pith. sign in

arxiv: 2409.10588 · v8 · submitted 2024-09-16 · 🧬 q-bio.PE · cs.AI· cs.GT· cs.MA

ADIOS: Antibody Development via Opponent Shaping

Sebastian Towers , Aleksandra Kalisz , Philippe A. Robert , Alicia Higueruelo , Francesca Vianello , Ming-Han Chloe Tsai , Harrison Steel , Jakob N. Foerster This is my paper

Pith reviewed 2026-05-23 21:00 UTC · model grok-4.3

classification 🧬 q-bio.PE cs.AIcs.GTcs.MA
keywords antibody designopponent shapingviral evolutionmeta-learningantiviral therapyevolutionary adaptation
0
0 comments X

The pith

Antibodies designed via opponent shaping resist current strains while steering viral evolution toward weaker future variants.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents ADIOS as a meta-learning method for antibody design that treats the virus as an adapting opponent rather than a fixed target. The outer loop optimizes the antibody while the inner loop simulates how the virus evolves in response, producing designs that remain effective against both present and anticipated variants. A sympathetic reader would care because conventional myopic therapies lose potency as selective pressure drives new strains, creating repeated cycles of obsolescence. Simulations show these shaped antibodies not only bind better across trajectories but also shift the overall distribution of emerging variants toward lower fitness.

Core claim

ADIOS is a meta-learning framework where the process of antibody therapy design, the outer loop, accounts for the virus's adaptive response, the inner loop. With ADIOS, antibodies are not only robust against potential future variants, they also influence, i.e., shape, which future variants emerge. In simulations, shapers successfully target both current and future viral variants, outperforming myopic antibodies, and modify the distribution over viral evolutionary trajectories to result in weaker variants.

What carries the argument

Opponent shaping meta-learning loop, with antibody optimization as the outer loop that anticipates and influences the inner loop of simulated viral adaptation.

If this is right

  • Shapers target both current and future viral variants, outperforming myopic antibodies.
  • Shapers modify the distribution over viral evolutionary trajectories to result in weaker variants.
  • The ADIOS paradigm facilitates discovery of long-lived vaccines and antibody therapies.
  • The approach generalizes to other domains with evolutionarily adaptive opponents such as antimicrobial resistance and cancer treatment.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the simulator holds, therapy redesign cycles could become less frequent for rapidly evolving pathogens.
  • Similar shaping logic might be tested in ecological or population models where one actor influences the adaptation of another.
  • Extending the framework to include host immune dynamics could clarify whether shaping effects remain stable in more complex biological settings.

Load-bearing premise

The Absolut! based viral evolution simulator accurately captures the relevant mutation, selection, and binding dynamics that would occur under real antibody pressure in vivo.

What would settle it

Laboratory passaging of virus under ADIOS-designed antibodies versus myopic controls, followed by measurement of fitness and virulence distributions in the resulting populations.

Figures

Figures reproduced from arXiv: 2409.10588 by Aleksandra Kalisz, Alicia Higueruelo, Francesca Vianello, Harrison Steel, Jakob N. Foerster, Ming-Han Chloe Tsai, Philippe A. Robert, Sebastian Towers.

Figure 1
Figure 1. Figure 1: Myopic Therapies Become Ineffective Over Time. Ini￾tial virus (variant A) evolves in response to the evolutionary pres￾sures induced by therapies, resulting in new variants. In case of traditional myopic therapies (top), the new emerging variants (vari￾ant B) are often therapy resistant. In contrast, ADIOS designs shapers or shaper therapies (bottom) which remain effective and steer the viral evolution tow… view at source ↗
Figure 2
Figure 2. Figure 2: Main Components of ADIOS. a The ADIOS framework. In the Antibody Optimisation Loop (i.e., outer loop), we optimise the antibody to perform well against current and future virus variants; thus influencing the viral evolution. We approximate the future variants through our Simulated Viral Escape via Evolution (i.e., inner loop) where the viruses evolve to escape from the current antibody over a given horizon… view at source ↗
Figure 3
Figure 3. Figure 3: Shapers Outperform Myopic Antibodies. a Distribution of antibody shapers optimised with horizon H = 100 (orange) vs. myopic antibodies distribution (blue). We highlight the top 10% shapers with respect to F 100 v (a) in red, and the top 10% myopic antibodies with respect to Ra(v, a) in green. The x-axis is the myopic antibody fitness Ra(v, a) and the y-axis is the escape averaged antibody fitness for H = 1… view at source ↗
Figure 4
Figure 4. Figure 4: Shapers Outperform Myopic Antibodies on Other Viruses and a Bacterium. Antibody optimisation learning curves (outer loop performance) for varying horizon lengths across three viruses - West Nile Virus, Influenza Virus, and MERS-CoV - as well as the bacterium Clostridium Difficile. The x-axis shows the antibody optimisation steps, i.e., meta-steps and the y-axis shows the antibody fitness F 100 v (a). Raw f… view at source ↗
Figure 5
Figure 5. Figure 5: Robustness vs. Shaping. We optimise 80 different antibodies aH across multiple horizons (Myopic, H = 5, H = 10, H = 20, H = 100), these are represented by the y-axis. We simulate the viral escape to each of these antibodies for 100 steps, and we group the escape viruses vH by the horizon H of the anti￾body that induced them; these escape viruses are represented by the x-axis. In colour, we show the mean an… view at source ↗
Figure 6
Figure 6. Figure 6: Shaping with External Pressure. A similar experiment to [PITH_FULL_IMAGE:figures/full_fig_p009_6.png] view at source ↗
read the original abstract

