{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T05:06:14Z","timestamp":1790139974919,"version":"4.0.1"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>\n                    Predicting drug release from polymer-based delivery systems remains challenging because release behavior depends on nonlinear interactions among formulation composition, polymer properties, drug characteristics, processing conditions, and time. This study develops an interpretable artificial intelligence framework for predicting cumulative drug release from PLGA nanoparticle formulations prepared by nanoprecipitation. A curated dataset containing 4,909 formulation\u2013release observations was used to integrate formulation-informed feature engineering, temporal representation learning, symbolic regression, latent-space analysis, and explainable machine learning. The proposed framework achieved\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    \u2009=\u20090.9977, RMSE\u2009=\u20091.56\u2009\u00d7\u200910\n                    <jats:sup>\u22124<\/jats:sup>\n                    , and MAE\u2009=\u20091.31\u2009\u00d7\u200910\n                    <jats:sup>\u22124<\/jats:sup>\n                    on the training data, while the independent test set yielded\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    \u2009=\u20090.9975, RMSE\u2009=\u20091.64\u2009\u00d7\u200910\n                    <jats:sup>\u22124<\/jats:sup>\n                    , and MAE\u2009=\u20091.31\u2009\u00d7\u200910\n                    <jats:sup>\u22124<\/jats:sup>\n                    . Y-scrambling produced substantially lower\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    values of 0.0636\u20130.0714, providing evidence that the observed predictive performance is not readily reproduced after randomization of the response. Temporal autoencoder representations further revealed structured organization of release trajectories in a low-dimensional latent space. Nevertheless, the high predictive accuracy should be interpreted cautiously because the dataset contains repeated observations associated with formulation\u2013release trajectories and includes release time as an input-related variable; therefore, random observation-level splitting may provide more favorable estimates than formulation-level or study-level external validation. The framework provides a computational basis for formulation screening and hypothesis generation, but experimentally validated release experiments and prospective external datasets remain necessary before practical deployment.\n                  <\/jats:p>","DOI":"10.3389\/fmed.2026.1975727","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T04:44:43Z","timestamp":1790138683000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mechanism-aware and explainable artificial intelligence for drug release prediction in polymeric drug delivery systems"],"prefix":"10.3389","volume":"13","author":[{"given":"Mohammed","family":"Ghazwani","sequence":"first","affiliation":[{"name":"Department of Pharmaceutics, College of Pharmacy, King Khalid University","place":["Abha, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yahia","family":"Alghazwani","sequence":"additional","affiliation":[{"name":"Department of Pharmacology, College of Pharmacy, King Khalid University","place":["Abha, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Umme","family":"Hani","sequence":"additional","affiliation":[{"name":"Department of Pharmaceutics, College of Pharmacy, King Khalid University","place":["Abha, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s10928-023-09887-3","article-title":"Learning pharmacometric covariate model structures with symbolic regression networks","volume":"51","author":"Wahlquist","year":"2024","journal-title":"J Pharmacokinet Pharmacodyn"},{"key":"B2","doi-asserted-by":"publisher","first-page":"3845","DOI":"10.1007\/s11831-023-09922-z","article-title":"Artificial intelligence in physical sciences: symbolic regression trends and perspectives: d. Angelis et al.","volume":"30","author":"Angelis","year":"2023","journal-title":"Arch Comput Methods Eng"},{"key":"B3","doi-asserted-by":"publisher","first-page":"114347","DOI":"10.1016\/j.jconrel.2025.114347","article-title":"A biocompatible tea polyphenol nanoplatform for efficient cytosolic delivery of protein therapeutics","volume":"388","author":"Wang","year":"2025","journal-title":"J Control Release"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e2605060123","DOI":"10.1073\/pnas.2605060123","article-title":"Physically intelligent capsule robots with embodied memory and logic in the gastrointestinal tract","volume":"123","author":"Chen","year":"2026","journal-title":"Proc Natl Acad Sci U S A."