Commit e17f245a authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

Kinase changes

parent c011725e

examples/kinase/KINASE_correlations.py

0 → 100644
+43 −0
Original line number Diff line number Diff line 
"""

Script that computes correlations of KINASE tasks. 

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import os

import numpy as np

import tempfile

import shutil

import deepchem as dc

import pandas as pd

from KINASE_datasets import load_kinase



###Load data###

np.random.seed(123)

shard_size = 2000

print("About to load KINASE data.")

KINASE_tasks, datasets, transformers = load_kinase(shard_size=shard_size)

train_dataset, valid_dataset, test_dataset = datasets



y_train = train_dataset.y

n_tasks = y_train.shape[1]



all_results = []

for task in range(n_tasks):

  y_task = y_train[:, task]

  task_results = []

  for other_task in range(n_tasks):

    if task == other_task:

      task_results.append(1.)

      continue

    y_other = y_train[:, other_task]

    r2 = dc.metrics.pearson_r2_score(y_task, y_other)

    print("r2 for %s-%s is %f" % (task, other_task, r2))

    task_results.append(r2)

  print("Task %d" % task)

  print(task_results)

  all_results.append(task_results)

print("Writing results to kinase_corr.csv")

df = pd.DataFrame(all_results)

df.to_csv("kinase_corr.csv")

examples/kinase/KINASE_datasets.py

+1 −5
Original line number Diff line number Diff line
@@ -30,11 +30,7 @@ def remove_missing_entries(dataset): 


def get_transformers(train_dataset):

  """Get transformers applied to datasets."""

  #transformers = []

  transformers = [

      dc.trans.LogTransformer(transform_X=True),

      dc.trans.NormalizationTransformer(transform_y=True,

                                        dataset=train_dataset)]

  transformers = []

  return transformers



def gen_kinase(KINASE_tasks, raw_train_dir, train_dir, valid_dir, test_dir,

examples/kinase/KINASE_rf_model.py

+3 −3
Original line number Diff line number Diff line
@@ -16,7 +16,8 @@ from KINASE_datasets import load_kinase 
###Load data###

np.random.seed(123)

shard_size = 2000

num_trials = 5

#num_trials = 5

num_trials = 1

print("About to load KINASE data.")

KINASE_tasks, datasets, transformers = load_kinase(shard_size=shard_size)

train_dataset, valid_dataset, test_dataset = datasets
@@ -35,8 +36,7 @@ metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, task_averager=np.mean) 


def task_model_builder(model_dir):

  sklearn_model = RandomForestRegressor(

      #n_estimators=100, max_features=int(num_features/3),

      n_estimators=1, max_features=int(num_features/3),

      n_estimators=100, max_features=int(num_features/3),

      min_samples_split=5, n_jobs=-1)

  return dc.models.SklearnModel(sklearn_model, model_dir)

examples/kinase/KINASE_tf_model.py

+67 −29
Original line number Diff line number Diff line
@@ -11,14 +11,16 @@ import tempfile 
import shutil

import numpy as np

import deepchem as dc

from MERCK_datasets import load_kinase

from KINASE_datasets import load_kinase



# Set numpy seed

np.random.seed(123)



###Load data###

shard_size = 2000

num_shards_per_batch = 4

print("About to load MERCK data.")

KINASE_tasks, datasets, transformers = load_kinase(

    shard_size=shard_size, num_shards_per_batch=num_shards_per_batch)

num_trials = 5

print("About to load KINASE data.")

KINASE_tasks, datasets, transformers = load_kinase(shard_size=shard_size)

train_dataset, valid_dataset, test_dataset = datasets



print("Number of compounds in train set")
@@ -28,6 +30,8 @@ print(len(valid_dataset)) 
print("Number of compounds in test set")

print(len(test_dataset))



all_results = []

for trial in range(num_trials):

  ###Create model###

  n_layers = 3

  nb_epoch = 50
@@ -43,18 +47,52 @@ model = dc.models.TensorflowMultiTaskRegressor( 
  metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, task_averager=np.mean)



  print("Training model")

model.fit(train_dataset, nb_epoch=nb_epoch)

  model.fit(train_dataset, nb_epoch=nb_epoch, max_checkpoints_to_keep=1)



  print("Evaluating models")

  train_score, train_task_scores = model.evaluate(

      train_dataset, [metric], transformers, per_task_metrics=True)

  valid_score, valid_task_scores = model.evaluate(

      valid_dataset, [metric], transformers, per_task_metrics=True)

  test_score, test_task_scores = model.evaluate(

      test_dataset, [metric], transformers, per_task_metrics=True)



  all_results.append((train_score, train_task_scores,

                      valid_score, valid_task_scores,

                      test_score, test_task_scores))



train_scores = model.evaluate(train_dataset, [metric], transformers)

valid_scores = model.evaluate(valid_dataset, [metric], transformers)

