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.

Unconstrained generation of synthetic antibody–antigen structures to guide machine learning methodology for antibody specificity prediction

A preprint version of the article is available at bioRxiv.

Abstract

Machine learning (ML) is a key technology for accurate prediction of antibody–antigen binding. Two orthogonal problems hinder the application of ML to antibody-specificity prediction and the benchmarking thereof: the lack of a unified ML formalization of immunological antibody-specificity prediction problems and the unavailability of large-scale synthetic datasets to benchmark real-world relevant ML methods and dataset design. Here we developed the Absolut! software suite that enables parameter-based unconstrained generation of synthetic lattice-based three-dimensional antibody–antigen-binding structures with ground-truth access to conformational paratope, epitope and affinity. We formalized common immunological antibody-specificity prediction problems as ML tasks and confirmed that for both sequence- and structure-based tasks, accuracy-based rankings of ML methods trained on experimental data hold for ML methods trained on Absolut!-generated data. The Absolut! framework has the potential to enable real-world relevant development and benchmarking of ML strategies for biotherapeutics design.

This is a preview of subscription content, access via your institution

Access options

Buy article

Get time limited or full article access on ReadCube.

$32.00

All prices are NET prices.

Fig. 1: Pipeline for the high-throughput generation of synthetic 3D antibody–antigen structure datasets suited for diverse ML formalizations.
Fig. 2: The Absolut! dataset reflects granular levels of the biological complexity of antibody–antigen binding.
Fig. 3: Classification of binding and non-binding antibody sequences with ML.
Fig. 4: Transferability of ML method rankings and impact of negative examples for pose classification.
Fig. 5: ML prediction of paratope–epitope pairs involved in antibody–antigen binding.

Data availability

The Absolut! database is available at https://greifflab.org/Absolut and in the NIRD research data archive113. Source data for Figs. 25 is available with this paper.

Code availability

The Absolut! package is freely available at https://github.com/csi-greifflab/Absolut/ and on Zenodo114.

References

  1. Lu, R.-M. et al. Development of therapeutic antibodies for the treatment of diseases. J. Biomed. Sci. 27, 1 (2020).

    Article  Google Scholar 

  2. Barlow, D. J., Edwards, M. S. & Thornton, J. M. Continuous and discontinuous protein antigenic determinants. Nature 322, 747–748 (1986).

    Article  Google Scholar 

  3. Sivalingam, G. N. & Shepherd, A. J. An analysis of B-cell epitope discontinuity. Mol. Immunol. 51, 304–309 (2012).

    Article  Google Scholar 

  4. Akbar, R., Robert, P. A., Pavlovic, M. & Jeliazkov, J. R. A compact vocabulary of paratope–epitope interactions enables predictability of antibody–antigen binding. Cell Rep. 34, 108856 (2021).

    Article  Google Scholar 

  5. Xu, J. L. & Davis, M. M. Diversity in the CDR3 region of VH is sufficient for most antibody specificities. Immunity 13, 37–45 (2000).

    Article  Google Scholar 

  6. Kunik, V., Ashkenazi, S. & Ofran, Y. Paratome: an online tool for systematic identification of antigen-binding regions in antibodies based on sequence or structure. Nucleic Acids Res. 40, W521–W524 (2012).

    Article  Google Scholar 

  7. Ferdous, S. & Martin, A. C. R. AbDb: antibody structure database-a database of PDB-derived antibody structures. Database 2018, (2018).

  8. Dunbar, J. et al. SAbDab: the structural antibody database. Nucleic Acids Res. 42, D1140–D1146 (2014).

    Article  Google Scholar 

  9. Raybould, M. I. J., Kovaltsuk, A., Marks, C. & Deane, C. M. CoV-AbDab: the coronavirus antibody database. Bioinformatics 37, 734–735 (2020).

    Article  Google Scholar 

  10. Wardemann, H. & Busse, C. E. Novel approaches to analyze immunoglobulin repertoires. Trends Immunol. 38, 471–482 (2017).

