{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T12:33:23Z","timestamp":1786365203336,"version":"build-2736575974"},"reference-count":38,"publisher":"American Chemical Society (ACS)","issue":"15","license":[{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/na","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["20Z103070002"],"award-info":[{"award-number":["20Z103070002"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Designing protein sequences with favorable predicted energetic properties is an important challenge in protein inverse folding, because many existing deep learning methods are primarily trained by maximizing sequence recovery and do not explicitly incorporate energy-related preferences during generation. In this work, we propose EnerBridge-DPO, an energy-aware inverse folding framework that integrates Markov bridge sequence generation with preference optimization for protein complex design. The framework builds on the Markov bridge inverse-folding process to generate structure-compatible sequences from an informative prior sequence. It then introduces a Bridge-DPO objective that uses energy-related winner\u2013loser preference pairs to bias the generator toward sequences favored by computational or experimental energy-related signals. In addition, we incorporate a quantitative energy-constrained loss based on mutation-induced binding free-energy changes to provide continuous \u0394\u0394G supervision. Evaluations show that EnerBridge-DPO maintains competitive inverse-folding performance while obtaining lower predicted energy scores under selected computational scoring functions for protein complexes. On SKEMPI, EnerBridge-DPO achieves competitive \u0394\u0394G prediction performance, with small numerical gains in several overall metrics that are not statistically conclusive under paired bootstrap analysis. These results suggest that incorporating energy-related preferences into Markov bridge inverse folding can improve computationally predicted energetic profiles, although experimental validation is required to confirm thermodynamic stability.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01697","type":"journal-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T13:10:40Z","timestamp":1785849040000},"page":"9709-9720","source":"Crossref","is-referenced-by-count":0,"title":["EnerBridge-DPO:\nEnergy-Aware Markov Bridge Inverse\nFolding for Protein Sequence Design"],"prefix":"10.1021","volume":"66","author":[{"given":"Dingyi","family":"Rong","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University , , 800 Dongchuan Road , Minhang District, ,","place":["Shanghai, China, 200240"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haotian","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University , , 800 Dongchuan Road , Minhang District, ,","place":["Shanghai, China, 200240"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xupeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University , , 800 Dongchuan Road , Minhang District, ,","place":["Shanghai, China, 200240"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhuo","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University , , 800 Dongchuan Road , Minhang District, ,","place":["Shanghai, China, 200240"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University , , 800 Dongchuan Road , Minhang District, ,","place":["Shanghai, China, 200240"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangjia","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University , , 800 Dongchuan Road , Minhang District, ,","place":["Shanghai, China, 200240"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6204-1313","authenticated-orcid":true,"given":"Ning","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University , , 800 Dongchuan Road , Minhang District, ,","place":["Shanghai, China, 200240"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,7,27]]},"reference":[{"key":"2026081008092432900_cit1","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1126\/science.add2187","article-title":"Robust deep learning-based protein sequence design\nusing ProteinMPNN","volume":"378","author":"Dauparas","year":"2022","journal-title":"Science"},{"key":"2026081008092432900_cit2","doi-asserted-by":"publisher","first-page":"1070","DOI":"10.1038\/s41586-023-06728-8","article-title":"Illuminating protein space with a programmable\ngenerative model","volume":"623","author":"Ingraham","year":"2023","journal-title":"Nature"},{"key":"2026081008092432900_cit3","doi-asserted-by":"publisher","first-page":"e2017228118","DOI":"10.1073\/pnas.2017228118","article-title":"Protein sequence design\nby conformational landscape optimization","volume":"118","author":"Norn","year":"2021","journal-title":"Proc.\nNatl. Acad. Sci. U.S.A."},{"key":"2026081008092432900_cit4","first-page":"1","article-title":"Generative models for\ngraph-based protein design","volume":"32","author":"Ingraham","year":"2019","journal-title":"Adv. Neural Inf.