Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.17249 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911278747877376 |
|---|---|
| author | Tedoldi, Riccardo Engkvist, Ola Bryant, Patrick Azizpour, Hossein Janet, Jon Paul Tibo, Alessandro |
| author_facet | Tedoldi, Riccardo Engkvist, Ola Bryant, Patrick Azizpour, Hossein Janet, Jon Paul Tibo, Alessandro |
| contents | Sampling useful three-dimensional molecular structures along with their most favorable conformations is a key challenge in drug discovery. Current state-of-the-art 3D de-novo design flow matching or diffusion-based models are limited to generating a single conformation. However, the conformational landscape of a molecule determines its observable properties and how tightly it is able to bind to a given protein target. By generating a representative set of low-energy conformers, we can more directly assess these properties and potentially improve the ability to generate molecules with desired thermodynamic observables. Towards this aim, we propose FlexiFlow, a novel architecture that extends flow-matching models, allowing for the joint sampling of molecules along with multiple conformations while preserving both equivariance and permutation invariance. We demonstrate the effectiveness of our approach on the QM9 and GEOM Drugs datasets, achieving state-of-the-art results in molecular generation tasks. Our results show that FlexiFlow can generate valid, unstrained, unique, and novel molecules with high fidelity to the training data distribution, while also capturing the conformational diversity of molecules. Moreover, we show that our model can generate conformational ensembles that provide similar coverage to state-of-the-art physics-based methods at a fraction of the inference time. Finally, FlexiFlow can be successfully transferred to the protein-conditioned ligand generation task, even when the dataset contains only static pockets without accompanying conformations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_17249 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FlexiFlow: decomposable flow matching for generation of flexible molecular ensemble Tedoldi, Riccardo Engkvist, Ola Bryant, Patrick Azizpour, Hossein Janet, Jon Paul Tibo, Alessandro Machine Learning Sampling useful three-dimensional molecular structures along with their most favorable conformations is a key challenge in drug discovery. Current state-of-the-art 3D de-novo design flow matching or diffusion-based models are limited to generating a single conformation. However, the conformational landscape of a molecule determines its observable properties and how tightly it is able to bind to a given protein target. By generating a representative set of low-energy conformers, we can more directly assess these properties and potentially improve the ability to generate molecules with desired thermodynamic observables. Towards this aim, we propose FlexiFlow, a novel architecture that extends flow-matching models, allowing for the joint sampling of molecules along with multiple conformations while preserving both equivariance and permutation invariance. We demonstrate the effectiveness of our approach on the QM9 and GEOM Drugs datasets, achieving state-of-the-art results in molecular generation tasks. Our results show that FlexiFlow can generate valid, unstrained, unique, and novel molecules with high fidelity to the training data distribution, while also capturing the conformational diversity of molecules. Moreover, we show that our model can generate conformational ensembles that provide similar coverage to state-of-the-art physics-based methods at a fraction of the inference time. Finally, FlexiFlow can be successfully transferred to the protein-conditioned ligand generation task, even when the dataset contains only static pockets without accompanying conformations. |
| title | FlexiFlow: decomposable flow matching for generation of flexible molecular ensemble |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.17249 |