{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T13:00:13Z","timestamp":1790600413945,"version":"4.1.0"},"reference-count":87,"publisher":"American Chemical Society (ACS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["22333003"],"award-info":[{"award-number":["22333003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["22361132528"],"award-info":[{"award-number":["22361132528"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Analyzing nonadiabatic molecular dynamics trajectories traditionally heavily relies on expert intuition and visual pattern recognition, a process that is difficult to formalize. We present VisU, a vision-driven framework that leverages the complementary strengths of two state-of-the-art large language models (Doubao-Seed-1.6-Vision and DeepSeek-V3.2) to establish a \u201cvirtual research cooperation\u201d. This operates through a \u201cMentor\u2013Engineer\u2013Student\u201d paradigm that mimics the collaborative intelligence of a professional chemistry laboratory. Within this ecosystem, the Mentor provides physical intuition through visual reasoning, while the Engineer adaptively constructs analysis scripts, and the Student executes the pipeline and manages the data and results. VisU autonomously orchestrates a four-stage workflow comprising Preprocessing, Recursive Channel Discovery, Important-Motion Identification, and Validation\/Summary. This systematic approach identifies reaction channels and key nuclear motions while generating a professional academic report at the end. By bridging visual insight with chemical expertise, VisU establishes a new framework for human\u2013AI collaboration in the analysis of excited-state dynamics simulation results, significantly reducing dependence on manual interpretation and enabling more intuitive, scalable mechanistic discovery in nonadiabatic dynamics simulations.<\/jats:p>","DOI":"10.1021\/jacsau.6c01054","type":"journal-article","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:01:28Z","timestamp":1789102888000},"page":"5494-5509","source":"Crossref","is-referenced-by-count":0,"title":["Bridging Visual Intuition\nand Chemical Expertise:\nA Virtual Collaborative Framework for Autonomous Nonadiabatic Dynamics\nAnalysis"],"prefix":"10.1021","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3025-8825","authenticated-orcid":true,"given":"Yifei","family":"Zhu","sequence":"first","affiliation":[{"name":"South China Normal University , , ,","place":["Guangzhou, P. R. China, 510006"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4543-0511","authenticated-orcid":true,"given":"Jiahui","family":"Zhang","sequence":"additional","affiliation":[{"name":"South China Normal University , , ,","place":["Guangzhou, P. R. China, 510006"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuqiao","family":"Feng","sequence":"additional","affiliation":[{"name":"South China Normal University , , ,","place":["Guangzhou, P. R. China, 510006"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binni","family":"Huang","sequence":"additional","affiliation":[{"name":"South China Normal University , , ,","place":["Guangzhou, P. R. China, 510006"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyi","family":"Yang","sequence":"additional","affiliation":[{"name":"South China Normal University , , ,","place":["Guangzhou, P. R. China, 510006"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8509-0388","authenticated-orcid":true,"given":"Zhenggang","family":"Lan","sequence":"additional","affiliation":[{"name":"South China Normal University , , ,","place":["Guangzhou, P. R. China, 510006"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"2026092808091827500_cit1","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1146\/annurev-physchem-032210-103522","article-title":"Role of Conical\nIntersections in Molecular Spectroscopy\nand Photoinduced Chemical Dynamics","volume":"63","author":"Domcke","year":"2012","journal-title":"Annu. Rev.\nPhys. Chem."