Commit cef2632f authored by Bharath Ramsundar's avatar Bharath Ramsundar Committed by GitHub
Browse files

Merge pull request #382 from miaecle/gdb7_mod 

SAMPL dataset
parents 294805bb ab936d7b

README.md

+15 −6
Original line number Diff line number Diff line
@@ -245,12 +245,18 @@ Scaffold splitting 


|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         |

|                |graphconv regression|Random      |0.996         |0.873         |

|                |MT-NN regression    |Scaffold    |0.782         |0.426         |

|                |graphconv regression|Scaffold    |0.994         |0.606         |

|delaney         |MT-NN regression    |Index       |0.868         |0.578         |

|                |graphconv regression|Index       |0.967         |0.790         |

|                |MT-NN regression    |Random      |0.865         |0.574         |

|                |graphconv regression|Random      |0.964         |0.782         |

|                |MT-NN regression    |Scaffold    |0.866         |0.342         |

|                |graphconv regression|Scaffold    |0.967         |0.606         |

|sampl           |MT-NN regression    |Index       |0.917         |0.764         |

|                |graphconv regression|Index       |0.982         |0.864         |

|                |MT-NN regression    |Random      |0.908         |0.830         |

|                |graphconv regression|Random      |0.987         |0.868         |

|                |MT-NN regression    |Scaffold    |0.891         |0.217         |

|                |graphconv regression|Scaffold    |0.985         |0.666         |

|nci             |MT-NN regression    |Index       |0.171         |0.062         |

|                |graphconv regression|Index       |0.123         |0.048         |

|                |MT-NN regression    |Random      |0.168         |0.085         |
@@ -286,6 +292,7 @@ Number of tasks and examples in the datasets 
|sider           |27         |1427       |

|toxcast         |617        |8615       |

|delaney         |1          |1128       |

|sampl           |1          |643        |

|kaggle          |15         |173065     |

|nci             |60         |19127      |

|pdbbind(core)   |1          |195        |
@@ -322,6 +329,8 @@ Time needed for benchmark test(~20h in total) 
|                |graph convolution   |80              |900            |

|delaney         |MT-NN regression    |10              |40             |

|                |graphconv regression|10              |40             |

|sampl           |MT-NN regression    |10              |30             |

|                |graphconv regression|10              |40             |

|nci             |MT-NN regression    |400             |1200           |

|                |graphconv regression|400             |2500           |

|pdbbind(core)   |MT-NN regression    |0(featurized)   |30             |

deepchem/splits/splitters.py

+8 −10
Original line number Diff line number Diff line
@@ -351,20 +351,18 @@ class IndiceSplitter(Splitter): 
    """

    num_datapoints = len(dataset)

    indices = np.arange(num_datapoints).tolist()

    train_indices = []

    if self.valid_indices is None:

      self.valid_indices = []

    else:

      for indice in indices:

        if indice in self.valid_indices:

          indices.remove(indice)

    if self.test_indices is None:

      self.test_indices = []

    else:

    valid_test = self.valid_indices

    valid_test.extend(self.test_indices)

    for indice in indices:

        if indice in self.valid_indices:

          indices.remove(indice)

      if not indice in valid_test:

        train_indices.append(indice)

    

    return (indices, self.valid_indices, self.test_indices)

    return (train_indices, self.valid_indices, self.test_indices)





class ScaffoldSplitter(Splitter):

examples/benchmark.py

+6 −5
Original line number Diff line number Diff line
@@ -52,6 +52,7 @@ from nci.nci_datasets import load_nci 
from pdbbind.pdbbind_datasets import load_pdbbind_grid

from chembl.chembl_datasets import load_chembl

from gdb7.gdb7_datasets import load_gdb7

from sampl.sampl_datasets import load_sampl



def benchmark_loading_datasets(hyper_parameters, 

                               dataset='tox21', model='tf', split=None,
@@ -77,7 +78,8 @@ def benchmark_loading_datasets(hyper_parameters, 
  

  if dataset in ['muv', 'pcba', 'tox21', 'sider', 'toxcast']:

    mode = 'classification'

  elif dataset in ['kaggle', 'delaney', 'nci', 'pdbbind', 'chembl', 'gdb7']:

  elif dataset in ['kaggle', 'delaney', 'nci', 'pdbbind', 'chembl', 

                   'gdb7', 'sampl']:

    mode = 'regression'

  else:

    raise ValueError('Dataset not supported')
@@ -130,7 +132,8 @@ def benchmark_loading_datasets(hyper_parameters, 
                       'sider': load_sider, 'toxcast': load_toxcast,

                       'kaggle': load_kaggle, 'delaney': load_delaney,

                       'pdbbind': load_pdbbind_grid,

                       'chembl': load_chembl, 'gdb7': load_gdb7}

                       'chembl': load_chembl, 'gdb7': load_gdb7,

                       'sampl': load_sampl}

  

  print('-------------------------------------')

  print('Benchmark %s on dataset: %s' % (model, dataset))
@@ -163,8 +166,6 @@ def benchmark_loading_datasets(hyper_parameters, 
          model=model)      

    elif mode == 'regression':

      metric = 'r2'

      if dataset in ['gdb7']:

        metric = 'mae'

      train_score, valid_score = benchmark_regression(

          train_dataset, valid_dataset, tasks, 

          transformers, hp, n_features, metric=metric,
@@ -594,7 +595,7 @@ if __name__ == '__main__': 
                           'dropouts': [0.25, 0.25], 

                           'penalty': 0.0005, 'penalty_type': 'l2', 

                           'batch_size': 128, 'nb_epoch': 50, 

                           'learning_rate': 0.00008}]

                           'learning_rate': 0.0008}]

  

  hps['graphconvreg'] = [{'batch_size': 128, 'nb_epoch': 20, 

                          'learning_rate': 0.0005, 'n_filters': 128,

examples/gdb7/gdb7_datasets.py

+2 −2
Original line number Diff line number Diff line
@@ -17,7 +17,7 @@ def load_gdb7_from_mat(split=0): 
  if not os.path.exists('qm7.mat'): os.system('wget http://www.quantum-machine.org/data/qm7.mat')

  dataset = scipy.io.loadmat('qm7.mat')

  

  P = dataset['P'][range(0,split)+range(split+1,5)].flatten()

  P = dataset['P'][list(range(0,split))+list(range(split+1,5))].flatten()

  X = dataset['X'][P]

  y = dataset['T'][0,P]

  w = np.ones_like(y)
@@ -67,7 +67,7 @@ def load_gdb7(featurizer=None, split='random'): 
  with open(split_file, 'r') as f:

    reader = csv.reader(f)

    for row in reader:

      row_int = (np.asarray(list(map(int, row)))-1).tolist()

      row_int = (np.asarray(list(map(int, row)))).tolist()

      split_indices.append(row_int)

examples/sampl/SAMPL.csv

0 → 100644
+644 −0

File added.

Preview size limit exceeded, changes collapsed.

CRA Git | Maintained and supported by SUSTech CRA and CCSE