A Computational Framework for Erythropoietin Protein Synthesis and Optimization: Integrating Protein Language Models, AlphaFold3 Structural Prediction, and Bayesian Optimization

References

[1] Senthil Velan Bhoopalan, Lily Jun-shen Huang, and Mitchell J. Weiss. Erythropoietin regulation of red blood cell production: from bench to bedside and back. F1000Research, 9:1153, 2020. doi: 10.12688/f1000research. 26648.1.

[2] Wolfgang Jelkmann. Erythropoietin: Structure, control of production, and function. Physiological Reviews, 72 (2):449–489, 1992. doi: 10.1152/physrev.1992.72.2.449.

[3] Steve Elliott, David Chang, Evelyne Delorme, Tamer Eris, and Tony Lorenzini. Structural requirements for additional n-linked carbohydrate on recombinant human erythropoietin. Journal of Biological Chemistry, 279 (16):16854–16862, 2004. doi: 10.1074/jbc.M311095200.

[4] Steve Elliott. Erythropoiesis-stimulating agents and other methods to enhance oxygen transport. British Journal of Pharmacology, 154:529–541, 2008. doi: 10.1038/bjp.2008.89.

[5] Stefan Schreiber, Stefanie Howaldt, Mareille Schnoor, Susanna Nikolaus, Jürgen Bauditz, Christoph Gasché, Herbert Lochs, and Andreas Raedler. Recombinant erythropoietin for the treatment of anemia in in-flammatory bowel disease. New England Journal of Medicine, 334(10):619–623, 1996. doi: 10.1056/ NEJM199603073341002.

[6] Iain C. Macdougall. Novel erythropoiesis-stimulating agents: A new era in anemia management. Clinical Journal of the American Society of Nephrology, 3:200–207, 2008. doi: 10.2215/CJN.03840907.

[7] Steve Elliott, Elizabeth Pham, and Iain C. Macdougall. Erythropoietins: A common mechanism of action. Experimental Hematology, 36:1573–1584, 2008. doi: 10.1016/j.exphem.2008.08.003.

[8] [M. Alejandro Carballo-Amador, Edward A. McKenzie, Alan J. Dickson, and Jim Warwicker. Surface patches on recombinant erythropoietin predict protein solubility: engineering proteins to minimise aggregation. BMC Biotechnology, 19:26, 2019. doi: 10.1186/s12896-019-0520-z.

[9] Alexander Rives, Joshua Meier, Tom Sercu, Siddharth Goyal, Zeming Lin, Jason Liu, Demi Guo, Myle Ott, C. Lawrence Zitnick, Jerry Ma, and Rob Fergus. Biological structure and function emerge from scaling unsu-pervised learning to 250 million protein sequences. Proceedings of the National Academy of Sciences, 118(15): e2016239118, 2021. doi: 10.1073/pnas.2016239118.

[10] Ali Madani, Ben Krause, Eric R. Greene, Subu Subramanian, Benjamin P. Mohr, James M. Holton, Jose Luis Olmos Jr., Caiming Xiong, Zachary Z. Sun, Richard Socher, James S. Fraser, and Nikhil Naik. Large language models generate functional protein sequences across diverse families. Nature Biotechnology, 2023. doi: 10. 1038/s41587-022-01618-2.

[11] Roshan Rao, Nicholas Bhattacharya, Neil Thomas, Yan Duan, Xi Chen, John Canny, Pieter Abbeel, and Yun S. Song. Evaluating protein transfer learning with TAPE. In 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), 2019.

[12] John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tun-yasuvunakool, Russ Bates, Augustin Žídek, Anna Potapenko, et al. Highly accurate protein structure prediction with AlphaFold. Nature, 596(7873):583–589, 2021. doi: 10.1038/s41586-021-03819-2.

[13] Mihaly Varadi, Stephen Anyango, Mandar Deshpande, Sreenath Nair, Cindy Natassia, Galabina Yordanova, David Yuan, Oana Stroe, Gemma Wood, Agata Laydon, et al. AlphaFold protein structure database: mas-sively expanding the structural coverage of protein-sequence space with high-accuracy models. Nucleic Acids Research, 50(D1):D439–D444, 2022. doi: 10.1093/nar/gkab1061.

[14] John M. McBride, Konstantin Polev, Amirbek Abdirasulov, Vladimir Reinharz, Bartosz A. Grzybowski, and Tsvi Tlusty. AlphaFold2 can predict single-mutation effects. Physical Review Letters, 131(21):218401, 2023. doi: 10.1103/PhysRevLett.131.218401.

[15] Peter I. Frazier. A tutorial on Bayesian optimization. arXiv preprint arXiv:1807.02811, 2018.

