{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T16:40:25Z","timestamp":1786466425237,"version":"build-2736575974"},"reference-count":49,"publisher":"American Chemical Society (ACS)","issue":"15","license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"name":"CAREER and CAS-Climate programs of the National Science Foundation"},{"name":"Infrastructure for Scientific Applications and Advanced Computing (ISAAC) of the University of Tennessee"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We present the data-driven coupled-cluster deep network (DDCCNet), a family of multitask, physics-enhanced deep learning architectures designed to predict coupled-cluster singles and doubles (CCSD) amplitudes and correlation energies from lower-level electronic structure methods. The three DDCCNet variants (termed as v1, v2, and v3) progressively incorporate architectural refinements ranging from parallel subnetworks for t1 and t2 amplitudes to feature-partitioned blocks and physics-enhanced intermediate prediction layers that are structured in accordance with coupled-cluster equations to enhance physical consistency and multitask learning efficiency. These models jointly learn correlated amplitude patterns while embedding symmetry and orbital\u2013level interactions directly into the network structure. Applied to methanol conformers, CO2 clusters, and small organic molecules, DDCCNet_v2 delivered the most accurate and transferable performance, achieving chemically precise correlation energies across diverse molecular systems. Collectively, DDCCNet establishes a scalable, physically grounded framework that unifies machine learning and ab initio theory for efficient, data-driven electronic structure prediction.<\/jats:p>","DOI":"10.1021\/acs.jctc.6c00906","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T13:55:14Z","timestamp":1784555714000},"page":"7720-7729","source":"Crossref","is-referenced-by-count":1,"title":["DDCCNet: Physics-Enhanced\nMultitask Neural Networks\nfor Data-Driven Coupled-Cluster"],"prefix":"10.1021","volume":"22","author":[{"given":"P. D. Varuna S.","family":"Pathirage","sequence":"first","affiliation":[{"name":"University of Tennessee , , , ,","place":["Knoxville, Tennessee, United States, 37996"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7439-3850","authenticated-orcid":true,"given":"Konstantinos D.","family":"Vogiatzis","sequence":"additional","affiliation":[{"name":"University of Tennessee , , , ,","place":["Knoxville, Tennessee, United States, 37996"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"issue":"8","key":"2026081111095822000_cit1","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1002\/jcc.20581","article-title":"Electron correlation: the many-body\nproblem at the heart of chemistry","volume":"28","author":"Tew","year":"2007","journal-title":"J. Comput.\nChem."},{"key":"2026081111095822000_cit2","article-title":"Post-Hartree-Fock\nmethods: configuration interaction, many-body perturbation theory,\ncoupled-cluster theory","volume-title":"Mathematical Physics\nin Theoretical Chemistry","author":"Townsend","year":"2018"},{"issue":"1","key":"2026081111095822000_cit3","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1103\/RevModPhys.79.291","article-title":"Coupled-cluster\ntheory in quantum chemistry","volume":"79","author":"Bartlett","year":"2007","journal-title":"Rev. Mod. Phys."},{"issue":"6","key":"2026081111095822000_cit4","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1016\/S0009-2614(89)87395-6","article-title":"A fifth-order\nperturbation comparison of electron correlation theories","volume":"157","author":"Raghavachari","year":"1989","journal-title":"Chem. Phys. Lett."},{"issue":"6","key":"2026081111095822000_cit5","doi-asserted-by":"publisher","first-page":"2336","DOI":"10.1021\/acs.jpclett.9b03664","article-title":"Quantum\nChemistry in the Age of Machine Learning","volume":"11","author":"Dral","year":"2020","journal-title":"J.