},{"key":"B5","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1186\/s12859-020-03682-4","article-title":"NEDD: a network embedding based method for predicting drug-disease associations","volume":"21","author":"Zhou","year":"2020","journal-title":"BMC Bioinformatics"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.1038\/s41598-023-28328-2","article-title":"A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge","volume":"13","author":"Keren","year":"2023","journal-title":"Sci Rep"},{"key":"B7","doi-asserted-by":"publisher","first-page":"114333","DOI":"10.1016\/j.ab.2021.114333","article-title":"Peptide-based system for sensing Pb2+and molecular logic computing","volume":"630","author":"Lu","year":"2021","journal-title":"Anal Biochem"},{"key":"B8","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1016\/j.omtn.2020.07.003","article-title":"An improved anticancer drug-response prediction based on an ensemble method integrating matrix completion and ridge regression","volume":"21","author":"Liu","year":"2020","journal-title":"Mol Ther Nucleic Acids"},{"key":"B9","author":"Lalande","year":"2023"},{"key":"B10","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s10462-023-10622-0","article-title":"Interpretable scientific discovery with symbolic regression: a review","volume":"57","author":"Makke","year":"2024","journal-title":"Artif Intell Rev"},{"key":"B11","doi-asserted-by":"publisher","first-page":"108108","DOI":"10.1016\/j.compchemeng.2022.108108","article-title":"Modeling of bioprocesses via MINLP-based symbolic regression of S-system formalisms","volume":"170","author":"Forster","year":"2023","journal-title":"Comput Chem Eng"},{"key":"B12","doi-asserted-by":"publisher","first-page":"L013301","DOI":"10.1103\/PhysRevE.107.L013301","article-title":"Data-driven discovery of the governing equations for transport in heterogeneous media by symbolic regression and stochastic optimization","volume":"107","author":"Im","year":"2023","journal-title":"Phys. Rev. E"},{"key":"B13","doi-asserted-by":"publisher","first-page":"126501","DOI":"10.1016\/j.ijpharm.2025.126501","article-title":"Advances in metal ion\u2013mediated macromolecular drug delivery","volume":"689","author":"Li","year":"2025","journal-title":"Int J Pharm"},{"key":"B14","article-title":"Arsenic trioxide-based nanoparticles for enhance chemotherapy by activating pyroptosis","author":"Wang","year":"2025","journal-title":"Acta Pharm. Sin. B"},{"key":"B15","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1208\/s12248-025-01101-1","article-title":"Machine learning predicts drug release profiles and kinetic parameters based on tablets\u2019 formulations","volume":"27","author":"Protopapa","year":"2025","journal-title":"AAPS J."},{"key":"B16","doi-asserted-by":"publisher","first-page":"4218","DOI":"10.1038\/s41598-024-82728-6","article-title":"Machine learning integrated with in vitro experiments for study of drug release from PLGA nanoparticles","volume":"15","author":"Sun","year":"2025","journal-title":"Sci Rep"},{"key":"B17","doi-asserted-by":"publisher","first-page":"25139","DOI":"10.1038\/s41598-025-10417-z","article-title":"Combination of machine learning and Raman spectroscopy for prediction of drug release in targeted drug delivery formulations","volume":"15","author":"Mahdi","year":"2025","journal-title":"Sci Rep"},{"key":"B18","doi-asserted-by":"publisher","first-page":"6611","DOI":"10.1021\/acs.molpharmaceut.5c00494","article-title":"Drug delivery from nanogel formulations: mathematical modeling of different release profiles and conditions","volume":"22","author":"D\u2019Ambrosio","year":"2025","journal-title":"Mol Pharm"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1395359","DOI":"10.3389\/fchem.2024.1395359","article-title":"Modeling and validation of drug release kinetics using hybrid method for prediction of drug efficiency and novel formulations","volume":"12","author":"Alshahrani","year":"2024","journal-title":"Front Chem"},{"key":"B20","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.ejpb.2023.02.014","article-title":"Model-based optimization of drug release rate from a size distributed population of biodegradable polymer carriers","volume":"186","author":"Vasileiadou","year":"2023","journal-title":"Eur J Pharm Biopharm"},{"key":"B21","doi-asserted-by":"publisher","first-page":"4595","DOI":"10.3390\/ma16134595","article-title":"Interplay between diffusion and bond cleavage reaction for determining release in polymer\u2013drug conjugates","volume":"16","author":"Kalosakas","year":"2023","journal-title":"Materials (Basel)."