Anti-viral therapies are typically designed to target only the current strains of a virus, a myopic response. However, therapy-induced selective pressures drive the emergence of new viral strains, against which the original myopic therapies are no longer effective. This evolutionary response presents an opportunity: our therapies could both defend against and actively influence viral evolution. This motivates our method ADIOS: Antibody Development vIa Opponent Shaping. ADIOS is a meta-learning framework where the process of antibody therapy design, the outer loop, accounts for the virus's adaptive response, the inner loop. With ADIOS, antibodies are not only robust against potential future variants, they also influence, i.e., shape, which future variants emerge. In line with the opponent shaping literature, we refer to our optimised antibodies as shapers. To demonstrate the value of ADIOS, we build a viral evolution simulator using the Absolut! framework, in which shapers successfully target both current and future viral variants, outperforming myopic antibodies. Furthermore, we show that shapers modify the distribution over viral evolutionary trajectories to result in weaker variants. We believe that our ADIOS paradigm will facilitate the discovery of long-lived vaccines and antibody therapies while also generalising to other domains. Specifically, domains such as antimicrobial resistance, cancer treatment, and others with evolutionarily adaptive opponents. Our code is available at https://github.com/olakalisz/adios.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper introduces ADIOS, a meta-learning framework for antibody design in which an outer loop optimizes antibodies while an inner loop models viral evolutionary responses; using a custom simulator built on the Absolut! framework, it claims that the resulting 'shapers' outperform myopic antibodies by binding both current and future variants and that they alter the distribution of viral evolutionary trajectories toward weaker variants. The work positions this as a general paradigm for therapies against adaptive opponents and releases code at https://github.com/olakalisz/adios.

Significance. If the simulator dynamics prove representative of in vivo antibody-virus interactions, the approach could meaningfully advance design of durable antiviral therapies by turning selective pressure into an explicit optimization target, with potential extension to antimicrobial resistance and cancer; the open code is a clear asset for reproducibility and follow-up.

major comments (3)
  1. [Simulator construction section] Simulator construction section: all quantitative claims (shapers outperforming myopic Abs, modification of trajectory distribution) are generated inside the Absolut!-based simulator; the manuscript provides no external validation of its mutation rates, binding-affinity mapping, or selection pressures against empirical viral-escape datasets, leaving open the possibility that the reported shaping effect is an artifact of the model's assumptions rather than a general property.
  2. [Results section] Results on trajectory modification: the claim that shapers 'modify the distribution over viral evolutionary trajectories to result in weaker variants' is supported only by simulation outputs; without reported statistical tests, effect sizes, or controls for simulation stochasticity, it is unclear whether the observed shift exceeds what would arise from sampling variance under the same fitness landscape.
  3. [Method / objective definition] Meta-learning objective definition: the opponent-shaping loss is introduced as a new objective rather than derived from first principles or fitted parameters; the manuscript does not demonstrate that the performance advantage survives ablation of the shaping term or variation in the meta-learning hyperparameters, which are the only free parameters listed.
minor comments (2)
  1. [Introduction / Method] Notation: the term 'shapers' is introduced without a concise mathematical definition distinguishing it from standard meta-learners; a single equation or boxed definition would improve clarity.
  2. [Figures] Figure captions: several simulation-result figures lack axis labels for the viral fitness or binding-affinity scales, making it difficult to interpret the magnitude of the reported improvements.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for their constructive and detailed feedback, which has identified several areas where the manuscript can be strengthened. We address each major comment below and indicate the revisions we will make to the next version of the manuscript.

read point-by-point responses

  1. Referee: [Simulator construction section] Simulator construction section: all quantitative claims (shapers outperforming myopic Abs, modification of trajectory distribution) are generated inside the Absolut!-based simulator; the manuscript provides no external validation of its mutation rates, binding-affinity mapping, or selection pressures against empirical viral-escape datasets, leaving open the possibility that the reported shaping effect is an artifact of the model's assumptions rather than a general property.

