Commit f792d5d2 authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

Removing files not used in paper

parent f8caf53d

examples/low_data/datasets.py

+1 −1
Original line number Diff line number Diff line
@@ -175,7 +175,7 @@ def load_sider_convmol(): 


  loader = dc.data.CSVLoader(

      tasks=SIDER_tasks, smiles_field="smiles", featurizer=featurizer)

  dataset = loader.featurize(dataset_file, debug=True)

  dataset = loader.featurize(dataset_file)

  print("%d datapoints in SIDER dataset" % len(dataset))



  # Initialize transformers

examples/low_data/muv_attn_one_fold_no_train.py

deleted100644 → 0
+0 −83
Original line number Diff line number Diff line 
"""

Train low-data attn models on MUV. Test last fold only.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import tempfile

import numpy as np

import deepchem as dc

import tensorflow as tf

from datasets import load_muv_convmol



# Number of folds for split 

K = 4 

# Depth of attention module

max_depth = 3

# number positive/negative ligands

n_pos = 10

n_neg = 10

# Set batch sizes for network

test_batch_size = 128

support_batch_size = n_pos + n_neg

nb_epochs = 1

n_train_trials = 2000

n_eval_trials = 20

learning_rate = 1e-4

log_every_n_samples = 50

# Number of features on conv-mols

n_feat = 71



muv_tasks, dataset, transformers = load_muv_convmol()



# Define metric

metric = dc.metrics.Metric(

    dc.metrics.roc_auc_score, verbosity="high", mode="classification")



task_splitter = dc.splits.TaskSplitter()

fold_datasets = task_splitter.k_fold_split(dataset, K)



train_folds = fold_datasets[:-1] 

train_dataset = dc.splits.merge_fold_datasets(train_folds)

test_dataset = fold_datasets[-1]



# Train support model on train

support_model = dc.nn.SequentialSupportGraph(n_feat)



# Add layers

support_model.add(dc.nn.GraphConv(64, activation='relu'))

support_model.add(dc.nn.GraphPool())

support_model.add(dc.nn.GraphConv(128, activation='relu'))

support_model.add(dc.nn.GraphPool())

support_model.add(dc.nn.GraphConv(64, activation='relu'))

support_model.add(dc.nn.GraphPool())

support_model.add(dc.nn.Dense(128, activation='tanh'))



support_model.add_test(dc.nn.GraphGather(test_batch_size, activation='tanh'))

support_model.add_support(dc.nn.GraphGather(support_batch_size, activation='tanh'))



# Apply an attention lstm layer

support_model.join(dc.nn.AttnLSTMEmbedding(

    test_batch_size, support_batch_size, max_depth))



with tf.Session() as sess:

  model = dc.models.SupportGraphClassifier(

    sess, support_model, test_batch_size=test_batch_size,

    support_batch_size=support_batch_size, learning_rate=learning_rate,

    verbosity="high")



  # Turning off training to investigate

  ############################################################# DEBUG

  #print("FIT")

  ############################################################# DEBUG

  #model.fit(train_dataset, nb_epochs=nb_epochs, 

  #          n_episodes_per_epoch=n_train_trials,

  #          n_pos=n_pos, n_neg=n_neg, log_every_n_samples=log_every_n_samples)

  ############################################################ DEBUG

  print("EVAL")

  ############################################################ DEBUG

  scores = model.evaluate(

      test_dataset, metric, n_pos, n_neg, n_trials=n_eval_trials)

  print("Scores on evaluation dataset")

  print(scores)

examples/low_data/muv_res_one_fold_no_train.py

deleted100644 → 0
+0 −83
Original line number Diff line number Diff line 
"""

Train low-data res models on MUV. Test last fold only.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import tempfile

import numpy as np

import deepchem as dc

import tensorflow as tf

from datasets import load_muv_convmol



# Number of folds for split 

K = 4 

# Depth of attention module

max_depth = 3

# num positive/negative ligands

n_pos = 10

n_neg = 10

# Set batch sizes for network

test_batch_size = 128

support_batch_size = n_pos + n_neg

nb_epochs = 1

n_train_trials = 2000

n_eval_trials = 20

learning_rate = 1e-4

log_every_n_samples = 50

# Number of features on conv-mols

n_feat = 71



muv_tasks, dataset, transformers = load_muv_convmol()



# Define metric

metric = dc.metrics.Metric(

    dc.metrics.roc_auc_score, verbosity="high", mode="classification")



task_splitter = dc.splits.TaskSplitter()

fold_datasets = task_splitter.k_fold_split(dataset, K)



train_folds = fold_datasets[:-1] 

train_dataset = dc.splits.merge_fold_datasets(train_folds)

test_dataset = fold_datasets[-1]



# Train support model on train

support_model = dc.nn.SequentialSupportGraph(n_feat)



# Add layers

support_model.add(dc.nn.GraphConv(64, activation='relu'))

support_model.add(dc.nn.GraphPool())

support_model.add(dc.nn.GraphConv(128, activation='relu'))

support_model.add(dc.nn.GraphPool())

support_model.add(dc.nn.GraphConv(64, activation='relu'))

support_model.add(dc.nn.GraphPool())

support_model.add(dc.nn.Dense(128, activation='tanh'))



support_model.add_test(dc.nn.GraphGather(test_batch_size, activation='tanh'))

support_model.add_support(dc.nn.GraphGather(support_batch_size, activation='tanh'))



