Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning

Abstract

The optimization of therapeutic antibodies is time-intensive and resource-demanding, largely because of the low-throughput screening of full-length antibodies (approximately 1 × 103 variants) expressed in mammalian cells, which typically results in few optimized leads. Here we show that optimized antibody variants can be identified by predicting antigen specificity via deep learning from a massively diverse space of antibody sequences. To produce data for training deep neural networks, we deep-sequenced libraries of the therapeutic antibody trastuzumab (about 1 × 104 variants), expressed in a mammalian cell line through site-directed mutagenesis via CRISPR–Cas9-mediated homology-directed repair, and screened the libraries for specificity to human epidermal growth factor receptor 2 (HER2). We then used the trained neural networks to screen a computational library of approximately 1 × 108 trastuzumab variants and predict the HER2-specific subset (approximately 1 × 106 variants), which can then be filtered for viscosity, clearance, solubility and immunogenicity to generate thousands of highly optimized lead candidates. Recombinant expression and experimental testing of 30 randomly selected variants from the unfiltered library showed that all 30 retained specificity for HER2. Deep learning may facilitate antibody engineering and optimization.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

Fig. 1: Implementing deep learning to predict antibody target specificity.
Fig. 2: Sequence-based analysis of the mutational landscape.
Fig. 3: Deep-learning models accurately predict antigen specificity.
Fig. 4: Neural-network-predicted sequences are experimentally validated to be antigen-specific.
Fig. 5: In silico screening of the predicted binders identifies candidate sequences for further validation.
Fig. 6: Experimental characterization of selected sequences reveals optimal candidates.

Data availability

The main data supporting the results in this study are available within the paper and its Supplementary Information. The raw and analysed datasets generated during the study are too large to be publicly shared; however, they are available for research purposes from the corresponding author on reasonable request.

Code availability

Deep-learning models were built in Python v3.6.5 using the Keras v2.1.6 Sequential model as a wrapper for TensorFlow v1.8.0. The code and models used to perform the work in this study are available at the following github repository: https://github.com/dahjan/DMS_opt.

References

  1. 1.

    Paul, S. M. et al. How to improve R&D productivity: the pharmaceutical industry’s grand challenge. Nat. Rev. Drug Discov. 9, 203–214 (2010).

    CAS  PubMed  Article  Google Scholar 

  2. 2.

    Sharma, V. K. et al. In silico selection of therapeutic antibodies for development: viscosity, clearance, and chemical stability. Proc. Natl Acad. Sci. USA 111, 18601–18606 (2014).

    CAS  PubMed  Article  Google Scholar 

  3. 3.

    Jain, T. et al. Biophysical properties of the clinical-stage antibody landscape. Proc. Natl Acad. Sci. USA 114, 944–949 (2017).

    CAS  PubMed  Article  Google Scholar 

  4. 4.

    Hu, D. et al. Effective optimization of antibody affinity by phage display integrated with high-throughput DNA synthesis and sequencing technologies. PLoS ONE 10, e0129125 (2015).

    PubMed  PubMed Central  Article  CAS  Google Scholar 

  5. 5.

    Bos, A. B. et al. Development of a semi-automated high throughput transient transfection system. J. Biotechnol. 180, 10–16 (2014).

    CAS  PubMed  Article  Google Scholar 

  6. 6.

    Tomar, D. S., Kumar, S., Singh, S. K., Goswami, S. & Li, L. Molecular basis of high viscosity in concentrated antibody solutions: strategies for high concentration drug product development. mAbs 8, 216–228 (2016).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  7. 7.

    Roth, E. M. et al. Antidrug antibodies in patients treated with alirocumab. N. Engl. J. Med. 376, 1589–1590 (2017).

    PubMed  Article  Google Scholar 

  8. 8.

    Greiff, V. et al. Learning the high-dimensional immunogenomic features that predict public and private antibody repertoires. J. Immunol. https://doi.org/10.4049/jimmunol.1700594 (2017).

  9. 9.

    Christensen, T., Frandsen, A., Glazier, S., Humpherys, J. & Kartchner, D. Machine learning methods for disease prediction with claims data. In 2018 IEEE International Conference on Healthcare Informatics https://doi.org/10.1109/ICHI.2018.00108 (IEEE, 2018).

  10. 10.

    Packer, M. S. & Liu, D. R. Methods for the directed evolution of proteins. Nat. Rev. Genet. 16, 379–394 (2015).