    Authors: We acknowledge this limitation. The current work introduces the ADIOS framework and evaluates it within the established Absolut! simulator, which has been validated in prior antibody-design literature. We do not claim that the specific quantitative outcomes generalize beyond this simulation environment. In the revision we will add an explicit limitations paragraph stating that external validation against empirical viral-escape datasets remains future work and that the reported effects should be interpreted as properties of the simulated fitness landscape. revision: partial

  2. Referee: [Results section] Results on trajectory modification: the claim that shapers 'modify the distribution over viral evolutionary trajectories to result in weaker variants' is supported only by simulation outputs; without reported statistical tests, effect sizes, or controls for simulation stochasticity, it is unclear whether the observed shift exceeds what would arise from sampling variance under the same fitness landscape.

    Authors: We agree that additional statistical controls are needed. The revised manuscript will report (i) the number of independent simulation runs with distinct random seeds, (ii) statistical tests (Kolmogorov-Smirnov and permutation tests) comparing trajectory distributions between shaper and myopic conditions, and (iii) effect-size measures. These additions will demonstrate that the observed distributional shifts exceed sampling variance. revision: yes

  3. Referee: [Method / objective definition] Meta-learning objective definition: the opponent-shaping loss is introduced as a new objective rather than derived from first principles or fitted parameters; the manuscript does not demonstrate that the performance advantage survives ablation of the shaping term or variation in the meta-learning hyperparameters, which are the only free parameters listed.

    Authors: The shaping term is motivated by the opponent-shaping literature rather than derived from first principles in this domain. To address the concern we will add (i) an ablation that removes the shaping component while keeping all other elements fixed and (ii) a sensitivity analysis over the meta-learning hyperparameters. These experiments will be included in the revised results section. revision: yes

Circularity Check

0 steps flagged

No circularity: meta-learning objective applied to external simulator

full rationale

The paper defines ADIOS as a meta-learning outer loop that explicitly models an inner-loop viral adaptation process, then evaluates the resulting shapers inside an independently constructed Absolut!-based simulator. No equations, fitted parameters, or self-citations reduce the reported performance gains or trajectory-distribution shifts to quantities defined by the same target data. The simulator construction and validation section is treated as an external modeling choice rather than a tautological input. Central claims therefore remain independent of the results they report.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 1 invented entities

The central claim depends on the fidelity of the Absolut! simulator and standard assumptions of meta-learning convergence; no new physical entities are postulated.

free parameters (1)
  • meta-learning hyperparameters
    Learning rates and shaping coefficients chosen to optimize shaper performance in the simulator.
axioms (1)
  • domain assumption Absolut! binding model plus simple mutation/selection rules suffice to represent real viral evolution under antibody pressure
    Invoked when constructing the inner-loop simulator.
invented entities (1)
  • shapers no independent evidence
    purpose: Optimized antibody policies that shape viral evolution
    New label for the meta-learned policies; no independent evidence outside the simulation.

pith-pipeline@v0.9.0 · 5819 in / 1252 out tokens · 27595 ms · 2026-05-23T21:00:00.323474+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

51 extracted references · 51 canonical work pages

  1. [1]

    write newline

    " write newline "" before.all 'output.state := FUNCTION n.dashify 't := "" t empty not t #1 #1 substring "-" = t #1 #2 substring "--" = not "--" * t #2 global.max substring 't := t #1 #1 substring "-" = "-" * t #2 global.max substring 't := while if t #1 #1 substring * t #2 global.max substring 't := if while FUNCTION format.date year duplicate empty "emp...

    work page

  2. [2]

    J., Bambrick, J., Bodenstein, S

    Abramson, J., Adler, J., Dunger, J., Evans, R., Green, T., Pritzel, A., Ronneberger, O., Willmore, L., Ballard, A. J., Bambrick, J., Bodenstein, S. W., Evans, D. A., Hung, C.-C., O’Neill, M., Reiman, D., Tunyasuvunakool, K., Wu, Z., Žemgulytė, A., Arvaniti, E., Beattie, C., Bertolli, O., Bridgland, A., Cherepanov, A., Congreve, M., Cowen-Rivers, A. I., Co...

    work page doi:10.1038/s41586-024-07487-w 2024

  3. [3]

    D., Hu, X., Adachi, Y., Schief, W

    Adolf-Bryfogle, J., Kalyuzhniy, O., Kubitz, M., Weitzner, B. D., Hu, X., Adachi, Y., Schief, W. R., and Jr, R. L. D. RosettaAntibodyDesign ( RAbD ): A general framework for computational antibody design. PLOS Computational Biology, 14 0 (4): 0 e1006112, April 2018. ISSN 1553-7358. doi:10.1371/journal.pcbi.1006112. URL https://journals.plos.org/ploscompbio...

    work page doi:10.1371/journal.pcbi.1006112 2018

  4. [4]

    R., Watson, J

    Bennett, N. R., Watson, J. L., Ragotte, R. J., Borst, A. J., See, D. L., Weidle, C., Biswas, R., Shrock, E. L., Leung, P. J. Y., Huang, B., Goreshnik, I., Ault, R., Carr, K. D., Singer, B., Criswell, C., Vafeados, D., Sanchez, M. G., Kim, H. M., Torres, S. V., Chan, S., and Baker, D. Atomically accurate de novo design of single-domain antibodies, March 20...

