Docs

Research topics

Generative binder design

Designing peptide and miniprotein binders with generative models, and moving from one target to several — Generative Binder Design.

What this research is trying to do

Binder design has changed character in the last few years — from selecting to making. A diffusion model generates the backbone, a graph neural network designs the sequence that will sit on it, and a structure prediction network checks the result. Chained into one pipeline, these produce folded, target-complementary binders directly from a target structure — and sometimes from a target sequence alone.

What changed is not only speed. What counts as a tractable target widened: conformationally variable peptide hormones, intrinsically disordered regions, peptide-bound MHC, receptors whose signalling depends on engagement geometry, and macrocyclic chemotypes that previously required large-scale library screening.

Why several targets

Over the same period, therapeutic practice moved toward polypharmacology. Unimolecular incretin polyagonists showed that a single peptide chain can balance activity across several receptors, and bispecific or bifunctional formats use avidity, induced proximity and geometric constraint to convert modest individual affinities into cell-selective function.

The problem is that these two trajectories — generative single-target design and deliberate multi-target pharmacology — have so far advanced in parallel rather than together. Encoding multi-target objectives explicitly into generative pipelines is the next step.

The bottleneck is not affinity

Designed binders can already be made to bind tightly enough. The remaining variable is specificity — whether the binder engages only the intended site and leaves lookalike proteins alone. Seen this way, choosing the epitope is already an implicit negative design decision. Targeting the non-catalytic hemopexin domain of MMP-9 rather than its catalytic site is the illustration: catalytic sites are conserved across the family, so where you aim is also what you avoid.

What contextBio does

PepDesigner turns this flow into a runnable procedure — a closed loop from target structure through generation, filtering, molecular dynamics and binding free energy evaluation, run as batch jobs on a GPU cluster. The design procedure itself is in peptide drugs; what happens when the design has to face an immune network is in immunomodulatory peptides.

References

40 items

This page draws on the review manuscript Generative Design of Peptide and Miniprotein Binders: From Single Target Recognition Toward Multi-Target and Bispecific Therapeutics; below is the literature it cites.

