Antibody complementarity determining region design using high-capacity machine learning
Open accessPublished version of a preprint
Abstract
MOTIVATION: The precise targeting of antibodies and other protein therapeutics is required for their proper function and the elimination of deleterious off-target effects. Often the molecular structure of a therapeutic target is unknown and randomized methods are used to design antibodies without a model that relates antibody sequence to desired properties. RESULTS: Here, we present Ens-Grad, a machine learning method that can design complementarity determining regions of human Immunoglobulin G antibodies with target affinities that are superior to candidates derived from phage display panning experiments. We also demonstrate that machine learning can improve target specificity by the modular composition of models from different experimental campaigns, enabling a new integrative approach to improving target specificity. Our results suggest a new path for the discovery of therapeutic molecules by demonstrating that predictive and differentiable models of antibody binding can be learned from high-throughput experimental data without the need for target structural data. AVAILABILITY AND IMPLEMENTATION: Sequencing data of the phage panning experiment are deposited at NIH's Sequence Read Archive (SRA) under the accession number SRP158510. We make our code available at https://github.com/gifford-lab/antibody-2019. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
A number of other related approaches use ML models to learn sequence models from directed evolution experiments.
“A number of other related approaches that use ML models to learn sequence models from directed evolution experiments have been developed [66][67][68].”
From Computational and artificial intelligence-based methods for antibody development (2023) · cites this paper as [68]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Basic local alignment search tool
Altschul, S. F., Gish, W., Miller, W., Myers, E. W., & Lipman, D. J. (1990) · Journal of Molecular Biology · doi:10.1006/jmbi.1990.9999 · Cited by 98,669 · see citing works
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · see citing works
EMBOSS: the European molecular biology open software suite.
Rice, P., Longden, I., & Bleasby, A. (2000) · Trends in Genetics · doi:10.1016/s0168-9525(00)02024-2 · Cited by 9,466 · see citing works
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
McInnes, L., Healy, J., & Melville, J. (2018) · arXiv · doi:10.48550/arxiv.1802.03426 · Cited by 7,101 · see citing works
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · see citing works
Smith, G. P. (1985) · Science · doi:10.1126/science.4001944 · Cited by 4,143 · see citing works
Phage antibodies: filamentous phage displaying antibody variable domains
McCafferty, J., Griffiths, A. D., Winter, G. P., & Chiswell, D. J. (1990) · Nature · doi:10.1038/348552a0 · Cited by 2,427 · see citing works
Ensembling neural networks: Many could be better than all
Zhou, Z.-H., Wu, J., & Tang, W. (2002) · Artificial Intelligence · doi:10.1016/s0004-3702(02)00190-x · Cited by 1,964 · see citing works
GARCÍA-ALONSO, C. R., Pérez, L. M., & Fernández, J. C. F. (2011) · Annals of Operations Research · doi:10.1007/s10479-011-0841-3 · Cited by 1,357 · see citing works
Field guide to next‐generation DNA sequencers
Glenn, T. C. (2011) · Molecular Ecology Resources · doi:10.1111/j.1755-0998.2011.03024.x · Cited by 1,139 · see citing works
Phage Display : A Laboratory Manual
Barbas, C. F. (2001) · Medical Entomology and Zoology · Cited by 952 · see citing works
Guidelines for accurate EC50/IC50 estimation
Sebaugh, J. L. (2010) · Pharmaceutical Statistics · doi:10.1002/pst.426 · Cited by 949 · see citing works
High-throughput SNP genotyping on universal bead arrays
Shen, R., Fan, J., Campbell, D., Chang, W., Chen, J., Doucet, D., Yeakley, J. M., Bibikova, M. V., Wickham‐Garcia, E., McBride, C., et al. (2005) · Mutation research. Fundamental and molecular mechanisms of mutagenesis · doi:10.1016/j.mrfmmm.2004.07.022 · Cited by 415 · see citing works
A surface expression vector for antibody screening
Breitling, F., DUBEL, S. J., Seehaus, T., et al. (1991) · Gene · doi:10.1016/0378-1119(91)90244-6 · Cited by 305 · see citing works
Computer-aided antibody design
Kuroda, D., Shirai, H., Jacobson, M. P., & Nakamura, H. (2012) · Protein Engineering Design and Selection · doi:10.1093/protein/gzs024 · Cited by 223 · see citing works
Tiller, T., Schuster, I., Deppe, D., Siegers, K., Strohner, R., Herrmann, T., Berenguer, M., Poujol, D., Stehle, J., Stark, Y., et al. (2013) · mAbs · doi:10.4161/mabs.24218 · Cited by 209 · see citing works
Parapred: antibody paratope prediction using convolutional and recurrent neural networks
Liberis, E., Veličković, P., Sormanni, P., Vendruscolo, M., & Liò, P. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty305 · Cited by 165 · see citing works