    CAS  PubMed  Article  Google Scholar 

  11. 11.

    Fox, R. et al. Optimizing the search algorithm for protein engineering by directed evolution. Protein Eng. Des. Sel. 16, 589–597 (2003).

    CAS  Article  Google Scholar 

  12. 12.

    Fox, R. Directed molecular evolution by machine learning and the influence of nonlinear interactions. J. Theor. Biol. 234, 187–199 (2005).

    CAS  PubMed  Article  Google Scholar 

  13. 13.

    Romero, P. A., Krause, A. & Arnold, F. H. Navigating the protein fitness landscape with Gaussian processes. Proc. Natl Acad. Sci. USA 110, E193–E201 (2013).

    CAS  PubMed  Article  Google Scholar 

  14. 14.

    Bedbrook, C. N., Yang, K. K., Rice, A. J., Gradinaru, V. & Arnold, F. H. Machine learning to design integral membrane channelrhodopsins for efficient eukaryotic expression and plasma membrane localization. PLoS Comput. Biol. 13, e1005786 (2017).

    PubMed  PubMed Central  Article  CAS  Google Scholar 

  15. 15.

    Angermueller, C., Pärnamaa, T., Parts, L. & Stegle, O. Deep learning for computational biology. Mol. Syst. Biol. 12, 878 (2016).

    PubMed  PubMed Central  Article  Google Scholar 

  16. 16.

    Wainberg, M., Merico, D., Delong, A. & Frey, B. J. Deep learning in biomedicine. Nat. Biotechnol. 36, 829–838 (2018).

    CAS  PubMed  Article  Google Scholar 

  17. 17.

    Alipanahi, B., Delong, A., Weirauch, M. T. & Frey, B. J. Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat. Biotechnol. 33, 831–838 (2015).

    CAS  PubMed  Article  Google Scholar 

  18. 18.

    Cuperus, J. T. et al. Deep learning of the regulatory grammar of yeast 5′ untranslated regions from 500,000 random sequences. Genome Res. https://doi.org/10.1101/gr.224964.117 (2017).

  19. 19.

    Bulik-Sullivan, B. et al. Deep learning using tumor HLA peptide mass spectrometry datasets improves neoantigen identification. Nat. Biotechnol. 37, 55–63 (2019).

    CAS  Article  Google Scholar 

  20. 20.

    LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).

    CAS  Article  Google Scholar 

  21. 21.

    Rosenblatt, F. The Perceptron, a Perceiving and Recognizing Automation Report 85-60-1 (Cornell Aeronautical Laboratory, 1957).

  22. 22.

    Pogson, M., Parola, C., Kelton, W. J., Heuberger, P. & Reddy, S. T. Immunogenomic engineering of a plug-and-(dis)play hybridoma platform. Nat. Commun. 7, 12535 (2016).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  23. 23.

    Mason, D. M. et al. High-throughput antibody engineering in mammalian cells by CRISPR/Cas9-mediated homology-directed mutagenesis. Nucleic Acids Res. https://doi.org/10.1093/nar/gky550 (2018).

  24. 24.

    Whitehead, T. A. et al. Optimization of affinity, specificity and function of designed influenza inhibitors using deep sequencing. Nat. Biotechnol. 30, 543–548 (2012).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  25. 25.

    Cho, H.-S. et al. Structure of the extracellular region of HER2 alone and in complex with the Herceptin Fab. Nature 421, 756–760 (2003).

    CAS  PubMed  Article  Google Scholar 

  26. 26.

    Rose, A. S. et al. NGL viewer: web-based molecular graphics for large complexes. Bioinformatics 34, 3755–3758 (2018).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  27. 27.

    Miho, E., Roškar, R., Greiff, V. & Reddy, S. T. Large-scale network analysis reveals the sequence space architecture of antibody repertoires. Nat. Commun. 10, 1321 (2019).

    PubMed  PubMed Central  Article  CAS  Google Scholar 

  28. 28.

    Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. Preprint at https://arxiv.org/abs/1703.01365 (2017).

  29. 29.

    Sormanni, P., Aprile, F. A. & Vendruscolo, M. The CamSol method of rational design of protein mutants with enhanced solubility. J. Mol. Biol. 427, 478–490 (2015).

    CAS  PubMed  Article  Google Scholar 

  30. 30.

