CoChat

Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery

Open access
Wilman, Wiktoria, Wróbel, Sonia, Bielska, Weronika, Deszynski, Piotr, Dudzic, Paweł, Jaszczyszyn, Igor, Kaniewski, Jędrzej, Młokosiewicz, Jakub, Rouyan, Anahita, Satława, Tadeusz, Kumar, Sandeep, Greiff, Victor, Krawczyk, Konrad · 2022 · Briefings in Bioinformatics
Cited by 79

The DOI matches its Crossref record; 58 of the 58 references it cites were found in a registry or an index.

Abstract

Antibodies are versatile molecular binders with an established and growing role as therapeutics. Computational approaches to developing and designing these molecules are being increasingly used to complement traditional lab-based processes. Nowadays, in silico methods fill multiple elements of the discovery stage, such as characterizing antibody–antigen interactions and identifying developability liabilities. Recently, computational methods tackling such problems have begun to follow machine learning paradigms, in many cases deep learning specifically. This paradigm shift offers improvements in established areas such as structure or binding prediction and opens up new possibilities such as language-based modeling of antibody repertoires or machine-learning-based generation of novel sequences. In this review, we critically examine the recent developments in (deep) machine learning approaches to therapeutic antibody design with implications for fully computational antibody design.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1093/bib/bbac267

