Reaction Prediction via Interaction Modeling of Symmetric Difference Shingle Sets

TL;DR

ReaDISH is a new reaction prediction model that uses permutation-invariant embeddings and interaction-aware features to improve accuracy and robustness in chemical reaction predictions.

Contribution

It introduces symmetric difference shingle encoding and geometry-structure interaction attention, addressing permutation sensitivity and interaction modeling limitations of prior models.

Findings

8.76% average improvement on R^2 under permutation perturbations

Enhanced robustness and prediction accuracy across benchmarks

Effective modeling of intra- and inter-molecular interactions

Abstract

Chemical reaction prediction remains a fundamental challenge in organic chemistry, where existing machine learning models face two critical limitations: sensitivity to input permutations (molecule/atom orderings) and inadequate modeling of substructural interactions governing reactivity. These shortcomings lead to inconsistent predictions and poor generalization to real-world scenarios. To address these challenges, we propose ReaDISH, a novel reaction prediction model that learns permutation-invariant representations while incorporating interaction-aware features. It introduces two innovations: (1) symmetric difference shingle encoding, which extends the differential reaction fingerprint (DRFP) by representing shingles as continuous high-dimensional embeddings, capturing structural changes while eliminating order sensitivity; and (2) geometry-structure interaction attention, a mechanism that models intra- and inter-molecular interactions at the shingle level. Extensive experiments demonstrate that ReaDISH improves reaction prediction performance across diverse benchmarks. It shows enhanced robustness with an average improvement of 8.76% on R$^2$ under permutation perturbations.