Structure-based drug design by denoising voxel grids
- URL: http://arxiv.org/abs/2405.03961v2
- Date: Tue, 2 Jul 2024 13:28:28 GMT
- Title: Structure-based drug design by denoising voxel grids
- Authors: Pedro O. Pinheiro, Arian Jamasb, Omar Mahmood, Vishnu Sresht, Saeed Saremi,
- Abstract summary: 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.
- Score: 5.9535699822923
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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. We extend the neural empirical Bayes formalism (Saremi & Hyvarinen, 2019) to the conditional setting and generate structure-conditioned molecules with a two-step procedure: (i) sample noisy molecules from the Gaussian-smoothed conditional distribution with underdamped Langevin MCMC using the learned score function and (ii) estimate clean molecules from the noisy samples with single-step denoising. Compared to the current state of the art, our model is simpler to train, significantly faster to sample from, and achieves better results on extensive in silico benchmarks -- the generated molecules are more diverse, exhibit fewer steric clashes, and bind with higher affinity to protein pockets. The code is available at https://github.com/genentech/voxbind/.
Related papers
- BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning [11.862370962277938]
We present a novel generative model, BindGPT, which uses a conceptually simple but powerful approach to create 3D molecules within the protein's binding site.
We show how such simple conceptual approach combined with pretraining and scaling can perform on par or better than the current best specialized diffusion models.
arXiv Detail & Related papers (2024-06-06T02:10:50Z) - DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design [62.68420322996345]
Existing structured-based drug design methods treat all ligand atoms equally.
We propose a new diffusion model, DecompDiff, with decomposed priors over arms and scaffold.
Our approach achieves state-of-the-art performance in generating high-affinity molecules.
arXiv Detail & Related papers (2024-02-26T05:21:21Z) - 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) - 3D molecule generation by denoising voxel grids [5.50581548670289]
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.
arXiv Detail & Related papers (2023-06-13T00:38:51Z) - Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration [63.23362798102195]
We propose D3FG, a functional-group-based diffusion model for pocket-specific molecule generation and elaboration.
D3FG decomposes molecules into two categories of components: functional groups defined as rigid bodies and linkers as mass points.
In the experiments, our method can generate molecules with more realistic 3D structures, competitive affinities toward the protein targets, and better drug properties.
arXiv Detail & Related papers (2023-05-30T06:41:20Z) - 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) - SILVR: Guided Diffusion for Molecule Generation [0.0]
We introduce a machine-learning method for conditioning an existing generative model without retraining.
The model allows the generation of new molecules that fit into a binding site of a protein based on fragment hits.
We show that moderate SILVR rates make it possible to generate new molecules of similar shape to the original fragments.
arXiv Detail & Related papers (2023-04-21T11:47:38Z) - Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design [82.23006955069229]
We propose DiffLinker, an E(3)-equivariant 3D-conditional diffusion model for molecular linker design.
Our model places missing atoms in between and designs a molecule incorporating all the initial fragments.
We demonstrate that DiffLinker outperforms other methods on the standard datasets generating more diverse and synthetically-accessible molecules.
arXiv Detail & Related papers (2022-10-11T09:13:37Z) - Pre-training via Denoising for Molecular Property Prediction [53.409242538744444]
We describe a pre-training technique that utilizes large datasets of 3D molecular structures at equilibrium.
Inspired by recent advances in noise regularization, our pre-training objective is based on denoising.
arXiv Detail & Related papers (2022-05-31T22:28:34Z) - Generating 3D Molecules Conditional on Receptor Binding Sites with Deep
Generative Models [0.0]
We describe for the first time a deep learning system for generating 3D molecular structures conditioned on a receptor binding site.
We apply atom fitting and bond inference procedures to construct valid molecular conformations from generated atomic densities.
This work opens the door for end-to-end prediction of stable bioactive molecules from protein structures with deep learning.
arXiv Detail & Related papers (2021-10-28T15:17:24Z) - MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization [51.00815310242277]
generative models and reinforcement learning approaches made initial success, but still face difficulties in simultaneously optimizing multiple drug properties.
We propose the MultI-constraint MOlecule SAmpling (MIMOSA) approach, a sampling framework to use input molecule as an initial guess and sample molecules from the target distribution.
arXiv Detail & Related papers (2020-10-05T20:18:42Z)
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.