import pathlib
import logging
from os import path
import dfpl.options as opt
import dfpl.fingerprint as fp
import dfpl.autoencoder as ac
import dfpl.predictions as p
project_directory = pathlib.Path(__file__).parent.absolute()
test_predict_args = opt.PredictOptions(
inputFile=f"{project_directory}/data/Sun_etal_dataset.cids.predictionSet.csv",
outputDir=f"{project_directory}/validation/case_01/results/",
acFile=f"{project_directory}/validation/case_01/results/Sun_etal_dataset.AC.encoder.weights.hdf5",
model=f"{project_directory}/validation/case_01/results/AR_compressed-True.full.FNN-.model.hdf5",
target="AR",
fpSize=2048,
type="smiles",
fpType="topological"
)
def test_predictions():
opts = test_predict_args
logging.basicConfig(format="DFPL-%(levelname)s: %(message)s", level=logging.INFO)
logging.info(f"Predicting compounds in the input file {opts.inputFile} for association with target {opts.target}")
df = fp.importDataFile(opts.inputFile, import_function=fp.importSmilesCSV, fp_size=opts.fpSize)
use_compressed = False
encFPSize=256,
enableMultiLabel=False,
testingFraction=0.2,
kFolds=5,
verbose=2,
trainAC=True,
trainFNN=True,
compressFeatures=True)
logging.basicConfig(level=logging.INFO)
test_predict_args = options.PredictOptions(
inputFile=
f"{project_directory}/data/Sun_etal_dataset.cids.predictionSet.csv",
outputDir=f"{project_directory}/validation/case_01/results/",
ecWeightsFile=
f"/home/hertelj/git-hertelj/deepFPlearn_CODE/validation/case_00/results_AC_S/ac_S.encoder.hdf5",
model=
f"{project_directory}/validation/case_01/results/AR_compressed-True.full.FNN-.model.hdf5",
target="AR",
fpSize=2048,
type="smiles",
fpType="topological")
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,
zip(df['cid'], df['tanimoto'], df['allBoolEqual'])] + \
[t for t in df['toxid']]
img = Draw.MolsToGridImage(df['molS'].to_list() + df['molD'].to_list(),
molsPerRow=df.shape[0],
subImgSize=(200, 200),
legends=legend)
img.save('cidVStoxid.structures.png')
img.show()
project_directory = ""
opts = opt.PredictOptions(
inputFile=f"",
outputDir=f"/home/hertelj/tmp/",
model=
f"/home/hertelj/git-hertelj/deepFPlearn_CODE/validation/case_03/results/ER_compressed-True_sampled-None.best.FNN.model.hdf5",
target="ER",
fpSize=2048,
type="smiles",
fpType="topological")
(_, encoder) = ac.define_ac_model(input_size=2048, encoding_dim=256)
encoder.load_weights(
"/home/hertelj/git-hertelj/deepFPlearn_CODE/modeltraining/Sun_etal_dataset.encoder.hdf5"
)
data = ac.compress_fingerprints(dfS, encoder)
s_compressed = data[data['cid'].isin(cid_of_interest)]['fpcompressed']
df2 = predictions.predict_values(df=data, opts=opts, use_compressed=True)
s_predictions = df2[df2['cid'].isin(cid_of_interest)][['cid', 'trained']]