2026-10-11T15:32:19Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33921202 2026-09-18T06:15:22Z category_873 category_734 category_931 category_135 portal_63 item_type_3 month_year_09_2026

CoTAR: Topology and Atomic State Reconstruction in Condensed Phases Hodaka Mori (23214868) Yu Miyazaki (529169) Takechika Kikkawa (24585052) Chemical Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified Computational Biology phase molecular dynamics free umlip trajectories enable performing condensed classical force fields chemically valid snapshots tested nonionic systems successfully reconnected systems study presents cotar revealed persistent formal cotar achieved category atomic state reconstruction reconstructs bond connectivity results establish cotar order f1 scores preserving systems formal charges atomic species macro bond conditional bond unpaired electrons temporal smoothing shot tests resolved diffusion present scope practical route joint fine ionic mixtures chemical constraints charge errors aware analysis accuracy approaching Universal machine learning interatomic potentials (uMLIPs) enable performing condensed-phase molecular dynamics (MD) simulations with accuracy approaching that of first-principles; however, their lack of explicit molecular topology limits bond-aware analysis and reconnection to classical force fields. This study presents CoTAR, a hybrid graph neural network (GNN)–hidden Markov model (HMM) framework that reconstructs bond connectivity and order, formal charges, and unpaired electrons from atomic species and coordinates by combining learned local environments, chemical constraints, and temporal smoothing. After joint fine-tuning with 20 labeled snapshots per benchmark system, CoTAR achieved category-macro bond and conditional bond-order F1 scores of 0.992 and 0.998 and chemically valid snapshots of 82.1% across 128 uMLIP systems. Zero-shot tests were successful for all tested nonionic systems but revealed persistent formal-charge errors in ionic mixtures. For successfully reconnected systems, the reconstructed-topology simulation results showed close agreement with the reference-topology results for the density, element-resolved diffusion, and intermolecular radial distribution functions. These results establish CoTAR as a practical route from topology-free uMLIP trajectories to chemically complete molecular representations within the present scope of nonreactive, topology-preserving systems. 2026-09-18T00:00:00Z Dataset Dataset 10.1021/acs.jcim.6c02184.s001 https://figshare.com/articles/dataset/CoTAR_Topology_and_Atomic_State_Reconstruction_in_Condensed_Phases/33921202 CC BY-NC 4.0