},{"key":"2026092808091827500_cit2","doi-asserted-by":"crossref","DOI":"10.1142\/5406","volume-title":"Conical Intersections:\nElectronic Structure, Dynamics & Spectroscopy","author":"Domcke","year":"2004"},{"key":"2026092808091827500_cit3","doi-asserted-by":"crossref","DOI":"10.1142\/7803","volume-title":"Conical Intersections:\nTheory, Computation, and Experiment","author":"Domcke","year":"2011"},{"key":"2026092808091827500_cit4","doi-asserted-by":"publisher","first-page":"9407","DOI":"10.1021\/acs.chemrev.1c00074","article-title":"Electronic\nstructure methods for the description of nonadiabatic effects and\nconical intersections","volume":"121","author":"Matsika","year":"2021","journal-title":"Chem. Rev."},{"key":"2026092808091827500_cit5","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1063\/1.459170","article-title":"Molecular\ndynamics with electronic transitions","volume":"93","author":"Tully","year":"1990","journal-title":"J. Chem.\nPhys."},{"key":"2026092808091827500_cit6","doi-asserted-by":"publisher","first-page":"7026","DOI":"10.1021\/acs.chemrev.7b00577","article-title":"Recent Advances\nand Perspectives on Nonadiabatic Mixed\nQuantum\u2013Classical Dynamics","volume":"118","author":"Crespo-Otero","year":"2018","journal-title":"Chem. Rev."},{"key":"2026092808091827500_cit7","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1370","article-title":"Nonadiabatic dynamics: The SHARC\napproach","volume":"8","author":"Mai","year":"2018","journal-title":"WIREs Comput. Mol. Sci."},{"key":"2026092808091827500_cit8","doi-asserted-by":"publisher","first-page":"4496","DOI":"10.1021\/cr3004899","article-title":"Theoretical\ninsights into photoinduced\ncharge transfer and catalysis at oxide interfaces","volume":"113","author":"Akimov","year":"2013","journal-title":"Chem. Rev."},{"key":"2026092808091827500_cit9","doi-asserted-by":"publisher","first-page":"1360","DOI":"10.1021\/ct501106d","article-title":"An on-the-fly surface-hopping program jade for nonadiabatic molecular\ndynamics of polyatomic systems: implementation and applications","volume":"11","author":"Du","year":"2015","journal-title":"J. Chem. Theory Comput."},{"key":"2026092808091827500_cit10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.98.023001","article-title":"Trajectory surface hopping within\nlinear response time-dependent density-functional theory","volume":"98","author":"Tapavicza","year":"2007","journal-title":"Phys. Rev. Lett."},{"key":"2026092808091827500_cit11","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.1021\/ar400263p","article-title":"Nonadiabatic\nexcited-state\nmolecular dynamics: Modeling photophysics in organic conjugated materials","volume":"47","author":"Nelson","year":"2014","journal-title":"Acc. Chem. Res."},{"key":"2026092808091827500_cit12","doi-asserted-by":"publisher","first-page":"2215","DOI":"10.1021\/acs.chemrev.9b00447","article-title":"Non-Adiabatic Excited-State Molecular Dynamics: Theory\nand Applications for Modeling Photophysics in Extended Molecular Materials","volume":"120","author":"Nelson","year":"2020","journal-title":"Chem. Rev."},{"key":"2026092808091827500_cit13","doi-asserted-by":"publisher","first-page":"9601","DOI":"10.1021\/acs.jpclett.4c01751","article-title":"Unsupervised Machine\nLearning in the Analysis of Nonadiabatic Molecular Dynamics Simulation","volume":"15","author":"Zhu","year":"2024","journal-title":"J. Phys. Chem. Lett."},{"key":"2026092808091827500_cit14","doi-asserted-by":"publisher","first-page":"22A301","DOI":"10.1063\/1.4757762","article-title":"Perspective:\nNonadiabatic dynamics theory","volume":"137","author":"Tully","year":"2012","journal-title":"J. Chem. Phys."},{"key":"2026092808091827500_cit15","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/0169-7439(87)80084-9","article-title":"Principal\nComponent Analysis","volume":"2","author":"Wold","year":"1987","journal-title":"Chemometr. Intell. Lab."},{"key":"2026092808091827500_cit16","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1002\/wics.101","article-title":"Principal Component\nAnalysis","volume":"2","author":"Abdi","year":"2010","journal-title":"WIREs Comput. Stat."},{"key":"2026092808091827500_cit17","first-page":"619","volume-title":"Quantum Chemistry in the Age of Machine\nLearning","author":"Zhu","year":"2022"},{"key":"2026092808091827500_cit18","doi-asserted-by":"publisher","first-page":"9722","DOI":"10.1021\/acs.chemrev.0c01195","article-title":"Unsupervised Learning\nMethods for Molecular Simulation Data","volume":"121","author":"Glielmo","year":"2021","journal-title":"Chem.