# Apply a residual lstm layer

support_model.join(dc.nn.ResiLSTMEmbedding(

    test_batch_size, support_batch_size, max_depth))



with tf.Session() as sess:

  model = dc.models.SupportGraphClassifier(

    sess, support_model, test_batch_size=test_batch_size,

    support_batch_size=support_batch_size, learning_rate=learning_rate,

    verbosity="high")



  # No training to see effect of random features.

  ############################################################# DEBUG

  #print("FIT")

  ############################################################# DEBUG

  #model.fit(train_dataset, nb_epochs=nb_epochs,

  #          n_episodes_per_epoch=n_train_trials,

  #          n_pos=n_pos, n_neg=n_neg, log_every_n_samples=log_every_n_samples)

  ############################################################ DEBUG

  print("EVAL")

  ############################################################ DEBUG

  scores = model.evaluate(

      test_dataset, metric, n_pos, n_neg, n_trials=n_eval_trials)

  print("Scores on evaluation dataset")

  print(scores)

examples/low_data/muv_siamese_one_fold_no_train.py

deleted100644 → 0
+0 −77
Original line number Diff line number Diff line 
"""

Train low-data siamese models on MUV. Test last fold only.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import numpy as np

import deepchem as dc

import tensorflow as tf

from datasets import load_muv_convmol



# Number of folds for split 

K = 4 

# num positive/negative ligands

n_pos = 10

n_neg = 10

# Set batch sizes for network

test_batch_size = 128

support_batch_size = n_pos + n_neg

nb_epochs = 1

n_train_trials = 2000

n_eval_trials = 20 

n_steps_per_trial = 1

learning_rate = 1e-4

log_every_n_samples = 50

# Number of features on conv-mols

n_feat = 71



muv_tasks, dataset, transformers = load_muv_convmol()



# Define metric

metric = dc.metrics.Metric(

    dc.metrics.roc_auc_score, verbosity="high", mode="classification")



task_splitter = dc.splits.TaskSplitter()

fold_datasets = task_splitter.k_fold_split(dataset, K)



train_folds = fold_datasets[:-1] 

train_dataset = dc.splits.merge_fold_datasets(train_folds)

test_dataset = fold_datasets[-1]



# Train support model on train

support_model = dc.nn.SequentialSupportGraph(n_feat)



# Add layers

support_model.add(dc.nn.GraphConv(64, activation='relu'))

support_model.add(dc.nn.GraphPool())

support_model.add(dc.nn.GraphConv(128, activation='relu'))

support_model.add(dc.nn.GraphPool())

support_model.add(dc.nn.GraphConv(64, activation='relu'))

support_model.add(dc.nn.GraphPool())

support_model.add(dc.nn.Dense(128, activation='tanh'))



support_model.add_test(dc.nn.GraphGather(test_batch_size, activation='tanh'))

support_model.add_support(dc.nn.GraphGather(support_batch_size, activation='tanh'))



with tf.Session() as sess:

  model = dc.models.SupportGraphClassifier(

    sess, support_model, test_batch_size=test_batch_size,

    support_batch_size=support_batch_size, learning_rate=learning_rate,

    verbosity="high")



  # Turning off training to gauge the accuracy of the random model.

  ############################################################# DEBUG

  #print("FIT")

  ############################################################# DEBUG

  #model.fit(train_dataset, nb_epochs=nb_epochs,

  #          n_episodes_per_epoch=n_train_trials,

  #          n_pos=n_pos, n_neg=n_neg, log_every_n_samples=log_every_n_samples)

  ############################################################ DEBUG

  print("EVAL")

  ############################################################ DEBUG

  scores = model.evaluate(

      test_dataset, metric, n_pos, n_neg, n_trials=n_eval_trials)

  print("Scores on evaluation dataset")

  print(scores)

examples/low_data/sider_attn_one_fold.py

+3 −5
Original line number Diff line number Diff line
@@ -27,13 +27,12 @@ n_eval_trials = 20 
learning_rate = 1e-4

log_every_n_samples = 50

# Number of features on conv-mols

n_feat = 71

n_feat = 75



sider_tasks, dataset, transformers = load_sider_convmol()



# Define metric

metric = dc.metrics.Metric(

    dc.metrics.roc_auc_score, verbosity="high", mode="classification")

metric = dc.metrics.Metric(dc.metrics.roc_auc_score, mode="classification")



task_splitter = dc.splits.TaskSplitter()

fold_datasets = task_splitter.k_fold_split(dataset, K)
@@ -64,8 +63,7 @@ support_model.join(dc.nn.AttnLSTMEmbedding( 
with tf.Session() as sess:

  model = dc.models.SupportGraphClassifier(

    sess, support_model, test_batch_size=test_batch_size,

    support_batch_size=support_batch_size, learning_rate=learning_rate,

    verbosity="high")

    support_batch_size=support_batch_size, learning_rate=learning_rate)



  ############################################################ DEBUG

  print("FIT")

CRA Git | Maintained and supported by SUSTech CRA and CCSE