\nProcess. Syst."},{"key":"2026081008092432900_cit5","doi-asserted-by":"crossref","unstructured":"Hsu, C.; Verkuil, R.; Liu, J.; Lin, Z.; Hie, B.; Sercu, T.; Lerer, A.; Rives, A.\n          Learning\nInverse Folding From Millions of Predicted Structures.  International Conference on Machine Learning, 2022; pp 8946\u20138970.","DOI":"10.1101\/2022.04.10.487779"},{"key":"2026081008092432900_cit6","first-page":"13266","article-title":"Representing long-range context for\ngraph neural networks with global attention","volume":"34","author":"Wu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026081008092432900_cit7","unstructured":"Gao, Z.; Tan, C.; Chaco\u0301n, P.; Li, S. Z.\n          Pifold: Toward effective and efficient\nprotein inverse folding, 2022."},{"key":"2026081008092432900_cit8","doi-asserted-by":"crossref","unstructured":"Zheng, Z.; Deng, Y.; Xue, D.; Zhou, Y.; Ye, F.; Gu, Q.\n          Structure-Informed Language Models Are Protein Designers.  International Conference on Machine Learning, 2023; pp 42317\u201342338.","DOI":"10.1101\/2023.02.03.526917"},{"key":"2026081008092432900_cit9","doi-asserted-by":"crossref","first-page":"10238","DOI":"10.52202\/075280-0449","article-title":"Graph denoising diffusion for inverse protein folding","volume":"36","author":"Yi","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026081008092432900_cit10","unstructured":"Gao, Z.; Tan, C.; Li, S. Z.\n          Knowledge-design: Pushing the limit\nof protein design via knowledge refinement, 2023."},{"key":"2026081008092432900_cit11","doi-asserted-by":"crossref","unstructured":"Zhu, Y.; Wu, J.; Li, Q.; Yan, J.; Yin, M.; Wu, W.; Li, M.; Ye, J.; Wang, Z.; Wu, J.\n          Bridge-IF: Learning Inverse\nProtein\nFolding with Markov Bridges, 2024.","DOI":"10.52202\/079017-1260"},{"key":"2026081008092432900_cit12","doi-asserted-by":"publisher","first-page":"1859","DOI":"10.1002\/bip.360261104","article-title":"Protein stability curves","volume":"26","author":"Becktel","year":"1987","journal-title":"Biopolymers"},{"key":"2026081008092432900_cit13","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1385\/1-59259-193-0:037","article-title":"The thermodynamic\nlinkage between protein structure, stability, and function","volume":"168","author":"Freire","year":"2001","journal-title":"Protein Struct., Stab., Fold."},{"key":"2026081008092432900_cit14","doi-asserted-by":"publisher","first-page":"4168","DOI":"10.1093\/bioinformatics\/btz184","article-title":"FoldX 5.0: working\nwith RNA, small molecules and a new graphical interface","volume":"35","author":"Delgado","year":"2019","journal-title":"Bioinformatics"},{"key":"2026081008092432900_cit15","doi-asserted-by":"publisher","first-page":"3031","DOI":"10.1021\/acs.jctc.7b00125","article-title":"The Rosetta\nall-atom energy function for macromolecular modeling and design","volume":"13","author":"Alford","year":"2017","journal-title":"J. Chem. Theory Comput."},{"key":"2026081008092432900_cit16","first-page":"66","volume-title":"Protein Structure Prediction\nUsing Rosetta","author":"Rohl","year":"2004"},{"key":"2026081008092432900_cit17","doi-asserted-by":"crossref","first-page":"53728","DOI":"10.52202\/075280-2338","article-title":"Direct preference optimization:\nYour language model is secretly a\nreward model","volume":"36","author":"Rafailov","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026081008092432900_cit18","unstructured":"Park, R.; Hsu, D. J.; Roland, C. B.; Korshunova, M.; Tessler, C.; Mannor, S.; Viessmann, O.; Trentini, B.\n          Improving inverse\nfolding for peptide design with diversity-regularized direct preference\noptimization, 2024."},{"key":"2026081008092432900_cit19","unstructured":"Xue, F.; Kubaney, A.; Guo, Z.; Min, J. K.; Liu, G.; Yang, Y.; Baker, D.\n          Improving Protein Sequence Design through Designability\nPreference Optimization, 2025."},{"key":"2026081008092432900_cit20","doi-asserted-by":"crossref","first-page":"120861","DOI":"10.52202\/079017-3840","article-title":"Antigen-specific\nantibody design via direct energy-based preference optimization","volume":"37","author":"Zhou","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026081008092432900_cit21","doi-asserted-by":"publisher","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure\nand function emerge from scaling\nunsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"2026081008092432900_cit22","doi-asserted-by":"crossref","unstructured":"Peebles, W.; Xie, S.\n          Scalable Diffusion Models With\nTransformers.  Proceedings of the IEEE\/CVF\nInternational Conference on Computer Vision, 2023; pp 4195\u20134205.","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"2026081008092432900_cit23","unstructured":"Jiao, X.; Mao, W.; Jin, W.; Yang, P.; Chen, H.; Shen, C.\n          Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational\nEffects on Protein-Protein Interactions, 2024."