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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Taewon, Seo, Hyunjin, Ahn, Sungsoo, Yang, Eunho
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910657815773184
author Kim, Taewon
Seo, Hyunjin
Ahn, Sungsoo
Yang, Eunho
author_facet Kim, Taewon
Seo, Hyunjin
Ahn, Sungsoo
Yang, Eunho
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14696
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle REBIND: Enhancing ground-state molecular conformation via force-based graph rewiring
Kim, Taewon
Seo, Hyunjin
Ahn, Sungsoo
Yang, Eunho
Chemical Physics
Artificial Intelligence
Machine Learning
Biomolecules
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.
title REBIND: Enhancing ground-state molecular conformation via force-based graph rewiring
topic Chemical Physics
Artificial Intelligence
Machine Learning
Biomolecules
url https://arxiv.org/abs/2410.14696