{"doi":"10.1021/acs.jpcb.5c02006","title":"Transferability of MACE Graph Neural Network for Range Corrected Δ-Machine Learning Potential QM/MM Applications","abstract":"We previously introduced a \"range corrected\" Δ-machine learning potential (ΔMLP) that used deep neural networks to improve the accuracy of combined quantum mechanical/molecular mechanical (QM/MM) simulations by correcting both the internal QM and QM/MM interaction energies and forces [J. Chem. Theory Comput. 2021, 17, 6993-7009]. The present work extends this approach to include graph neural networks. Specifically, the approach is applied to the MACE message passing neural network architecture, and a series of AM1/d + MACE models are trained to reproduce PBE0/6-31G* QM/MM energies and forces of model phosphoryl transesterification reactions. Several models are designed to test the transferability of AM1/d + MACE by varying the amount of training data and calculating free energy surfaces of reactions that were not included in the parameter refinement. The transferability is compared to AM1/d + DP models that use the DeepPot-SE (DP) deep neural network architecture. The AM1/d + MACE models are found to reproduce the target free energy surfaces even in instances where the AM1/d + DP models exhibit inaccuracies. We train \"end-state\" models that include data only from the reactant and product states of the 6 reactions. Unlike the uncorrected AM1/d profiles, the AM1/d + MACE method correctly reproduces a stable pentacoordinated phosphorus intermediate even though the training did not include structures with a similar bonding pattern. Furthermore, the message passing mechanism hyperparameters defining the MACE network are varied to explore their effect on the model's accuracy and performance. The AM1/d + MACE simulations are 28% slower than AM1/d QM/MM when the ΔMLP correction is performed on a graphics processing unit. Our results suggest that the MACE architecture may lead to ΔMLP models with improved transferability.","journal":"The Journal of Physical Chemistry B","year":2025,"id":512944,"datarank":0.41588830833596724,"base_score":2.772588722239781,"endowment":2.772588722239781,"self_citation_contribution":0.41588830833596724,"citation_network_contribution":0.0,"self_endowment_contribution":0.41588830833596724,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":15,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9503,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":635959,"name":"Jinzhe Zeng","orcid":"0000-0002-1515-8172","position":1,"is_corresponding":false},{"id":61660,"name":"Darrin M. York","orcid":"0000-0002-9193-7055","position":2,"is_corresponding":false},{"id":345742,"name":"Timothy J. Giese","orcid":"0000-0002-0653-9168","position":0,"is_corresponding":true}],"reference_count":120,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T02:48:11.233009Z","pmid":"40418048","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}