The DOI matches its Crossref record; 59 of the 59 references it cites were found in a registry or an index.
Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning
Open accessAbstract
The optimization of therapeutic antibodies is time-intensive and resource-demanding, largely because of the low-throughput screening of full-length antibodies (approximately 1 × 10 3 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 × 10 4 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 × 10 8 trastuzumab variants and predict the HER2-specific subset (approximately 1 × 10 6 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.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Mason et al. [65] presented a method to train a convolutional neural network on the results of a directed evolution experiment to generate improved libraries.”
From Computational and artificial intelligence-based methods for antibody development (2023) · cites this paper as [65]
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
CRC Handbook of Chemistry and Physics
(2014) · doi:10.1201/b17118 · Cited by 57,706
TensorFlow: A system for large-scale machine learningPreprint
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.5555/3026877.3026899 · Cited by 16,548
ggplot2: Elegant Graphics for Data Analysis
Wickham, H. (2009) · doi:10.1007/978-0-387-98141-3 · Cited by 14,447
Wickham, H. (2016) · Use R! · doi:10.1007/978-3-319-24277-4_9 · Cited by 12,675
The igraph software package for complex network research
Csárdi, G., & Nepusz, T. (2006) · Medical Entomology and Zoology · Cited by 10,078
A systematic analysis of performance measures for classification tasks
Sokolova, M., & Lapalme, G. (2009) · Information Processing & Management · doi:10.1016/j.ipm.2009.03.002 · Cited by 7,515
How to improve R&D productivity: the pharmaceutical industry's grand challenge
Paul, S. M., Mytelka, D. S., Dunwiddie, C. T., Persinger, C. C., Munos, B. H., Lindborg, S. R., & Schacht, A. L. (2010) · Nature Reviews Drug Discovery · doi:10.1038/nrd3078 · Cited by 3,566
Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning
Alipanahi, B., Delong, A., Weirauch, M. T., & Frey, B. J. (2015) · Nature Biotechnology · doi:10.1038/nbt.3300 · Cited by 2,873
MiXCR: software for comprehensive adaptive immunity profiling
Bolotin, D. A., Poslavskii, S., Mitrophanov, I., Shugay, M., Mamedov, I. Z., Putintseva, E. V., & Chudakov, D. M. (2015) · Nature Methods · doi:10.1038/nmeth.3364 · Cited by 1,730
Structure of the extracellular region of HER2 alone and in complex with the Herceptin Fab
Cho, H., Mason, K., Ramyar, K. X., Stanley, A. M., Gabelli, S. B., Denney, D. W., & Leahy, D. J. (2003) · Nature · doi:10.1038/nature01392 · Cited by 1,637
Deep learning for computational biology
Angermueller, C., Pärnamaa, T., Parts, L., & Stegle, O. (2016) · Molecular Systems Biology · doi:10.15252/msb.20156651 · Cited by 1,473
Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric
Boughorbel, S., Jarray, F., & El-Anbari, M. (2017) · PLOS ONE · doi:10.1371/journal.pone.0177678 · Cited by 1,222
Methods for the directed evolution of proteins
Packer, M. S., & Liu, D. R. (2015) · Nature Reviews Genetics · doi:10.1038/nrg3927 · Cited by 1,002
ggseqlogo: a versatile R package for drawing sequence logos
Wagih, O. (2017) · Bioinformatics · doi:10.1093/bioinformatics/btx469 · Cited by 933
Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning
Gaínza, P., Sverrisson, F., Monti, F., Rodolà, E., Boscaini, D., Bronstein, M. M., & Correia, B. E. (2019) · Nature Methods · doi:10.1038/s41592-019-0666-6 · Cited by 839
Self-citationImproved methods for predicting peptide binding affinity to MHC class II molecules
Jensen, K. K., Andreatta, M., Marcatili, P., Buus, S., Greenbaum, J., Zhen, Y., Sette, A., Peters, B., & Nielsen, M. (2018) · Immunology · doi:10.1111/imm.12889 · Cited by 805
Biophysical properties of the clinical-stage antibody landscape
Jain, T., Sun, T., Durand, S., Hall, A., Houston, N. R., Nett, J. H., Sharkey, B., Bobrowicz, B., Caffry, I., Yu, Y., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1616408114 · Cited by 629 · cited 3×
“…plasmids, this last stage of development is done at very low throughput, as elaborate cloning, transfection and purification strategies must be implemented to screen libraries in the maximum range of 1 × 10 3 , meaning that only minor changes (for example, point mutations) are screened 5 .”
