loading
examples/benchmark.py +2 −2 Original line number Diff line number Diff line Loading @@ -101,8 +101,8 @@ def benchmark_loading_datasets(hyper_parameters, if dataset in ['pdbbind']: featurizer = 'grid' #pdbbind use grid featurizer if split in ['scaffold']: return #skip the scaffold splitting of pdbbind if split in ['scaffold', 'index']: return #skip the scaffold and index splitting of pdbbind if not model in ['tf_regression']: return Loading
examples/stable_results.csv +1 −0 Original line number Diff line number Diff line Loading @@ -48,6 +48,7 @@ 0,delaney,random,regression,train,graphconvreg,0.9951851944,valid,graphconvreg,0.8397307618,time_for_running,102.9403319359 0,nci,random,regression,train,tf_regression,0.167724376,valid,tf_regression,0.0846994662,time_for_running,1255.847104311 0,nci,random,regression,train,graphconvreg,0.1173603957,valid,graphconvreg,0.0762376225,time_for_running,2608.3014204502 0,pdbbind,random,regression,train,tf_regression,0.9826504619,valid,tf_regression,0.5282495192,time_for_running,59.4712688923 0,tox21,scaffold,classification,train,tf,0.8626085326,valid,tf,0.7030201614,time_for_running,63.5685660839 0,tox21,scaffold,classification,train,tf_robust,0.8608722489,valid,tf_robust,0.7100530015,time_for_running,101.614424944 0,tox21,scaffold,classification,train,logreg,0.9004137009,valid,logreg,0.650190286,time_for_running,60.018599987 Loading
