ASPIRE improves protein binder prioritization through cross-target priors and sparse preference feedback
摘要
Generative protein design can produce thousands to hundreds of thousands of candidates for a single target, making accurate experimental prioritization a central bottleneck. Existing protein Bayesian optimization and active-learning workflows generally require initial measurements from the current target and therefore retain a cold-start problem. Here, we introduce Active Selection with Prior-Informed Ranking for Experiments (ASPIRE), which combines a transferable cross-target ranking prior with sparse within-target preference updates.
ASPIRE learns target-binder ranking from multi-target interaction data and assigns candidate priorities before target-specific measurements are available. Experimental outcomes are converted into preference relations within the same target and assay method, enabling subsequent ranking updates. Across four parallel protein landscapes containing 2,000-149,361 candidates, first-round ASPIRE selection identified candidates within the top 0.055%-3.54% of the true landscape using batches of four or ten. Iterative updates further improved candidate ranks and outperformed random-initialized Gaussian-process, prior-initialized Gaussian-process, and random-initialized Bradley-Terry/Laplace controls.
In a prospective ASPIRE-guided VISTA-binding peptide campaign, four of eight synthesized candidates produced clear binding signals. A ninth lead advanced to kinetic validation yielded an affinity range of 1.62-2.31 pM. ASPIRE therefore improves protein-binder prioritization from the first experimental round, with reduced experimental burden emerging as a practical consequence of more accurate selection.
参考文献
1. Watson, J. L. et al. De novo design of protein structure and function with RFdiffusion. Nature 620, 1089–1100 (2023).
2. Dauparas, J. et al. Robust deep learning–based protein sequence design using ProteinMPNN. Science 378, 49–56 (2022).
3. Cao, L. et al. Design of protein-binding proteins from the target structure alone. Nature 605, 551–560 (2022).
4. Gainza, P. et al. De novo design of protein interactions with learned surface fingerprints. Nature 617, 176–184 (2023).
5. Pacesa, M. et al. One-shot design of functional protein binders with BindCraft. Nature 646, 483–492 (2025).
6. Cao, L. et al. De novo design of picomolar SARS-CoV-2 miniprotein inhibitors. Science 370, 426–431 (2020).
7. Homola, J. Surface Plasmon Resonance Sensors for Detection of Chemical and Biological Species. Chemical Reviews 108, 462–493 (2008).
8. Abdiche, Y., Malashock, D., Pinkerton, A. & Pons, J. Determining kinetics and affinities of protein interactions using a parallel real-time label-free biosensor, the Octet. Analytical Biochemistry 377, 209–217 (2008).
9. Engvall, E. & Perlmann, P. Enzyme-linked immunosorbent assay (ELISA) quantitative assay of immunoglobulin G. Immunochemistry 8, 871–874 (1971).
10. Fowler, D. M. & Fields, S. Deep mutational scanning: A new style of protein science. Nature Methods 11, 801–807 (2014).
11. Fan, H. et al. A nanoplasmonic portable molecular interaction platform for high‐throughput drug screening. Advanced Functional Materials 32, 2203635 (2022).
12. Chen, M. et al. A Low-Cost Biomolecular Detection Platform Integrating Meta-SPR with Industrial Machine Vision for Affinity Analysis. ACS Sensors 10, 8628–8639 (2025).
13. Chen, M. et al. Direct Visualization and Quantitative Modeling of Mass Transport Limitation in Biomolecular Kinetics via Imaging-Based Meta-SPR. Analytical Chemistry 98, 8382–8393 (2026).
14. Romero, P. A., Krause, A. & Arnold, F. H. Navigating the Protein Fitness Landscape with Gaussian Processes. Proceedings of the National Academy of Sciences 110, E193–E201 (2013).
15. Hie, B., Bryson, B. D. & Berger, B. Leveraging Uncertainty in Machine Learning Accelerates Biological Discovery and Design. Cell Systems 11, 461–477.e9 (2020).
16. Cheng, L., Yang, Z., Hsieh, C., Liao, B. & Zhang, S. ODBO: Bayesian Optimization with Search Space Prescreening for Directed Protein Evolution. Arxiv https://doi.org/10.48550/arXiv.2205.09548 (2022) doi:10.48550/arXiv.2205.09548.
17. Notin, P., Weitzman, R., Marks, D. & Gal, Y. ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers. in Advances in Neural Information Processing Systems 36 (2023).
18. Wu, Z., Kan, S. B. J., Lewis, R. D., Wittmann, B. J. & Arnold, F. H. Machine learning-assisted directed protein evolution with combinatorial libraries. Proceedings of the National Academy of Sciences 116, 8852–8858 (2019).
19. Yang, K. K., Wu, Z. & Arnold, F. H. Machine-learning-guided directed evolution for protein engineering. Nature Methods 16, 687–694 (2019).
20. Biswas, S., Khimulya, G., Alley, E. C., Esvelt, K. M. & Church, G. M. Low-N protein engineering with data-efficient deep learning. Nature Methods 18, 389–396 (2021).
21. Rapp, J. T., Bremer, B. J. & Romero, P. A. Self-driving Laboratories to Autonomously Navigate the Protein Fitness Landscape. Nature Chemical Engineering 1, 97–107 (2024).
22. Yang, J. et al. Active Learning-assisted Directed Evolution. Nature Communications 16, 714 (2025).
23. Huot, M., Wang, D., Liu, J. & Shakhnovich, E. I. Predicting High-fitness Viral Protein Variants with Bayesian Active Learning and Biophysics. Proceedings of the National Academy of Sciences 122, e2503742122 (2025).
24. Bradley, R. A. & Terry, M. E. Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons. Biometrika 39, 324 (1952).
25. MacKay, D. J. C. A Practical Bayesian Framework for Backpropagation Networks. Neural Computation 4, 448–472 (1992).
26. Jankauskaite, J., Jimenez-Garcia, B., Dapkunas, J., Fernandez-Recio, J. & Moal, I. H. SKEMPI 2.0: An Updated Benchmark of Changes in Protein–Protein Binding Energy, Kinetics and Thermodynamics upon Mutation. Bioinformatics 35, 462–469 (2019).
27. Wu, N. C., Dai, L., Olson, C. A., Lloyd-Smith, J. O. & Sun, R. Adaptation in protein fitness landscapes is facilitated by indirect paths. eLife 5, (2016).
28. Heyne, M. et al. Climbing Up and Down Binding Landscapes through Deep Mutational Scanning of Three Homologous Protein–Protein Complexes. Journal of the American Chemical Society 143, 17261–17275 (2021).
29. Johnston, R. J. et al. VISTA is an acidic pH-selective ligand for PSGL-1. Nature 574, 565–570 (2019).
30. Zhao, X. et al. Benchmark for Antibody Binding Affinity Maturation and Design. arXiv https://arxiv.org/abs/2506.04235 (2025).
指标
DOI：
Submission ID：
下载次数
已发布
如何引用
下载引用
利益冲突声明
作者声明无任何需要披露的利益冲突。
Copyright
本预印本的版权持有者为作者/资助方。
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.