Equivariant Diffusion for Molecule Generation in 3D
- URL: http://arxiv.org/abs/2203.17003v1
- Date: Thu, 31 Mar 2022 12:52:25 GMT
- Title: Equivariant Diffusion for Molecule Generation in 3D
- Authors: Emiel Hoogeboom, Victor Garcia Satorras, Cl\'ement Vignac, Max Welling
- Abstract summary: This work introduces a diffusion model for molecule computation generation in 3D that is equivariant to Euclidean transformations.
Experimentally, the proposed method significantly outperforms previous 3D molecular generative methods regarding the quality of generated samples and efficiency at training time.
- Score: 74.289191525633
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This work introduces a diffusion model for molecule generation in 3D that is
equivariant to Euclidean transformations. Our E(3) Equivariant Diffusion Model
(EDM) learns to denoise a diffusion process with an equivariant network that
jointly operates on both continuous (atom coordinates) and categorical features
(atom types). In addition, we provide a probabilistic analysis which admits
likelihood computation of molecules using our model. Experimentally, the
proposed method significantly outperforms previous 3D molecular generative
methods regarding the quality of generated samples and efficiency at training
time.
Related papers
- Unified Generative Modeling of 3D Molecules via Bayesian Flow Networks [19.351562908683334]
GeoBFN naturally fits molecule geometry by modeling diverse modalities in the differentiable parameter space of distributions.
We demonstrate that GeoBFN achieves state-of-the-art performance on multiple 3D molecule generation benchmarks in terms of generation quality.
GeoBFN can also conduct sampling with any number of steps to reach an optimal trade-off between efficiency and quality.
arXiv Detail & Related papers (2024-03-17T08:40:06Z) - Equivariant Flow Matching with Hybrid Probability Transport [69.11915545210393]
Diffusion Models (DMs) have demonstrated effectiveness in generating feature-rich geometries.
DMs typically suffer from unstable probability dynamics with inefficient sampling speed.
We introduce geometric flow matching, which enjoys the advantages of both equivariant modeling and stabilized probability dynamics.
arXiv Detail & Related papers (2023-12-12T11:13:13Z) - Molecular Conformation Generation via Shifting Scores [21.986775283620883]
We propose a novel molecular conformation generation approach driven by the observation that the disintegration of a molecule can be viewed as casting increasing force fields to its composing atoms.
The corresponding generative modeling ensures a feasible inter-atomic distance geometry and exhibits time reversibility.
arXiv Detail & Related papers (2023-09-12T07:39:43Z) - MUDiff: Unified Diffusion for Complete Molecule Generation [104.7021929437504]
We present a new model for generating a comprehensive representation of molecules, including atom features, 2D discrete molecule structures, and 3D continuous molecule coordinates.
We propose a novel graph transformer architecture to denoise the diffusion process.
Our model is a promising approach for designing stable and diverse molecules and can be applied to a wide range of tasks in molecular modeling.
arXiv Detail & Related papers (2023-04-28T04:25:57Z) - GeoDiff: a Geometric Diffusion Model for Molecular Conformation
Generation [102.85440102147267]
We propose a novel generative model named GeoDiff for molecular conformation prediction.
We show that GeoDiff is superior or comparable to existing state-of-the-art approaches.
arXiv Detail & Related papers (2022-03-06T09:47:01Z) - Learning Equivariant Energy Based Models with Equivariant Stein
Variational Gradient Descent [80.73580820014242]
We focus on the problem of efficient sampling and learning of probability densities by incorporating symmetries in probabilistic models.
We first introduce Equivariant Stein Variational Gradient Descent algorithm -- an equivariant sampling method based on Stein's identity for sampling from densities with symmetries.
We propose new ways of improving and scaling up training of energy based models.
arXiv Detail & Related papers (2021-06-15T01:35:17Z) - E(n) Equivariant Normalizing Flows for Molecule Generation in 3D [87.12477361140716]
This paper introduces a generative model equivariant to Euclidean symmetries: E(n) Equivariant Normalizing Flows (E-NFs)
To the best of our knowledge, this is the first likelihood-based deep generative model that generates molecules in 3D.
arXiv Detail & Related papers (2021-05-19T09:28:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.