Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914710550478848 |
|---|---|
| author | Lu, Jiarui Zhang, Zuobai Zhong, Bozitao Shi, Chence Tang, Jian |
| author_facet | Lu, Jiarui Zhang, Zuobai Zhong, Bozitao Shi, Chence Tang, Jian |
| contents | The protein dynamics are common and important for their biological functions and properties, the study of which usually involves time-consuming molecular dynamics (MD) simulations in silico. Recently, generative models has been leveraged as a surrogate sampler to obtain conformation ensembles with orders of magnitude faster and without requiring any simulation data (a "zero-shot" inference). However, being agnostic of the underlying energy landscape, the accuracy of such generative model may still be limited. In this work, we explore the few-shot setting of such pre-trained generative sampler which incorporates MD simulations in a tractable manner. Specifically, given a target protein of interest, we first acquire some seeding conformations from the pre-trained sampler followed by a number of physical simulations in parallel starting from these seeding samples. Then we fine-tuned the generative model using the simulation trajectories above to become a target-specific sampler. Experimental results demonstrated the superior performance of such few-shot conformation sampler at a tractable computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_10433 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulations Lu, Jiarui Zhang, Zuobai Zhong, Bozitao Shi, Chence Tang, Jian Biomolecules Machine Learning Quantitative Methods The protein dynamics are common and important for their biological functions and properties, the study of which usually involves time-consuming molecular dynamics (MD) simulations in silico. Recently, generative models has been leveraged as a surrogate sampler to obtain conformation ensembles with orders of magnitude faster and without requiring any simulation data (a "zero-shot" inference). However, being agnostic of the underlying energy landscape, the accuracy of such generative model may still be limited. In this work, we explore the few-shot setting of such pre-trained generative sampler which incorporates MD simulations in a tractable manner. Specifically, given a target protein of interest, we first acquire some seeding conformations from the pre-trained sampler followed by a number of physical simulations in parallel starting from these seeding samples. Then we fine-tuned the generative model using the simulation trajectories above to become a target-specific sampler. Experimental results demonstrated the superior performance of such few-shot conformation sampler at a tractable computational cost. |
| title | Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulations |
| topic | Biomolecules Machine Learning Quantitative Methods |
| url | https://arxiv.org/abs/2402.10433 |