Engineering antibodies by yeast display
Boder, E. T., Raeeszadeh‐Sarmazdeh, M., & Price, J. V. (2012) · Archives of Biochemistry and Biophysics · doi:10.1016/j.abb.2012.03.009 · Cited by 137 · see citing works
Protein–protein binding affinity prediction on a diverse set of structures
Moal, I. H., Agius, R., & Bates, P. A. (2011) · Bioinformatics · doi:10.1093/bioinformatics/btr513 · Cited by 112 · see citing works
Confidence and prediction intervals for neural network ensembles
Carney, J. G., Cunningham, P., & Bhagwan, U. (2003) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1999.831133 · Cited by 102 · see citing works
Kunik, V., & Ofran, Y. (2013) · Protein Engineering Design and Selection · doi:10.1093/protein/gzt027 · Cited by 96 · see citing works
Computational design of antibodies
Fischman, S., & Ofran, Y. (2018) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2018.04.007 · Cited by 56 · see citing works
Transient recombinant protein expression in a human amniocyte cell line: The CAP‐T® cell system
Fischer, S., Charara, N., Gerber, A., Wölfel, J., Schiedner, G., Voedisch, B., & Geisse, S. (2012) · Biotechnology and Bioengineering · doi:10.1002/bit.24514 · Cited by 50 · see citing works
Prediction of hypervariable CDR-H3 loop structures in antibodies
Reczko, M., Martin, A. C. R., Bohr, H. G., & Suhai, S. (1995) · Protein Engineering Design and Selection · doi:10.1093/protein/8.4.389 · Cited by 34 · see citing works
Visualizing complex feature interactions and feature sharing in genomic deep neural networks
Liu, G., Zeng, H., & Gifford, D. K. (2019) · BMC Bioinformatics · doi:10.1186/s12859-019-2957-4 · Cited by 23 · see citing works
Self-citationCritiquing Protein Family Classification Models Using Sufficient Input Subsets
Carter, B., Bileschi, M. L., Smith, J., Sanderson, T., Bryant, D., Belanger, D., & Colwell, L. J. (2019) · Journal of Computational Biology · doi:10.1089/cmb.2019.0339 · Cited by 10 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 3
- Carter B. et al (2019b) What made you do this? Understanding black-box decisions with sufficient input subsets. In The 22nd International Conference on Artificial Intelligence and Statistics, pp. 567– 576.
- Lakshminarayanan B. et al (2017) Simple and scalable predictive uncertainty estimation using deep ensembles In: Guyon, I. et al. (eds.) Advances in The 31st Neural Information Processing Systems, Long Beach, CA, USA, pp. 6402– 6413.
- O’Brien P.M., Aitken R. (2004) Antibody Phage Display: Methods and Protocols. Springer Science & Business Media, Heidelberg, New York.
Cited by
Sorted by citations
Learning the protein language: Evolution, structure, and function
Bepler, T., & Berger, B. (2021) · Cell Systems · doi:10.1016/j.cels.2021.05.017 · Cited by 483 · see citing works
Protein design and variant prediction using autoregressive generative models
Shin, J.-E., Riesselman, A. J., Kollasch, A. W., McMahon, C., Simon, E., Sander, C., Manglik, A., Kruse, A. C., & Marks, D. S. (2021) · Nature Communications · doi:10.1038/s41467-021-22732-w · Cited by 320 · see citing works
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 · see citing works
Saka, K., Kakuzaki, T., Metsugi, S., Kashiwagi, D., Yoshida, K., Wada, M., Tsunoda, H., & Teramoto, R. (2021) · Scientific Reports · doi:10.1038/s41598-021-85274-7 · Cited by 144 · see citing works
Predicting antibody binders and generating synthetic antibodies using deep learning
Lim, Y. W., Adler, A. S., & Johnson, D. S. (2022) · mAbs · doi:10.1080/19420862.2022.2069075 · Cited by 49 · see citing works
- Authors
- Liu, G., Zeng, H., Mueller, J., Carter, B., Wang, Z., Schilz, J., Horny, G., Birnbaum, M. E., Ewert, S., & Gifford, D. K.
- Affiliations
- MIT Computer Science and Artificial Intelligence Laboratory (US)
- Novartis (Switzerland) (CH)
- Koch Institute for Integrative Cancer Research At MIT (US)
- Corresponding author
- Liu, Ge
- Gifford, David K
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2019-11-28
- Volume
- 36
- Issue
- 7
- Pages
- 2126-2133
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- PMC
- PMC7141872
- OpenAlex
- W2990497243
- Cited by
- 157
- References
- 27
- Citations by year
- 2026: 13 · 2025: 27 · 2024: 27 · 2023: 29 · 2022: 26 · 2021: 23 · 2020: 9 · 2019: 2
- FWCI
- 9.90
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Bioinformatics (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- National Institutes of Health (R01CA218094)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Monoclonal and Polyclonal Antibodies Research
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › vaccines and immunoinformatics approaches
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Keywords
- antibody design, hypervariable region, human immunoglobulin G, target specificity, differentiable models, therapeutic antibodies
- MeSH terms
- Machine Learning, Antibodies, Humans, Complementarity Determining Regions
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