    Article  Google Scholar 

  11. Shiakolas, A. R. et al. Efficient discovery of SARS-CoV-2-neutralizing antibodies via B cell receptor sequencing and ligand blocking. Nat. Biotechnol. 40(8):1270-1275 https://doi.org/10.1038/s41587-022-01232-2 (2022).

  12. Laustsen, A. H., Greiff, V., Karatt-Vellatt, A., Muyldermans, S. & Jenkins, T. P. Animal immunization, in vitro display technologies, and machine learning for antibody discovery. Trends Biotechnol. https://doi.org/10.1016/j.tibtech.2021.03.003 (2021).

  13. Kanyavuz, A., Marey-Jarossay, A., Lacroix-Desmazes, S. & Dimitrov, J. D. Breaking the law: unconventional strategies for antibody diversification. Nat. Rev. Immunol. 19, 355–368 (2019).

    Article  Google Scholar 

  14. Hoffecker, I. T., Shaw, A., Sorokina, V., Smyrlaki, I. & Högberg, B. Stochastic modeling of antibody binding predicts programmable migration on antigen patterns. Nat. Comput. Sci. 2, 179–192 (2022).

    Article  Google Scholar 

  15. Gainza, P. et al. Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning. Nat. Methods https://doi.org/10.1038/s41592-019-0666-6 (2019).

  16. Pedotti, M., Simonelli, L., Livoti, E. & Varani, L. Computational docking of antibody–antigen complexes, opportunities and pitfalls illustrated by influenza hemagglutinin. Int. J. Mol. Sci. 12, 226 (2011).

    Article  Google Scholar 

  17. Yin, R., Feng, B. Y., Varshney, A. & Pierce, B. G. Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants. Protein Science. 2022; 31(8):e4379. https://doi.org/10.1002/pro.4379 (2021).

  18. Raybould, M. I. J., Wong, W. K. & Deane, C. M. Antibody–antigen complex modelling in the era of immunoglobulin repertoire sequencing. Mol. Syst. Des. Eng. 4, 679–688 (2019).

    Article  Google Scholar 

  19. Norman, R. A. et al. Computational approaches to therapeutic antibody design: established methods and emerging trends. Brief. Bioinform. https://doi.org/10.1093/bib/bbz095 (2019).

  20. Brown, A. J. et al. Augmenting adaptive immunity: progress and challenges in the quantitative engineering and analysis of adaptive immune receptor repertoires. Mol. Syst. Des. Eng. 4, 701–736 (2019).

    Article  Google Scholar 

  21. Greiff, V., Yaari, G. & Cowell, L. Mining adaptive immune receptor repertoires for biological and clinical information using machine learning. Curr. Opin. Syst. Biol. https://doi.org/10.1016/j.coisb.2020.10.010 (2020).

  22. Fischman, S. & Ofran, Y. Computational design of antibodies. Curr. Opin. Struct. Biol. 51, 156–162 (2018).

    Article  Google Scholar 

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

    Article  Google Scholar 

  24. Burton, D. R. What Are the Most Powerful Immunogen Design Vaccine Strategies?: Reverse Vaccinology 2.0 Shows Great Promise. Cold Spring Harb. Perspect. Biol. 9, a030262 (2017).

    Article  Google Scholar 

  25. Daberdaku, S. & Ferrari, C. Antibody interface prediction with 3D Zernike descriptors and SVM. Bioinformatics 35, 1870–1876 (2019).

    Article  Google Scholar 

  26. Liberis, E., Velickovic, P., Sormanni, P., Vendruscolo, M. & Liò, P. Parapred: antibody paratope prediction using convolutional and recurrent neural networks. Bioinformatics 34, 2944–2950 (2018).

    Article  Google Scholar 

  27. Eguchi, R. R., Anand, N., Choe, C. A. & Huang, P.-S. IG-VAE: Generative Modeling of Immunoglobulin Proteins by Direct 3D Coordinate Generation. bioRxiv 2020.08.07.242347 (2020) https://doi.org/10.1101/2020.08.07.242347

  28. Jespersen, M. C., Mahajan, S., Peters, B., Nielsen, M. & Marcatili, P. Antibody specific B-cell epitope predictions: leveraging information from antibody–antigen protein complexes. Front. Immunol. 10, 298 (2019).

