{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T22:39:50Z","timestamp":1773268790599,"version":"3.50.1"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"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. Bioinform."],"abstract":"<jats:p>Understanding protein interactions and dynamics of biological systems is central in drug discovery. Advances in artificial intelligence (AI) have expanded the scope of predictive learning for complex biological systems. Repurposing current gold-standard AI algorithms for structural and biological applications illustrates how flexible and powerful these approaches can be. In this mini-review, we examine how AI models are repurposed across domains and analyze how inductive biases, learning objectives, and representation choices inherited from their original applications shape performance in protein interaction and dynamics tasks. We discuss where AI approaches succeed, where they systematically fail, and how their behavior differs from physics-based modeling. We further highlight unresolved biological challenges, data and benchmarking limitations, and emerging opportunities for hybrid AI-physics workflows that balance efficiency with physical realism. By framing recent developments through a cross-domain adaptation framework, this review aims to provide practical guidance for selecting, evaluating, and integrating AI models in protein interaction and dynamics studies, and to support more reliable and biologically meaningful applications of AI in computational protein science.<\/jats:p>","DOI":"10.3389\/fbinf.2026.1749317","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T06:52:19Z","timestamp":1773211939000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Repurposing AI for protein interactions and dynamics: opportunities, limitations, and lessons"],"prefix":"10.3389","volume":"6","author":[{"given":"E. Sila","family":"Ozdemir","sequence":"first","affiliation":[{"name":"Independent Researcher","place":["Seattle, WA, United States"]}]},{"given":"Hyunbum","family":"Jang","sequence":"additional","affiliation":[{"name":"Computational Structural Biology Section, Frederick National Laboratory for Cancer Research in the Cancer Innovation Laboratory, National Cancer Institute","place":["Frederick, MD, United States"]}]},{"given":"Ruth","family":"Nussinov","sequence":"additional","affiliation":[{"name":"Computational Structural Biology Section, Frederick National Laboratory for Cancer Research in the Cancer Innovation Laboratory, National Cancer Institute","place":["Frederick, MD, United States"]},{"name":"Department of Human Molecular Genetics and Biochemistry, Sackler School of Medicine, Tel Aviv University","place":["Tel Aviv, Israel"]}]},{"given":"Attila","family":"Gursoy","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Koc University","place":["Istanbul, T\u00fcrkiye"]}]},{"given":"Ozlem","family":"Keskin","sequence":"additional","affiliation":[{"name":"Department of Chemical and Biological Engineering, Koc University","place":["Istanbul, T\u00fcrkiye"]}]}],"member":"1965","published-online":{"date-parts":[[2026,3,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"168686","DOI":"10.1016\/j.jmb.2024.168686","article-title":"PPInterface: a comprehensive dataset of 3D protein-protein interface structures","volume":"43617","author":"Abali","year":"2024","journal-title":"J. Mol. Biol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"B3","doi-asserted-by":"publisher","first-page":"6151","DOI":"10.1021\/acs.jctc.3c00702","article-title":"Two for one: diffusion models and force fields for coarse-grained molecular dynamics","volume":"1918","author":"Arts","year":"2023","journal-title":"J. Chem. Theory Comput."},{"key":"B4","doi-asserted-by":"publisher","first-page":"2102","DOI":"10.1093\/bioinformatics\/btac020","article-title":"ProteinBERT: a universal deep-learning model of protein sequence and function","volume":"388","author":"Brandes","year":"2022","journal-title":"Bioinformatics"},{"key":"B5","doi-asserted-by":"publisher","first-page":"5041","DOI":"10.1021\/acs.jcim.3c01905","article-title":"DiPPI: a curated data set for drug-like molecules in protein-protein interfaces","volume":"6413","author":"Cankara","year":"2024","journal-title":"J. Chem. Inf. Model"},{"key":"B6","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1038\/s41592-024-02516-y","article-title":"SurfDock is a surface-informed diffusion generative model for reliable and accurate protein-ligand complex prediction","volume":"222","author":"Cao","year":"2025","journal-title":"Nat. Methods"},{"key":"B7","doi-asserted-by":"publisher","first-page":"3165","DOI":"10.1021\/jacsau.3c00503","article-title":"Deep learning dynamic allostery of G-Protein-Coupled receptors","volume":"311","author":"Do","year":"2023","journal-title":"JACS Au"},{"key":"B8","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: toward understanding the language of life through self-supervised learning","volume":"4410","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B10","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1126\/science.ads0018","article-title":"Simulating 