\nRev."},{"key":"2026092808091827500_cit19","doi-asserted-by":"publisher","first-page":"150901","DOI":"10.1063\/1.5091842","article-title":"Unsupervised\nMachine Learning in Atomistic Simulations, between Predictions and\nUnderstanding","volume":"150","author":"Ceriotti","year":"2019","journal-title":"J. Chem. Phys."},{"key":"2026092808091827500_cit20","doi-asserted-by":"publisher","first-page":"22A519","DOI":"10.1063\/1.4742066","article-title":"Nonlinear\nDimensionality Reduction\nfor Nonadiabatic Dynamics: The Influence of Conical Intersection Topography\non Population Transfer Rates","volume":"137","author":"Virshup","year":"2012","journal-title":"J. Chem. Phys."},{"key":"2026092808091827500_cit21","doi-asserted-by":"publisher","first-page":"6126","DOI":"10.1021\/acs.jctc.3c00776","article-title":"Automatic\nClustering of Excited-State Trajectories:\nApplication to Photoexcited Dynamics","volume":"19","author":"Acheson","year":"2023","journal-title":"J. Chem.\nTheory Comput."},{"key":"2026092808091827500_cit22","doi-asserted-by":"publisher","first-page":"104307","DOI":"10.1063\/1.4913962","article-title":"Nonadiabatic\nNuclear\nDynamics of the Ammonia Cation Studied by Surface Hopping Classical\nTrajectory Calculations","volume":"142","author":"Belyaev","year":"2015","journal-title":"J. Chem. Phys."},{"key":"2026092808091827500_cit23","doi-asserted-by":"publisher","first-page":"19590","DOI":"10.1039\/C7CP00436B","article-title":"Photophysics\nof a Copper Phenanthroline Eluciyeard by Trajectory and Wavepacket-Based\nQuantum Dynamics: A Synergetic Approach","volume":"19","author":"Capano","year":"2017","journal-title":"Phys.\nChem. Chem. Phys."},{"key":"2026092808091827500_cit24","doi-asserted-by":"publisher","first-page":"6611","DOI":"10.1021\/acs.jctc.5c00110","article-title":"Automated Selection of Nuclear Coordinates\nfor Reduced Dimensionality Nonadiabatic Dynamics","volume":"21","author":"Delmas","year":"2025","journal-title":"J. Chem. Theory Comput."},{"key":"2026092808091827500_cit25","doi-asserted-by":"publisher","first-page":"12026","DOI":"10.1021\/acs.jpclett.1c03469","article-title":"Significance of the Chemical Environment of an Element\nin Nonadiabatic Molecular Dynamics: Feature Selection and Dimensionality\nReduction with Machine Learning","volume":"12","author":"How","year":"2021","journal-title":"J. Phys. Chem.\nLett."},{"key":"2026092808091827500_cit26","doi-asserted-by":"publisher","DOI":"10.1063\/5.0078473","article-title":"Dimensionality Reduction\nin Machine\nLearning for Nonadiabatic Molecular Dynamics: Effectiveness of Elemental\nSublattices in Lead Halide Perovskites","volume":"156","author":"How","year":"2022","journal-title":"J. Chem.\nPhys."},{"key":"2026092808091827500_cit27","doi-asserted-by":"publisher","first-page":"acs.jctc.4c01750","DOI":"10.1021\/acs.jctc.4c01750","article-title":"DONKEY: A\nFlexible and Accurate Algorithm\nfor Clustering","volume":"21","author":"Ka\u0301ra","year":"2025","journal-title":"J. Chem. Theory Comput."},{"key":"2026092808091827500_cit28","doi-asserted-by":"publisher","first-page":"14327","DOI":"10.1039\/D3NJ04752K","article-title":"Nonadiabatic\nMolecular Dynamics Simulations Shed Light on the Timescale of Furylfulgide\nPhotocyclisation","volume":"48","author":"Kochman","year":"2024","journal-title":"New J. Chem."},{"key":"2026092808091827500_cit29","doi-asserted-by":"publisher","first-page":"4611","DOI":"10.1021\/acs.jctc.7b00394","article-title":"Analysis of the Geometrical Evolution\nin On-the-Fly Surface-Hopping Nonadiabatic Dynamics with Machine Learning\nDimensionality Reduction Approaches: Classical Multidimensional Scaling\nand Isometric Feature Mapping","volume":"13","author":"Li","year":"2017","journal-title":"J. Chem. Theory\nComput."