Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Irwin, Ross, Tibo, Alessandro, Janet, Jon Paul, Olsson, Simon
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2406.07266
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912251325186048
author Irwin, Ross
Tibo, Alessandro
Janet, Jon Paul
Olsson, Simon
author_facet Irwin, Ross
Tibo, Alessandro
Janet, Jon Paul
Olsson, Simon
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_07266
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matching
Irwin, Ross
Tibo, Alessandro
Janet, Jon Paul
Olsson, Simon
Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
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.
title SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matching
topic Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
url https://arxiv.org/abs/2406.07266