[16] Jasper Snoek, Hugo Larochelle, and Ryan P. Adams. Practical Bayesian optimization of machine learning algorithms. In Advances in Neural Information Processing Systems (NeurIPS), volume 25, 2012.

[17] Jia Ren, Jayson McAllister, Zukui Li, Jinfeng Liu, and Ulrich Simonsmeier. Modeling of hemoglobin response to erythropoietin therapy through constrained optimization. In 2017 6th International Symposium on Advanced Control of Industrial Processes (AdCONIP), 2017.

[18] Joshua Meehl and Prasad Siddavatam. Efficient protein engineering via integrated language models and Bayesian optimization. bioRxiv preprint, 2025. doi: 10.1101/2025.09.30.679490.

[19] Farid Vahedi, Mohammadreza Nassiri, Shahrokh Ghovvati, and Ali Javadmanesh. Evaluation of different signal peptides using bioinformatics tools to express recombinant erythropoietin in mammalian cells. International Journal of Peptide Research and Therapeutics, 25:989–995, 2019. doi: 10.1007/s10989-018-9746-1.

[20] Naima Thahsin, Khairul Islam Khan, Abu Nasor Md Rakib Sarwar, Mohammad Nazmus Sakib, and Moham-mad Shahedur Rahman. Unveiling novel hyperglycosylated analog of human erythropoietin: a comprehensive computational exploration. Computational and Structural Biotechnology Reports, 2:100029, 2025.

[21] Wei Wang. Protein aggregation and its inhibition in biopharmaceutics. International Journal of Pharmaceutics, 289:1–30, 2005. doi: 10.1016/j.ijpharm.2004.11.014.

[22] John F. Carpenter, Theodore W. Randolph, Wim Jiskoot, Daan J. A. Crommelin, C. Russell Middaugh, Gerhard Winter, Ying-Xin Fan, Susan Kirshner, Daniela Verthelyi, Steven Kozlowski, Kathleen A. Clouse, Patrick G. Swann, Amy Rosenberg, and Barry Cherney. Overlooking subvisible particles in therapeutic protein products: Gaps that may compromise product quality. Journal of Pharmaceutical Sciences, 98(4):1201–1205, 2009. doi: 10.1002/jps.21530.

[23] Alexey S. Kazakov, Evgenia I. Deryusheva, Andrey S. Sokolov, Maria E. Permyakova, Ekaterina A. Litus, Victoria A. Rastrygina, Vladimir N. Uversky, Eugene A. Permyakov, and Sergei E. Permyakov. Erythropoietin interacts with specific s100 proteins. Biomolecules, 2022.

[24] Gerd G. Kochendoerfer, Shui-Yu Chen, Feng Mao, Sonya Cressman, Steve Traviglia, Haiyan Shao, C. Landon Hunter, Daniel W. Low, Erik N. Cagle, Marco Carnevali, et al. Design and chemical synthesis of a homogeneous polymer-modified erythropoiesis protein. Science, 299(5608):884–887, 2003. doi: 10.1126/science.1079085.

[25] Ly Minh Nguyen, Calvin J. Meaney, Gauri G. Rao, Mandip Panesar, and Wojciech Krzyzanski. Population pharmacodynamic modeling of epoetin alfa in end-stage renal disease patients receiving maintenance treatment using Bayesian approach. CPT: Pharmacometrics & Systems Pharmacology, 9:596–605, 2020. doi: 10.1002/ psp4.12556.

[26] ScienceDirect Corpus Source. Erythropoiesis stimulating agent recommendation model using recurrent neural networks for patient with kidney failure with replacement therapy. Computers in Biology and Medicine, 137: 104718, 2021. doi: 10.1016/j.compbiomed.2021.104718.

[27] Lei Wang, Xudong Li, Han Zhang, Jinyi Wang, Dingkang Jiang, Zhidong Xue, and Yan Wang. A comprehensive review of protein language models. arXiv preprint arXiv:2502.06881, 2025.

[28] Xuechun Zhang, Xiaoxuan Hu, Tongtong Zhang, Ling Yang, Chunhong Liu, Ning Xu, Haoyi Wang, and Wen Sun. Predicting protein solubility by benchmarking multiple protein language models. Briefings in Bioinfor-matics, 25(5):bbae404, 2024. doi: 10.1093/bib/bbae404.

[29] Suresh Pokharel. Protein Language Models-Based Representation for Post-translational Modification Predic-tion. PhD thesis, Rochester Institute of Technology, 2025.

