HydroNet: Benchmark Tasks for Preserving Intermolecular Interactions and Structural Motifs in Predictive and Generative Models for Molecular Data

TL;DR

HydroNet introduces benchmark tasks and a large dataset to evaluate and improve machine learning models in capturing intermolecular interactions and structural motifs in molecular data.

Contribution

The paper presents a new benchmark dataset and challenge tasks focused on preserving intermolecular interactions in ML models for chemical applications.

Findings

Provides a dataset of 4.95 million water clusters with detailed structural information.

Defines benchmark tasks for evaluating ML models on intermolecular interaction preservation.

Facilitates development of models that better capture long-range molecular interactions.

Abstract

Intermolecular and long-range interactions are central to phenomena as diverse as gene regulation, topological states of quantum materials, electrolyte transport in batteries, and the universal solvation properties of water. We present a set of challenge problems for preserving intermolecular interactions and structural motifs in machine-learning approaches to chemical problems, through the use of a recently published dataset of 4.95 million water clusters held together by hydrogen bonding interactions and resulting in longer range structural patterns. The dataset provides spatial coordinates as well as two types of graph representations, to accommodate a variety of machine-learning practices.