Multi-objective generative AI for designing novel brain-targeting small molecules

Ayush Noori, Iñaki Arango, William E. Byrd, Nada Amin

Track: Machine learning: computational method and/or computational results

Keywords: molecular design, small molecules, blood-brain-barrier, generative AI

TL;DR: Using multi-objective generative AI, we design small molecule drug candidates to transit the blood-brain-barrier and target the human brain, while also satisfying other therapeutically relevant properties.

Abstract: The strict selectivity of the blood-brain barrier (BBB) represents one of the most formidable challenges to successful central nervous system (CNS) drug delivery, preventing the diagnosis and treatment of CNS disorders. Computational methods to generate BBB permeable lead compounds in silico may be valuable tools in the CNS drug design pipeline. However, in real-world applications, BBB penetration alone is insufficient; rather, after transiting the BBB, molecules must perform some desired function – such as binding to a specific target or receptor in the brain – and must also be safe and non-toxic for use in human patients. To discover small molecules that concurrently satisfy these constraints, we use multi‑objective generative AI to synthesize drug-like blood-brain-barrier permeable small molecules that also have high predicted binding affinity to a disease-relevant CNS target. Specifically, we computationally synthesize molecules with predicted bioactivity against dopamine receptor D2, the primary target for almost all clinically effective antipsychotic drugs. After training several graph neural network-based property predictors, we adapt SyntheMol (Swanson et al., 2024), a recently developed Monte Carlo Tree Search-based algorithm for antibiotic design, to perform a multi‑objective guided traversal over an easily synthesizable molecular space. We design a library of 26,581 novel and diverse small molecules containing hits with high predicted BBB permeability and favorable predicted safety and toxicity profiles, and that could readily be synthesized for experimental validation in the wet lab. We also validate top scoring molecules with molecular docking simulation against the D2 receptor and demonstrate predicted binding affinity on par with risperidone, a clinically prescribed D2-targeting antipsychotic. In the future, the SyntheMol-based computational approach described here may enable the discovery of novel neurotherapeutics for currently intractable disorders of the CNS.

Submission Number: 49