Drug development labs embrace digitization to overcome challenges and enhance healthcare.
Barriers to Innovation
Today, the discovery and development of new drugs is essential to the continued improvement of healthcare outcomes. The identification of effective therapeutics and vaccines for COVID-19, for example, shows how successful innovation can have a game-changing impact on medical practice and human health across the world.
The rewards may be huge, but on the flip side, drug discovery is an increasingly costly, risky and laborious affair. On average, it costs approximately US$ 2.6 billion to bring a new drug to market.
Scientific and technical challenges mean the probability of discovering a new drug and progressing it to clinical trials is around 35%, and the probability of successfully taking a candidate drug from Phase 1 trials to regulatory approval is somewhere in the region of 10% to 15%. From end to end, the whole process can take anywhere up to 15 years.
This perfect storm of expense, risk, and time represents a major obstacle to novel drug discovery, with market forces often skewing R&D towards areas with large financial returns, such as oncology and immunological diseases. Many therapeutic areas that lack the requisite economic drivers, such as infectious diseases, often struggle to secure the necessary funding for innovation.
The application of AI
Over the past five to 10 years, the field of artificial intelligence (AI) has developed hugely, with significant advances in areas such as machine learning (ML), neural networks, deep learning and generative AI. This development is already promising to transform drug discovery.
Martin Redhead, Executive Director Primary Pharmacology at UK-based, AI-driven pharmatech company Exscientia, explained:
“AI can offer multiple benefits in terms of novel drug innovation.
Firstly, through faster, more efficient drug discovery and design. Based on our track record to date, Exscientia is able to design a qualified clinical development candidate in around 12 months, compared to the traditional industry average of four to five years.
Our average number of compounds synthesized in this process averages approximately 250, versus industry average of 2,500 to 5,000.”
Redhead, who recently gave a keynote address at the Lab of the Future 2023 Congress in Amsterdam, also expects AI to enable the design and refinement of better-quality drugs, and to enhance clinical research. He added:
“This would potentially revert patients to good health faster, saving healthcare expenses, minimizing human suffering, and keeping people in jobs and productive.”
The Evolution of the AI-Driven Lab
The so-called “laboratory of the future” is a visionary concept: a goal that continually evolves as technology advances. Autonomous labs that combine AI-based data analysis with robotic synthesis and validation are now being demonstrated in both academia and industry.
These labs represent a radical new work environment in which machines perform many of the traditional functions of researchers. Proponents argue that this self-driven R&D environment will enhance the efforts of multidisciplinary scientists, who will maintain ultimate control.
With digitization and automation driving operational efficiency and scientific innovation, deep learning AI is now positioned to impact the entire nonclinical pathology laboratory workflow. Martin Redhead said:
“The laboratory of the future is a valuable platform for scientists and engineers at the intersection of drug discovery, automation, AI, and computer-aided experimentation, where we can share thoughts, ideas and best practices, and plot a course together.”
Towards an AI-Empowered Future
Many see 2023 as a formative year in the pharmaceutical industry’s journey to adopt AI and its pivotal role in the discovery and development of next-generation medicines. Martin Redhead added:
“At the moment, we’re just scratching the surface of what AI can help us do.
However, at Exscientia we predict that all drugs will be designed by AI by 2030. I also believe we’ll see the field move toward an end-to-end approach, which will help us truly deliver on the tremendous promise of AI-driven drug development.
Exscientia is pursuing an end-to-end approach utilizing AI, ML, automation, and other innovative methods across the entire drug discovery and early development value chain. For instance, the recent opening of our new automation lab in Oxford will enable us to complement AI with automation to close gaps and further enhance the efficiency and quality of the drug design process.”