    Article  Google Scholar 

  29. Liu, G. et al. Antibody complementarity determining region design using high-capacity machine learning. Bioinformatics 36, 2126–2133 (2020).

    Article  Google Scholar 

  30. Marks, C. & Deane, C. M. How repertoire data is changing antibody science. J. Biol. Chem. https://doi.org/jbc.REV120.010181 (2020).

  31. Friedensohn, S. et al. Convergent selection in antibody repertoires is revealed by deep learning. Preprint at bioRxiv https://doi.org/10.1101/2020.02.25.965673 (2020).

  32. Ripoll, D. R., Chaudhury, S. & Wallqvist, A. Using the antibody–antigen binding interface to train image-based deep neural networks for antibody-epitope classification. PLoS Comput. Biol. 17, e1008864 (2021).

    Article  Google Scholar 

  33. Ruffolo, J. A., Sulam, J. & Gray, J. J. Antibody structure prediction using interpretable deep learning. Patterns Volume 3, Issue 2,100406 (2022).

  34. Del Vecchio, A., Deac, A., Liò, P. & Velickovic, P. Neural message passing for joint paratope–epitope prediction. Preprint at https://arxiv.org/abs/2106.00757 (2021).

  35. Deac, A., Velickovic, P. & Sormanni, P. Attentive cross-modal paratope prediction. J. Comput. Biol. 26, 536–545 (2019).

    Article  Google Scholar 

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

  37. Sela-Culang, I., Ofran, Y. & Peters, B. Antibody specific epitope prediction—emergence of a new paradigm. Curr. Opin. Virol. 11, 98–102 (2015).

    Article  Google Scholar 

  38. Nimrod, G. et al. Computational design of epitope-specific functional antibodies. Cell Rep. 25, 2121–2131.e5 (2018).

    Article  Google Scholar 

  39. Xu, J. Distance-based protein folding powered by deep learning. Proc. Natl Acad. Sci. USA 116, 16856–16865 (2019).

    Article  Google Scholar 

  40. AlQuraishi, M. End-to-end differentiable learning of protein structure. Cell Syst. 8, 292–301.e3 (2019).

    Article  Google Scholar 

  41. Sverrisson, F., Feydy, J., Correia, B. & Bronstein, M. Fast end-to-end learning on protein surfaces. Preprint at bioRxiv https://doi.org/10.1101/2020.12.28.424589 (2020).

  42. Narayanan, H. et al. Machine learning for biologics: opportunities for protein engineering, developability, and formulation. Trends Pharmacol. Sci. https://doi.org/10.1016/j.tips.2020.12.004 (2021).

  43. Townshend, R. J. L., Bedi, R., Suriana, P. A. & Dror, R. O. End-to-end learning on 3D protein structure for interface prediction. Preprint at https://arxiv.org/abs/1807.01297 (2018).

  44. Olimpieri, P. P., Chailyan, A., Tramontano, A. & Marcatili, P. Prediction of site-specific interactions in antibody–antigen complexes: the proABC method and server. Bioinformatics 29, 2285–2291 (2013).

    Article  Google Scholar 

  45. Pittala, S. & Bailey-Kellogg, C. Learning context-aware structural representations to predict antigen and antibody binding interfaces. Issue 13, Pages 3996–4003 (2020).

  46. Lu, S., Li, Y., Wang, F., Nan, X. & Zhang, S. Leveraging sequential and spatial neighbors information by using CNNs linked with GCNs for paratope prediction. In IEEE/ACM Trans. Comput. Biol. Bioinform.Volume 19 issue 1 Page(s): 68 - 74 (2021).

  47. Honda, S., Koyama, K. & Kotaro, K. Cross attentive antibody-antigen interaction prediction with multi-task learning. In 2021 ICML Workshop on Computational Biology.

