Score-based 3D molecule generation with neural fields
This addresses molecule generation for drug discovery, offering a scalable and efficient method, though it appears incremental as it builds on existing walk-jump sampling and neural field techniques.
The paper tackles 3D molecule generation by introducing a continuous atomic density field representation and a model called FuncMol that uses neural fields and walk-jump sampling for unconditional generation. It achieves competitive results on drug-like molecules, scales to macro-cyclic peptides, and provides at least 10x faster sampling.
We introduce a new representation for 3D molecules based on their continuous atomic density fields. Using this representation, we propose a new model based on walk-jump sampling for unconditional 3D molecule generation in the continuous space using neural fields. Our model, FuncMol, encodes molecular fields into latent codes using a conditional neural field, samples noisy codes from a Gaussian-smoothed distribution with Langevin MCMC (walk), denoises these samples in a single step (jump), and finally decodes them into molecular fields. FuncMol performs all-atom generation of 3D molecules without assumptions on the molecular structure and scales well with the size of molecules, unlike most approaches. Our method achieves competitive results on drug-like molecules and easily scales to macro-cyclic peptides, with at least one order of magnitude faster sampling. The code is available at https://github.com/prescient-design/funcmol.