\nPhys. Chem. Lett."},{"issue":"30","key":"2026081111095822000_cit6","doi-asserted-by":"publisher","first-page":"2402369","DOI":"10.1002\/adma.202402369","article-title":"Silico Chemical\nExperiments in the Age of AI: From Quantum Chemistry to Machine Learning\nand Back","volume":"36","author":"Aldossary","year":"2024","journal-title":"Adv. Mater."},{"issue":"10","key":"2026081111095822000_cit7","doi-asserted-by":"publisher","first-page":"4790","DOI":"10.1039\/D5CS00104H","article-title":"The evolution of machine learning\npotentials for molecules, reactions and materials","volume":"54","author":"Xia","year":"2025","journal-title":"Chem. Soc. Rev."},{"issue":"9","key":"2026081111095822000_cit8","doi-asserted-by":"publisher","first-page":"4772","DOI":"10.1021\/acs.jctc.8b00636","article-title":"Transferability\nin Machine Learning for Electronic Structure via the Molecular Orbital\nBasis","volume":"14","author":"Welborn","year":"2018","journal-title":"J. Chem. Theory Comput."},{"issue":"30","key":"2026081111095822000_cit9","doi-asserted-by":"publisher","first-page":"6343","DOI":"10.1021\/acs.jpca.8b04455","article-title":"Making the Coupled\nCluster Correlation Energy Machine-Learnable","volume":"122","author":"Margraf","year":"2018","journal-title":"J. Phys. Chem. A"},{"issue":"35","key":"2026081111095822000_cit10","doi-asserted-by":"publisher","first-page":"7155","DOI":"10.1021\/acs.jpca.0c03886","article-title":"Ground State\nEnergy Functional with\nHartree-Fock Efficiency and Chemical Accuracy","volume":"124","author":"Chen","year":"2020","journal-title":"J. Phys. Chem. A"},{"issue":"2","key":"2026081111095822000_cit11","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1021\/acs.jctc.0c00898","article-title":"A Machine Learning\nApproach for MP2\nCorrelation Energies and Its Application to Organic Compounds","volume":"17","author":"Han","year":"2021","journal-title":"J. Chem. Theory Comput."},{"issue":"22","key":"2026081111095822000_cit12","doi-asserted-by":"publisher","first-page":"5324","DOI":"10.1021\/acs.jpclett.1c00900","article-title":"Fast Estimation of M?ller-Plesset Correlation Energies\nBased on Atomic\nContributions","volume":"12","author":"Han","year":"2021","journal-title":"J. Phys. Chem. Lett."},{"issue":"8","key":"2026081111095822000_cit13","doi-asserted-by":"publisher","first-page":"4826","DOI":"10.1021\/acs.jctc.2c00396","article-title":"Accurate Molecular-Orbital-Based\nMachine Learning Energies via Unsupervised Clustering of Chemical\nSpace","volume":"18","author":"Cheng","year":"2022","journal-title":"J. Chem. Theory Comput."},{"issue":"31","key":"2026081111095822000_cit14","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2205221119","article-title":"Informing geometric deep learning\nwith electronic interactions to accelerate quantum chemistry","volume":"119","author":"Qiao","year":"2022","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"issue":"8","key":"2026081111095822000_cit15","doi-asserted-by":"publisher","first-page":"4846","DOI":"10.1021\/acs.jctc.2c00501","article-title":"Machine\nLearning of Coupled Cluster\n(T)-Energy Corrections via Delta (Delta)-Learning","volume":"18","author":"Ruth","year":"2022","journal-title":"J. Chem. Theory Comput."},{"issue":"15","key":"2026081111095822000_cit16","doi-asserted-by":"publisher","first-page":"4912","DOI":"10.1021\/acs.jctc.3c00274","article-title":"Machine\nLearning for Bridging the\nGap between Density Functional Theory and Coupled Cluster Energies","volume":"19","author":"Ruth","year":"2023","journal-title":"J. Chem. Theory Comput."