{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T20:46:31Z","timestamp":1791924391405,"version":"4.3.4"},"reference-count":20,"publisher":"American Chemical Society (ACS)","issue":"40","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The automated discovery of governing kinetic laws from observational data is a critical challenge in systems biology, pharmacology, and chemical engineering. In these experimental domains, data-driven mechanism discovery is complicated by sparse sampling, measurement noise (e.g., blood assays), and the prevalence of nonlinear saturation limits (Michaelis-Menten kinetics). Existing symbolic regression methods, such as SINDy, rely on polynomial basis functions that fundamentally fail to extrapolate physical saturation, and their reliance on numerical differentiation degrades catastrophically in high-noise regimes (&amp;gt;5%). In this work, we introduce ChemODE, a physics-informed gray-box framework tailored for biochemical and pharmacokinetic (PK) networks. ChemODE integrates (1) Constrained Rational Layers to autonomously enforce physical saturation laws, (2) On-the-fly Feature Normalization to resolve magnitude bias in multicompartment scale separations, and (3) a noise-robust integral-based optimization scheme. We validate ChemODE on fundamental biological benchmarks, including the nonlinear Brusselator limit cycle and a synthetic 3-compartment pharmacokinetic model. To demonstrate clinical applicability, ChemODE successfully extracts physiological absorption and elimination rates from real-world human theophylline pharmacokinetic assays. Furthermore, rigorous uncertainty quantification (10-seed ensembles) proves that ChemODE recovers enzyme kinetics with high precision (Vmax error \u2248 1%), significantly outperforming unconstrained baselines. This work establishes that integral-based minimization, combined with rational architectural constraints and a neural residual paradigm, provides a robust surrogate modeling path for interpretable mechanism discovery in noise-dominated biochemical settings.<\/jats:p>","DOI":"10.1021\/acsomega.6c04487","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T08:02:04Z","timestamp":1790755324000},"page":"60914-60919","source":"Crossref","is-referenced-by-count":0,"title":["ChemODE: A Physics-Informed\nNeural Surrogate for Robust\nPharmacokinetics and Biochemical Dynamics"],"prefix":"10.1021","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6177-9433","authenticated-orcid":true,"given":"Wit","family":"Kulvutiroj","sequence":"first","affiliation":[{"name":"Kamnoetvidya Science Academy , Wang Chan District, , ,","place":["Pa Yup Nai, Rayong, Thailand, 21210"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"2026101315072096800_cit1","doi-asserted-by":"publisher","first-page":"1049","DOI":"10.1021\/acs.chemrev.0c00394","article-title":"Microkinetic Modeling: A Tool for Rational Catalyst\nDesign","volume":"121","author":"Motagamwala","year":"2021","journal-title":"Chem. Rev."},{"key":"2026101315072096800_cit2","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2021.100118","article-title":"ChemNODE: A Neural\nOrdinary Differential Equations Framework for\nChemical Kinetics","volume":"7","author":"Owoyele","year":"2022","journal-title":"Energy AI"},{"key":"2026101315072096800_cit3","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1038\/s42256-025-01087-7","article-title":"Kolmogorov\u2013Arnold\ngraph neural networks for molecular property prediction","volume":"7","author":"Li","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026101315072096800_cit4","doi-asserted-by":"publisher","first-page":"3932","DOI":"10.1073\/pnas.1517384113","article-title":"Discovering governing\nequations from\ndata by sparse identification of nonlinear dynamical systems","volume":"113","author":"Brunton","year":"2016","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"2026101315072096800_cit5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113620","article-title":"Sparse identification\nof nonlinear\ndynamical systems via reweighted L1-regularized least squares","volume":"376","author":"Cortiella","year":"2021","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"2026101315072096800_cit6","unstructured":"Chen, R. T. Q.; Rubanova, Y.; Bettencourt, J.; Duvenaud, D. In  Neural Ordinary Differential\nEquations, Advances in Neural Information Processing Systems, 2018; Vol. 31, pp 6571\u20136583."