[30] Can Chen, Jingbo Zhou, Fan Wang, Xue Liu, and Dejing Dou. Structure-aware protein self-supervised learning. Bioinformatics, 39(4):btad189, 2023. doi: 10.1093/bioinformatics/btad189.

[31] Jia-Ying Chen et al. Evaluating the advancements in protein language models for encoding strategies in protein function prediction: a comprehensive review. Frontiers in Bioengineering and Biotechnology, 2025. doi: 10. 3389/fbioe.2025.1506508.

[32] Minkyung Baek, Frank DiMaio, Ivan Anishchenko, Justas Dauparas, Sergey Ovchinnikov, Gyu Rie Lee, Jue Wang, Qian Cong, Lisa N. Kinch, R. Dustin Schaeffer, et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science, 373(6557):871–876, 2021. doi: 10.1126/science. abj8754.

[33] Jennifer Fleming, Paulyna Magana, Sreenath Nair, Maxim Tsenkov, Damian Bertoni, Ivanna Pidruchna, Marcelo Querino Lima Afonso, Adam Midlik, Urmila Paramval, Augustin Žídek, et al. AlphaFold protein structure database and 3d-beacons: New data and capabilities. Journal of Molecular Biology, 2025. doi: 10.1016/j.jmb.2025.168967.

[34] Bobak Shahriari, Kevin Swersky, Ziyu Wang, Ryan P. Adams, and Nando de Freitas. Taking the human out of the loop: A review of Bayesian optimization. Proceedings of the IEEE, 104(1):148–175, 2016. doi: 10.1109/ JPROC.2015.2494218.

[35] Rodolphe Le Riche and Victor Picheny. Revisiting Bayesian optimization in the light of the COCO benchmark. Structural and Multidisciplinary Optimization, 64:3063–3087, 2021. doi: 10.1007/s00158-021-02977-1.

[36] Koray Açıcı. Hemoglobin value prediction with Bayesian optimization assisted machine learning mod-els. Communications Faculty of Sciences University of Ankara Series A2-A3, 66(2):176–200, 2024. doi: 10.33769/aupse.1462331.

[37] Anonymous. Drug delivery optimization through Bayesian networks. Provided reference corpus (unattributed scanned source), 1998. Bibliographic metadata incomplete in source file; cited for conceptual application of Bayesian networks to dosage/delivery optimization.

@article{1722326,
      author = {Gaurav Nandagawli},
      title = {A Computational Framework for Erythropoietin Protein Synthesis and Optimization: Integrating Protein Language Models, AlphaFold3 Structural Prediction, and Bayesian Optimization},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {2},
      pages = {1475-1489},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1722326.pdf},
      abstract = {Erythropoietin (EPO) is a 166-residue, four-helix-bundle glycoprotein hormone that regulates erythropoiesis and remains one of the most clinically significant recombinant biopharmaceuticals in use today. Despite four decades of structural and pharmacological characterization, the rational engineering of EPO analogues with improved solubility, extended half-life, and reduced immunogenicity is still constrained by the combinatorial size of sequence, glycosylation, and formulation space. This paper proposes and evaluates an integrated in-silico framework that couples three complementary artificial-intelligence technologies: (i) Protein Language Models (PLMs) for sequence representation, variant scoring, and generative design; (ii) AlphaFold3-class structure-prediction networks for tertiary/quaternary structural validation and confidence estimation; and (iii) Bayesian Optimization (BO) for sample-efficient, closed-loop navigation of the mutational and process-parameter landscape. Using the published literature on EPO structure–function relationships, protein language modelling, AlphaFold architectures, and Bayesian optimization of biologic dosing and manufacturing parameters, we construct a methodological pipeline, present representative comparative benchmarks drawn from the cited literature, and illustrate how a PLM→AlphaFold3→BO loop could reduce the number of wet-laboratory iterations required to identify a hyperglycosylated, high-solubility EPO analogue. Results synthesized from the literature indicate that PLM-based fitness scoring correlates with experimentally observed solubility and expression outcomes, that AlphaFold3-class models achieve high per-residue confidence (pLDDT) for EPO’s four-helix bundle, and that Bayesian optimization historically outperforms grid and random search in hemoglobin-response and hyperparameter-tuning tasks by requiring substantially fewer evaluations to converge. We discuss the pharmacological, immunogenic, and manufacturing implications of this framework and conclude that hybrid PLM–structure–optimization pipelines represent a promising route toward next-generation erythropoiesis-stimulating agents (ESAs).},
      keywords = {erythropoietin, protein language model, alphafold3, bayesian optimization, protein engineering, glycoprotein design},
      month = {August},
      doi = {https://doi.org/10.64388/IREV10I2-1722326}
  }