Interaction Profiles as a Universal Language for Generative Molecular Design with ShEPhERD–2

Three-dimensional intermolecular interactions govern molecular recognition and are fundamental to the pharmacological activity of small-molecule drugs. We propose that an interaction profile, comprising shape, electrostatics, and directional pharmacophores, is a sufficient and transferable design specification for molecular design. We introduce ShEPhERD–2, a 3D generative model that generates molecular structures conditioned on explicit interaction profiles. ShEPhERD–2 generates low-strain, drug-like molecules more efficiently and with greater fidelity to target interaction profiles than its predecessor while enabling precise control over molecular design through pharmacophore prioritization, substructure constraints, and composition of multiple interaction profiles. We demonstrate the application of a single model to bioisosteric fragment merging, dual-target design, selectivity engineering, and modality hopping without task-specific retraining. These results establish interaction profiles as a chemotype-agnostic interface between structure hypotheses and molecular design.

Kento Abeywardane is a 4^th year PhD student in the Coley Research Group at MIT studying chemical engineering and computation. His thesis focuses on interaction aware 3D generative modeling for molecular design where he aims to imbue generative models with biases for intermolecular interactions to improve learning and steering. He is interested in the applications of these generative approaches to medicinal chemistry and catalyst design.

Kenji Walker is a 2nd year PhD student in the Harvard-MIT Health Sciences and Technology program advised by Connor Coley and Angela Koehler. His interest is in improving small molecule generative models to enable therapeutics hypotheses that are otherwise intractable.