Cites

58 of 58 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 83

  1. Krawczyk, 2021, Data mining patented antibody sequences, MAbs, 13, 1892366, 10.1080/19420862.2021.1892366 · DOI
  2. Kaplon, 2022, Antibodies to watch in 2022, MAbs, 14, 2014296, 10.1080/19420862.2021.2014296 · DOI · Paper page
  3. Kaplon, 2021, Antibodies to watch in 2021, MAbs, 13, 1860476, 10.1080/19420862.2020.1860476 · DOI · Paper page
  4. Arslan, 2021, Antibody-mediated drug delivery, Int J Pharm, 596, 120268, 10.1016/j.ijpharm.2021.120268 · DOI
  5. Ferrara, 2022, A pandemic-enabled comparison of discovery platforms demonstrates a naïve antibody library can match the best immune-sourced antibodies, Nat Commun, 13, 462, 10.1038/s41467-021-27799-z · DOI
  6. Breden, 2020, 486 iReceptor plus: a data integration platform to share, compare and analyze adaptive immune receptor repertoire (AIRR-seq) data from antibody/B- and T-cell repertoires, J Immunother Cancer, 8, A522
  7. Graves, 2020, A review of deep learning methods for antibodies, Antibodies (Basel), 9, 12, 10.3390/antib9020012 · DOI · Paper page
  8. Pertseva, 2021, Applications of machine and deep learning in adaptive immunity, Annu Rev Chem Biomol Eng, 12, 39, 10.1146/annurev-chembioeng-101420-125021 · DOI
  9. Robert, 2021, One billion synthetic 3D-antibody-antigen complexes enable unconstrained machine-learning formalized investigation of antibody specificity prediction, 10.1101/2021.07.06.451258 · DOI
  10. Lefranc, 2003, IMGT unique numbering for immunoglobulin and T cell receptor variable domains and Ig superfamily V-like domains, Dev Comp Immunol, 27, 55, 10.1016/S0145-305X(02)00039-3 · DOI · Paper page
  11. Abhinandan, 2008, Analysis and improvements to Kabat and structurally correct numbering of antibody variable domains, Mol Immunol, 45, 3832, 10.1016/j.molimm.2008.05.022 · DOI · Paper page
  12. Cohen, 2021, NanoNet: rapid end-to-end nanobody modeling by deep learning at sub angstrom resolution, 10.1101/2021.08.03.454917 · DOI
  13. Pittala, 2020, Learning context-aware structural representations to predict antigen and antibody binding interfaces, Bioinformatics, 36, 3996, 10.1093/bioinformatics/btaa263 · DOI · Paper page
  14. Chakrabarty, 2016, NAPS: network analysis of protein structures, Nucleic Acids Res, 44, W375, 10.1093/nar/gkw383 · DOI · Paper page
  15. Brinda, 2005, A network representation of protein structures: implications for protein stability, Biophys J, 89, 4159, 10.1529/biophysj.105.064485 · DOI · Paper page
  16. Leem, 2021, Deciphering the language of antibodies using self-supervised learning, 10.1101/2021.11.10.468064 · doi:10.1101/2021.11.10.468064
  17. Proteins, 74
  18. Cho, 2014, Learning phrase representations using RNN encoder-decoder for statistical machine translation, 10.3115/v1/D14-1179 · DOI · Paper page
  19. Wollacott, 2019, Quantifying the nativeness of antibody sequences using long short-term memory networks, Protein Eng Des Sel, 32, 347, 10.1093/protein/gzz031 · DOI
  20. Ripoll, 2021, Using the antibody-antigen binding interface to train image-based deep neural networks for antibody-epitope classification, PLoS Comput Biol, 17, e1008864, 10.1371/journal.pcbi.1008864 · DOI
  21. Amimeur, 2020, Designing feature-controlled humanoid antibody discovery libraries using generative adversarial networks, 10.1101/2020.04.12.024844 · DOI · Paper page
  22. Samek, 2019, Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, 5, 10.1007/978-3-030-28954-6_1 · DOI · Paper page
  23. Vaswani, 2017, Attention is all you need, Adv Neural Inf Process Syst, 30
  24. Ott, 2019, Fairseq: a fast, extensible toolkit for sequence Modeling, 10.18653/v1/N19-4009 · DOI · Paper page
  25. Silva, 2022, epitope3D: a machine learning method for conformational B-cell epitope prediction, Brief Bioinform, 23, bbab423, 10.1093/bib/bbab423 · DOI · Paper page
  26. Myung, 2020, mmCSM-AB: guiding rational antibody engineering through multiple point mutations, Nucleic Acids Res, 48, W125, 10.1093/nar/gkaa389 · DOI
  27. He, 2016, Proceedings of the IEEE conference on computer vision and pattern recognition, 770
  28. Ostrovsky-Berman, 2021, Immune2vec: embedding B/T cell receptor sequences in ℝN using natural language processing, Front Immunol, 12, 680687, 10.3389/fimmu.2021.680687 · DOI
  29. Asgari, 2015, Continuous distributed representation of biological sequences for deep proteomics and genomics, PLoS One, 10, e0141287, 10.1371/journal.pone.0141287 · DOI · Paper page
  30. Friedensohn, 2020, Convergent selection in antibody repertoires is revealed by deep learning, 10.1101/2020.02.25.965673 · DOI
  31. Shuai, 2021, Generative language Modeling for antibody design, 10.1101/2021.12.13.472419 · DOI
  32. Khan, 2022, AntBO: towards real-world automated antibody design with combinatorial Bayesian optimisation, 10.2139/ssrn.4115860 · DOI
