Recursion Pharmaceuticals recently announced results from its Phase 2 SYCAMORE trial for REC-994, a drug candidate targeting cerebral cavernous malformation (CCM). The trial met its primary safety endpoint but showed mixed efficacy results, illustrating the complexities of translating AI-driven discoveries into clinical success. This outcome underscores both the promise and the hurdles of leveraging artificial intelligence in pharmaceutical research and development.
The SYCAMORE clinical trial targeted CCM, a rare brain disorder affecting approximately 360,000 symptomatic individuals in the U.S. and EU. Recursion's approach involves using its Recursion OS platform, which employs machine-learning algorithms to analyze extensive datasets, aiming to identify new drug candidates more efficiently than traditional methods.
AI's Role in Drug Discovery
Alister Campbell, VP of science and technology at Dotmatics, noted that AI-native biotechnology companies and their partners have advanced 75 candidates to clinical trials since 2015, with increasing numbers each year. AI applications range from drug repurposing to predicting structures of antibodies and proteins using algorithms like AlphaFold, designing small molecule drugs using generative AI methods, and mining vast OMIC datasets for insights into disease biology, druggable targets, and biomarkers.
However, challenges remain, particularly for rare neurological conditions. Keaun Amani, CEO of Neurosnap, pointed out that the scarcity of information on uncommon neurological conditions poses a major challenge, as limited patient populations make it difficult to gather sufficient data for training accurate AI models.
Trial Outcomes and Industry Challenges
Dr. Najat Khan, chief R&D officer at Recursion, noted "promising trends in exploratory efficacy endpoints," particularly at the highest dose of REC-994. However, the company acknowledged that "improvements in either patient or physician-reported outcomes were not yet seen at the 12-month time point." This reflects broader industry challenges in accurately predicting drug efficacy due to the complexity of biological systems.
Jo Varshney, founder and CEO of VeriSIM Life, added that neurological conditions often lack clear, easily measurable indicators in lab tests or clinical assessments, resulting in data scarcity that limits the effectiveness of AI systems.
Navigating the Path Forward
Experts suggest various approaches to advance AI in drug discovery. Amani envisions developing more complex, all-atom models capable of analyzing larger biological systems, combined with a growing trend of blending machine learning and physics-based methods to simulate molecular interactions with unprecedented accuracy.
Campbell proposes combining AI with traditional techniques to identify relevant biological targets and develop drug candidates more efficiently. This multi-pronged approach aims to identify clinically relevant biological targets, develop ideal candidates more quickly and cheaply, and reduce the chances of failure due to safety, efficacy, and cost issues.
Accessibility of AI tools is also crucial. Amani noted that platforms like Neurosnap have streamlined the process, making it easier for scientists to use these tools. Varshney said that developing more sophisticated "knowledge" or mechanistic systems that intricately incorporate detailed aspects of biology could yield more accurate and reliable predictions when integrated with AI.
