SynthFormer: Equivariant Pharmacophore-based Generation of Molecules for Ligand-Based Drug Design

Zygimantas Jocys, Henriette M. G. Willems, Katayoun Farrahi

Keywords: Generative Machine Learning, Drug Discovery, Chemical Space Exploration, 3D Equivariant Encoder, Pharmacophore Representation, Molecule Generation, Synthetic Trees, Synthesis Pathways, Docking Scores, Late-stage Optimization, In Silico to In Vitro Integration, Deep Learning in Chemistry, Structure-based Drug Design, 3D Molecular Embedding, Computational Chemistry, ML-driven Molecule Design

TL;DR: SynthFormer is a generative ML model that uses 3D pharmacophore data to generate synthesizable molecules.

Abstract: Drug discovery is a complex and resource-intensive process, with significant time and cost investments required to bring new medicines to patients. Recent advancements in generative machine learning (ML) methods offer promising avenues to accelerate early-stage drug discovery by efficiently exploring chemical space. This paper addresses the gap between in silico generative approaches and practical in vitro methodologies, highlighting the need for their integration to optimize molecule discovery. We introduce SynthFormer, a novel ML model that utilizes a 3D equivariant encoder for pharmacophores to generate fully synthesizable molecules, constructed as synthetic trees. Unlike previous methods, SynthFormer incorporates 3D information and provides synthetic paths, enhancing its ability to produce molecules with good docking scores across various proteins. Our contributions include a new methodology for efficient chemical space exploration using 3D information, a novel architecture called Synthformer for translating 3D pharmacophore representations into molecules, and a meaningful embedding space that organizes reagents for drug discovery optimization. Synthformer generates molecules that dock well and enables effective hit expansion and later-stage optimization restricted by synthesis paths.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 13902