By: Dr Neil Thompson, Chief Scientific Officer at Healx, a company member of the Rare Disease Company Coalition
Innovation in the biopharma industry isn’t always about the development of a new therapy for a condition – sometimes it means pioneering an entirely new approach. Right now, we’re witnessing exactly that, as artificial intelligence (AI) promises to re-engineer the entire drug discovery and development process.
Indeed, AI and other new approaches are allowing novel treatments to be designed, developed and delivered more quickly and on a scale never before seen in the industry. This is offering hope to millions of patients in need – particularly those living with a rare condition (95% of which still lack an approved treatment today).
But what are the implications of this technology for policy, patients and treatment pipelines?
How did we get here?
The historical phenotypic-based and target-based approaches of drug discovery have delivered many of the life-saving and life-changing treatments that health systems now have available to them. Yet, despite the successes, the philosophy of ‘one disease, one target, one drug’ has its limitations.
Traditionally, drugs have been developed to target a single biological entity, and it was viewed as undesirable for a drug to interact with multiple targets due to possible adverse side effects. But this approach often fails complex medical conditions, especially many rare diseases which exhibit a broad range of symptoms and causes.
Increasingly, there is evidence that a molecule hitting more than one target, or multiple molecules targeting a single disease, can create a more efficacious profile compared to single-targeted molecules. However, whilst we are seeing a slight increase in the number of multi-target therapies being approved by the FDA (21% of all FDA-approved agents between 2015-2017 were multi-target drugs), the majority of drugs being studied and in line for approval are still addressing a single target.
This poses a problem for rare diseases not only for the biological reasons mentioned above, but also because policy focused on single target therapies continues to steer therapy development towards common diseases – where there are larger patient populations from which to recoup R&D costs – meaning rare conditions remain overlooked.
Policy for progress
Advances in AI in the last decade have helped improve core processes within the drug discovery and development pipeline – from predicting protein structures and discovering new compounds, to monitoring patients during clinical trials and shaping go-to-market strategies.
AI is particularly adept at tackling the conventional challenges of rare disease treatment development. For example, Natural Language Processing (NLP) models can overcome the lack of consolidated knowledge about a rare condition by automatically scanning literature to fill in the gaps with up-to-date data. Machine Learning (ML) algorithms can speed up the drug discovery and development timeline by looking for connections between diseases and the pharmacology of compounds that are already approved for use in another condition, thereby providing valuable insight into targetable mechanisms for diseases that are still poorly understood biologically. And AI can provide the automation and scale needed to provide cost-effective treatments, thereby reducing the cost of R&D for smaller patient populations.
But therapies for rare diseases can only be developed more efficiently and cost-effectively when policy and regulation keeps up with technology. Promisingly, progress is being made in this space.
The Orphan Drug Act of 1983 ushered in a new energy to focus on rare diseases, granting financial and regulatory incentives for the biotech and pharmaceutical industry to develop treatments for them. The 21st Century Cures Act also provided additional incentives and regulatory changes, and policies like the Orphan Drug Tax Credit and the Accelerated Approval Pathway help improve the likelihood of investment in the rare disease space in order to catalyse the therapy development process and increase the likelihood of therapies reaching patients.
Then there are groups like the Rare Disease Company Coalition, who are championing further changes in policy and regulation to support technological advances in rare therapy development.
Just the beginning
What makes AI and other technological advances so fascinating is that as computing power and improvements to data quality are made, they can be rapidly scaled up. The solutions will come faster and faster as biotechs become able to automate more of the process and run more of it in parallel, with expert humans placed along the chain, at decision points where they can provide maximum impact.
It’s not hard to imagine a future where we’re able to discover treatments for whole groups of conditions at once, guided by both technological and human insight. Suddenly, no disease, however rare, need be overlooked, no question about biology left unanswered. But policies and regulations need to be in place to support these advances, so that tech-derived therapies can reach patients more quickly, especially in the rare disease sector.
Pharmacology isn’t just another discipline for AI to be applied to. It could be the most disruptive transformation in the 21st century. It is essential that government policies continue to keep pace with innovation so that novel uses of technology, including AI, can be readily deployed and utilized across treatment discovery and development to better support people with rare diseases.
We are on the cusp of great progress, we can’t afford to be slowed down now.
Bringing over 30 years experience in drug discovery and development, Neil leads Healx’s preclinical work and is deeply passionate about the application of AI to improve rare disease patient access to treatments.