},{"key":"B22","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/j.jconrel.2023.06.019","article-title":"Controlling release from encapsulated drug-loaded devices: insights from modeling the dissolution front propagation","volume":"360","author":"Jain","year":"2023","journal-title":"J Control Release"},{"key":"B23","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1038\/s41467-022-35343-w","article-title":"Machine learning models to accelerate the design of polymeric long-acting injectables","volume":"14","author":"Bannigan","year":"2023","journal-title":"Nat Commun"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1038\/s41597-025-05520-9","article-title":"A formulation dataset of poly (lactide-co-glycolide) nanoparticles for small molecule delivery","volume":"12","author":"Goren","year":"2025","journal-title":"Sci Data"},{"key":"B25","author":"Zhi-Han","year":"2022"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.1109\/TIP.2025.3564829","article-title":"Variational Bayes image restoration with compressive autoencoders","volume":"34","author":"Biquard","year":"2025","journal-title":"IEEE Trans Image Process."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.61603\/ceas.v2i1.33","article-title":"Auto-encoding variational Bayes","volume":"2","author":"Chen","year":"2024","journal-title":"Cambridge Explor Arts Sci."},{"key":"B28","first-page":"771","article-title":"A comparison of LSTM and GRU networks for learning symbolic sequences","volume-title":"Science and Information conference","author":"Cahuantzi","year":"2023"},{"key":"B29","author":"Oh","year":"2023"},{"key":"B30","author":"Seetharaman","year":"2025"},{"key":"B31","doi-asserted-by":"publisher","first-page":"2343","DOI":"10.3390\/en16052343","article-title":"A review of physics-informed machine learning in fluid mechanics","volume":"16","author":"Sharma","year":"2023","journal-title":"Energies"},{"key":"B32","doi-asserted-by":"publisher","first-page":"14123","DOI":"10.1007\/s00521-021-06483-9","article-title":"A Bayesian sampling framework for asymmetric generalized Gaussian mixture models learning","volume":"34","author":"Vemuri","year":"2022","journal-title":"Neural Comput Appl"},{"key":"B33","doi-asserted-by":"publisher","first-page":"589","DOI":"10.3390\/ijms26020589","article-title":"Exploring the pharmacogenomic map of Croatia: pGx clustering of 522-patient cohort based on UMAP+ HDBSCAN algorithm","volume":"26","author":"Brlek","year":"2025","journal-title":"Int J Mol Sci"},{"key":"B34","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/ITIS67966.2025.11308961","article-title":"Self-supervised embeddings and UMAP for discovering plant morphological features","volume-title":"2025 IEEE 11th Information Technology International Seminar (ITIS)","author":"Imani","year":"2025"},{"key":"B35","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1146\/annurev-statistics-112723-034707","article-title":"Theory of random forests","volume":"13","author":"Scornet","year":"2026","journal-title":"Annu Rev Stat Appl."},{"key":"B36","doi-asserted-by":"publisher","first-page":"105971","DOI":"10.1016\/j.envsoft.2024.105971","article-title":"Applications of XGBoost in water resources engineering: a systematic literature review (Dec 2018\u2013May 2023)","volume":"174","author":"Niazkar","year":"2024","journal-title":"Environ Model Softw"},{"key":"B37","doi-asserted-by":"publisher","first-page":"19828","DOI":"10.1038\/s41598-024-67562-0","article-title":"Integrating cat boost algorithm with triangulating feature importance to predict survival outcome in recurrent cervical cancer","volume":"14","author":"Geeitha","year":"2024","journal-title":"Sci Rep"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1975727\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T04:44:51Z","timestamp":1790138691000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1975727\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,23]]},"references-count":37,"alternative-id":["10.3389\/fmed.2026.1975727"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1975727","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,23]]},"article-number":"1975727"}}