  48. Swindells, M. B. et al. abYsis: integrated antibody sequence and structure-management, analysis, and prediction. J. Mol. Biol. 429, 356–364 (2017).

    Article  Google Scholar 

  49. Rangel, M. A. et al. Fragment-based computational design of antibodies targeting structured epitopes. Preprint at bioRxiv https://doi.org/10.1101/2021.03.02.433360 (2021).

  50. Kang, Y., Leng, D., Guo, J. & Pan, L. Sequence-based deep learning antibody design for in silico antibody affinity maturation. Preprint at https://arxiv.org/abs/2103.03724 (2021).

  51. Akbar, R. et al. Progress and challenges for the machine learning-based design of fit-for-purpose monoclonal antibodies. MAbs 14, 2008790 (2022).

    Article  Google Scholar 

  52. Prakash, E., Shrikumar, A. & Kundaje, A. Towards more realistic simulated datasets for benchmarking deep learning models in regulatory genomics. Preprint at bioRxiv https://doi.org/10.1101/2021.12.26.474224 (2021).

  53. Cao, Y., Yang, P. & Yang, J. Y. H. A benchmark study of simulation methods for single-cell RNA sequencing data. Nat. Commun. 12, 6911 (2021).

    Article  Google Scholar 

  54. Schuler, A., Jung, K., Tibshirani, R., Hastie, T. & Shah, N. Synth-validation: selecting the best causal inference method for a given dataset. Preprint at https://arxiv.org/abs/1711.00083 (2017).

  55. Sandve, G. K. & Greiff, V. Access to ground truth at unconstrained size makes simulated data as indispensable as experimental data for bioinformatics methods development and benchmarking. Bioinformatics btac612 (2022).

  56. Lavin, A. et al. Simulation intelligence: towards a new generation of scientific methods. Preprint at https://arxiv.org/abs/2112.03235 (2021).

  57. Chen, V. et al. Best practices for interpretable machine learning in computational biology. Preprint at bioRxiv https://doi.org/10.1101/2022.10.28.513978 (2022).

  58. Robert, P. A. & Meyer-Hermann, M. Ymir, A 3D structural affinity model for multi-epitope in silico germinal center simulations. Volume 24 issue 9, 102979 iScience (20201).

  59. Mann, M., Saunders, R., Smith, C., Backofen, R. & Deane, C. M. Producing high-accuracy lattice models from protein atomic coordinates including side chains. Adv. Bioinformatics 2012, 148045 (2012).

  60. Robinson, S. A. et al. Epitope profiling of coronavirus-binding antibodies using computational structural modelling. PLoS Comput Biol 17(12):e1009675 (2021).

  61. Behrens, A-J. et al. Composition and antigenic effects of individual glycan sites of a trimeric HIV-1 envelope glycoprotein. Cell Rep. 14, 2695–2706 (2016).

    Article  Google Scholar 

  62. Miyazawa, S. & Jernigan, R. L. An empirical energy potential with a reference state for protein fold and sequence recognition. Proteins 36, 357–369 (1999).

    Article  Google Scholar 

  63. Ambrosetti, F., Jiménez-García, B., Roel-Touris, J. & Bonvin, A. M. J. Modeling antibody–antigen complexes by information-driven docking. Structure 28, 119–129.e2 (2020).

    Article  Google Scholar 

  64. Greiff, V. et al. Systems analysis reveals high genetic and antigen-driven predetermination of antibody repertoires throughout B cell development. Cell Rep. 19, 1467–1478 (2017).

    Article  Google Scholar 

  65. DeWitt, W. S. et al. A public database of memory and naive B-cell receptor sequences. PLoS ONE 11, e0160853 (2016).

    Article  Google Scholar 

  66. Pires, D. E. & Ascher, D. B. mCSM-AB: a web server for predicting antibody–antigen affinity changes upon mutation with graph-based signatures. Nucleic Acids Res. 44, W469–W473 (2016).

