{"ID":2844352,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06356","arxiv_id":"2511.06356","title":"Reaction Prediction via Interaction Modeling of Symmetric Difference Shingle Sets","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.","short_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 inco...","url_abs":"https://arxiv.org/abs/2511.06356","url_pdf":"https://arxiv.org/pdf/2511.06356v3","authors":"[\"Runhan Shi\",\"Letian Chen\",\"Gufeng Yu\",\"Yang Yang\"]","published":"2025-11-09T12:29:16Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"q-bio.BM\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}