Structure-based drug design by denoising voxel grids

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Pinheiro, Pedro O., Jamasb, Arian, Mahmood, Omar, Sresht, Vishnu, Saremi, Saeed
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911939661135872
author Pinheiro, Pedro O.
Jamasb, Arian
Mahmood, Omar
Sresht, Vishnu
Saremi, Saeed
author_facet Pinheiro, Pedro O.
Jamasb, Arian
Mahmood, Omar
Sresht, Vishnu
Saremi, Saeed
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03961
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Structure-based drug design by denoising voxel grids
Pinheiro, Pedro O.
Jamasb, Arian
Mahmood, Omar
Sresht, Vishnu
Saremi, Saeed
Machine Learning
Biomolecules
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/.
title Structure-based drug design by denoising voxel grids
topic Machine Learning
Biomolecules
url https://arxiv.org/abs/2405.03961