An evaluation of unconditional 3D molecular generation methods

Martin Buttenschoen, Yael Ziv, Garrett M Morris, Charlotte Deane

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

Nature Biotechnology: Yes

Keywords: benchmarking, 3d molecular generation, de novo drug design

TL;DR: A benchmark of five recent 3D unconditional molecular generation methods including chemical and physical validity checks.

Abstract: Unconditional molecular generation is a stepping stone for conditional molecular generation, which is important in *de novo* drug design. Recent unconditional 3D molecular generation methods report saturated benchmarks, suggesting it is time to re-evaluate our benchmarks and compare the latest models. We assess five recent high performing 3D molecular generation methods (EQGAT-diff, FlowMol, GCDM, GeoLDM, SemlaFlow), in terms of both standard benchmarks and chemical and physical validity. Overall, the best method, SemlaFlow, has an 87\% success rate in generating valid, unique, and novel molecules without post-processing and 92.4\% with post-processing.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Presenter: ~Martin_Buttenschoen1

Format: Maybe: the presenting author will attend in person, contingent on other factors that still need to be determined (e.g., visa, funding).

Funding: Yes, the presenting author of this submission falls under ICLR’s funding aims, and funding would significantly impact their ability to attend the workshop in person.

Submission Number: 89