    Article  Google Scholar 

  67. Ju, F. et al. CopulaNet: learning residue co-evolution directly from multiple sequence alignment for protein structure prediction. Preprint at bioRxiv https://doi.org/10.1101/2020.10.06.327585 (2020).

  68. Nogal, B. et al. Mapping polyclonal antibody responses in non-human primates vaccinated with HIV env trimer subunit vaccines. Cell Rep. 30, 3755–3765.e7 (2020).

    Article  Google Scholar 

  69. Adams, R. M., Kinney, J. B., Walczak, A. M. & Mora, T. Epistasis in a fitness landscape defined by antibody–antigen binding free energy. Cell Syst. 8, 86–93.e3 (2019).

    Article  Google Scholar 

  70. Hawkins-Hooker, A. et al. Generating functional protein variants with variational autoencoders. PLoS Comput. Biol. 17, e1008736 (2021).

    Article  Google Scholar 

  71. Angeletti, D. et al. Defining B cell immunodominance to viruses. Nat. Immunol. 18, 456–463 (2017).

    Article  Google Scholar 

  72. Angeletti, D. & Yewdell, J. W. Understanding and manipulating viral immunity: antibody immunodominance enters center stage. Trends Immunol. 39, 549–561 (2018).

    Article  Google Scholar 

  73. Kanduri, C. et al. Profiling the baseline performance and limits of machine learning models for adaptive immune receptor repertoire classification. Preprint at bioRxiv https://doi.org/10.1101/2021.05.23.445346 (2021).

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

  75. Schneider, C., Buchanan, A., Taddese, B. & Deane, C. M. DLAB: deep learning methods for structure-based virtual screening of antibodies. Bioinformatics 38, 377–383 (2021).

    Article  Google Scholar 

  76. Ragoza, M., Hochuli, J., Idrobo, E., Sunseri, J. & Koes, D. R. Protein-ligand scoring with convolutional neural networks. J. Chem. Inf. Model. 57, 942–957 (2017).

    Article  Google Scholar 

  77. Leem, J., Dunbar, J., Georges, G., Shi, J. & Deane, C. M. ABodyBuilder: automated antibody structure prediction with data-driven accuracy estimation. MAbs 8, 1259–1268 (2016).

    Article  Google Scholar 

  78. Schneider, C. Deep Learning Algorithms for Predicting Association between Antibody Sequence, Structure, and Antibody Properties (Univ. Oxford, 2022).

  79. Bahdanau, D., Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. Preprint at https://arxiv.org/abs/1409.0473 (2014).

  80. Vaswani, A. et al. Attention is all you need. Preprint at https://arxiv.org/abs/1706.03762 (2017).

  81. Springer, I., Besser, H., Tickotsky-Moskovitz, N., Dvorkin, S. & Louzoun, Y. Prediction of specific TCR–peptide binding from large dictionaries of TCR–peptide pairs. Front. Immunol. 11:1803.doi: 10.3389/fimmu.2020.01803. eCollection 2020. (2020).

  82. Moris, P. et al. Current challenges for unseen-epitope TCR interaction prediction and a new perspective derived from image classification. Brief. Bioinform. 22, bbaa318 (2021).

    Article  Google Scholar 

  83. Khan, A. et al. AntBO: Towards real-world automated antibody design with combinatorial Bayesian optimisation. Preprint at https://arxiv.org/abs/2201.12570 (2022).

  84. Akbar, R. et al. In silico proof of principle of machine learning-based antibody design at unconstrained scale. MAbs 14(1):2031482 (2022).

  85. Robert, P. A., Marschall, A. L. & Meyer-Hermann, M. Induction of broadly neutralizing antibodies in germinal centre simulations. Curr. Opin. Biotechnol. 51, 137–145 (2018).

    Article  Google Scholar 

  86. Shaw, A. et al. Binding to nanopatterned antigens is dominated by the spatial tolerance of antibodies. Nat. Nanotechnol. 14, 184–190 (2019).