},{"issue":"16","key":"2026081111095822000_cit17","doi-asserted-by":"publisher","first-page":"5439","DOI":"10.1021\/acs.jctc.3c00518","article-title":"Low-Data Deep Quantum\nChemical Learning\nfor Accurate MP2 and Coupled-Cluster Correlations","volume":"19","author":"Ng","year":"2023","journal-title":"J. Chem. Theory Comput."},{"issue":"4","key":"2026081111095822000_cit18","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.1021\/acs.jctc.4c01261","article-title":"Accurate Neural Network\nFine-Tuning\nApproach for Transferable Ab Initio Energy Prediction across Varying\nMolecular and Crystalline Scales","volume":"21","author":"Ng","year":"2025","journal-title":"J. Chem. Theory\nComput."},{"issue":"3","key":"2026081111095822000_cit19","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1039\/D1DD00050K","article-title":"SPA(H)M: the spectrum of approximated\nHamiltonian matrices representations","volume":"1","author":"Fabrizio","year":"2022","journal-title":"Digit.\nDiscovery"},{"issue":"3","key":"2026081111095822000_cit20","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.1021\/acs.jctc.3c01040","article-title":"SPA(H)M(a,b):\nEncoding the Density Information from Guess Hamiltonian in Quantum\nMachine Learning Representations","volume":"20","author":"Briling","year":"2024","journal-title":"J. Chem. Theory\nComput."},{"key":"2026081111095822000_cit21","doi-asserted-by":"publisher","first-page":"5024","DOI":"10.1038\/s41467-019-12875-2","article-title":"Unifying machine learning and quantum chemistry with\na deep neural network for molecular wavefunctions","volume":"10","author":"Schu\u0308tt","year":"2019","journal-title":"Nat. Commun."},{"issue":"4","key":"2026081111095822000_cit22","doi-asserted-by":"publisher","first-page":"044123","DOI":"10.1063\/5.0012911","article-title":"A deep\nneural network for molecular wave functions in quasi-atomic minimal\nbasis representation","volume":"153","author":"Gastegger","year":"2020","journal-title":"J. Chem. Phys."},{"issue":"3","key":"2026081111095822000_cit23","doi-asserted-by":"publisher","first-page":"033429","DOI":"10.1103\/PhysRevResearch.2.033429","article-title":"Ab initio solution\nof the many-electron Schro\u0308dinger equation with deep neural\nnetworks","volume":"2","author":"Pfau","year":"2020","journal-title":"Phys. Rev. Res."},{"key":"2026081111095822000_cit24","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1038\/s41557-020-0544-y","article-title":"Deep-neural-network solution of the\nelectronic Schro\u0308dinger equation","volume":"12","author":"Hermann","year":"2020","journal-title":"Nat.\nChem."},{"issue":"4","key":"2026081111095822000_cit25","doi-asserted-by":"publisher","first-page":"044110","DOI":"10.1063\/5.0037090","article-title":"Accelerating coupled cluster calculations\nwith nonlinear dynamics and supervised machine learning","volume":"154","author":"Agarawal","year":"2021","journal-title":"J. Chem. Phys."},{"issue":"1","key":"2026081111095822000_cit26","doi-asserted-by":"publisher","first-page":"014109","DOI":"10.1063\/5.0072250","article-title":"A hybrid coupled\ncluster-machine\nlearning algorithm: Development of various regression models and benchmark\napplications","volume":"156","author":"Agarawal","year":"2022","journal-title":"J. Chem. Phys."},{"issue":"1","key":"2026081111095822000_cit27","doi-asserted-by":"publisher","first-page":"6281","DOI":"10.1038\/s41467-023-41953-9","article-title":"Machine learning\nelectronic structure methods based on the one-electron reduced density\nmatrix","volume":"14","author":"Shao","year":"2023","journal-title":"Nat. Commun."},{"issue":"1","key":"2026081111095822000_cit28","doi-asserted-by":"publisher","first-page":"10811","DOI":"10.1038\/s41467-025-66844-z","article-title":"Physics-informed\ntransformers for\nelectronic quantum states","volume":"16","author":"Sobral","year":"2025","journal-title":"Nat. Commun."