    work page doi:10.1101/2024.03.14.585103v1 2024

  5. [5]

    M., Westbrook, J., Feng, Z., Gilliland, G., Bhat, T

    Berman, H. M., Westbrook, J., Feng, Z., Gilliland, G., Bhat, T. N., Weissig, H., Shindyalov, I. N., and Bourne, P. E. The Protein Data Bank . Nucleic Acids Research, 28 0 (1): 0 235--242, January 2000. ISSN 0305-1048. doi:10.1093/nar/28.1.235. URL https://doi.org/10.1093/nar/28.1.235

    work page doi:10.1093/nar/28.1.235 2000

  6. [6]

    J., Leary, C., Maclaurin, D., Necula, G., Paszke, A., VanderPlas, J., and Wanderman-Milne, S

    Bradbury, J., Frostig, R., Hawkins, P., Johnson, M. J., Leary, C., Maclaurin, D., Necula, G., Paszke, A., VanderPlas, J., and Wanderman-Milne, S. JAX : composable transformations of Python + NumPy programs. 2018. URL https://scholar.google.com/scholar?cluster=8800325452556162710&hl=en&oi=scholarr

    work page 2018

  7. [7]

    M., Peacock, T

    Carabelli, A. M., Peacock, T. P., Thorne, L. G., Harvey, W. T., Hughes, J., de Silva, T. I., Peacock, S. J., Barclay, W. S., de Silva, T. I., Towers, G. J., and Robertson, D. L. SARS - CoV -2 variant biology: immune escape, transmission and fitness. Nature Reviews Microbiology, 21 0 (3): 0 162--177, March 2023. ISSN 1740-1534. doi:10.1038/s41579-022-00841...

    work page doi:10.1038/s41579-022-00841-7 2023

  8. [8]

    W., Choi, J., and Shakhnovich, E

    Chéron, N., Serohijos, A. W., Choi, J., and Shakhnovich, E. I. Evolutionary dynamics of viral escape under antibodies stress: A biophysical model. Protein Science : A Publication of the Protein Society, 25 0 (7): 0 1332--1340, July 2016. ISSN 0961-8368. doi:10.1002/pro.2915. URL https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4918420/

    work page doi:10.1002/pro.2915 2016

  9. [9]

    Protein Data Bank : the single global archive for 3D macromolecular structure data

    consortium, w. Protein Data Bank : the single global archive for 3D macromolecular structure data. Nucleic Acids Research, 47 0 (D1): 0 D520--D528, October 2018. ISSN 0305-1048. doi:10.1093/nar/gky949. URL https://doi.org/10.1093/nar/gky949

    work page doi:10.1093/nar/gky949 2018

  10. [10]

    A., Errington, D., Schneider, C., and Deane, C

    Cutting, D., Dreyer, F. A., Errington, D., Schneider, C., and Deane, C. M. De novo antibody design with SE (3) diffusion, May 2024. URL http://arxiv.org/abs/2405.07622. arXiv:2405.07622 [q-bio]

    work page arXiv 2024

  11. [11]

    S., Arenz, D., Weight, H., Overbaugh, J., and Bloom, J

    Dingens, A. S., Arenz, D., Weight, H., Overbaugh, J., and Bloom, J. D. An Antigenic Atlas of HIV -1 Escape from Broadly Neutralizing Antibodies Distinguishes Functional and Structural Epitopes . Immunity, 50 0 (2): 0 520--532.e3, February 2019. ISSN 1074-7613. doi:10.1016/j.immuni.2018.12.017. URL https://www.cell.com/immunity/abstract/S1074-7613(18)30565...

    work page doi:10.1016/j.immuni.2018.12.017 2019

  12. [12]

    B., Lee, J

    Doud, M. B., Lee, J. M., and Bloom, J. D. How single mutations affect viral escape from broad and narrow antibodies to H1 influenza hemagglutinin. Nature Communications, 9 0 (1): 0 1386, April 2018. ISSN 2041-1723. doi:10.1038/s41467-018-03665-3. URL https://www.nature.com/articles/s41467-018-03665-3. Publisher: Nature Publishing Group

    work page doi:10.1038/s41467-018-03665-3 2018

  13. [13]

    The global economic burden of COVID -19 disease: a comprehensive systematic review and meta-analysis

    Faramarzi, A., Norouzi, S., Dehdarirad, H., Aghlmand, S., Yusefzadeh, H., and Javan-Noughabi, J. The global economic burden of COVID -19 disease: a comprehensive systematic review and meta-analysis. Systematic Reviews, 13 0 (1): 0 68, February 2024. ISSN 2046-4053. doi:10.1186/s13643-024-02476-6. URL https://doi.org/10.1186/s13643-024-02476-6

    work page doi:10.1186/s13643-024-02476-6 2024

  14. [14]

