EquiJump: Protein Dynamics Simulation via SO(3)-Equivariant Stochastic Interpolants
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909418982998016 |
|---|---|
| author | Costa, Allan dos Santos Mitnikov, Ilan Pellegrini, Franco Daigavane, Ameya Geiger, Mario Cao, Zhonglin Kreis, Karsten Smidt, Tess Kucukbenli, Emine Jacobson, Joseph |
| author_facet | Costa, Allan dos Santos Mitnikov, Ilan Pellegrini, Franco Daigavane, Ameya Geiger, Mario Cao, Zhonglin Kreis, Karsten Smidt, Tess Kucukbenli, Emine Jacobson, Joseph |
| contents | Mapping the conformational dynamics of proteins is crucial for elucidating their functional mechanisms. While Molecular Dynamics (MD) simulation enables detailed time evolution of protein motion, its computational toll hinders its use in practice. To address this challenge, multiple deep learning models for reproducing and accelerating MD have been proposed drawing on transport-based generative methods. However, existing work focuses on generation through transport of samples from prior distributions, that can often be distant from the data manifold. The recently proposed framework of stochastic interpolants, instead, enables transport between arbitrary distribution endpoints. Building upon this work, we introduce EquiJump, a transferable SO(3)-equivariant model that bridges all-atom protein dynamics simulation time steps directly. Our approach unifies diverse sampling methods and is benchmarked against existing models on trajectory data of fast folding proteins. EquiJump achieves state-of-the-art results on dynamics simulation with a transferable model on all of the fast folding proteins. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_09667 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EquiJump: Protein Dynamics Simulation via SO(3)-Equivariant Stochastic Interpolants Costa, Allan dos Santos Mitnikov, Ilan Pellegrini, Franco Daigavane, Ameya Geiger, Mario Cao, Zhonglin Kreis, Karsten Smidt, Tess Kucukbenli, Emine Jacobson, Joseph Machine Learning Chemical Physics Biomolecules Mapping the conformational dynamics of proteins is crucial for elucidating their functional mechanisms. While Molecular Dynamics (MD) simulation enables detailed time evolution of protein motion, its computational toll hinders its use in practice. To address this challenge, multiple deep learning models for reproducing and accelerating MD have been proposed drawing on transport-based generative methods. However, existing work focuses on generation through transport of samples from prior distributions, that can often be distant from the data manifold. The recently proposed framework of stochastic interpolants, instead, enables transport between arbitrary distribution endpoints. Building upon this work, we introduce EquiJump, a transferable SO(3)-equivariant model that bridges all-atom protein dynamics simulation time steps directly. Our approach unifies diverse sampling methods and is benchmarked against existing models on trajectory data of fast folding proteins. EquiJump achieves state-of-the-art results on dynamics simulation with a transferable model on all of the fast folding proteins. |
| title | EquiJump: Protein Dynamics Simulation via SO(3)-Equivariant Stochastic Interpolants |
| topic | Machine Learning Chemical Physics Biomolecules |
| url | https://arxiv.org/abs/2410.09667 |