    Article  Google Scholar 

  87. Yaari, G. et al. Models of somatic hypermutation targeting and substitution based on synonymous mutations from high-throughput immunoglobulin sequencing data. Front. Immunol. 4, 358 (2013).

    Article  Google Scholar 

  88. Cassioli, A. et al. An algorithm to enumerate all possible protein conformations verifying a set of distance constraints. BMC Bioinform. 16, 23 (2015).

    Article  Google Scholar 

  89. Hollingsworth, S. A., Lewis, M. C., Berkholz, D. S., Wong, W.-K. & Karplus, P. A. (f,ψ)2 Motifs: a purely conformation-based fine-grained enumeration of protein parts at the two-residue level. J. Mol. Biol. 416, 78–93 (2012).

    Article  Google Scholar 

  90. Lees, W. D., Stejskal, L., Moss, D. S. & Shepherd, A. J. Investigating substitutions in antibody–antigen complexes using molecular dynamics: a case study with broad-spectrum, influenza A antibodies. Front. Immunol. 8:143(2017).

  91. Rodrigues, J. P. G. L., Teixeira, J. M. C., Trellet, M. & Alexandre, M. J. pdb-tools: a Swiss army knife for molecular structures. F1000Res. 7, 1961 (2018).

    Article  Google Scholar 

  92. Boyoglu-Barnum, S. et al. Glycan repositioning of influenza hemagglutinin stem facilitates the elicitation of protective cross-group antibody responses. Nat. Commun. 11, 791 (2020).

    Article  Google Scholar 

  93. Ward, A. B. & Wilson, I. A. The HIV-1 envelope glycoprotein structure: nailing down a moving target. Immunol. Rev. 275, 21–32 (2017).

    Article  Google Scholar 

  94. Andrabi, R. et al. Glycans function as anchors for antibodies and help drive HIV broadly neutralizing antibody development. Immunity 47, 524 (2017).

    Article  Google Scholar 

  95. Mosca, R., Céol, A., Stein, A., Olivella, R. & Aloy, P. 3did: a catalog of domain-based interactions of known three-dimensional structure. Nucleic Acids Res. 42, D374–D379 (2014).

  96. Karp, R. M. Reducibility among combinatorial problems. In Complexity of Computer Computations 85–103 (1972).

  97. The PyMOL Molecular Graphics System, Version 1.8 (Schrödinger) (2015); http://www.sciepub.com/reference/159710

  98. Luong, M.-T., Pham, H. & Manning, C. D. Effective approaches to attention-based neural machine translation. Preprint at https://arxiv.org/abs/1508.04025 (2015).

  99. Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. Preprint at https://arxiv.org/abs/1412.6980 (2014).

  100. Abadi, M. et al. TensorFlow: a system for large-scale machine learning. (2016). OSDI'16: Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation Pages 265–283

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

    MathSciNet  MATH  Google Scholar 

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

    Article  Google Scholar 

  103. Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. Preprint at https://dl.acm.org/doi/10.5555/3454287.3455008 (2019).

  104. Kingma, D. P. & Welling, M. An Introduction to variational autoencoders. Found. Trends Mach. Learn. (2019).

  105. Higgins, I. et al. beta-VAE: learning basic visual concepts with a constrained variational framework. International Conference on Learning Representations (2016).

  106. Dupont, E. Learning disentangled joint continuous and discrete representations. Adv. Neural Inf. Process. Syst. 31, (2018).

  107. Rives, A. et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl Acad. Sci. USA 118, e2016239118 (2021).

    Article  Google Scholar 

  108. Katanforoush, A. & Shahshahani, M. Distributing points on the sphere, I. Exp. Math. 12, 199–209 (2003).

    Article  MathSciNet  MATH  Google Scholar 

  109. Wickham, H. ggplot2: Elegant Graphics for Data Analysis (Springer-Verlag, 2009).

  110. Waskom, M. seaborn: statistical data visualization. J. Open Source Softw. 6, 3021 (2021).

    Article  Google Scholar 

  111. Hunter, J. D. Matplotlib: a 2D graphics environment. Comput. Sci. Eng. 9, 90–95 (2007).

    Article  Google Scholar 

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

    Article  Google Scholar 

  113. Robert, P. A., Akbar, R. & Greiff, V. Absolut! in silico antibody–antigen binding database. Nird Research Data Archive https://doi.org/10.11582/2021.00063 (2021).