  1. Yang W, Wang S, Lee GR, Zhang JZ, Courbet A, Juergens D, et al. The past, present and future of de novo protein design. Nature. 2026;652(8112):1139-1152. doi:10.1038/s41586-026-10328-7
  2. Watson JL, Juergens D, Bennett NR, Trippe BL, Yim J, Eisenach HE, et al. De novo design of protein structure and function with RFdiffusion. Nature. 2023;620(7976):1089-1100. doi:10.1038/s41586-023-06415-8
  3. Dauparas J, Anishchenko I, Bennett N, Bai H, Ragotte RJ, Milles LF, et al. Robust deep learning-based protein sequence design using ProteinMPNN. Science. 2022;378(6615):49-56. doi:10.1126/science.add2187
  4. Miao Z, Zhu S, Qin L, Ma D, Lai M, Xu P, et al. Integrating single-cell profiling with generative AI for de novo design of MMP9 protein binders in diffuse large B-cell lymphoma. Molecules. 2026;31(11):1969. doi:10.3390/molecules31111969
  5. Chen T, Sun T, Bian Y, Pei Y, Feng F, Chi H, et al. The design and optimization of monomeric multitarget peptides for the treatment of multifactorial diseases. J Med Chem. 2022;65(5):3685-3705. doi:10.1021/acs.jmedchem.1c01456
  6. Vadevoo SMP, Gurung S, Lee HS, Gunassekaran GR, Lee SM, Yoon JW, et al. Peptides as multifunctional players in cancer therapy. Exp Mol Med. 2023;55(6):1099-1109. doi:10.1038/s12276-023-01016-x
  7. Krishna R, Wang J, Ahern W, Sturmfels P, Venkatesh P, Kalvet I, et al. Generalized biomolecular modeling and design with RoseTTAFold All-Atom. Science. 2024;384(6693):eadl2528. doi:10.1126/science.adl2528
  8. Kim D, Woodbury SM, Ahern W, Tischer D, Kang A, Joyce E, et al. Computational design of metallohydrolases. Nature. 2026;649(8095):246-253. doi:10.1038/s41586-025-09746-w
  9. Dauparas J, Lee GR, Pecoraro R, An L, Anishchenko I, Glasscock C, et al. Atomic context-conditioned protein sequence design using LigandMPNN. Nat Methods. 2025;22(4):717-723. doi:10.1038/s41592-025-02626-1
  10. Bennett NR, Coventry B, Goreshnik I, Huang B, Allen A, Vafeados D, et al. Improving de novo protein binder design with deep learning. Nat Commun. 2023;14(1):2625. doi:10.1038/s41467-023-38328-5
  11. Pacesa M, Nickel L, Schellhaas C, Schmidt J, Pyatova E, Kissling L, et al. One-shot design of functional protein binders with BindCraft. Nature. 2025;646(8084):483-492. doi:10.1038/s41586-025-09429-6
  12. Chen LT, Quinn Z, Dumas M, Peng C, Hong L, Lopez-Gonzalez M, et al. Target sequence-conditioned design of peptide binders using masked language modeling. Nat Biotechnol. 2026;44(6):1002-1010. doi:10.1038/s41587-025-02761-2
  13. Rettie SA, Campbell KV, Bera AK, Kang A, Kozlov S, Bueso YF, et al. Cyclic peptide structure prediction and design using AlphaFold2. Nat Commun. 2025;16(1):4730. doi:10.1038/s41467-025-59940-7
  14. Rettie SA, Juergens D, Adebomi V, Bueso YF, Zhao Q, Leveille AN, et al. Accurate de novo design of high-affinity protein-binding macrocycles using deep learning. Nat Chem Biol. 2025;21(12):1948-1956. doi:10.1038/s41589-025-01929-w
  15. Bennett NR, Watson JL, Ragotte RJ, Borst AJ, See DL, Weidle C, et al. Atomically accurate de novo design of antibodies with RFdiffusion. Nature. 2026;649(8095):183-193. doi:10.1038/s41586-025-09721-5
  16. Vazquez Torres S, Leung PJY, Venkatesh P, Lutz ID, Hink F, Huynh HH, et al. De novo design of high-affinity binders of bioactive helical peptides. Nature. 2024;626(7998):435-442. doi:10.1038/s41586-023-06953-1
  17. Liu C, Wu K, Choi H, Han HL, Zhang X, Watson JL, et al. Diffusing protein binders to intrinsically disordered proteins. Nature. 2025;644(8077):809-817. doi:10.1038/s41586-025-09248-9
  18. Liu B, Greenwood NF, Bonzanini JE, Motmaen A, Meyerberg J, Dao T, et al. Design of high-specificity binders for peptide-MHC-I complexes. Science. 2025;389(6758):386-391. doi:10.1126/science.adv0185
  19. Johansen KH, Wolff DS, Scapolo B, Fernandez-Quintero ML, Risager Christensen C, Loeffler JR, et al. De novo-designed pMHC binders facilitate T cell-mediated cytotoxicity toward cancer cells. Science. 2025;389(6758):380-385. doi:10.1126/science.adv0422
  20. Wang X, Cardoso S, Cai K, Venkatesh P, Hung A, Ng M, et al. Tuning insulin receptor signaling using de novo-designed agonists. Mol Cell. 2025;85(21):4064-4081.e9. doi:10.1016/j.molcel.2025.09.020
  21. Wang X, Guillem-Marti J, Kumar S, Lee DS, Cabrerizo-Aguado D, Werther R, et al. De novo design of integrin alpha5beta1 modulating proteins to enhance biomaterial properties. Adv Mater. 2025;37(34):e2500872. doi:10.1002/adma.202500872
