Commit 8903c2d8 authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

Modifications for revision

parent a963863b

examples/low_data/muv_attn_one_fold.py

+13 −15
Original line number Diff line number Diff line
@@ -16,8 +16,8 @@ K = 4 
# Depth of attention module

max_depth = 3

# number positive/negative ligands

n_pos = 1

n_neg = 1

n_pos = 10

n_neg = 10

# Set batch sizes for network

test_batch_size = 128

support_batch_size = n_pos + n_neg
@@ -27,13 +27,13 @@ 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



muv_tasks, dataset, transformers = load_muv_convmol()



# Define metric

metric = dc.metrics.Metric(

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

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



task_splitter = dc.splits.TaskSplitter()

fold_datasets = task_splitter.k_fold_split(dataset, K)
@@ -64,19 +64,17 @@ 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")

  ############################################################ 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(

  mean_scores, std_scores = model.evaluate(

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

  print("Scores on evaluation dataset")

  print(scores)
 


print("Mean Scores on evaluation dataset")

print(mean_scores)

print("Standard Deviations on evaluation dataset")

print(std_scores)

print("Median of Mean Scores")

print(np.median(np.array(mean_scores.values())))

examples/low_data/muv_graph_conv_one_fold.py

0 → 100644
+94 −0
Original line number Diff line number Diff line 
"""

Train low-data MUV models with graph-convolution. 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 tensorflow as tf

import deepchem as dc

from datasets import load_muv_convmol



# 4-fold splits

K = 4

# num positive/negative ligands

n_pos = 10

n_neg = 10

# 10 trials on test-set

n_trials = 20



muv_tasks, dataset, transformers = load_muv_convmol()



# Define metric

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)



train_folds = fold_datasets[:-1] 

train_dataset = dc.splits.merge_fold_datasets(train_folds)

test_dataset = fold_datasets[-1]



# Get supports on test-set

support_generator = dc.data.SupportGenerator(

    test_dataset, n_pos, n_neg, n_trials)



# Compute accuracies

task_scores = {task: [] for task in range(len(test_dataset.get_task_names()))}



for trial_num, (task, support) in enumerate(support_generator):

  print("Starting trial %d" % trial_num)

  # Train model on support

  g = tf.Graph()

  sess = tf.Session(graph=g)



  # Do setup required for tf/keras models

  # Number of features on conv-mols

  n_feat = 75

  # Batch size of models

  batch_size = 50



  with g.as_default():

    graph_model = dc.nn.SequentialGraph(n_feat)

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

    graph_model.add(dc.nn.GraphPool())

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

    graph_model.add(dc.nn.GraphPool())

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

    graph_model.add(dc.nn.GraphPool())

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

    graph_model.add(dc.nn.GraphGather(batch_size, activation="tanh"))



    with tf.Session() as sess:

      model = dc.models.MultitaskGraphClassifier(

        sess, graph_model, 1, batch_size=batch_size,

        learning_rate=1e-3, learning_rate_decay_time=1000,

        optimizer_type="adam", beta1=.9, beta2=.999)



      # Fit trained model

      model.fit(support, nb_epoch=10)



      # Test model

      task_dataset = dc.data.get_task_dataset_minus_support(

          test_dataset, support, task)

      y_pred = model.predict_proba(task_dataset)

      score = metric.compute_metric(

          task_dataset.y, y_pred, task_dataset.w)

      print("Score on task %s is %s" % (str(task), str(score)))

      task_scores[task].append(score)



# Join information for all tasks.

mean_task_scores = {}

std_task_scores = {}

for task in range(len(test_dataset.get_task_names())):

  mean_task_scores[task] = np.mean(np.array(task_scores[task]))

  std_task_scores[task] = np.std(np.array(task_scores[task]))



print("Mean scores")

print(mean_task_scores)

print("Standard Deviations")

print(std_task_scores)

print("Median of Mean Scores")

print(np.median(np.array(mean_task_scores.values())))

examples/low_data/muv_res_one_fold.py

+13 −16
Original line number Diff line number Diff line
@@ -16,8 +16,8 @@ K = 4 
# Depth of attention module

max_depth = 3

# num positive/negative ligands

n_pos = 1

n_neg = 1

n_pos = 10

n_neg = 10

# Set batch sizes for network

test_batch_size = 128

support_batch_size = n_pos + n_neg
@@ -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



muv_tasks, dataset, transformers = load_muv_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)
@@ -64,19 +63,17 @@ support_model.join(dc.nn.ResiLSTMEmbedding( 
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")

  ############################################################ 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(

  mean_scores, std_scores = model.evaluate(

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

  print("Scores on evaluation dataset")

  print(scores)
 


print("Mean Scores on evaluation dataset")

print(mean_scores)

print("Standard Deviations on evaluation dataset")

print(std_scores)

print("Median of Mean Scores")

print(np.median(np.array(mean_scores.values())))

examples/low_data/muv_rf_one_fold.py

+10 −2
Original line number Diff line number Diff line
@@ -14,8 +14,8 @@ from sklearn.ensemble import RandomForestClassifier 
# 4-fold splits

K = 4

# num positive/negative ligands

n_pos = 1

n_neg = 1

n_pos = 10

n_neg = 10

# 10 trials on test-set

n_trials = 20
@@ -55,6 +55,14 @@ for (task, support) in support_generator: 


# Join information for all tasks.

mean_task_scores = {}

std_task_scores = {}

for task in range(len(test_dataset.get_task_names())):

  mean_task_scores[task] = np.mean(np.array(task_scores[task]))

  std_task_scores[task] = np.std(np.array(task_scores[task]))



print("Mean scores")

print(mean_task_scores)

print("Standard Deviations")

print(std_task_scores)

print("Median of Mean Scores")

print(np.median(np.array(mean_task_scores.values())))

examples/low_data/muv_siamese_one_fold.py

+13 −16
Original line number Diff line number Diff line
@@ -13,8 +13,8 @@ from datasets import load_muv_convmol 
# Number of folds for split 

K = 4 

# num positive/negative ligands

n_pos = 1

n_neg = 1

n_pos = 10

n_neg = 10

# Set batch sizes for network

test_batch_size = 128

support_batch_size = n_pos + n_neg
@@ -25,13 +25,12 @@ n_steps_per_trial = 1 
learning_rate = 1e-4

log_every_n_samples = 50

# Number of features on conv-mols

n_feat = 71

n_feat = 75



muv_tasks, dataset, transformers = load_muv_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)
@@ -58,19 +57,17 @@ 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")

    support_batch_size=support_batch_size, learning_rate=learning_rate)



  ############################################################ 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(

  mean_scores, std_scores = model.evaluate(

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

  print("Scores on evaluation dataset")

  print(scores)
 


print("Mean Scores on evaluation dataset")

print(mean_scores)

print("Standard Deviations on evaluation dataset")

print(std_scores)

print("Median of Mean Scores")

print(np.median(np.array(mean_scores.values())))

CRA Git | Maintained and supported by SUSTech CRA and CCSE