Description
462 medicinal products were withdrawn from the market between 1953and 2013[1]. The most common reason was hepatotoxicity. Determining
the toxicity at the early stages of drug discovery pipeline is therefore cru-
cial. At this point, using ‘in silico’ techniques is quick and effective for toxi-
city determination.
Over the past decades, rapid technological advancements in storing and
processing big data allowed scientists to use so called data hungry deep
learning algorithms in several tasks such as finding anomalies in climate
simulations, pattern learning in cosmology mass maps, speech decoding
from human neural recordings, new physics events classification at the
Large Hadron Collider.
The use of deep learning in pharmaceutical research has also started in re-
cent years. The Tox21[2] Data Challenge results showed that the deep
learning surpassed many other computational approaches like naive
Bayes, support vector machines, and random forests.
However, small and imbalanced dataset problems remained unsolved. To
solve these problems, we setup a deep learning framework named as
deepHUNT. deepHUNT is the first ML framework that uses image classifi-
cation for toxicity prediction. The architecture uses convolutional neural
networks. To reduce the possible bias, it uses 5 fold cross validation for
hyper parameter tuning. The first studies are applied on a cholestatic
dataset.
Preliminary results are quite encouraging and demonstrate the applicability
of deepHUNT for ‘in silico’ toxicology.
Finally, this work was made possible with the financial support provided by
eTRANSAFE.
| Period | 20 Sept 2018 |
|---|---|
| Event title | 22nd EuroQSAR: Translational and Health Informatics: Implications for Drug Discovery |
| Event type | Conference |
| Location | GreeceShow on map |
| Degree of Recognition | International |