BackgroundMachine learning-assisted directed protein evolution with combinatorial libraries
Wu, Z., Kan, S. B. J., Lewis, R. D., Wittmann, B. J., & Arnold, F. H. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1901979116 · Cited by 603
Deep generative models of genetic variation capture the effects of mutations
Riesselman, A. J., Ingraham, J. B., & Marks, D. S. (2018) · Nature Methods · doi:10.1038/s41592-018-0138-4 · Cited by 601
Wainberg, M., Merico, D., Delong, A., & Frey, B. J. (2018) · Nature Biotechnology · doi:10.1038/nbt.4233 · Cited by 596
Logomaker: beautiful sequence logos in Python
Tareen, A., & Kinney, J. B. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz921 · Cited by 530
High-resolution mapping of protein sequence-function relationships
Fowler, D. M., Araya, C. L., Fleishman, S. J., Kellogg, E. H., Stephany, J. J., Baker, D., & Fields, S. (2010) · Nature Methods · doi:10.1038/nmeth.1492 · Cited by 516
The CamSol method of rational design of protein mutants with enhanced solubility
Sormanni, P., Aprile, F. A., & Vendruscolo, M. (2015) · Journal of Molecular Biology · doi:10.1016/j.jmb.2014.09.026 · Cited by 494 · cited 7×
“With recent advances in computational predictions 38,39 , a number of these properties—including viscosity, clearance, stability 2 , specificity 40 , solubility 29 and immunogenicity 31 —can be approximated from the sequence information alone.”
BackgroundMethodInfluentialNGL viewer: web-based molecular graphics for large complexes
Rose, A. S., Bradley, A. R., Valasatava, Y., Duarte, J. M., Prlić, A., & Rose, P. W. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty419 · Cited by 489
Greenbaum, J., Sidney, J., Chung, J., Brander, C., Peters, B., & Sette, A. (2011) · Immunogenetics · doi:10.1007/s00251-011-0513-0 · Cited by 449
Whitehead, T. A., Chevalier, A. A., Song, Y., Dreyfus, C., Fleishman, S. J., de Mattos, C., Myers, C., Kamisetty, H., Blair, P. J., Wilson, I. A., et al. (2012) · Nature Biotechnology · doi:10.1038/nbt.2214 · Cited by 367
Five computational developability guidelines for therapeutic antibody profiling
Raybould, M. I. J., Marks, C., Krawczyk, K., Taddese, B., Nowak, J., Lewis, A. P., Bujotzek, A., Shi, J., & Deane, C. M. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1810576116 · Cited by 357
Igawa, T., Ishii, S., Tachibana, T., Maeda, A., Higuchi, Y., Shimaoka, S., Moriyama, C., Watanabe, T., Takubo, R., Doi, Y., et al. (2010) · Nature Biotechnology · doi:10.1038/nbt.1691 · Cited by 349
Navigating the protein fitness landscape with Gaussian processes
Romero, P. A., Krause, A., & Arnold, F. H. (2012) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1215251110 · Cited by 346
Deep learning using tumor HLA peptide mass spectrometry datasets improves neoantigen identification
Bulik-Sullivan, B. K., Busby, J., Palmer, C. D., Davis, M. J., Murphy, T., Clark, A., Busby, M., Duke, F. F., Yang, A., Young, L., et al. (2018) · Nature Biotechnology · doi:10.1038/nbt.4313 · Cited by 317
Vaisman‐Mentesh, A., Gutiérrez-González, M., DeKosky, B. J., & Wine, Y. (2020) · Frontiers in Immunology · doi:10.3389/fimmu.2020.01951 · Cited by 303
Sharma, V. K., Patapoff, T. W., Kabakoff, B., Pai, S., Hilario, E., Zhang, B., Li, C., Borisov, O., Kelley, R. F., Chorny, I., et al. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1421779112 · Cited by 256
ColorBrewer in Print: A Catalog of Color Schemes for Maps