},{"key":"2026092808091827500_cit30","doi-asserted-by":"publisher","first-page":"244104","DOI":"10.1063\/1.5048049","article-title":"Analysis of Trajectory Similarity\nand Configuration Similarity in On-the-Fly Surface-Hopping Simulation\non Multi-Channel Nonadiabatic Photoisomerization Dynamics","volume":"149","author":"Li","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2026092808091827500_cit31","doi-asserted-by":"publisher","first-page":"130831","DOI":"10.1016\/j.chemosphere.2021.130831","article-title":"Prediction\nof the Excited-State Reaction Channels in Photo-Induced Processes\nof Nitrofurantoin Using First-Principle Calculations and Dynamics\nSimulations","volume":"281","author":"Lin","year":"2021","journal-title":"Chemosphere"},{"key":"2026092808091827500_cit32","doi-asserted-by":"publisher","first-page":"8672","DOI":"10.1021\/acs.jpclett.1c02361","article-title":"Dependence between\nStructural and Electronic Properties of CsPbI3: Unsupervised Machine\nLearning of Nonadiabatic Molecular Dynamics","volume":"12","author":"Mangan","year":"2021","journal-title":"J. Phys. Chem. Lett."},{"key":"2026092808091827500_cit33","doi-asserted-by":"publisher","DOI":"10.1063\/5.0039743","article-title":"Analysis of\nBath Motion in MM-SQC\nDynamics via Dimensionality Reduction Approach: Principal Component\nAnalysis","volume":"154","author":"Peng","year":"2021","journal-title":"J. Chem. Phys."},{"key":"2026092808091827500_cit34","doi-asserted-by":"publisher","first-page":"7418","DOI":"10.3390\/molecules26247418","article-title":"Analyzing\nGrid-Based Direct Quantum Molecular Dynamics\nUsing Non-Linear Dimensionality Reduction","volume":"26","author":"Richings","year":"2021","journal-title":"Molecules"},{"key":"2026092808091827500_cit35","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1021\/jacs.7b10030","article-title":"A Machine-Driven\nHunt for Global Reaction Coordinates\nof Azobenzene Photoisomerization","volume":"140","author":"Tavadze","year":"2018","journal-title":"J. Am. Chem.\nSoc."},{"key":"2026092808091827500_cit36","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1021\/acsenergylett.0c00899","article-title":"Structural Deformation Controls Charge Losses in MAPbI3:\nUnsupervised Machine Learning of Nonadiabatic Molecular Dynamics","volume":"5","author":"Zhou","year":"2020","journal-title":"ACS Energy Lett."},{"key":"2026092808091827500_cit37","unstructured":"Liu, H.; Zhu, Y.; Lan, Z.\n          An Automated Framework for\nAnalyzing\nStructural Evolution in On-the-fly Non-adiabatic Molecular Dynamics\nUsing Autoencoder and Multiple Molecular Descriptors. 2025; https:\/\/arxiv.org\/abs\/2511.13364."},{"key":"2026092808091827500_cit38","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s41061-022-00377-7","article-title":"Reaction Space Projector (ReSPer) for Visualizing Dynamic\nReaction Routes Based on Reduced-Dimension Space","volume":"380","author":"Tsutsumi","year":"2022","journal-title":"Top. Curr. Chem."},{"key":"2026092808091827500_cit39","doi-asserted-by":"publisher","first-page":"4263","DOI":"10.1021\/acs.jctc.8b00176","article-title":"Visualization of the Intrinsic Reaction\nCoordinate and Global Reaction Route Map by Classical Multidimensional\nScaling","volume":"14","author":"Tsutsumi","year":"2018","journal-title":"J. Chem. Theory Comput."},{"key":"2026092808091827500_cit40","doi-asserted-by":"publisher","first-page":"24362","DOI":"10.1039\/D2CP03323B","article-title":"The Principal\nComponent Analysis of the Ring Deformation in the Nonadiabatic Surface\nHopping Dynamics","volume":"24","author":"Zhu","year":"2022","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2026092808091827500_cit41","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1039\/D4DD00374H","article-title":"ULaMDyn: Enhancing\nExcited-State Dynamics Analysis\nthrough Streamlined Unsupervised Learning","volume":"4","author":"Pinheiro","year":"2025","journal-title":"Digit.\nDiscovery"},{"key":"2026092808091827500_cit42","unstructured":"AI4Science Microsoft Research; Microsoft Azure Quantum.. The Impact of Large Language Models on Scientific Discovery: a Preliminary\nStudy using GPT-4. 2023; https:\/\/arxiv.org\/abs\/2311.07361."},{"key":"2026092808091827500_cit43","unstructured":"Jimenez, C. E.; Yang, J.; Wettig, A.; Yao, S.; Pei, K.; Press, O.; Narasimhan, K. R.\n          SWE-bench: Can Language Models Resolve Real-world\nGithub Issues? The Twelfth International Conference on Learning Representations. 