# Committors without Descriptors

## TL;DR

This paper introduces a method using graph neural networks to study rare events in molecular simulations without relying on predefined descriptors.

## Contribution

The novel approach uses graph neural networks to automate and improve the modeling of committors in rare event simulations.

## Key findings

- Graph neural networks can directly process atomic coordinates, improving the modeling of rare events.
- The method enables efficient sampling of transition states in systems like ion pair dissociation and ligand binding.
- The approach is self-consistent and semiautomatic, using a variational criterion to optimize the committor.

## Abstract

The study of rare events is one of the major challenges
in atomistic
simulations, and several enhanced sampling methods toward its solution
have been proposed. Recently, it has been suggested that the use of
the committor, which provides a precise formal description of rare
events, could be of use in this context. We have recently followed
up on this suggestion and proposed a committor-based method that promotes
frequent transitions between the metastable states of the system and
allows extensive sampling of the process transition state ensemble.
One of the strengths of our approach is being self-consistent and
semiautomatic, exploiting a variational criterion to iteratively optimize
a neural-network-based parametrization of the committor, which uses
a set of physical descriptors as input. Here, we further automate
this procedure by combining our previous method with the expressive
power of graph neural networks, which can directly process atomic
coordinates rather than descriptors. Besides applications on benchmark
systems, we highlight the advantages of a graph-based approach in
describing the role of solvent molecules in systems, such as ion pair
dissociation or ligand binding.