  33. Akbar, 2021, A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding, Cell Rep, 34, 108856, 10.1016/j.celrep.2021.108856 · DOI · Paper page
  34. Kovaltsuk, 2017, How B-cell receptor repertoire sequencing can be enriched with structural antibody data, Front Immunol, 8, 1753, 10.3389/fimmu.2017.01753 · DOI · Paper page
  35. Jones, 2015, MetaPSICOV: combining coevolution methods for accurate prediction of contacts and long range hydrogen bonding in proteins, Bioinformatics, 31, 999, 10.1093/bioinformatics/btu791 · DOI · Paper page
  36. Yamashita, 2014, Kotai antibody builder: automated high-resolution structural modeling of antibodies, Bioinformatics, 30, 3279, 10.1093/bioinformatics/btu510 · DOI · Paper page
  37. Jeliazkov, 2021, Robustification of RosettaAntibody and Rosetta SnugDock, PLoS One, 16, e0234282, 10.1371/journal.pone.0234282 · DOI · Paper page
  38. Marcatili, 2008, PIGS: automatic prediction of antibody structures, Bioinformatics, 24, 1953, 10.1093/bioinformatics/btn341 · DOI · Paper page
  39. Källberg, 2012, Template-based protein structure modeling using the RaptorX web server, Nat Protoc, 7, 1511, 10.1038/nprot.2012.085 · DOI · Paper page
  40. Weitzner, 2014, Blind prediction performance of RosettaAntibody 3.0: grafting, relaxation, kinematic loop modeling, and full CDR optimization, Proteins, 82, 1611, 10.1002/prot.24534 · DOI · Paper page
  41. Adolf-Bryfogle, 2015, PyIgClassify: a database of antibody CDR structural classifications, Nucleic Acids Res, 43, D432, 10.1093/nar/gku1106 · DOI · Paper page
  42. Du, 2021, The trRosetta server for fast and accurate protein structure prediction, Nat Protoc, 16, 5634, 10.1038/s41596-021-00628-9 · DOI · Paper page
  43. Jespersen, 2017, BepiPred-2.0: improving sequence-based B-cell epitope prediction using conformational epitopes, Nucleic Acids Res, 45, W24, 10.1093/nar/gkx346 · DOI · Paper page
  44. Sweredoski, 2008, PEPITO: improved discontinuous B-cell epitope prediction using multiple distance thresholds and half sphere exposure, Bioinformatics, 24, 1459, 10.1093/bioinformatics/btn199 · DOI · Paper page
  45. Sircar, 2010, SnugDock: paratope structural optimization during antibody-antigen docking compensates for errors in antibody homology models, PLoS Comput Biol, 6, e1000644, 10.1371/journal.pcbi.1000644 · DOI · Paper page
  46. Guest JD, Vreven T, Zhou J, Moal I, Jeliazkov JR, Gray JJ, Weng Z, Pierce BG, 2021, An expanded benchmark for antibody-antigen docking and affinity prediction reveals insights into antibody recognition determinants, 606
  47. Ambrosetti, 2020, Modeling antibody-antigen complexes by information-driven docking, Structure, 28, 119, 10.1016/j.str.2019.10.011 · DOI · Paper page
  48. Sharma, 2014, In silico selection of therapeutic antibodies for development: viscosity, clearance, and chemical stability, Proc Natl Acad Sci U S A, 111, 18601, 10.1073/pnas.1421779112 · DOI · Paper page
  49. Jurtz, 2017, NetMHCpan-4.0: improved peptide-MHC class I interaction predictions integrating eluted ligand and peptide binding affinity data, J Immunol, 199, 3360, 10.4049/jimmunol.1700893 · DOI · Paper page
  50. Maia, 2020, Structure-based virtual screening: from classical to artificial intelligence, Front Chem, 8, 343, 10.3389/fchem.2020.00343 · DOI · Paper page
  51. Geng, 2020, iScore: a novel graph kernel-based function for scoring protein-protein docking models, Bioinformatics, 36, 112, 10.1093/bioinformatics/btz496 · DOI · Paper page
  52. Renaud, 2021, DeepRank: a deep learning framework for data mining 3D protein-protein interfaces, Nat Commun, 12, 7068, 10.1038/s41467-021-27396-0 · DOI · Paper page
  53. Wang, 2020, Protein docking model evaluation by 3D deep convolutional neural networks, Bioinformatics, 36, 2113, 10.1093/bioinformatics/btz870 · DOI · Paper page
  54. Kilambi, 2017, Structure-based cross-docking analysis of antibody–antigen interactions, Sci Rep, 7, 1, 10.1038/s41598-017-08414-y · DOI
  55. Hummer, 2022, Advances in computational structure-based antibody design, Curr Opin Struct Biol, 74, 102379, 10.1016/j.sbi.2022.102379 · DOI · Paper page
  56. Khetan, 2022, Current advances in biopharmaceutical informatics: guidelines, impact and challenges in the computational developability assessment of antibody therapeutics, MAbs, 14, 2020082, 10.1080/19420862.2021.2020082 · DOI
  57. Kim, 2012, Humanization by CDR grafting and specificity-determining residue grafting, Methods Mol Biol, 907, 237, 10.1007/978-1-61779-974-7_13 · DOI
  58. Gao, 2013, Monoclonal antibody humanness score and its applications, BMC Biotechnol, 13, 55, 10.1186/1472-6750-13-55 · DOI · Paper page
  59. Schmitz, 2020, Human-likeness of antibody biologics determined by back-translation and comparison with large antibody variable gene repertoires, MAbs, 12, 1758291, 10.1080/19420862.2020.1758291 · DOI
