def runAutoencoder(opts: opt.TrainOptions) -> None:
"""
Run and test auto-encoder
"""
logging.basicConfig(format="DFPL-%(levelname)s: %(message)s", level=logging.INFO)
logging.info("Adding fingerprint to dataset")
df = fp.importDataFile(opts.inputFile, import_function=fp.importSmilesCSV, fp_size=opts.fpSize)
logging.info("Training autoencoder")
ac.train_full_ac(df, opts)
logging.info("Done")
def run_fnn_training_multi(opts: opt.TrainOptions) -> None:
logging.basicConfig(format="DFPL-%(levelname)s: %(message)s",
level=logging.INFO)
logging.info("Adding fingerprint to dataset")
df = fp.importDataFile(opts.inputFile,
import_function=fp.importSmilesCSV,
fp_size=opts.fpSize)
t = opts.ecWeightsFile
opts.ecWeightsFile = opts.outputDir + t
if opts.trainAC:
logging.info("Training autoencoder")
encoder = ac.train_full_ac(df, opts)
# encoder.save_weights(opts.acFile)
else:
logging.info("Using trained autoencoder")
(_, encoder) = ac.define_ac_model(input_size=opts.fpSize,
encoding_dim=opts.encFPSize)
df = ac.compress_fingerprints(df, encoder)
# train FNNs with compressed features
logging.info("Training the FNN using compressed input data.")
fNN.train_nn_models_multi(df=df, opts=opts, use_compressed=True)
# train FNNs with uncompressed features
logging.info("Training the FNN using un-compressed input data.")
fNN.train_nn_models_multi(df=df, opts=opts, use_compressed=False)
logging.info("Done")
def train(opts: options.TrainOptions):
"""
Run the main training procedure
:param opts: Options defining the details of the training
"""
df = fp.importDataFile(opts.inputFile, import_function=fp.importSmilesCSV, fp_size=opts.fpSize)
# Create output dir if it doesn't exist
createDirectory(opts.outputDir)
if opts.compressFeatures: # compress features
if opts.trainAC:
# train an autoencoder on the full feature matrix
encoder = ac.train_full_ac(df, opts)
else:
# load trained model for autoencoder
(_, encoder) = ac.define_ac_model(input_size=opts.fpSize, encoding_dim=opts.encFPSize)
encoder.load_weights(makePathAbsolute(opts.ecWeightsFile))
# compress the fingerprints using the autoencoder
df = ac.compress_fingerprints(df, encoder)
if opts.trainFNN:
# train single label models
fNN.train_nn_models(df=df, opts=opts)
# train multi-label models
if opts.enableMultiLabel:
fNN.train_nn_models_multi(df=df, opts=opts)
ecWeightsFile="Sun_etal_dataset.encoder.hdf5",
type='smiles',
fpType='topological',
epochs=11,
fpSize=2048,
encFPSize=256,
enableMultiLabel=False,
testingFraction=0.2,
kFolds=5,
verbose=2,
trainFNN=False,
trainAC=True
)
def runAutoencoder(opts: opt.TrainOptions) -> None:
"""
Run and test auto-encoder
"""
logging.basicConfig(format="DFPL-%(levelname)s: %(message)s", level=logging.INFO)
logging.info("Adding fingerprint to dataset")
df = fp.importDataFile(opts.inputFile, import_function=fp.importSmilesCSV, fp_size=opts.fpSize)
logging.info("Training autoencoder")
ac.train_full_ac(df, opts)
logging.info("Done")
if __name__ == '__main__':
logging.basicConfig(format="DFPL-%(levelname)s: %(message)s", level=logging.INFO)
ac.train_full_ac(pd.read_pickle("/home/patrick/Workspace/PycharmProjects/deepFPlearn/modeltraining/df.pkl"), test_train_args)