Brewer, C. A., Hatchard, G. W., & Harrower, M. (2003) · Cartography and Geographic Information Science · doi:10.1559/152304003100010929 · Cited by 230
Tomar, D. S., Kumar, S., Singh, S. K., Goswami, S., & Li, L. (2016) · mAbs · doi:10.1080/19420862.2015.1128606 · Cited by 215
Cuperus, J. T., Groves, B., Kuchina, A., Rosenberg, A. B., Jojic, N., Fields, S., & Seelig, G. (2017) · Genome Research · doi:10.1101/gr.224964.117 · Cited by 205
Antidrug Antibody Formation in Oncology: Clinical Relevance and Challenges
van Brummelen, E. M. J., Ros, W., Wolbink, G., Beijnen, J. H., & Schellens, J. H. M. (2016) · The Oncologist · doi:10.1634/theoncologist.2016-0061 · Cited by 150
Third generation antibody discovery methods: in silico rational design
Sormanni, P., Aprile, F. A., & Vendruscolo, M. (2018) · Chemical Society Reviews · doi:10.1039/c8cs00523k · Cited by 143
Large-scale network analysis reveals the sequence space architecture of antibody repertoires
Miho, E., Roškar, R., Greiff, V., & Reddy, S. T. (2019) · Nature Communications · doi:10.1038/s41467-019-09278-8 · Cited by 138
Self-citationSlaga, D., Ellerman, D. A., Lombana, T. N., Vij, R., Li, J., Hristopoulos, M. L., Clark, R., Johnston, J., Shelton, A., Mai, E., et al. (2018) · Science Translational Medicine · doi:10.1126/scitranslmed.aat5775 · Cited by 137
Vajdos, F. F., Adams, C. W., Breece, T., Presta, L. G., de Vos, A. M., & Sidhu, S. S. (2002) · Journal of Molecular Biology · doi:10.1016/s0022-2836(02)00264-4 · Cited by 118
Bedbrook, C. N., Yang, K., Rice, A. J., Gradinaru, V., & Arnold, F. H. (2017) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1005786 · Cited by 113
Greiff, V., Weber, C. R., Palme, J., Bodenhofer, U., Miho, E., Menzel, U., & Reddy, S. T. (2017) · The Journal of Immunology · doi:10.4049/jimmunol.1700594 · Cited by 106
Self-citationAnalyzing the ‘Degree of Humanness’ of antibody sequences
Abhinandan, K. R., & Martin, A. C. R. (2007) · Journal of Molecular Biology · doi:10.1016/j.jmb.2007.02.100 · Cited by 99
In vitro and in silico assessment of the developability of a designed monoclonal antibody library
Wolf Pérez, A.-M., Sormanni, P., Andersen, J. S., Sakhnini, L. I., Rodriguez-Leon, I., Bjelke, J. R., Gajhede, A. J., De Maria, L., Otzen, D. E., Vendruscolo, M., et al. (2019) · mAbs · doi:10.1080/19420862.2018.1556082 · Cited by 97
Kang, J. C., Sun, W., Khare, P., Karimi, M., Wang, X., Shen, Y., Ober, R. J., & Ward, E. S. (2019) · Nature Biotechnology · doi:10.1038/s41587-019-0073-7 · Cited by 91
Antidrug Antibodies in Patients Treated with Alirocumab
Roth, E. M., Goldberg, A. C., Catapano, A. L., Torri, A., Yancopoulos, G. D., Stahl, N., Brunet, A., Lecorps, G., & Colhoun, H. M. (2017) · New England Journal of Medicine · doi:10.1056/nejmc1616623 · Cited by 90
Mason, D. M., Weber, C. R., Parola, C., Meng, S. M., Greiff, V., Kelton, W., & Reddy, S. T. (2018) · Nucleic Acids Research · doi:10.1093/nar/gky550 · Cited by 87
Self-citationHu, D., Hu, S., Wan, W., Xu, M., Du, R., Zhao, W., Gao, X., Liu, J., Liu, H., & Hong, J. (2015) · PLOS ONE · doi:10.1371/journal.pone.0129125 · Cited by 86 · cited 1×
“…has been discovered, additional engineering is often required; phage and yeast display offer a powerful method for high-throughput screening of large mutagenesis libraries ( > 1 × 10 9 ); however, they are primarily used only for increasing affinity or specificity to the target antigen 4 .”