},{"key":"2026081111095822000_cit29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2512.06858","article-title":"Physics-Informed Generative\nMachine Learning for Accelerated Quantum-centric Supercomputing","author":"Patra","year":"2026","journal-title":"arXiv"},{"issue":"14","key":"2026081111095822000_cit30","doi-asserted-by":"publisher","first-page":"4129","DOI":"10.1021\/acs.jpclett.9b01442","article-title":"Data-Driven Acceleration of the Coupled-Cluster Singles\nand Doubles Iterative Solver","volume":"10","author":"Townsend","year":"2019","journal-title":"J. Phys. Chem.\nLett."},{"issue":"12","key":"2026081111095822000_cit31","doi-asserted-by":"publisher","first-page":"7453","DOI":"10.1021\/acs.jctc.0c00927","article-title":"Transferable MP2-Based Machine Learning for Accurate\nCoupled-Cluster Energies","volume":"16","author":"Townsend","year":"2020","journal-title":"J. Chem. Theory Comput."},{"key":"2026081111095822000_cit32","volume-title":"Data\u2013Driven\nAcceleration of Coupled\u2013Cluster and Perturbation Theory Methods\nIn Quantum Chemistry in the Age of Machine Learning","author":"Jones","year":"2022"},{"issue":"28","key":"2026081111095822000_cit33","doi-asserted-by":"publisher","first-page":"6377","DOI":"10.1021\/acs.jpclett.3c01382","article-title":"Data-Driven\nRefinement of Electronic Energies from Two-Electron Reduced-Density-Matrix\nTheory","volume":"14","author":"Jones","year":"2023","journal-title":"J. Phys. Chem. Lett."},{"issue":"10","key":"2026081111095822000_cit34","doi-asserted-by":"publisher","first-page":"1938","DOI":"10.1021\/acs.jpca.3c06600","article-title":"Exploration\nof the Two-Electron Excitation\nSpace with Data-Driven Coupled Cluster","volume":"128","author":"Pathirage","year":"2024","journal-title":"J. Phys.\nChem. A"},{"issue":"13","key":"2026081111095822000_cit35","doi-asserted-by":"publisher","first-page":"2988","DOI":"10.1021\/acs.jpca.4c05718","article-title":"Transferability\nAcross Different Molecular Systems and Levels of Theory with the Data-Driven\nCoupled-Cluster Scheme","volume":"129","author":"Pathirage","year":"2025","journal-title":"J. Phys. Chem. A"},{"issue":"21","key":"2026081111095822000_cit36","doi-asserted-by":"publisher","first-page":"10879","DOI":"10.1021\/acs.jctc.5c01333","article-title":"Capturing\nElectron Correlation with Machine Learning\nthrough a Data-Driven CASPT2 Framework","volume":"21","author":"Jones","year":"2025","journal-title":"J. Chem.\nTheory Comput."},{"key":"2026081111095822000_cit37","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1016\/j.jcp.2018.10.045","article-title":"Physics-informed\nneural networks:\nA deep learning framework for solving forward and inverse problems\ninvolving nonlinear partial differential equations","volume":"378","author":"Raissi","year":"2019","journal-title":"J. Comput. Phys."},{"issue":"6","key":"2026081111095822000_cit38","doi-asserted-by":"publisher","first-page":"4334","DOI":"10.1063\/1.460620","article-title":"A direct product\ndecomposition approach for symmetry exploitation in many-body methods.\nI. Energy calculations","volume":"94","author":"Stanton","year":"1991","journal-title":"J. Chem. Phys."},{"key":"2026081111095822000_cit39","first-page":"8026","article-title":"PyTorch: An\nImperative Style, High-Performance Deep Learning Library","volume":"32","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"issue":"7","key":"2026081111095822000_cit40","doi-asserted-by":"publisher","first-page":"3504","DOI":"10.1021\/acs.jctc.8b00286","article-title":"Psi4NumPy: An Interactive Quantum Chemistry Programming\nEnvironment for Reference Implementations and Rapid Development","volume":"14","author":"Smith","year":"2018","journal-title":"J. Chem. Theory Comput."},{"issue":"18","key":"2026081111095822000_cit41","doi-asserted-by":"publisher","first-page":"184108","DOI":"10.1063\/5.0006002","article-title":"Psi4 1.4: Open-source\nsoftware for high-throughput quantum chemistry","volume":"152","author":"Smith","year":"2020","journal-title":"J. Chem. Phys."