article

Machine learning approaches as tools to accelerate drug discovery

Posted: 12 December 2017 | , | No comments yet

Computational methods based on machine learning approaches are being introduced increasingly widely to screen the large number of molecules that have never participated in the drug discovery process, but which might have significant drug development potential. This article considers the latest advances in machine learning as applied to drug discovery…

Machine learning - image of computer circuits in a head

THE process of drug development is time consuming and costly. Several years are required for lead identification, optimisation, in vitro and in vivo testing, before the first clinical trials begin. The cost of developing a prescription drug that gains market approval, accounting for the very high failure rate, exceeds $2.5bn.1 Different approaches have been developed in recent years to accelerate and improve the success rate of the early drug discovery process, including high-throughput screening technology,2 3D culture screening,3 tissue printing4 and organs-on-chips technology.5 A significant advancement in the process of screening was introduced over a decade ago with quantitative high-throughput screening (qHTS),6 which allows the efficient identification of biological activities in chemical libraries by testing each library compound in a dose-response format. It was shown that qHTS can be successfully applied to finding new inhibitors for druggable7 and undruggable8 targets, epigenetics modulators,9 de-orphanisation of GPCR receptors,10 characterisation of cytochrome P450 isozyme selectivity across chemical libraries,11 and profiling of environmental chemicals’ potential to disrupt processes in the human body that may lead to negative health effects.12 qHTS can be used to screen large chemical libraries,13 producing high-quality chemical genomic data sets, which can be made publicly available through sites such as PubChem.

Send this to a friend