  22. Berger S, Seeger F, Yu TY, Aydin M, Yang H, Rosenblum D, et al. Preclinical proof of principle for orally delivered Th17 antagonist miniproteins. Cell. 2024;187(16):4305-4317.e18. doi:10.1016/j.cell.2024.05.052
  23. Zhao F, Zhou Q, Cong Z, Hang K, Zou X, Zhang C, et al. Structural insights into multiplexed pharmacological actions of tirzepatide and peptide 20 at the GIP, GLP-1 or glucagon receptors. Nat Commun. 2022;13(1):1057. doi:10.1038/s41467-022-28683-0
  24. Alavi SE, Boshrouyeh R, Raza A, Ebrahimi Shahmabadi H. Multi-target incretin-based therapeutics: the rise of dual and triple agonists for metabolic disorders. Eur J Med Chem. 2026;305:118587. doi:10.1016/j.ejmech.2026.118587
  25. Lawitz EJ, Fraessdorf M, Neff GW, Schattenberg JM, Noureddin M, Alkhouri N, et al. Efficacy, tolerability and pharmacokinetics of survodutide, a glucagon/glucagon-like peptide-1 receptor dual agonist, in cirrhosis. J Hepatol. 2024;81(5):837-846. doi:10.1016/j.jhep.2024.06.003
  26. Kasus-Jacobi A, Washburn JL, Laurence RB, Pereira HA. Selecting multitarget peptides for Alzheimer's disease. Biomolecules. 2022;12(10):1386. doi:10.3390/biom12101386
  27. Zhang Y, Yao P, Chen F, Zheng S, Niu X, Wang H, et al. In situ proliferating peptide nanoparticle augments multi-target intervention of secondary brain damage following subarachnoid hemorrhage. Adv Sci (Weinh). 2025;12(31):e17456. doi:10.1002/advs.202417456
  28. Wang D, Li Y, Lu J, Zhou Y, Chang X, Liu J, et al. Natural bioactive peptides in photoaging: multi-target mechanisms, clinical progress, and future anti-aging applications. Ageing Res Rev. 2026;114:102966. doi:10.1016/j.arr.2025.102966
  29. Torielli L, Castelli M, Milani F, Heritz JA, Cayaban SJ, Hernandez J, et al. Design of multi-target peptide modulators for protein chaperone networks. Structure. 2025;33(11):1944-1957.e6. doi:10.1016/j.str.2025.07.021
  30. Crook ZR, Girard EJ, Sevilla GP, Brusniak MY, Rupert PB, Friend DJ, et al. Ex silico engineering of cystine-dense peptides yielding a potent bispecific T cell engager. Sci Transl Med. 2022;14(645):eabn0402. doi:10.1126/scitranslmed.abn0402
  31. Skrzypczynska K, Schimert K, Stephenson H, Mah IK, Mortenson D, Boyd K, et al. Development of a PRAME pMHC targeted T cell engager for solid tumor therapy. MAbs. 2025;17(1):2563773. doi:10.1080/19420862.2025.2563773
  32. Dao T, Xiong G, Mun SS, Meyerberg J, Korontsvit T, Xiang J, et al. A dual-receptor T-cell platform with Ab-TCR and costimulatory receptor achieves specificity and potency against AML. Blood. 2024;143(6):507-521. doi:10.1182/blood.2023021054
  33. Driscoll CL, Keeble AH, Howarth MR. SpyMask enables combinatorial assembly of bispecific binders. Nat Commun. 2024;15(1):2403. doi:10.1038/s41467-024-46599-9
  34. Strittmatter T, Wang Y, Bertschi A, Scheller L, Freitag PC, Ray PG, et al. Programmable DARPin-based receptors for the detection of thrombotic markers. Nat Chem Biol. 2022;18(10):1125-1134. doi:10.1038/s41589-022-01095-3
  35. Vukovic D, Winkelvoss D, Udovcic A, Riermeier L, Jaime-Figueroa S, Crews CM, et al. Quantitative degradation rate assessment of bioPROTACs based on peptide degrons, E3 domains, adapters and conjugated small molecules. ACS Chem Biol. 2026;21(1):62-73. doi:10.1021/acschembio.5c00569
  36. Lin Z, Garcia BA, Lv D. Bifunctional peptide nanofibrils for targeted protein degradation. Angew Chem Int Ed Engl. 2024;63(3):e202316581. doi:10.1002/anie.202316581
  37. von Witting E, Lindbo S, Lundqvist M, Moller M, Wisniewski A, Kanje S, et al. Small bispecific affinity proteins for simultaneous target binding and albumin-associated half-life extension. Mol Pharm. 2021;18(1):328-337. doi:10.1021/acs.molpharmaceut.0c00975
  38. Ghosh P, Dinh H, Kocak A, Homer AK, Bou-Dip P, Schlicht S, et al. Bispecific DNA-peptide probes for targeting receptor pairs on live cells. Angew Chem Int Ed Engl. 2025;64(39):e202514237. doi:10.1002/anie.202514237
  39. Cheng X, Hubner R, von Kiedrowski V, Fricker G, Schirrmacher R, Wangler C, et al. Design, synthesis, in vitro and in vivo evaluation of heterobivalent SiFAlin-modified peptidic radioligands targeting both integrin alphavbeta3 and the MC1 receptor. Pharmaceuticals (Basel). 2021;14(6):547. doi:10.3390/ph14060547
  40. Farokhinejad F, Anderson W, Niu X, Wuethrich A, Howard CB, Trau M. Programmable dual-targeting nano bioconjugates: a universal bioconjugation strategy to enhance single molecule proteomic assays. Small Methods. 2026;10(7):e01235. doi:10.1002/smtd.202501235

Last updated ·