  114. Robert, P. A., Akbar, R. & Greiff, V. csi-greifflab/Absolut: v2.0 Zenodo https://doi.org/10.5281/zenodo.7415772 (2022).

Download references

Acknowledgements

We acknowledge generous support by The Leona M. and Harry B. Helmsley Charitable Trust (#2019PG-T1D011, to V.G.), UiO World-Leading Research Community (to V.G.), UiO:LifeScience Convergence Environment Immunolingo (to V.G., G.K.S. and I.H.H.), EU Horizon 2020 iReceptorplus (#825821) (to V.G.), a Research Council of Norway FRIPRO project (#300740, to V.G.), a Research Council of Norway IKTPLUSS project (#311341, to V.G. and G.K.S.), a Norwegian Cancer Society Grant (#215817, to V.G.), and Stiftelsen Kristian Gerhard Jebsen (K.G. Jebsen Coeliac Disease Research Centre) (to L.S. and G.K.S.). This work was not funded by Marie Skłodowska-Curie Actions while grant writing was supported by the German Arbeitsamt. This work was carried out on Immunohub e-Infrastructure funded by University of Oslo and jointly operated by GreiffLab and SandveLab (the authors) in close collaboration with the University Center for Information Technology, University of Oslo, IT-Department (USIT). We acknowledge T. Malliavin (Institut Pasteur, Paris, France) for comments and suggestions that helped in the analysis of the results, and C. Schneider for helping us reproduce the DLAB-VS pipeline.

Author information

Authors and Affiliations

Authors

Contributions

Study conception: P.A.R., V.G.; study design: P.A.R., R.A., E.M., D.T.T.H., F.L.-J., S.H., I.H.H., G.K., G.K.S., V.G.; study implementation: P.A.R., R.A., R.F., M.P., M.W., I.S., A.P., K.A., A.O., A.S., M.C., L.S., I.F.M.; contributed data and analysis tools: E.S., P.R., B.B.M., M.H.V.; performed the analysis: P.A.R., R.A., R.F., I.F.M., K.A., A.O., A.S.; wrote the paper: P.A.R., R.A., R.F., M.P., M.W., I.S., A.S., M.C., L.S., E.S., P.R., B.B.M., M.H.V., I.F.M., G.K.S., V.G.

Corresponding authors

Correspondence to Philippe A. Robert or Victor Greiff.

Ethics declarations

Competing interests

E.M. declares holding shares in aiNET GmbH. V.G. declares advisory board positions in aiNET GmbH, Enpicom B.V, Specifica Inc, Adaptyv Biosystems, EVQLV, Omniscope, Diagonal Therapeutics, and Absci. V.G. is a consultant for Roche/Genentech, immunai, and Proteinea. The other authors declare no competing interests.

Peer review

Peer review information

Nature Computational Science thanks Charlotte Deane, Pieter Meysman and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Primary Handling Editor: Fernando Chirigati, in collaboration with the Nature Computational Science team.

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 Results, Discussion, Figs. 1–24, Algorithms, Tables 1–6 and References.

Reporting Summary

Peer Review File

Source data

Source Data Fig. 2

One tab-separated text file per plot.

Source Data Fig. 3

One tab-separated text file per plot.

Source Data Fig. 4

tab-separated text file per plot + scripts in R.

Source Data Fig. 5

SOne tab-separated text file per plot.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Robert, P.A., Akbar, R., Frank, R. et al. Unconstrained generation of synthetic antibody–antigen structures to guide machine learning methodology for antibody specificity prediction. Nat Comput Sci 2, 845–865 (2022). https://doi.org/10.1038/s43588-022-00372-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s43588-022-00372-4

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