AI in Drug Discovery
Over the past 50 years, drug discovery has focused largely on high-throughput screening for known disease-associated targets. This makes drug discovery a long, expensive and largely unsuccessful process.
According to one research report, the estimated average time to bring a molecule from discovery through to launch is 10-12 years.1 Another study has calculated that the average cost of the R&D process is now $2.168 billion per drug – almost double the $1.188 billion calculated in 2010. At the same time, the average forecast peak sales for assets in the drug pipeline fell by half to $407 million in 2018 from $816 million in 2010. As a result, the expected return on investment from drug development has declined steadily from 10.1 percent in 2010 to 1.9 percent in 2018.2 Finding ways to reduce the cost of bringing new drugs to market is an imperative for the entire industry.
One of the factors that can drive throughput in the discovery process is precise knowledge of the three-dimensional structure of compounds and targets and their binding affinity (specificity), which is ultimately what determines the efficacy of drug action, together with efficient drug delivery. This is where the market for drug discovery is focusing its attention: on using AI to improve the accuracy, predictability and speed of drug discovery.
AI can help in various ways, such as:
- Improving the agility of the research process
- Improving the accuracy of predictions on the efficacy and safety of drugs
- Improving the opportunity to diversify drug pipelines
Our first publication in the series on AI in Biopharma focuses on “Intelligent drug discovery” and showcases the impact that AI is making through a detailed review of 8 case studies. These case studies are from around the world and highlight the changing landscape of biopharma firms engaged in drug development; government and non-government interventions to drive AI-led discovery; and the growing importance of emerging markets in drug discovery. Regulations and laws are changing continually in response to the use of new technologies across industries, and biopharma companies need to develop their legal and ethical expertise in AI drug discovery. One thing is for sure - the future of drug discovery is going to be very different from the past!
1. Helen Dowden and Jamie Munro, Trends in clinical success rates and therapeutic focus, Springer Nature Limited, 8 May 2019, https://www.nature.com/articles/d41573-019-00074-z, accessed 23 September 2019.
2. Measuring the return from pharmaceutical innovation 2018, Deloitte