2024; https:\/\/doi.org\/10.48550\/arXiv.2310.06770."},{"key":"2026092808091827500_cit44","unstructured":"Laurent, J. M.; Janizek, J. D.; Ruzo, M.; Hinks, M. M.; Hammerling, M. J.; Narayanan, S.; Ponnapati, M.; White, A. D.; Rodriques, S. G.\n          LAB-Bench:\nMeasuring Capabilities of Language Models for Biology Research. 2024; https:\/\/arxiv.org\/abs\/2407.10362."},{"key":"2026092808091827500_cit45","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1038\/s42256-025-01058-y","article-title":"Enabling large language models for real-world materials\ndiscovery","volume":"7","author":"Miret","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026092808091827500_cit46","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1038\/s41570-023-00502-0","article-title":"The future\nof chemistry is language","volume":"7","author":"White","year":"2023","journal-title":"Nat. Rev. Chem."},{"key":"2026092808091827500_cit47","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1039\/D3DD00113J","article-title":"14 examples\nof how LLMs can transform materials science\nand chemistry: a reflection on a large language model hackathon","volume":"2","author":"Jablonka","year":"2023","journal-title":"Digit. Discovery"},{"key":"2026092808091827500_cit48","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1039\/D4SC03921A","article-title":"A review of large language models\nand autonomous agents in chemistry","volume":"16","author":"Ramos","year":"2025","journal-title":"Chem. Sci."},{"key":"2026092808091827500_cit49","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1038\/s43588-025-00849-y","article-title":"SciToolAgent:\na knowledge-graph-driven scientific agent for multitool integration","volume":"5","author":"Ding","year":"2025","journal-title":"Nat. Comput. Sci."},{"key":"2026092808091827500_cit50","unstructured":"Li, J.; et al.; . ChemVLM: Exploring the Power of Multimodal Large Language Models\nin Chemistry Area. 2025; https:\/\/arxiv.org\/abs\/2408.07246."},{"key":"2026092808091827500_cit51","doi-asserted-by":"publisher","first-page":"21464","DOI":"10.1039\/D5SC04173B","article-title":"Towards Large-Scale\nChemical Reaction\nImage Parsing via a Multimodal Large Language Model","volume":"16","author":"Chen","year":"2025","journal-title":"Chem. Sci."},{"key":"2026092808091827500_cit52","unstructured":"ByteDance,\nDoubao-Seed-1.6-Vision: A Multimodal Large Language Model. VolcEngine\/ByteDance\nAI, 2025; https:\/\/www.volcengine.com\/product\/doubao, Accessed: September 30, 2025."},{"key":"2026092808091827500_cit53","unstructured":"; et al.\n          DeepSeek-AI,  DeepSeek-V3.2: Pushing\nthe Frontier of Open Large Language Models. 2025; https:\/\/arxiv.org\/abs\/2512.02556."},{"key":"2026092808091827500_cit54","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.1063\/1.462844","article-title":"Geometry Optimization\nin Redundant Internal Coordinates","volume":"96","author":"Pulay","year":"1992","journal-title":"J. Chem.\nPhys."},{"key":"2026092808091827500_cit55","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1002\/(SICI)1096-987X(19960115)17:1&lt;49::AID-JCC5&gt;3.0.CO;2-0","article-title":"Using Redundant\nInternal Coordinates to Optimize Equilibrium Geometries and Transition\nStates","volume":"17","author":"Peng","year":"1996","journal-title":"J. Comput. Chem."},{"key":"2026092808091827500_cit56","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least Squares\nQuantization in PCM","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Trans. Inf. Theory"},{"key":"2026092808091827500_cit57","unstructured":"MacQueen, J.; et al., Some Methods for Classification and Analysis of Multivariate Observations.  Proceedings of the fifth Berkeley symposium on mathematical\nstatistics and probability. 1967; pp 281\u2013297."},{"key":"2026092808091827500_cit58","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.ins.2022.11.139","article-title":"K-Means Clustering\nAlgorithms: A Comprehensive Review, Variants Analysis, and Advances\nin the Era of Big Data","volume":"622","author":"Ikotun","year":"2023","journal-title":"Inf. Sci."