    Y., Al-Shedivat, M., Whiteson, S., Abbeel, P., and Mordatch, I

    Foerster, J., Chen, R. Y., Al-Shedivat, M., Whiteson, S., Abbeel, P., and Mordatch, I. Learning with Opponent - Learning Awareness . In Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems , AAMAS '18, pp.\ 122--130, Richland, SC, July 2018. International Foundation for Autonomous Agents and Multiagent Systems

    work page 2018

  15. [15]

    J., Starr, T

    Greaney, A. J., Starr, T. N., Gilchuk, P., Zost, S. J., Binshtein, E., Loes, A. N., Hilton, S. K., Huddleston, J., Eguia, R., Crawford, K. H. D., Dingens, A. S., Nargi, R. S., Sutton, R. E., Suryadevara, N., Rothlauf, P. W., Liu, Z., Whelan, S. P. J., Carnahan, R. H., Crowe, J. E., and Bloom, J. D. Complete Mapping of Mutations to the SARS - CoV -2 Spike ...

    work page doi:10.1016/j.chom.2020.11.007 2021

  16. [16]

    P.-H., and Gao, X

    Han, W., Chen, N., Xu, X., Sahil, A., Zhou, J., Li, Z., Zhong, H., Gao, E., Zhang, R., Wang, Y., Sun, S., Cheung, P. P.-H., and Gao, X. Predicting the antigenic evolution of SARS - COV -2 with deep learning. Nature Communications, 14 0 (1): 0 3478, June 2023. ISSN 2041-1723. doi:10.1038/s41467-023-39199-6. URL https://www.nature.com/articles/s41467-023-39199-6

    work page doi:10.1038/s41467-023-39199-6 2023

  17. [17]

    Hollingsworth, S. A. and Dror, R. O. Molecular dynamics simulation for all. Neuron, 99 0 (6): 0 1129--1143, September 2018. ISSN 0896-6273. doi:10.1016/j.neuron.2018.08.011. URL https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6209097/

    work page doi:10.1016/j.neuron.2018.08.011 2018

  18. [18]

    Emerging SARS - CoV -2 variants reduce neutralization sensitivity to convalescent sera and monoclonal antibodies

    Hu, J., Peng, P., Wang, K., Fang, L., Luo, F.-y., Jin, A.-s., Liu, B.-z., Tang, N., and Huang, A.-l. Emerging SARS - CoV -2 variants reduce neutralization sensitivity to convalescent sera and monoclonal antibodies. Cellular and Molecular Immunology, 18 0 (4): 0 1061--1063, April 2021. ISSN 1672-7681. doi:10.1038/s41423-021-00648-1. URL https://www.ncbi.nl...

    work page doi:10.1038/s41423-021-00648-1 2021

  19. [19]

    Antibody- Antigen Docking and Design via Hierarchical Equivariant Refinement , July 2022

    Jin, W., Barzilay, R., and Jaakkola, T. Antibody- Antigen Docking and Design via Hierarchical Equivariant Refinement , July 2022. URL http://arxiv.org/abs/2207.06616. arXiv:2207.06616 [q-bio]

    work page arXiv 2022

  20. [20]

    M., Eguia, R., Zost, S

    Lee, J. M., Eguia, R., Zost, S. J., Choudhary, S., Wilson, P. C., Bedford, T., Stevens-Ayers, T., Boeckh, M., Hurt, A. C., Lakdawala, S. S., Hensley, S. E., and Bloom, J. D. Mapping person-to-person variation in viral mutations that escape polyclonal serum targeting influenza hemagglutinin. eLife, 8: 0 e49324, August 2019. ISSN 2050-084X. doi:10.7554/eLif...

    work page doi:10.7554/elife.49324 2019

  21. [21]

    J., and Maranas, C

    Li, T., Pantazes, R. J., and Maranas, C. D. OptMAVEn – A New Framework for the de novo Design of Antibody Variable Region Models Targeting Specific Antigen Epitopes . PLOS ONE, 9 0 (8): 0 e105954, August 2014. ISSN 1932-6203. doi:10.1371/journal.pone.0105954. URL https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0105954. Publisher: Public ...

    work page doi:10.1371/journal.pone.0105954 2014

  22. [22]

    F., and Yan, J

    Li, Y., Wan, Y., Liu, P., Zhao, J., Lu, G., Qi, J., Wang, Q., Lu, X., Wu, Y., Liu, W., Zhang, B., Yuen, K.-Y., Perlman, S., Gao, G. F., and Yan, J. A humanized neutralizing antibody against MERS - CoV targeting the receptor-binding domain of the spike protein. Cell Research, 25 0 (11): 0 1237--1249, November 2015. ISSN 1748-7838. doi:10.1038/cr.2015.113. ...

    work page doi:10.1038/cr.2015.113 2015

  23. [23]

    W., Adler, A

    Lim, Y. W., Adler, A. S., and Johnson, D. S. Predicting antibody binders and generating synthetic antibodies using deep learning. mAbs, 14 0 (1): 0 2069075, 2022. ISSN 1942-0870. doi:10.1080/19420862.2022.2069075

    work page doi:10.1080/19420862.2022.2069075 2022

  24. [24]