},{"key":"2026081008092432900_cit24","doi-asserted-by":"crossref","unstructured":"Lu, W.; Zhang, J.; Gu, M.; Zheng, S.\n          BindingGYM: A Large-Scale Mutational Dataset Toward\nDeciphering Protein-Protein Interactions, 2024.","DOI":"10.1101\/2024.12.03.626712"},{"key":"2026081008092432900_cit25","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1093\/bioinformatics\/bty635","article-title":"SKEMPI\n2.0: an updated\nbenchmark of changes in protein-protein binding energy, kinetics and\nthermodynamics upon mutation","volume":"35","author":"Jankauskaite","year":"2019","journal-title":"Bioinformatics"},{"key":"2026081008092432900_cit26","doi-asserted-by":"publisher","first-page":"107385","DOI":"10.1016\/j.compstruc.2024.107385","article-title":"Structgnn: an efficient\ngraph neural network framework\nfor static structural analysis","volume":"299","author":"Chou","year":"2024","journal-title":"Comput. Struct."},{"key":"2026081008092432900_cit27","unstructured":"Jing, B.; Eismann, S.; Suriana, P.; Townshend, R. J.; Dror, R.\n          Learning from\nprotein structure with geometric vector perceptrons, 2020."},{"key":"2026081008092432900_cit28","doi-asserted-by":"crossref","unstructured":"Tan, C.; Gao, Z.; Xia, J.; Hu, B.; Li, S. Z.\n          Global-Context Aware Generative Protein Design.  IEEE International Conference on Acoustics, Speech and\nSignal Processing (ICASSP), 2023; pp 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10095229"},{"key":"2026081008092432900_cit29","unstructured":"Gao, Z.; Tan, C.; Li, S. Z.\n          Alphadesign: A graph protein design\nmethod and benchmark on alphafolddb, 2022."},{"key":"2026081008092432900_cit30","doi-asserted-by":"publisher","first-page":"e2122954119","DOI":"10.1073\/pnas.2122954119","article-title":"Deep learning\nguided optimization of human antibody against SARS-CoV-2 variants\nwith broad neutralization","volume":"119","author":"Shan","year":"2022","journal-title":"Proc. Natl. Acad.\nSci. U.S.A."},{"key":"2026081008092432900_cit31","doi-asserted-by":"publisher","first-page":"gzad015","DOI":"10.1093\/protein\/gzad015","article-title":"Masked Inverse Folding with Sequence\nTransfer for Protein Representation Learning","volume":"36","author":"Yang","year":"2023","journal-title":"Protein Eng. Des. Sel."},{"key":"2026081008092432900_cit32","doi-asserted-by":"crossref","unstructured":"Luo, S.; Su, Y.; Wu, Z.; Su, C.; Peng, J.; Ma, J.\n          Rotamer density estimator is\nan unsupervised learner of the effect\nof mutations on protein-protein interaction, 2023.","DOI":"10.1101\/2023.02.28.530137"},{"key":"2026081008092432900_cit33","doi-asserted-by":"publisher","first-page":"48994","DOI":"10.52202\/075280-2128","article-title":"Predicting\nMutational Effects on Protein-Protein Binding via a Side-Chain Diffusion\nProbabilistic Model","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process.\nSyst."},{"key":"2026081008092432900_cit34","unstructured":"Wu, L.; Tian, Y.; Lin, H.; Huang, Y.; Li, S.; Chawla, N. V.; Li, S. Z.\n          Learning to predict mutation effects of protein-protein\ninteractions\nby microenvironment-aware hierarchical prompt learning, 2024."},{"key":"2026081008092432900_cit35","unstructured":"Mo, Y.; Hong, X.; Gao, B.; Jia, Y.; Lan, Y.\n          Multi-level interaction modeling for\nprotein mutational\neffect prediction, 2024."},{"key":"2026081008092432900_cit36","unstructured":"Wu, F.; Li, S. Z.\n          Surface-vqmae: Vector-Quantized\nMasked Auto-Encoders on Molecular Surfaces.  Forty-First International Conference on Machine Learning, 2024."},{"key":"2026081008092432900_cit37","unstructured":"Chen, X.; Zhang, Y.; Lu, C.; Ma, W.; Guan, J.; Gong, C.; Yang, J.; Zhang, H.; Zhang, K.; et al.\n          Protenix-advancing\nstructure prediction through a comprehensive AlphaFold3 reproduction, 2025."},{"key":"2026081008092432900_cit38","doi-asserted-by":"crossref","unstructured":"Passaro, S.; Corso, G.; Wohlwend, J.; Reveiz, M.; Thaler, S.; Somnath, V. R.; Getz, N.; Portnoi, T.; Roy, J.; Stark, H.; et al.\n          Boltz-2: Towards\naccurate and efficient\nbinding affinity prediction, 2025.","DOI":"10.1101\/2025.06.14.659707"}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01697","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/15\/9709\/66287888\/acs.jcim.6c01697.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/15\/9709\/66287888\/acs.jcim.6c01697.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T12:18:43Z","timestamp":1786364323000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/15\/9709\/5234418\/EnerBridge-DPO-Energy-Aware-Markov-Bridge-Inverse"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,27]]},"references-count":38,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,7,27]]},"published-print":{"date-parts":[[2026,8,10]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01697","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,27]]}}}