    Pérez, A.-M. W. et al. In vitro and in silico assessment of the developability of a designed monoclonal antibody library. mAbs 11, 388–400 (2019).

    Article  Google Scholar 

  31. 31.

    Jensen, K. K. et al. Improved methods for predicting peptide binding affinity to MHC class II molecules. Immunology 154, 394–406 (2018).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  32. 32.

    Greenbaum, J. et al. Functional classification of class II human leukocyte antigen (HLA) molecules reveals seven different supertypes and a surprising degree of repertoire sharing across supertypes. Immunogenetics 63, 325–335 (2011).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  33. 33.

    Wu, Z., Kan, S. B. J., Lewis, R. D., Wittmann, B. J. & Arnold, F. H. Machine learning-assisted directed protein evolution with combinatorial libraries. Proc. Natl Acad. Sci. USA https://doi.org/10.1073/pnas.1901979116 (2019).

  34. 34.

    Vajdos, F. F. et al. Comprehensive functional maps of the antigen-binding site of an anti-ErbB2 antibody obtained with shotgun scanning mutagenesis. J. Mol. Biol. 320, 415–428 (2002).

    CAS  PubMed  Article  Google Scholar 

  35. 35.

    Townsend, S. et al. Augmented binary substitution: single-pass CDR germ-lining and stabilization of therapeutic antibodies. Proc. Natl Acad. Sci. USA 112, 15354–15359 (2015).

    CAS  PubMed  Article  Google Scholar 

  36. 36.

    Trudeau, D. L., Smith, M. A. & Arnold, F. H. Innovation by homologous recombination. Curr. Opin. Chem. Biol. 17, 902–909 (2013).

    CAS  PubMed  Article  Google Scholar 

  37. 37.

    Riesselman, A. J., Ingraham, J. B. & Marks, D. S. Deep generative models of genetic variation capture the effects of mutations. Nat. Methods 15, 816–822 (2018).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  38. 38.

    Sormanni, P., Aprile, F. A. & Vendruscolo, M. Third generation antibody discovery methods: in silico rational design. Chem. Soc. Rev. 47, 9137–9157 (2018).

    CAS  PubMed  Article  Google Scholar 

  39. 39.

    Raybould, M. I. J. et al. Five computational developability guidelines for therapeutic antibody profiling. Proc. Natl Acad. Sci. USA 116, 4025–4030 (2019).

    CAS  PubMed  Article  Google Scholar 

  40. 40.

    Rabia, L. A., Zhang, Y., Ludwig, S. D., Julian, M. C. & Tessier, P. M. Net charge of antibody complementarity-determining regions is a key predictor of specificity. Protein Eng. Des. Sel. https://doi.org/10.1093/protein/gzz002 (2019)

  41. 41.

    Abhinandan, K. R. & Martin, A. C. R. Analyzing the “degree of humanness” of antibody sequences. J. Mol. Biol. 369, 852–862 (2007).

    CAS  PubMed  Article  Google Scholar 

  42. 42.

    van Brummelen, E. M. J., Ros, W., Wolbink, G., Beijnen, J. H. & Schellens, J. H. M. Antidrug antibody formation in oncology: clinical relevance and challenges. Oncologist 21, 1260–1268 (2016).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  43. 43.

    Vaisman-Mentesh, A., Gutierrez-Gonzalez, M., DeKosky, B. J. & Wine, Y. The molecular mechanisms that underlie the immune biology of anti-drug antibody formation following treatment with monoclonal antibodies. Front. Immunol. 11, 1951 (2020).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  44. 44.

    Igawa, T. et al. Antibody recycling by engineered pH-dependent antigen binding improves the duration of antigen neutralization. Nat. Biotechnol. 28, 1203–1207 (2010).

    CAS  PubMed  Article  Google Scholar 

  45. 45.

    Kang, J. C. et al. Engineering a HER2-specific antibody–drug conjugate to increase lysosomal delivery and therapeutic efficacy. Nat. Biotechnol. https://doi.org/10.1038/s41587-019-0073-7 (2019).

  46. 46.

    Slaga, D. et al. Avidity-based binding to HER2 results in selective killing of HER2-overexpressing cells by anti-HER2/CD3. Sci. Transl. Med. 10, eaat5775 (2018).

    PubMed  Article  CAS  Google Scholar 

  47. 47.

    Gainza, P. et al. Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning. Nat. Methods 17, 184–192 (2020).

