2024/06/11 by Ross Irwin, Ross W. Irwin, Irwin, Ross +7 · 2 voices · 6 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Innovative Microfluidic and Catalytic Techniques Innovation #Machine Learning (cs.LG) #Microfluidic and Capillary Electrophoresis Applications #Nanopore and Nanochannel Transport Studies #Neural and Evolutionary Computing (cs.NE) #cs.AI #cs.LG #cs.NE
paper · pdf · doi:10.48550/arxiv.2406.07266
openalex publication_date 2024/06/11 · arxiv published 2024/06/11 · openalex created_date 2024/06/13 · arxiv updated 2025/02/28 · openalex updated_date 2026/07/28
Methods for jointly generating molecular graphs along with their 3D conformations have gained prominence recently due to their potential impact on structure-based drug design. Current approaches, however, often suffer from very slow sampling times or generate molecules with poor chemical validity. Addressing these limitations, we propose Semla, a scalable E(3)-equivariant message passing architecture. We further introduce an unconditional 3D molecular generation model, SemlaFlow, which is trained using equivariant flow matching to generate a joint distribution over atom types, coordinates, bond types and formal charges. Our model produces state-of-the-art results on benchmark datasets with as few as 20 sampling steps, corresponding to a two order-of-magnitude speedup compared to state-of-the-art. Furthermore, we highlight limitations of current evaluation methods for 3D generation and propose new benchmark metrics for unconditional molecular generators. Finally, using these new metrics, we compare our model's ability to generate high quality samples against current approaches and further demonstrate SemlaFlow's strong performance.