{"ID":2868779,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.15872","arxiv_id":"2509.15872","title":"DeepMech: A Machine Learning Framework for Chemical Reaction Mechanism Prediction","abstract":"Prediction of complete step-by-step chemical reaction mechanisms (CRMs) remains a major challenge. Whereas the traditional approaches in CRM tasks rely on expert-driven experiments or costly quantum chemical computations, contemporary deep learning (DL) alternatives ignore key intermediates and mechanistic steps and often suffer from hallucinations. We present DeepMech, an interpretable graph-based DL framework employing atom- and bond-level attention, guided by generalized templates of mechanistic operations (TMOps), to generate CRMs. Trained on our curated ReactMech dataset (~30K CRMs with 100K atom-mapped and mass-balanced elementary steps), DeepMech achieves 98.98+/-0.12% accuracy in predicting elementary steps and 95.94+/-0.21% in complete CRM tasks, besides maintaining high fidelity even in out-of-distribution scenarios as well as in predicting side and/or byproducts. Extension to multistep CRMs relevant to prebiotic chemistry, demonstrates the ability of DeepMech in effectively reconstructing 2 pathways from simple primordial substrates to complex biomolecules such as serine and aldopentose. Attention analysis identifies reactive atoms/bonds in line with chemical intuition, rendering our model interpretable and suitable for reaction design.","short_abstract":"Prediction of complete step-by-step chemical reaction mechanisms (CRMs) remains a major challenge. Whereas the traditional approaches in CRM tasks rely on expert-driven experiments or costly quantum chemical computations, contemporary deep learning (DL) alternatives ignore key intermediates and mechanistic steps and of...","url_abs":"https://arxiv.org/abs/2509.15872","url_pdf":"https://arxiv.org/pdf/2509.15872v2","authors":"[\"Manajit Das\",\"Ajnabiul Hoque\",\"Mayank Baranwal\",\"Raghavan B. Sunoj\"]","published":"2025-09-19T11:14:46Z","proceeding":"physics.chem-ph","tasks":"[\"physics.chem-ph\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}