    E., Ewert, S., and Gifford, D

    Liu, G., Zeng, H., Mueller, J., Carter, B., Wang, Z., Schilz, J., Horny, G., Birnbaum, M. E., Ewert, S., and Gifford, D. K. Antibody complementarity determining region design using high-capacity machine learning. Bioinformatics, 36 0 (7): 0 2126--2133, April 2020. ISSN 1367-4803. doi:10.1093/bioinformatics/btz895. URL https://doi.org/10.1093/bioinformatics/btz895

    work page doi:10.1093/bioinformatics/btz895 2020

  25. [25]

    E., Holdaway, H

    Lok, S.-M., Kostyuchenko, V., Nybakken, G. E., Holdaway, H. A., Battisti, A. J., Sukupolvi-Petty, S., Sedlak, D., Fremont, D. H., Chipman, P. R., Roehrig, J. T., Diamond, M. S., Kuhn, R. J., and Rossmann, M. G. Binding of a neutralizing antibody to dengue virus alters the arrangement of surface glycoproteins. Nature Structural & Molecular Biology, 15 0 (3...

    work page doi:10.1038/nsmb.1382 2008

  26. [26]

    Lu, C., Willi, T., Witt, C. A. S. D., and Foerster, J. Model- Free Opponent Shaping . In Proceedings of the 39th International Conference on Machine Learning , pp.\ 14398--14411. PMLR, June 2022. URL https://proceedings.mlr.press/v162/lu22d.html

    work page 2022

  27. [27]

    Viral escape mechanisms – escapology taught by viruses

    Lucas, M., Karrer, U., Lucas, A., and Klenerman, P. Viral escape mechanisms – escapology taught by viruses. International Journal of Experimental Pathology, 82 0 (5): 0 269--286, 2001. ISSN 1365-2613. doi:10.1046/j.1365-2613.2001.00204.x. URL https://onlinelibrary.wiley.com/doi/abs/10.1046/j.1365-2613.2001.00204.x

    work page doi:10.1046/j.1365-2613.2001.00204.x 2001

  28. [28]

    A., Baillie, V., Cutland, C

    Madhi, S. A., Baillie, V., Cutland, C. L., Voysey, M., Koen, A. L., Fairlie, L., Padayachee, S. D., Dheda, K., Barnabas, S. L., Bhorat, Q. E., Briner, C., Kwatra, G., Ahmed, K., Aley, P., Bhikha, S., Bhiman, J. N., Bhorat, A. E., du Plessis, J., Esmail, A., Groenewald, M., Horne, E., Hwa, S.-H., Jose, A., Lambe, T., Laubscher, M., Malahleha, M., Masenya, ...

    work page doi:10.1056/nejmoa2102214 2021

  29. [29]

    AbDiffuser : Full - Atom Generation of in vitro Functioning Antibodies , March 2024

    Martinkus, K., Ludwiczak, J., Cho, K., Liang, W.-C., Lafrance-Vanasse, J., Hotzel, I., Rajpal, A., Wu, Y., Bonneau, R., Gligorijevic, V., and Loukas, A. AbDiffuser : Full - Atom Generation of in vitro Functioning Antibodies , March 2024. URL http://arxiv.org/abs/2308.05027. arXiv:2308.05027 [q-bio]

    work page arXiv 2024

  30. [30]

    M., Friedensohn, S., Weber, C

    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., and Reddy, S. T. Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning. Nature Biomedical Engineering, 5 0 (6): 0 600--612, June 2021. ISSN 2157-84...

    work page doi:10.1038/s41551-021-00699-9 2021

  31. [31]

    Vaccination shapes evolutionary trajectories of SARS - CoV -2, July 2022

    Meijers, M., Ruchnewitz, D., Łuksza, M., and Lässig, M. Vaccination shapes evolutionary trajectories of SARS - CoV -2, July 2022. URL http://arxiv.org/abs/2207.09329. arXiv:2207.09329 [q-bio]

    work page arXiv 2022

  32. [32]

    and Jernigan, R

    Miyazawa, S. and Jernigan, R. L. An empirical energy potential with a reference state for protein fold and sequence recognition. Proteins: Structure, Function, and Bioinformatics, 36 0 (3): 0 357--369, 1999. ISSN 1097-0134. doi:10.1002/(SICI)1097-0134(19990815)36:3<357::AID-PROT10>3.0.CO;2-U. URL https://onlinelibrary.wiley.com/doi/abs/10.1002/

    work page doi:10.1002/(sici)1097-0134(19990815)36:3 1999

  33. [33]

    and Shet, A

    Nandi, A. and Shet, A. Why vaccines matter: understanding the broader health, economic, and child development benefits of routine vaccination. Human Vaccines & Immunotherapeutics, 16 0 (8): 0 1900--1904. ISSN 2164-5515. doi:10.1080/21645515.2019.1708669. URL https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7482790/

    work page doi:10.1080/21645515.2019.1708669 1900

  34. [34]