},{"issue":"2","key":"2026081111095822000_cit42","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1063\/1.456153","article-title":"Gaussian\nbasis sets for use in correlated molecular calculations. I. The atoms\nboron through neon and hydrogen","volume":"90","author":"Dunning","year":"1989","journal-title":"J. Chem. Phys."},{"issue":"1063","key":"2026081111095822000_cit43","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1098\/rspa.1950.0036","article-title":"Electronic\nwave functions - I. A general method of calculation for the stationary\nstates of any molecular system","volume":"200","author":"Boys","year":"1950","journal-title":"Proc. R. Soc.\nLondon A Math. Phys. Sci."},{"key":"2026081111095822000_cit44","doi-asserted-by":"publisher","first-page":"108171","DOI":"10.1016\/j.cpc.2021.108171","article-title":"LAMMPS\n- a flexible simulation tool for particle-based materials modeling\nat the atomic, meso, and continuum scales","volume":"271","author":"Thompson","year":"2022","journal-title":"Comput.\nPhys. Commun."},{"issue":"5","key":"2026081111095822000_cit45","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1002\/(SICI)1096-987X(19980415)19:5&lt;535::AID-JCC6&gt;3.0.CO;2-N","article-title":"Parametrization\nof aliphatic CHn\nunited atoms of GROMOS96 force field","volume":"19","author":"Daura","year":"1998","journal-title":"J. Comput.\nChem."},{"issue":"7","key":"2026081111095822000_cit46","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1007\/s00249-011-0700-9","article-title":"Definition and testing of the GROMOS\nforce-field versions 54A7 and 54B7","volume":"40","author":"Schmid","year":"2011","journal-title":"Eur. Biophys.\nJ."},{"issue":"2","key":"2026081111095822000_cit47","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1021\/ci600423u","article-title":"Virtual exploration\nof the chemical universe up to\n11 atoms of C, N, O, F: assembly of 26.4 million structures (110.9\nmillion stereoisomers) and analysis for new ring systems, stereochemistry,\nphysicochemical properties, compound classes, and drug discovery","volume":"47","author":"Fink","year":"2007","journal-title":"J. Chem. Inf. Model."},{"key":"2026081111095822000_cit48","unstructured":"RDKit.\n          : Open-Source Cheminformatics Software, https:\/\/www.rdkit.org; https:\/\/www.rdkit.org (accessed."},{"issue":"4","key":"2026081111095822000_cit49","doi-asserted-by":"publisher","first-page":"2044","DOI":"10.1021\/acs.jcim.0c00025","article-title":"Improving\nConformer\nGeneration for Small Rings and Macrocycles Based on Distance Geometry\nand Experimental Torsional-Angle Preferences","volume":"60","author":"Wang","year":"2020","journal-title":"J. Chem. Inf. Model."}],"container-title":["Journal of Chemical Theory\nand Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jctc.6c00906","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jctcce\/article-pdf\/22\/15\/7720\/66056629\/acs.jctc.6c00906.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jctcce\/article-pdf\/22\/15\/7720\/66056629\/acs.jctc.6c00906.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T15:43:38Z","timestamp":1786463018000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jctcce\/article\/22\/15\/7720\/5220155\/DDCCNet-Physics-Enhanced-Multitask-Neural-Networks"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"references-count":49,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,7,20]]},"published-print":{"date-parts":[[2026,8,11]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jctc.6c00906","relation":{},"ISSN":["1549-9618","1549-9626"],"issn-type":[{"value":"1549-9618","type":"print"},{"value":"1549-9626","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]}}}