3D molecule generation by denoising voxel grids
- URL: http://arxiv.org/abs/2306.07473v2
- Date: Fri, 8 Mar 2024 19:30:22 GMT
- Title: 3D molecule generation by denoising voxel grids
- Authors: Pedro O. Pinheiro, Joshua Rackers, Joseph Kleinhenz, Michael Maser,
Omar Mahmood, Andrew Martin Watkins, Stephen Ra, Vishnu Sresht, Saeed Saremi
- Abstract summary: We propose a new score-based approach to generate 3D molecules represented as atomic densities on regular grids.
We train a denoising neural network that learns to map from a smooth distribution of noisy molecules to the distribution of real molecules.
Our experiments show that VoxMol captures the distribution of drug-like molecules better than state of the art, while being faster to generate samples.
- Score: 5.50581548670289
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We propose a new score-based approach to generate 3D molecules represented as
atomic densities on regular grids. First, we train a denoising neural network
that learns to map from a smooth distribution of noisy molecules to the
distribution of real molecules. Then, we follow the neural empirical Bayes
framework (Saremi and Hyvarinen, 19) and generate molecules in two steps: (i)
sample noisy density grids from a smooth distribution via underdamped Langevin
Markov chain Monte Carlo, and (ii) recover the "clean" molecule by denoising
the noisy grid with a single step. Our method, VoxMol, generates molecules in a
fundamentally different way than the current state of the art (ie, diffusion
models applied to atom point clouds). It differs in terms of the data
representation, the noise model, the network architecture and the generative
modeling algorithm. Our experiments show that VoxMol captures the distribution
of drug-like molecules better than state of the art, while being faster to
generate samples.
Related papers
- Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space [46.11163798008912]
We introduce a new framework for molecular graph generation with 3D molecular generative models.
Our framework maps molecular graphs to Euclidean point clouds via synthetic conformer coordinates and learns the inverse map using an E(n)-Equivariant Graph Neural Network (EGNN)
The induced point cloud-structured latent space is well-suited to apply existing 3D molecular generative models.
arXiv Detail & Related papers (2024-06-15T05:29:07Z) - SubGDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning [14.338345772161102]
We propose a novel diffusion model termed SubGDiff for involving the molecular subgraph information in diffusion.
SubGDiff adopts three vital techniques: subgraph prediction, expectation state, and k-step same subgraph diffusion.
Experimentally, extensive downstream tasks demonstrate the superior performance of our approach.
arXiv Detail & Related papers (2024-05-09T10:37:33Z) - Structure-based drug design by denoising voxel grids [5.9535699822923]
We present VoxBind, a new score-based generative model for 3D molecules conditioned on protein structures.
Our approach represents molecules as 3D atomic density grids and leverages a 3D voxel-denoising network for learning and generation.
arXiv Detail & Related papers (2024-05-07T02:48:15Z) - Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation [32.464905769094536]
Existing diffusion-based generative methods on de novo 3D molecule generation face two major challenges.
We introduce a Dual-Track Transformer Network (DTN) to fully excevate global spatial relationships and learn high quality representations.
As for the second challenge, we design Geometric-Facilitated Loss (GFLoss) which intervenes the formation of bonds during the training period, instead of directly embedding edges into the latent space.
arXiv Detail & Related papers (2024-01-05T07:29:21Z) - 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) - MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation [47.15291538945242]
This work introduces MiDi, a novel diffusion model for jointly generating molecular graphs and their corresponding 3D arrangement of atoms.
Unlike existing methods that rely on predefined rules to determine molecular bonds based on the 3D conformation, MiDi offers an end-to-end differentiable approach that streamlines the molecule generation process.
arXiv Detail & Related papers (2023-02-17T18:27:14Z) - OCD: Learning to Overfit with Conditional Diffusion Models [95.1828574518325]
We present a dynamic model in which the weights are conditioned on an input sample x.
We learn to match those weights that would be obtained by finetuning a base model on x and its label y.
arXiv Detail & Related papers (2022-10-02T09:42:47Z) - DiGress: Discrete Denoising diffusion for graph generation [79.13904438217592]
DiGress is a discrete denoising diffusion model for generating graphs with categorical node and edge attributes.
It achieves state-of-the-art performance on molecular and non-molecular datasets, with up to 3x validity improvement.
It is also the first model to scale to the large GuacaMol dataset containing 1.3M drug-like molecules.
arXiv Detail & Related papers (2022-09-29T12:55:03Z) - Equivariant Diffusion for Molecule Generation in 3D [74.289191525633]
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.
arXiv Detail & Related papers (2022-03-31T12:52:25Z) - 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)
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.