},{"key":"2026092808091827500_cit59","unstructured":"Ester, M.; Kriegel, H.-P.; Sander, J.; Xu, X.; et al., A density-based\nalgorithm for discovering clusters in large spatial databases with\nnoise.  Proceedings of the Second International\nConference on Knowledge Discovery and Data Mining. 1996; pp 226\u2013231.10.5555\/3001460.3001507."},{"key":"2026092808091827500_cit60","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3068335","article-title":"DBSCAN revisited,\nrevisited: why and how you should (still) use DBSCAN","volume":"42","author":"Schubert","year":"2017","journal-title":"ACM T. Database Syst."},{"key":"2026092808091827500_cit61","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1002\/widm.30","article-title":"Density-based clustering","volume":"1","author":"Kriegel","year":"2011","journal-title":"WIREs Data. Min. Knowl."},{"key":"2026092808091827500_cit62","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1080\/01621459.1963.10500845","article-title":"Hierarchical grouping to optimize an objective function","volume":"58","author":"Ward","year":"1963","journal-title":"J. Am. Stat. Assoc."},{"key":"2026092808091827500_cit63","volume-title":"Finding groups in\ndata: an introduction to cluster analysis","author":"Kaufman","year":"2009"},{"key":"2026092808091827500_cit64","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/S0166-1280(99)00139-6","article-title":"A theoretical\ninvestigation of tautomeric\nequilibria and proton transfer in isolated and monohydrated cytosine\nand isocytosine molecules","volume":"487","author":"Gorb","year":"1999","journal-title":"J. Mol. Struct."},{"key":"2026092808091827500_cit65","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/0022-2860(95)09067-3","article-title":"Quantum chemical study\nof structure and stability of all 14 isomers of isocytosine","volume":"376","author":"Ha","year":"1996","journal-title":"J. Mol. Struct."},{"key":"2026092808091827500_cit66","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1002\/(SICI)1097-461X(1997)61:3&lt;453::AID-QUA12&gt;3.0.CO;2-A","article-title":"Density functional theory study on\nmolecular structure\nand vibrational IR spectra of isocytosine","volume":"61","author":"Kwiatkowski","year":"1997","journal-title":"Int.\nJ. Quantum Chem."},{"key":"2026092808091827500_cit67","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1016\/0584-8539(94)80135-5","article-title":"Infrared spectra\nand tautomerism of isocytosine; an\nab initio and matrix isolation study","volume":"50","author":"Vranken","year":"1994","journal-title":"Spectrochim.\nActa, Part A"},{"key":"2026092808091827500_cit68","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1002\/(SICI)1097-461X(2000)77:1&lt;240::AID-QUA22&gt;3.0.CO;2-Z","article-title":"Investigations of the excited-state properties of isocytosine:\nAn ab initio approach","volume":"77","author":"Shukla","year":"2000","journal-title":"Int. J. Quantum Chem."},{"key":"2026092808091827500_cit69","doi-asserted-by":"publisher","first-page":"5133","DOI":"10.1007\/s00894-012-1506-0","article-title":"Comparative study\nof the relaxation mechanisms of the\nexcited states of cytosine and isocytosine","volume":"18","author":"Bakalska","year":"2012","journal-title":"J. Mol. Model."},{"key":"2026092808091827500_cit70","doi-asserted-by":"publisher","first-page":"20208","DOI":"10.1039\/C6CP01391K","article-title":"Ultrafast\nexcited-state dynamics\nof isocytosine","volume":"18","author":"Szabla","year":"2016","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2026092808091827500_cit71","doi-asserted-by":"publisher","first-page":"19168","DOI":"10.1039\/C7CP01732D","article-title":"Nonadiabatic dynamics\nsimulation of keto isocytosine: a comparison of dynamical performance\nof different electronic-structure methods","volume":"19","author":"Hu","year":"2017","journal-title":"Phys.\nChem. Chem. Phys."},{"key":"2026092808091827500_cit72","doi-asserted-by":"publisher","first-page":"2172","DOI":"10.1002\/cphc.202100402","article-title":"Modelling Photoionisation in Isocytosine: Potential\nFormation of Longer-Lived Excited State Cations in its Keto Form","volume":"22","author":"Segarra-Marti\u0301","year":"2021","journal-title":"ChemPhysChem"},{"key":"2026092808091827500_cit73","unstructured":"https:\/\/github.com\/zglan\/JADE-NAMD."