#Only use for final evaluation

test_scores = model.evaluate(test_dataset, [metric], transformers)

  print("Scores for trial %d" % trial)

  print("----------------------------------------------------------------")

  print("train_task_scores")

  print(train_task_scores)

  print("Mean Train score")

  print(train_score)

  print("valid_task_scores")

  print(valid_task_scores)

  print("Mean Validation score")

  print(valid_score)

  print("test_task_scores")

  print(test_task_scores)

  print("Mean Test score")

  print(test_score)



print("Train scores")

print(train_scores)

print("####################################################################")



print("Validation scores")

print(valid_scores)

for trial in range(num_trials):

  (train_score, train_task_scores, valid_score, valid_task_scores,

   test_score, test_task_scores) = all_results[trial]



print("Test scores")

print(test_scores)
 
  print("Scores for trial %d" % trial)

  print("----------------------------------------------------------------")

  print("train_task_scores")

  print(train_task_scores)

  print("Mean Train score")

  print(train_score)

  print("valid_task_scores")

  print(valid_task_scores)

  print("Mean Validation score")

  print(valid_score)

  print("test_task_scores")

  print(test_task_scores)

  print("Mean Test score")

  print(test_score)

examples/kinase/KINASE_tf_progressive.py

+63 −30
Original line number Diff line number Diff line
@@ -11,17 +11,16 @@ import tempfile 
import shutil

import numpy as np

import deepchem as dc

from MERCK_datasets import load_kinase

from KINASE_datasets import load_kinase



# Set numpy seed

np.random.seed(123)



###Load data###

shard_size = 2000

num_shards_per_batch = 4

print("About to load MERCK data.")

KINASE_tasks, datasets, transformers = load_kinase(

    shard_size=shard_size, num_shards_per_batch=num_shards_per_batch)

num_trials = 5

print("About to load KINASE data.")

KINASE_tasks, datasets, transformers = load_kinase(shard_size=shard_size)

train_dataset, valid_dataset, test_dataset = datasets



print("Number of compounds in train set")
@@ -31,6 +30,8 @@ print(len(valid_dataset)) 
print("Number of compounds in test set")

print(len(test_dataset))



all_results = []

for trial in range(num_trials):

  ###Create model###

  n_layers = 3

  nb_epoch = 50
@@ -40,26 +41,58 @@ model = dc.models.ProgressiveMultitaskRegressor( 
      alpha_init_stddevs=[.02]*n_layers, weight_init_stddevs=[.02]*n_layers,

      bias_init_consts=[1.]*n_layers, learning_rate=.0003,

      penalty=.0001, penalty_type="l2", optimizer="adam", batch_size=100,

    seed=123, verbosity="high")



      seed=123)



  #Use R2 classification metric

  metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, task_averager=np.mean)



  print("Training model")

  model.fit(train_dataset, nb_epoch=nb_epoch)

#model.old_fit(train_dataset, nb_epoch=nb_epoch)



train_scores = model.evaluate(train_dataset, [metric], transformers)

valid_scores = model.evaluate(valid_dataset, [metric], transformers)

#Only use for final evaluation

test_scores = model.evaluate(test_dataset, [metric], transformers)

  print("Evaluating models")

  train_score, train_task_scores = model.evaluate(

      train_dataset, [metric], transformers, per_task_metrics=True)

  valid_score, valid_task_scores = model.evaluate(

      valid_dataset, [metric], transformers, per_task_metrics=True)

  test_score, test_task_scores = model.evaluate(

      test_dataset, [metric], transformers, per_task_metrics=True)



  all_results.append((train_score, train_task_scores,

                      valid_score, valid_task_scores,

                      test_score, test_task_scores))



  print("Scores for trial %d" % trial)

  print("----------------------------------------------------------------")

  print("train_task_scores")

  print(train_task_scores)

  print("Mean Train score")

  print(train_score)

  print("valid_task_scores")

  print(valid_task_scores)

  print("Mean Validation score")

  print(valid_score)

  print("test_task_scores")

  print(test_task_scores)

  print("Mean Test score")

  print(test_score)



print("Train scores")

print(train_scores)

print("####################################################################")



print("Validation scores")

print(valid_scores)

for trial in range(num_trials):

  (train_score, train_task_scores, valid_score, valid_task_scores,

   test_score, test_task_scores) = all_results[trial]



print("Test scores")

print(test_scores)
 
  print("Scores for trial %d" % trial)

  print("----------------------------------------------------------------")

  print("train_task_scores")

  print(train_task_scores)

  print("Mean Train score")

  print(train_score)

  print("valid_task_scores")

  print(valid_task_scores)

  print("Mean Validation score")

  print(valid_score)

  print("test_task_scores")

  print(test_task_scores)

  print("Mean Test score")

  print(test_score)

CRA Git | Maintained and supported by SUSTech CRA and CCSE