3D molecule generation by denoising voxel grids
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929268768899072 |
|---|---|
| author | Pinheiro, Pedro O. Rackers, Joshua Kleinhenz, Joseph Maser, Michael Mahmood, Omar Watkins, Andrew Martin Ra, Stephen Sresht, Vishnu Saremi, Saeed |
| author_facet | Pinheiro, Pedro O. Rackers, Joshua Kleinhenz, Joseph Maser, Michael Mahmood, Omar Watkins, Andrew Martin Ra, Stephen Sresht, Vishnu Saremi, Saeed |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_07473 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | 3D molecule generation by denoising voxel grids Pinheiro, Pedro O. Rackers, Joshua Kleinhenz, Joseph Maser, Michael Mahmood, Omar Watkins, Andrew Martin Ra, Stephen Sresht, Vishnu Saremi, Saeed Machine Learning Quantitative Methods 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. |
| title | 3D molecule generation by denoising voxel grids |
| topic | Machine Learning Quantitative Methods |
| url | https://arxiv.org/abs/2306.07473 |