London, UK — August 14, 2025 — Receptor.AI, an AI- and technology-driven drug discovery company, today announced a strategic collaboration with Sareum Holdings plc (AIM: SAR), a clinical-stage biotechnology company developing next-generation kinase inhibitors.
The collaboration will focus on the discovery and optimisation of blood–brain barrier (BBB)-permeable, isoform-selective TYK2/JAK1 inhibitors for neuroinflammatory conditions, including multiple sclerosis and Parkinson’s disease.
Receptor.AI will use its Oracle.AI virtual screening platform, which combines AI models, including the proprietary ArtiDock, currently ranked as the world’s top-performing molecular docking model, and physics-based approaches to identify the most promising drug candidates. Selected compounds will then be refined using AdmetIQ, the company’s predictive system that evaluates a wide range of safety and efficacy factors, including a dedicated BBB model, to support successful development.
Lead optimisation will be carried out by Receptor.AI’s team of highly experienced scientists, under the direct supervision of Chief Scientific Advisor Dr. R. Aldrin Denny. Working closely with the Sareum team, Dr. Denny will guide the programme from candidate selection through to advanced development stages. Over his distinguished career, he has advanced eight compounds into clinical development and led a team instrumental in establishing Pfizer’s JAK inhibitor platform, contributing to several of the industry’s most successful kinase-targeted therapies.
Sareum will conduct synthesis and laboratory profiling of shortlisted compounds, including ADMET experiments, to validate and refine candidates for preclinical development.
Detailed terms remain undisclosed; however, Sareum will retain ownership of all intellectual property and compounds resulting from the collaboration.
Dr Alan Nafiev, Chief Executive Officer of Receptor.AI, commented:
“Designing BBB-permeable, isoform-selective kinase inhibitors requires simultaneous optimisation across multiple parameters. By combining Oracle.AI’s multi-engine docking and meta-scoring with our high-performance ADMET models, we can systematically address binding, selectivity, brain penetration, and synthetic feasibility from the outset.”
Dr Stephen Parker, Executive Chairman of Sareum, commented:
“This collaboration is a logical and timely next step following our recent findings on BBB-penetrant TYK2/JAK1 inhibitors. Receptor.AI’s expertise in integrating predictive modelling and generative chemistry into the discovery process will help us accelerate the identification of high-potential candidates for neuroinflammatory conditions. This technology allows us to harness the speed and accuracy of AI to de-risk and optimise our discovery and early development.”