    A unified evolution-driven deep learning framework for virus variation driver prediction

    Nie, Z., Liu, X., Chen, J., Wang, Z., Liu, Y., Si, H., Dong, T., Xu, F., Song, G., Wang, Y., Zhou, P., Gao, W., and Tian, Y. A unified evolution-driven deep learning framework for virus variation driver prediction. Nature Machine Intelligence, 7 0 (1): 0 131--144, January 2025. ISSN 2522-5839. doi:10.1038/s42256-024-00966-9. URL https://www.nature.com/art...

    work page doi:10.1038/s42256-024-00966-9 2025

  35. [35]

    E., Oliphant, T., Johnson, S., Burke, S., Diamond, M

    Nybakken, G. E., Oliphant, T., Johnson, S., Burke, S., Diamond, M. S., and Fremont, D. H. Structural basis of West Nile virus neutralization by a therapeutic antibody. Nature, 437 0 (7059): 0 764--769, September 2005. ISSN 1476-4687. doi:10.1038/nature03956. URL https://www.nature.com/articles/nature03956. Publisher: Nature Publishing Group

    work page doi:10.1038/nature03956 2005

  36. [36]

    Orenstein, W. A. and Ahmed, R. Simply put: Vaccination saves lives. Proceedings of the National Academy of Sciences, 114 0 (16): 0 4031--4033, April 2017. doi:10.1073/pnas.1704507114. URL https://www.pnas.org/doi/10.1073/pnas.1704507114. Publisher: Proceedings of the National Academy of Sciences

    work page doi:10.1073/pnas.1704507114 2017

  37. [37]

    D., Reichert, P., Sheth, P

    Orth, P., Xiao, L., Hernandez, L. D., Reichert, P., Sheth, P. R., Beaumont, M., Yang, X., Murgolo, N., Ermakov, G., DiNunzio, E., Racine, F., Karczewski, J., Secore, S., Ingram, R. N., Mayhood, T., Strickland, C., and Therien, A. G. Mechanism of Action and Epitopes of Clostridium difficile Toxin B -neutralizing Antibody Bezlotoxumab Revealed by X -ray Cry...

    work page doi:10.1074/jbc.m114.560748 2014

  38. [38]

    M., and Mora, T

    Pereira, P., Minoux, H., Walczak, A. M., and Mora, T. Energy-based generative models for monoclonal antibodies, November 2024. URL http://arxiv.org/abs/2411.13390. arXiv:2411.13390 [q-bio]

    work page arXiv 2024

  39. [39]

    A., Akbar, R., Frank, R., Pavlović, M., Widrich, M., Snapkov, I., Slabodkin, A., Chernigovskaya, M., Scheffer, L., Smorodina, E., Rawat, P., Mehta, B

    Robert, P. A., Akbar, R., Frank, R., Pavlović, M., Widrich, M., Snapkov, I., Slabodkin, A., Chernigovskaya, M., Scheffer, L., Smorodina, E., Rawat, P., Mehta, B. B., Vu, M. H., Mathisen, I. F., Prósz, A., Abram, K., Olar, A., Miho, E., Haug, D. T. T., Lund-Johansen, F., Hochreiter, S., Haff, I. H., Klambauer, G., Sandve, G. K., and Greiff, V. Unconstraine...

    work page doi:10.1038/s43588-022-00372-4 2022

  40. [40]

    A., Chu, L.-S., Mahajan, S

    Ruffolo, J. A., Chu, L.-S., Mahajan, S. P., and Gray, J. J. Fast, accurate antibody structure prediction from deep learning on massive set of natural antibodies. Nature Communications, 14 0 (1): 0 2389, April 2023. ISSN 2041-1723. doi:10.1038/s41467-023-38063-x

    work page doi:10.1038/s41467-023-38063-x 2023

  41. [41]

    Antibody design using LSTM based deep generative model from phage display library for affinity maturation

    Saka, K., Kakuzaki, T., Metsugi, S., Kashiwagi, D., Yoshida, K., Wada, M., Tsunoda, H., and Teramoto, R. Antibody design using LSTM based deep generative model from phage display library for affinity maturation. Scientific Reports, 11 0 (1): 0 5852, March 2021. ISSN 2045-2322. doi:10.1038/s41598-021-85274-7. URL https://www.nature.com/articles/s41598-021-...

    work page doi:10.1038/s41598-021-85274-7 2021

  42. [42]

    Z., Yasin, S

    Samsudin, E. Z., Yasin, S. M., Ruslan, N.-H., Abdullah, N. N., Noor, A. F. A., and Hair, A. F. A. Socioeconomic impacts of airborne and droplet-borne infectious diseases on industries: a systematic review. BMC Infectious Diseases, 24 0 (1): 0 93, January 2024. ISSN 1471-2334. doi:10.1186/s12879-024-08993-y. URL https://doi.org/10.1186/s12879-024-08993-y

    work page doi:10.1186/s12879-024-08993-y 2024

  43. [43]