MethodNet charge of antibody complementarity-determining regions is a key predictor of specificity
Rabia, L. A., Zhang, Y., Ludwig, S. D., Julian, M. C., & Tessier, P. M. (2018) · Protein Engineering Design and Selection · doi:10.1093/protein/gzz002 · Cited by 81
Optimizing the search algorithm for protein engineering by directed evolution
Fox, R. I., Roy, A., Govindarajan, S., Minshull, J., Gustafsson, C., Jones, J. T., & Emig, R. (2003) · Protein Engineering Design and Selection · doi:10.1093/protein/gzg077 · Cited by 73
Directed molecular evolution by machine learning and the influence of nonlinear interactions
Fox, R. J. (2005) · Journal of Theoretical Biology · doi:10.1016/j.jtbi.2004.11.031 · Cited by 65
Menzel, U., Greiff, V., Khan, T. A., Haessler, U., Hellmann, I., Friedensohn, S., Cook, S. C., Pogson, M., & Reddy, S. T. (2014) · PLoS ONE · doi:10.1371/journal.pone.0096727 · Cited by 51
Self-citationImmunogenomic engineering of a plug-and-(dis)play hybridoma platform
Pogson, M., Parola, C., Kelton, W., Heuberger, P., & Reddy, S. T. (2016) · Nature Communications · doi:10.1038/ncomms12535 · Cited by 49
Self-citationInnovation by homologous recombination
Trudeau, D. L., Smith, M. A., & Arnold, F. H. (2013) · Current Opinion in Chemical Biology · doi:10.1016/j.cbpa.2013.10.007 · Cited by 35
Development of a semi-automated high throughput transient transfection system
Bos, A. B., Duque, J. N., Bhakta, S., Farahi, F., Chirdon, L. A., Junutula, J. R., Harms, P. D., & Wong, A. W. (2014) · Journal of Biotechnology · doi:10.1016/j.jbiotec.2014.03.027 · Cited by 31
Townsend, S., Fennell, B. J., Apgar, J. R., Lambert, M. A., McDonnell, B., Grant, J., Wade, J. M., Franklin, E., Foy, N., Shúilleabháin, D. N., et al. (2015) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1510944112 · Cited by 26
Machine Learning Methods for Disease Prediction with Claims Data
Christensen, T., Frandsen, A., Glazier, S., Humpherys, J., & Kartchner, D. (2018) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi.2018.00108 · Cited by 24
Research works printed but not linked: 1
- Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. Preprint at https://arxiv.org/abs/1703.01365 (2017). · arXiv
Cited by
Sorted by citations
Efficient evolution of human antibodies from general protein language models
Hie, B., Shanker, V. R., Xu, D., Bruun, T. U. J., Weidenbacher, P. A. B., Tang, S., Wu, W. C. H., Pak, J. E., & Kim, P. S. (2023) · Nature Biotechnology · doi:10.1038/s41587-023-01763-2 · Cited by 472
Machine learning for functional protein design
Notin, P., Rollins, N. J., Gal, Y., Sander, C., & Marks, D. S. (2024) · Nature Biotechnology · doi:10.1038/s41587-024-02127-0 · Cited by 304
Designing antibodies as therapeutics
Carter, P. J., & Rajpal, A. (2022) · Cell · doi:10.1016/j.cell.2022.05.029 · Cited by 282
Prihoda, D., Maamary, J., Waight, A., Juan, V., Fayadat-Dilman, L., Svozil, D., & Bitton, D. A. (2022) · mAbs · doi:10.1080/19420862.2021.2020203 · Cited by 190
Computational and artificial intelligence-based methods for antibody development
Kim, J., McFee, M., Fang, Q., Abdin, O., & Kim, P. M. (2023) · Trends in Pharmacological Sciences · doi:10.1016/j.tips.2022.12.005 · Cited by 178
Metadata
- Authors
- Mason, D. M., Friedensohn, S., Weber, C. R., Jordi, C., Wagner, B., Meng, S. M., Ehling, R. A., Bonati, L., Dahinden, J., Gainza, P., Correia, B. E., & Reddy, S. T.
- Affiliations
- ETH Zurich (CH)
- École Polytechnique Fédérale de Lausanne (CH)
- Corresponding author
- Reddy, Sai T.
- ORCID
- Venue
- Nature Biomedical Engineering
- Published
- 2021-04-15
- Volume
- 5
- Issue
- 6
- Pages
- 600-612
- ISSN
- 2157-846X (ISSN-L)
- OpenAlex
- W3156522942
- Cited by
- 308
- References
- 59
- Citations by year
- 2026: 55 · 2025: 66 · 2024: 62 · 2023: 60 · 2022: 48 · 2021: 17
- FWCI
- 24.67
- Type
- journal article
- Language
- en
- Open access
- green
- infoscience.epfl.ch
- Licence
- Locations
- Nature Biomedical Engineering (publishedVersion)
- PubMed (publishedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Funders
- NCCR Molecular Systems Engineering
- Topics
- Life Sciences › Immunology and Microbiology › Immunology › Monoclonal and Polyclonal Antibodies Research
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › vaccines and immunoinformatics approaches
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Keywords
- therapeutic antibodies, antibody engineering, trastuzumab, HER2, deep learning, antibody optimization
- MeSH terms
- Trastuzumab, Deep Learning, Amino Acid Sequence, Animals, Antibody Affinity, Antibody Specificity, Antigens, Humans, Hybridomas, Protein Binding, Protein Engineering, Mutagenesis, Site-Directed, Erb-b2 Receptor Tyrosine Kinases, Sequence Analysis, Protein, Recombinational DNA Repair, CRISPR-Cas Systems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
