Unified all-atom molecule generation with neural fields
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918210316533760 |
|---|---|
| author | Kirchmeyer, Matthieu Pinheiro, Pedro O. Willett, Emma Martinkus, Karolis Kleinhenz, Joseph Makowski, Emily K. Watkins, Andrew M. Gligorijevic, Vladimir Bonneau, Richard Saremi, Saeed |
| author_facet | Kirchmeyer, Matthieu Pinheiro, Pedro O. Willett, Emma Martinkus, Karolis Kleinhenz, Joseph Makowski, Emily K. Watkins, Andrew M. Gligorijevic, Vladimir Bonneau, Richard Saremi, Saeed |
| contents | Generative models for structure-based drug design are often limited to a specific modality, restricting their broader applicability. To address this challenge, we introduce FuncBind, a framework based on computer vision to generate target-conditioned, all-atom molecules across atomic systems. FuncBind uses neural fields to represent molecules as continuous atomic densities and employs score-based generative models with modern architectures adapted from the computer vision literature. This modality-agnostic representation allows a single unified model to be trained on diverse atomic systems, from small to large molecules, and handle variable atom/residue counts, including non-canonical amino acids. FuncBind achieves competitive in silico performance in generating small molecules, macrocyclic peptides, and antibody complementarity-determining region loops, conditioned on target structures. FuncBind also generated in vitro novel antibody binders via de novo redesign of the complementarity-determining region H3 loop of two chosen co-crystal structures. As a final contribution, we introduce a new dataset and benchmark for structure-conditioned macrocyclic peptide generation. The code is available at https://github.com/prescient-design/funcbind. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_15906 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unified all-atom molecule generation with neural fields Kirchmeyer, Matthieu Pinheiro, Pedro O. Willett, Emma Martinkus, Karolis Kleinhenz, Joseph Makowski, Emily K. Watkins, Andrew M. Gligorijevic, Vladimir Bonneau, Richard Saremi, Saeed Machine Learning Biomolecules Generative models for structure-based drug design are often limited to a specific modality, restricting their broader applicability. To address this challenge, we introduce FuncBind, a framework based on computer vision to generate target-conditioned, all-atom molecules across atomic systems. FuncBind uses neural fields to represent molecules as continuous atomic densities and employs score-based generative models with modern architectures adapted from the computer vision literature. This modality-agnostic representation allows a single unified model to be trained on diverse atomic systems, from small to large molecules, and handle variable atom/residue counts, including non-canonical amino acids. FuncBind achieves competitive in silico performance in generating small molecules, macrocyclic peptides, and antibody complementarity-determining region loops, conditioned on target structures. FuncBind also generated in vitro novel antibody binders via de novo redesign of the complementarity-determining region H3 loop of two chosen co-crystal structures. As a final contribution, we introduce a new dataset and benchmark for structure-conditioned macrocyclic peptide generation. The code is available at https://github.com/prescient-design/funcbind. |
| title | Unified all-atom molecule generation with neural fields |
| topic | Machine Learning Biomolecules |
| url | https://arxiv.org/abs/2511.15906 |