From Atoms to Dynamics: Learning the Committor Without Collective Variables
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_ | 1866915406766145536 |
|---|---|
| author | Arredondo, Sergio Contreras Tang, Chenyu Talmazan, Radu A. Megías, Alberto Chen, Cheng Giuseppe Chipot, Christophe |
| author_facet | Arredondo, Sergio Contreras Tang, Chenyu Talmazan, Radu A. Megías, Alberto Chen, Cheng Giuseppe Chipot, Christophe |
| contents | This Brief Communication introduces a graph-neural-network architecture built on geometric vector perceptrons to predict the committor function directly from atomic coordinates, bypassing the need for hand-crafted collective variables (CVs). The method offers atom-level interpretability, pinpointing the key atomic players in complex transitions without relying on prior assumptions. Applied across diverse molecular systems, the method accurately infers the committor function and highlights the importance of each heavy atom in the transition mechanism. It also yields precise estimates of the rate constants for the underlying processes. The proposed approach opens new avenues for understanding and modeling complex dynamics, by enabling CV-free learning and automated identification of physically meaningful reaction coordinates of complex molecular processes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_17700 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Atoms to Dynamics: Learning the Committor Without Collective Variables Arredondo, Sergio Contreras Tang, Chenyu Talmazan, Radu A. Megías, Alberto Chen, Cheng Giuseppe Chipot, Christophe Computational Physics Statistical Mechanics Data Analysis, Statistics and Probability This Brief Communication introduces a graph-neural-network architecture built on geometric vector perceptrons to predict the committor function directly from atomic coordinates, bypassing the need for hand-crafted collective variables (CVs). The method offers atom-level interpretability, pinpointing the key atomic players in complex transitions without relying on prior assumptions. Applied across diverse molecular systems, the method accurately infers the committor function and highlights the importance of each heavy atom in the transition mechanism. It also yields precise estimates of the rate constants for the underlying processes. The proposed approach opens new avenues for understanding and modeling complex dynamics, by enabling CV-free learning and automated identification of physically meaningful reaction coordinates of complex molecular processes. |
| title | From Atoms to Dynamics: Learning the Committor Without Collective Variables |
| topic | Computational Physics Statistical Mechanics Data Analysis, Statistics and Probability |
| url | https://arxiv.org/abs/2507.17700 |