  60. Sheng, 2017, Gene-specific substitution profiles describe the types and frequencies of amino acid changes during antibody somatic Hypermutation, Front Immunol, 8, 537, 10.3389/fimmu.2017.00537 · DOI · Paper page
  61. Fathallah, 2015, The effect of small oligomeric protein aggregates on the immunogenicity of intravenous and subcutaneous administered antibodies, J Pharm Sci, 104, 3691, 10.1002/jps.24592 · DOI
  62. Lazar, 2007, A molecular immunology approach to antibody humanization and functional optimization, Mol Immunol, 44, 1986, 10.1016/j.molimm.2006.09.029 · DOI
  63. Boeckmann, 2003, The SWISS-PROT protein knowledgebase and its supplement TrEMBL in 2003, Nucleic Acids Res, 31, 365, 10.1093/nar/gkg095 · DOI · Paper page
  64. Alfaleh, 2020, Phage display derived monoclonal antibodies: from bench to bedside, Front Immunol, 11, 1986, 10.3389/fimmu.2020.01986 · DOI · Paper page
  65. Rees, 2014, Antibody structure prediction and development of humanization strategies, The Antibody Molecule, 260
  66. Galson, 2020, Deep sequencing of B cell receptor repertoires from COVID-19 patients reveals strong convergent immune signatures, Front Immunol, 11, 605170, 10.3389/fimmu.2020.605170 · DOI · Paper page
  67. Radford, 2019, Language models are unsupervised multitask learners, OpenAI blog, 1, 9
  68. Akbar, 2022, Progress and challenges for the machine learning-based design of fit-for-purpose monoclonal antibodies, MAbs, 14, 2008790, 10.1080/19420862.2021.2008790 · DOI · Paper page
  69. Brooks, 1983, CHARMM: a program for macromolecular energy, minimization, and dynamics calculations, J Comput Chem, 4, 187, 10.1002/jcc.540040211 · DOI · Paper page
  70. Richardson, 2021, A computational method for immune repertoire mining that identifies novel binders from different clonotypes, demonstrated by identifying anti-pertussis toxoid antibodies, MAbs, 13, 1869406, 10.1080/19420862.2020.1869406 · DOI · Paper page
  71. Crowe, 2022, Human antibodies for viral infections, Annu Rev Immunol, 40, 349, 10.1146/annurev-immunol-042718-041309 · DOI
  72. Christley, 2020, The ADC API: a web API for the programmatic query of the AIRR data commons, Front Big Data, 3, 22, 10.3389/fdata.2020.00022 · DOI
  73. Deszyński, 2022, INDI—integrated nanobody database for immunoinformatics, Nucleic Acids Res, 50, D1273, 10.1093/nar/gkab1021 · DOI
  74. Corrie, 2018, iReceptor: a platform for querying and analyzing antibody/B-cell and T-cell receptor repertoire data across federated repositories, Immunol Rev, 284, 24, 10.1111/imr.12666 · DOI · Paper page
  75. Lima, 2020, The ABCD database: a repository for chemically defined antibodies, Nucleic Acids Res, 48, D261, 10.1093/nar/gkz714 · DOI
  76. Pavlović, 2021, The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires, Nat Mach Intell, 3, 936, 10.1038/s42256-021-00413-z · DOI
  77. Jones, 2021, ClonoMatch: a tool for identifying homologous immunoglobulin and T cell receptor sequences in large databases, Bioinformatics, 36, 5695, 10.1093/bioinformatics/btaa1028 · DOI
  78. Sang, 2021, Llamanade: an open-source computational pipeline for robust nanobody humanization, Structure, 30, 418, 10.1016/j.str.2021.11.006 · DOI
  79. Kovaltsuk, 2020, Structural diversity of B-cell receptor repertoires along the B-cell differentiation axis in humans and mice, PLoS Comput Biol, 16, e1007636, 10.1371/journal.pcbi.1007636 · DOI · Paper page
  80. Raybould, 2021, Public baseline and shared response structures support the theory of antibody repertoire functional commonality, PLoS Comput Biol, 17, e1008781, 10.1371/journal.pcbi.1008781 · DOI
  81. Robinson, 2021, Epitope profiling using computational structural modelling demonstrated on coronavirus-binding antibodies, PLoS Comput Biol, 17, e1009675, 10.1371/journal.pcbi.1009675 · DOI · Paper page
  82. Kumar, 2018, Biopharmaceutical informatics: supporting biologic drug development via molecular modelling and informatics, J Pharm Pharmacol, 70, 595, 10.1111/jphp.12700 · DOI
  83. Kumar, 2015, Developability of Biotherapeutics: Computational Approaches, 10.1201/b19023 · doi:10.1201/b19023

Cited by

See all 79

Metadata

Authors
Wilman, W., Wróbel, S., Bielska, W., Deszynski, P., Dudzic, P., Jaszczyszyn, I., Kaniewski, J., Młokosiewicz, J., Rouyan, A., Satława, T., Kumar, S., Greiff, V., & Krawczyk, K.
Venue
Briefings in Bioinformatics
Published
2022-07-14
Volume
23
Issue
4
ISSN
  • 1467-5463 (ISSN-L)
  • 1477-4054
OpenAlex
W4285386587
Cited by
79
References
58
FWCI
9.01
Type
journal article
Language
en
Open access
hybrid
Funders
  • European Regional Development Fund (2014-2020 POIR.01.01.01-00-0962/21)
  • Helmsley Charitable Trust (#2019PG-T1D011)
  • UiO:LifeSciences Convergence Environment Immunolingo (#825821)
  • Research Council of Norway FRIPRO project (#300740)
  • Research Council of Norway (#311341)
  • Norwegian Cancer Society (#215817)

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.