Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

REBIND: Enhancing ground-state molecular conformation via force-based graph rewiring

About

Predicting the ground-state 3D molecular conformations from 2D molecular graphs is critical in computational chemistry due to its profound impact on molecular properties. Deep learning (DL) approaches have recently emerged as promising alternatives to computationally-heavy classical methods such as density functional theory (DFT). However, we discover that existing DL methods inadequately model inter-atomic forces, particularly for non-bonded atomic pairs, due to their naive usage of bonds and pairwise distances. Consequently, significant prediction errors occur for atoms with low degree (i.e., low coordination numbers) whose conformations are primarily influenced by non-bonded interactions. To address this, we propose REBIND, a novel framework that rewires molecular graphs by adding edges based on the Lennard-Jones potential to capture non-bonded interactions for low-degree atoms. Experimental results demonstrate that REBIND significantly outperforms state-of-the-art methods across various molecular sizes, achieving up to a 20\% reduction in prediction error.

Taewon Kim, Hyunjin Seo, Sungsoo Ahn, Eunho Yang• 2024

Related benchmarks

TaskDatasetResultRank
Ground-State Conformation PredictionGEOM-DRUGS (test)
MAE (Distance)0.776
13
Showing 1 of 1 rows

Other info

Follow for update