},{"key":"2026101315072096800_cit7","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1016\/j.jcp.2018.10.045","article-title":"Physics-informed neural 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."},{"key":"2026101315072096800_cit8","doi-asserted-by":"crossref","unstructured":"Rackauckas, C.; Ma, Y.; Martensen, J.; et al.\n          Universal\nDifferential Equations for Scientific Machine Learning. 2020, arXiv:2001.04385. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2001.04385.","DOI":"10.21203\/rs.3.rs-55125\/v1"},{"key":"2026101315072096800_cit9","doi-asserted-by":"publisher","DOI":"10.1063\/5.0060697","article-title":"Stiff Neural\nOrdinary Differential Equations","volume":"31","author":"Kim","year":"2021","journal-title":"Chaos"},{"key":"2026101315072096800_cit10","doi-asserted-by":"publisher","DOI":"10.1007\/s10928-026-10019-w","article-title":"A physics-informed neural network\napproach for estimating population-level pharmacokinetic parameters\nfrom aggregated concentration data","volume":"53","author":"Tsiros","year":"2026","journal-title":"J. Pharmacokinet.\nPharmacodyn."},{"key":"2026101315072096800_cit11","unstructured":"Wickramasinghe, C. D.; Weerasinghe, K. C.; Ranaweera, P. K.; Hapuhinna, N. S.\n          PBPK-iPINNs: Inverse Physics-Informed Neural Networks for Physiologically\nBased Pharmacokinetic Brain Models. 2025, arXiv:2509.12666. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2509.12666."},{"key":"2026101315072096800_cit12","doi-asserted-by":"publisher","DOI":"10.3390\/e27060602","article-title":"Leveraging\nNeural ODEs for Population Pharmacokinetics\nof Dalbavancin in Sparse Clinical Data","volume":"27","author":"Giacometti","year":"2025","journal-title":"Entropy"},{"key":"2026101315072096800_cit13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2020.109985","article-title":"DeepMoD: Deep\nlearning for model discovery in noisy data","volume":"428","author":"Both","year":"2021","journal-title":"J. Comput. Phys."},{"key":"2026101315072096800_cit14","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.1602614","article-title":"Data-driven discovery\nof partial differential equations","volume":"3","author":"Rudy","year":"2017","journal-title":"Sci. Adv."},{"key":"2026101315072096800_cit15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2021.110525","article-title":"Weak SINDy for partial differential\nequations","volume":"443","author":"Messenger","year":"2021","journal-title":"J. Comput. Phys."},{"key":"2026101315072096800_cit16","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2020.0279","article-title":"SINDy-PI:\nA robust algorithm for\nparallel implicit sparse identification of nonlinear dynamics","volume":"476","author":"Kaheman","year":"2020","journal-title":"Proc. R. Soc. A"},{"key":"2026101315072096800_cit17","unstructured":"Ioffe, S.; Szegedy, C. In  Batch Normalization:\nAccelerating Deep Network Training by Reducing Internal Covariate\nShift, International Conference on Machine Learning, 2015; pp 448\u2013456."},{"key":"2026101315072096800_cit18","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-05221-7","volume-title":"Solving Ordinary Differential\nEquations II: Stiff and Differential-Algebraic Problems","author":"Hairer","year":"1996"},{"key":"2026101315072096800_cit19","unstructured":"Boeckmann, A. J.; Sheiner, L. B.; Beal, S. L.\n          NONMEM\nUsers Guide: Part V, NONMEM Project Group; University of California: San Francisco, 1994."},{"key":"2026101315072096800_cit20","doi-asserted-by":"publisher","first-page":"1695","DOI":"10.1063\/1.1668896","article-title":"Symmetry Breaking\nInstabilities in Dissipative Systems.\nII","volume":"48","author":"Prigogine","year":"1968","journal-title":"J. Chem. Phys."}],"container-title":["ACS Omega"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acsomega.6c04487","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/40\/60914\/68708215\/acsomega.6c04487.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/40\/60914\/68708215\/acsomega.6c04487.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T20:02:46Z","timestamp":1791921766000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/acsodf\/article\/11\/40\/60914\/5442176\/ChemODE-A-Physics-Informed-Neural-Surrogate-for"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":20,"journal-issue":{"issue":"40","published-online":{"date-parts":[[2026,9,30]]},"published-print":{"date-parts":[[2026,10,13]]}},"URL":"https:\/\/doi.org\/10.1021\/acsomega.6c04487","relation":{},"ISSN":["2470-1343"],"issn-type":[{"value":"2470-1343","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]}}}