Critical assessment of AI in drug discovery

ABSTRACT

Introduction: Artificial Intelligence (AI) has become a component of our everyday lives, with applications ranging from recommendations on what to buy to the analysis of radiology images. Many of the techniques originally developed for other fields such as language translation and computer vision are now being applied in drug discovery. AI has enabled multiple aspects of drug discovery including the analysis of high content screening data, and the design and synthesis of new molecules.

Areas covered: This perspective provides an overview of the application of AI in several areas relevant to drug discovery including property prediction, molecule generation, image analysis, and organic synthesis planning.

Expert opinion: While a variety of machine learning methods are now being routinely used to predict biological activity and ADME properties, methods of representing molecules continue to evolve. Molecule generation methods are relatively new and unproven but hold the potential to access new, unexplored areas of chemical space. The application of AI in drug discovery will continue to benefit from dedicated research, as well as AI developments in other fields. With this pairing algorithmic advancements and high-quality data, the impact of AI in drug discovery will continue to grow in the coming years.

KEYWORDS:

• Artificial intelligence
• machine learning
• drug discovery
• QSAR; generative models; image analysis

Article Highlights

• AI is being applied to many aspects of the drug discovery process. Machine learning is being used to generate predictive models for a range of physical and biological endpoints.

• Neural networks are being used to develop new molecular representations for QSAR.

• Techniques adapted from areas such as computer vision are being applied to the analysis of microscopic images to identify cellular phenotypes.

• AI techniques are being used to analyze information from the chemical literature and propose new routes for organic synthesis.

• Generative models are able to extract patterns from chemical databases and use this information for the de novo design of new molecules.

While the field has made significant technical advances in a short period of time, it is still somewhat limited by the paucity of high-quality, publicly available, data.

Declaration of interest

WP Walters is an employee of Relay Therapeutics. The authors have no other relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript apart from those disclosed.

Reviewer Disclosures

Peer reviewers on this manuscript have no relevant financial or other relationships to disclose.