Learning Collective Variables with Synthetic Data Augmentation through Physics-Inspired Geodesic Interpolation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917727961088000 |
|---|---|
| author | Yang, Soojung Nam, Juno Dietschreit, Johannes C. B. Gómez-Bombarelli, Rafael |
| author_facet | Yang, Soojung Nam, Juno Dietschreit, Johannes C. B. Gómez-Bombarelli, Rafael |
| contents | In molecular dynamics simulations, rare events, such as protein folding, are typically studied using enhanced sampling techniques, most of which are based on the definition of a collective variable (CV) along which acceleration occurs. Obtaining an expressive CV is crucial, but often hindered by the lack of information about the particular event, e.g., the transition from unfolded to folded conformation. We propose a simulation-free data augmentation strategy using physics-inspired metrics to generate geodesic interpolations resembling protein folding transitions, thereby improving sampling efficiency without true transition state samples. This new data can be used to improve the accuracy of classifier-based methods. Alternatively, a regression-based learning scheme for CV models can be adopted by leveraging the interpolation progress parameter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01542 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Collective Variables with Synthetic Data Augmentation through Physics-Inspired Geodesic Interpolation Yang, Soojung Nam, Juno Dietschreit, Johannes C. B. Gómez-Bombarelli, Rafael Chemical Physics Machine Learning Biomolecules In molecular dynamics simulations, rare events, such as protein folding, are typically studied using enhanced sampling techniques, most of which are based on the definition of a collective variable (CV) along which acceleration occurs. Obtaining an expressive CV is crucial, but often hindered by the lack of information about the particular event, e.g., the transition from unfolded to folded conformation. We propose a simulation-free data augmentation strategy using physics-inspired metrics to generate geodesic interpolations resembling protein folding transitions, thereby improving sampling efficiency without true transition state samples. This new data can be used to improve the accuracy of classifier-based methods. Alternatively, a regression-based learning scheme for CV models can be adopted by leveraging the interpolation progress parameter. |
| title | Learning Collective Variables with Synthetic Data Augmentation through Physics-Inspired Geodesic Interpolation |
| topic | Chemical Physics Machine Learning Biomolecules |
| url | https://arxiv.org/abs/2402.01542 |