    CAS  PubMed  Article  Google Scholar 

  48. 48.

    Menzel, U. et al. Comprehensive evaluation and optimization of amplicon library preparation methods for high-throughput antibody sequencing. PLoS ONE 9, e96727 (2014).

    PubMed  PubMed Central  Article  CAS  Google Scholar 

  49. 49.

    Bolotin, D. A. et al. MiXCR: software for comprehensive adaptive immunity profiling. Nat. Methods 12, 380–381 (2015).

    CAS  PubMed  Article  Google Scholar 

  50. 50.

    R Core Development Team. R: a language and environment for statistical computing (R Foundation for Statistical Computing, 2014).

  51. 51.

    van Rossum, G. & Drake, F. L. The Python Language Reference Manual (Network Theory Ltd., 2011).

  52. 52.

    Wickham, H. ggplot2: Elegant Graphics for Data Analysis (Springer International Publishing, 2016).

  53. 53.

    Brewer, C. A., Hatchard, G. W. & Harrower, M. A. ColorBrewer in print: a catalog of color schemes for maps. Cartogr. Geogr. Inf. Sci. 30, 5–32 (2003).

    Article  Google Scholar 

  54. 54.

    Wagih, O. ggseqlogo: a versatile R package for drawing sequence logos. Bioinformatics 33, 3645–3647 (2017).

    CAS  PubMed  Article  Google Scholar 

  55. 55.

    Fowler, D. M. et al. High-resolution mapping of protein sequence-function relationships. Nat. Methods 7, 741–746 (2010).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  56. 56.

    Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Machine Learning Res. 12, 2825–2830 (2011).

    Google Scholar 

  57. 57.

    Chollet, F. Keras. https://keras.io (2015).

  58. 58.

    Abadi, M. et al. TensorFlow: a system for large-scale machine learning. In Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation 265–283 (USENIX Association, 2016).

  59. 59.

    Sokolova, M. & Lapalme, G. A systematic analysis of performance measures for classification tasks. Inf. Process. Manag. 45, 427–437 (2009).

    Article  Google Scholar 

  60. 60.

    Boughorbel, S., Jarray, F. & El-Anbari, M. Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric. PLoS ONE 12, e0177678 (2017).

    PubMed  PubMed Central  Article  CAS  Google Scholar 

  61. 61.

    Csárdi, G. & Nepusz, T. The igraph software package for complex network research. InterJournal 1695 (2006).

  62. 62.

    Tareen, A. & Kinney, J. B. Logomaker: beautiful sequence logos in Python. Bioinformatics 36, 2272–2274 (2020).

    CAS  PubMed  Article  Google Scholar 

  63. 63.

    Lide, D. R. Handbook of Chemistry and Physics 72nd edn (CRC Press, 1991).

Download references

Acknowledgements

We thank the ETH Zurich D-BSSE Single Cell Unit and the ETH Zurich D-BSSE Genomics Facility for support—in particular M. Di Tacchio, A. Gumienny, E. Burcklen and C. Beisel. We also thank the Vendruscolo Laboratory (Cambridge, UK), P. Sormanni in particular, for assistance with implementing the CamSol method on large libraries as well as the group of M. Nielson (DTU, Denmark) for providing an easy-to-use package for MHC class II affinity predictions. Funding was provided by the National Competence Center for Research on Molecular Systems Engineering.

Author information

Affiliations

Authors

Contributions

D.M.M., S.F., C.R.W. and S.T.R. developed the methodology. D.M.M. and S.T.R. designed the experiments and wrote the manuscript. D.M.M., C.R.W., S.F. and J.D. analysed the sequencing data and performed deep-learning analyses. P.G. and B.E.C. designed and performed the structural modelling experiments and analysis. C.J. generated in silico libraries. D.M.M. and R.A.E. performed experiments. B.W., S.M.M. and L.B. performed the cell-line development.

Corresponding author

Correspondence to Sai T. Reddy.

Ethics declarations

Competing interests

ETH Zurich has filed for patent protection on the technology described herein, and D.M.M., S.F., C.R.W. and S.T.R. are named as co-inventors on this patent (International Filing Application PCT/IB2020/053370).

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary methods, figures and tables.

Reporting Summary

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Mason, D.M., Friedensohn, S., Weber, C.R. et al. Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning. Nat Biomed Eng (2021). https://doi.org/10.1038/s41551-021-00699-9

Download citation

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing