Improving discovery and clinical trial success rates is critical for the future of drug development.
Drug discovery is a long and expensive process. A Deloitte Insights report from the Deloitte Centre for Health Solutions indicates that the expected return on investment has declined steadily from 10.1% in 2010 to 1.9% in 2018. As a result, the report states, finding ways of improving the efficiency and cost effectiveness of bringing new drugs to market is an imperative for the industry.
One of the factors reducing the accuracy of the discovery process is the lack of precise knowledge of the three-dimensional structure of drug compounds and targets; hence drug developers are leveraging Artificial Intelligence (AI) to improve the accuracy, predictability and speed of drug discovery.
According to the Deloitte Insight report, the number of AI companies focussed on discovering new drugs, while using innovative approaches to discovery and pre-clinical testing has increased rapidly. In Drug discovery, AI algorithms will mainly use research data or available information on the 3D structure and binding properties of small molecules to ‘recognise’ and target specificity with greater accuracy than has been possible. This is achieved using the same ‘deep learning’ processes used for face recognition, this concept is used to indentify unwanted interactions that would cause toxicity.
There are a large number of data sources for AI-enabled drug discovery and drug candidate selection. ‘Having real time access to as many datasets as possible will lead to new promising and unbiased insights on rare disease mechanisms and help optimise drug efficacy and safety,’ the report says.
‘Biopharma companies are increasingly adopting AI solutions to improve the discovery process. Like all innovation, the integration of AI into traditional processes needs to be underpinned by a robust strategy. Developing such a strategy has to include a number of considerations,’ the report says. These considerations include: Improving access to robust reliable data, increasing diversification of the drug discovery pipeline and acquiring new AI skills and talent.
The use of digital technologies holds many possibilities, not only for drug companies but across the chemical using sector as a whole. Computer models of molecules, on their own and in combination, enable the prediction of properties and chemical biological activity.
An SCI online webinar: Digital Design of Molecules and Formulations, supported by the Chemistry Council Innovation Committee, will explore the development journey of chemical products, focussing on the enabling technologies which are most critical for increasing productivity in chemistry using businesses, both now and in the future.
29 July 2020: 14:00-15:30 (BST)