Many drugs fail because of unexpected pharmacokinetics or side effects.
We present two novel machine learning algorithms that can, for any small molecule, perform : i. ADMET properties identification and ii. Off-target binding risk identification.
1. ADMET properties prediction
We have developed a novel in silico machine learning model that can predict 88 ADMET property endpoints for any compound.
We are using deep learning, a subset of machine learning based on artificial neural networks in which multiple layers of processing are used to extract many different features from the data. In particular, our machine learning algorithm for ADMET prediction can infer the following properties:
a. Absorption (e.g. Caco-2 permeability, PGP-inhibitor, HIA, etc.)
b. Distribution (e.g. BBB penetration, PPB, VD, etc.)
c. Metabolism (e.g. CYP inhibitor and substrate)
d. Excretion (e.g. drug half-life, clearance of drug)
e. Toxicity (e.g. hepatotoxicity, carcinogenicity, respiratory toxicity, etc.)
2. Off-target effect prediction
Determining side effects of drugs that have not yet entered clinical trials is an expensive and complex task. When a drug compound interacts with proteins other than those for which it was intended to bind (i.e. off-target interaction), unexpected side effects can occur which may be harmful for the human organism.
Our team has developed a machine learning algorithm to assess the degree of interaction that any drug compound has with numerous proteins across the human body, to predict potential side effects.
The solution can learn how a drug compound reacts with any human protein, and thereby be used to identify potential side effects. When a drug compound shows a low degree of interaction, it means that it interacts with a few proteins only. On the other hand, a high degree of interaction means that the drug displays activity with many proteins within the body.