500 million years of evolution with a language model","volume":"387","author":"Hayes","year":"2025","journal-title":"Science"},{"key":"B11","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2706","DOI":"10.1021\/acsomega.1c05203","article-title":"TransDTI: transformer-based language models for estimating DTIs and building a drug recommendation workflow","volume":"73","author":"Kalakoti","year":"2022","journal-title":"ACS Omega"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaf294","article-title":"DeepAllo: allosteric site prediction using protein language model (pLM) with multitask learning","volume":"41","author":"Khokhar","year":"2025","journal-title":"Bioinformatics"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad496","article-title":"Structural coverage of the human interactome","volume":"25","author":"Kosoglu","year":"2023","journal-title":"Brief. Bioinform"},{"key":"B15","doi-asserted-by":"publisher","first-page":"3896761","DOI":"10.1126\/science.adv9817","article-title":"Scalable emulation of protein equilibrium ensembles with generative deep learning","volume":"389","author":"Lewis","year":"2025","journal-title":"Science"},{"key":"B16","doi-asserted-by":"publisher","first-page":"023013","DOI":"10.1103\/prxlife.3.023013","article-title":"ExEnDiff: an experiment-guided diffusion model for protein conformational ensemble generation","volume":"32","author":"Liu","year":"2025","journal-title":"PRX Life"},{"key":"B17","doi-asserted-by":"publisher","first-page":"6298","DOI":"10.1038\/s41467-022-34032-y","article-title":"Protein language models trained on multiple sequence alignments learn phylogenetic relationships","volume":"131","author":"Lupo","year":"2022","journal-title":"Nat. Commun."},{"key":"B19","doi-asserted-by":"publisher","first-page":"9759","DOI":"10.1021\/acs.jctc.4c01108","article-title":"Advances and challenges in milestoning simulations for drug-target kinetics","volume":"2022","author":"Ojha","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"B20","doi-asserted-by":"publisher","first-page":"2979","DOI":"10.1021\/acs.jcim.3c01788","article-title":"ProInterVal: validation of protein-protein interfaces through learned interface representations","volume":"648","author":"Ovek","year":"2024","journal-title":"J. Chem. Inf. Model"},{"key":"B21","doi-asserted-by":"publisher","first-page":"5870","DOI":"10.3390\/ijms25115870","article-title":"Protein-protein interfaces: a graph neural network approach","volume":"25","author":"Pancino","year":"2024","journal-title":"Int. J. Mol. Sci."},{"key":"B22","doi-asserted-by":"publisher","first-page":"2300219","DOI":"10.1002\/pmic.202300219","article-title":"Prediction of protein interactions is essential for studying biomolecular mechanisms","volume":"2317","author":"Vakser","year":"2023","journal-title":"Proteomics"},{"key":"B23","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v37i4.25663","article-title":"DIFFMD: a geometric diffusion model for molecular dynamics simulations","author":"Wu","year":"2023"},{"key":"B24","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1186\/s12859-024-05753-2","article-title":"CAT-DTI: cross-attention and transformer network with domain adaptation for drug-target interaction prediction","volume":"251","author":"Zeng","year":"2024","journal-title":"BMC Bioinforma."},{"key":"B25","doi-asserted-by":"publisher","first-page":"102327","DOI":"10.1016\/j.sbi.2021.102327","article-title":"Graph neural network approaches for drug-target interactions","volume":"73","author":"Zhang","year":"2022","journal-title":"Curr. Opin. Struct. Biol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1038\/s43588-023-00511-5","article-title":"Efficient and accurate large library ligand docking with KarmaDock","volume":"39","author":"Zhang","year":"2023","journal-title":"Nat. Comput. Sci."},{"key":"B27","doi-asserted-by":"publisher","first-page":"8796","DOI":"10.1021\/acs.jcim.4c01850","article-title":"ProAffinity-GNN: a novel approach to structure-based protein-protein binding affinity prediction via a curated data set and graph neural networks","volume":"6423","author":"Zhou","year":"2024","journal-title":"J. Chem. Inf. Model"},{"key":"B28","doi-asserted-by":"publisher","first-page":"7926","DOI":"10.1039\/d3sc06803j","article-title":"DiffBindFR: an SE(3) equivariant network for flexible protein-ligand docking","volume":"1521","author":"Zhu","year":"2024","journal-title":"Chem. Sci."}],"container-title":["Frontiers in Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1749317\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T06:52:20Z","timestamp":1773211940000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1749317\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,11]]},"references-count":26,"alternative-id":["10.3389\/fbinf.2026.1749317"],"URL":"https:\/\/doi.org\/10.3389\/fbinf.2026.1749317","relation":{},"ISSN":["2673-7647"],"issn-type":[{"value":"2673-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,11]]},"article-number":"1749317"}}