    R., Bruun, T

    Shanker, V. R., Bruun, T. U. J., Hie, B. L., and Kim, P. S. Unsupervised evolution of protein and antibody complexes with a structure-informed language model. Science, 385 0 (6704): 0 46--53, July 2024. doi:10.1126/science.adk8946. URL https://www-science-org.ezproxy-prd.bodleian.ox.ac.uk/doi/10.1126/science.adk8946. Publisher: American Association for th...

    work page doi:10.1126/science.adk8946 2024

  44. [44]

    N., Gurev, S., Notin, P., Youssef, N., Rollins, N

    Thadani, N. N., Gurev, S., Notin, P., Youssef, N., Rollins, N. J., Ritter, D., Sander, C., Gal, Y., and Marks, D. S. Learning from prepandemic data to forecast viral escape. Nature, 622 0 (7984): 0 818--825, October 2023. ISSN 1476-4687. doi:10.1038/s41586-023-06617-0. URL https://www.nature.com/articles/s41586-023-06617-0. Publisher: Nature Publishing Group

    work page doi:10.1038/s41586-023-06617-0 2023

  45. [45]

    and Meek, K

    VanDyk, L. and Meek, K. Assembly of IgH CDR3 : mechanism, regulation, and influence on antibody diversity. International Reviews of Immunology, 8 0 (2-3): 0 123--133, 1992. ISSN 0883-0185. doi:10.3109/08830189209055568

    work page doi:10.3109/08830189209055568 1992

  46. [46]

    A., Garten, R

    Wan, H., Yang, H., Shore, D. A., Garten, R. J., Couzens, L., Gao, J., Jiang, L., Carney, P. J., Villanueva, J., Stevens, J., and Eichelberger, M. C. Structural characterization of a protective epitope spanning A ( H1N1 )pdm09 influenza virus neuraminidase monomers. Nature Communications, 6 0 (1): 0 6114, February 2015. ISSN 2041-1723. doi:10.1038/ncomms71...

    work page doi:10.1038/ncomms7114 2015

  47. [47]

    T., Yang, X

    Wang, G., Liu, X., Wang, K., Gao, Y., Li, G., Baptista-Hon, D. T., Yang, X. H., Xue, K., Tai, W. H., Jiang, Z., Cheng, L., Fok, M., Lau, J. Y.-N., Yang, S., Lu, L., Zhang, P., and Zhang, K. Deep-learning-enabled protein–protein interaction analysis for prediction of SARS - CoV -2 infectivity and variant evolution. Nature Medicine, 29 0 (8): 0 2007--2018, ...

    work page doi:10.1038/s41591-023-02483-5 2007

  48. [48]

    C., Muecksch, F., Rutkowska, M., Hoffmann, H.-H., Michailidis, E., Gaebler, C., Agudelo, M., Cho, A., Wang, Z., Gazumyan, A., Cipolla, M., Luchsinger, L., Hillyer, C

    Weisblum, Y., Schmidt, F., Zhang, F., DaSilva, J., Poston, D., Lorenzi, J. C., Muecksch, F., Rutkowska, M., Hoffmann, H.-H., Michailidis, E., Gaebler, C., Agudelo, M., Cho, A., Wang, Z., Gazumyan, A., Cipolla, M., Luchsinger, L., Hillyer, C. D., Caskey, M., Robbiani, D. F., Rice, C. M., Nussenzweig, M. C., Hatziioannou, T., and Bieniasz, P. D. Escape from...

    work page doi:10.7554/elife.61312 2020

  49. [49]

    AbAgIntPre : A deep learning method for predicting antibody-antigen interactions based on sequence information

    Yan Huang , Ziding Zhang , and Yuan Zhou . AbAgIntPre : A deep learning method for predicting antibody-antigen interactions based on sequence information. Frontiers in Immunology, 2022. doi:10.3389/fimmu.2022.1053617

    work page doi:10.3389/fimmu.2022.1053617 2022

  50. [50]

    and Weiner, L

    Zahavi, D. and Weiner, L. Monoclonal Antibodies in Cancer Therapy . Antibodies, 9 0 (3): 0 34, July 2020. ISSN 2073-4468. doi:10.3390/antib9030034. URL https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7551545/

    work page doi:10.3390/antib9030034 2020

  51. [51]

    E., Patani, H., Danson, A

    Zambaldi, V., La, D., Chu, A. E., Patani, H., Danson, A. E., Kwan, T. O. C., Frerix, T., Schneider, R. G., Saxton, D., Thillaisundaram, A., Wu, Z., Moraes, I., Lange, O., Papa, E., Stanton, G., Martin, V., Singh, S., Wong, L. H., Bates, R., Kohl, S. A., Abramson, J., Senior, A. W., Alguel, Y., Wu, M. Y., Aspalter, I. M., Bentley, K., Bauer, D. L. V., Cher...

    work page arXiv 2024