},{"key":"2026092808091827500_cit74","unstructured":"Thiel, W.\n          \n          MNDO program, version 6.1. Max-Planck-Institut fu\u0308r Kohlenforschung, Mu\u0308lheim an der Ruhr, Germany2007."},{"key":"2026092808091827500_cit75","doi-asserted-by":"publisher","first-page":"6851","DOI":"10.1021\/acs.jctc.2c00804","article-title":"Newton-X platform: New software developments\nfor surface hopping and nuclear ensembles","volume":"18","author":"Barbatti","year":"2022","journal-title":"J.\nChem. Theory Comput."},{"key":"2026092808091827500_cit76","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1021\/acs.jctc.3c01203","article-title":"MLatom\n3: a platform for machine learning-enhanced\ncomputational chemistry simulations and workflows","volume":"20","author":"Dral","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"2026092808091827500_cit77","volume-title":"MLatom:\nA Package for Atomistic Simulations with Machine Learning","author":"Dral","year":"2024"},{"key":"2026092808091827500_cit78","first-page":"2825","article-title":"Scikit-learn: Machine\nlearning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"2026092808091827500_cit79","unstructured":"Landrum, G.\n           RDKit\nContributors, RDKit: Open-source\ncheminformatics software. 2025; https:\/\/github.com\/rdkit\/rdkit."},{"key":"2026092808091827500_cit80","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib:\nA 2D Graphics Environment","volume":"9","author":"Hunter","year":"2007","journal-title":"Comput. Sci. Eng."},{"key":"2026092808091827500_cit81","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1107\/S0567739476001873","article-title":"A Solution\nfor the Best Rotation to Relate Two Sets of Vectors","volume":"32","author":"Kabsch","year":"1976","journal-title":"Acta Crystallogr. A Cryst. Phys. Diffr. Theor. Gen. Crystallogr."},{"key":"2026092808091827500_cit82","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1107\/S0567739478001680","article-title":"A discussion\nof the solution for the best rotation to relate two sets of vectors","volume":"34","author":"Kabsch","year":"1978","journal-title":"Acta Crystallogr. A Cryst. Phys. Diffr. Theor. Gen. Crystallogr."},{"key":"2026092808091827500_cit83","doi-asserted-by":"publisher","DOI":"10.1002\/qua.26390","article-title":"pysisyphus:\nExploring potential energy\nsurfaces in ground and excited states","volume":"121","author":"Steinmetzer","year":"2021","journal-title":"Int.\nJ. Quantum Chem."},{"key":"2026092808091827500_cit84","unstructured":"Schro\u0308dinger, LLC.\n          .  The PyMOL Molecular Graphics System, Version 3.1.0., 2025. https:\/\/github.com\/schrodinger\/pymol-open-source."},{"key":"2026092808091827500_cit85","first-page":"10","article-title":"Converting\nvideo formats with FFmpeg","volume":"2006","author":"Tomar","year":"2006","journal-title":"Linux J."},{"key":"2026092808091827500_cit86","unstructured":"VolcEngine\/ByteDance-AI,\nVolcEngine Python SDK. GitHub, 2025; https:\/\/github.com\/volcengine\/volcengine-python-sdk, Version 4.0.34."},{"key":"2026092808091827500_cit87","unstructured":"OpenAI,\nOpenAI Python SDK. 2025; https:\/\/github.com\/openai\/openai-python."}],"container-title":["JACS Au"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/jacsau.6c01054","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jaaucr\/article-pdf\/6\/9\/5494\/68478945\/jacsau.6c01054.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jaaucr\/article-pdf\/6\/9\/5494\/68478945\/jacsau.6c01054.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T12:28:21Z","timestamp":1790598501000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jaaucr\/article\/6\/9\/5494\/5428072\/Bridging-Visual-Intuition-and-Chemical-Expertise-A"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,11]]},"references-count":87,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,11]]},"published-print":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.1021\/jacsau.6c01054","relation":{},"ISSN":["2691-3704"],"issn-type":[{"value":"2691-3704","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,11]]}}}