Biophysical cartography of the native and human-engineered antibody landscapes quantifies the plasticity of antibody developability
Open accessPublished version of a preprint
Abstract
Designing effective monoclonal antibody (mAb) therapeutics faces a multi-parameter optimization challenge known as "developability", which reflects an antibody's ability to progress through development stages based on its physicochemical properties. While natural antibodies may provide valuable guidance for mAb selection, we lack a comprehensive understanding of natural developability parameter (DP) plasticity (redundancy, predictability, sensitivity) and how the DP landscapes of human-engineered and natural antibodies relate to one another. These gaps hinder fundamental developability profile cartography. To chart natural and engineered DP landscapes, we computed 40 sequence- and 46 structure-based DPs of over two million native and human-engineered single-chain antibody sequences. We find lower redundancy among structure-based compared to sequence-based DPs. Sequence DP sensitivity to single amino acid substitutions varied by antibody region and DP, and structure DP values varied across the conformational ensemble of antibody structures. We show that sequence DPs are more predictable than structure-based ones across different machine-learning tasks and embeddings, indicating a constrained sequence-based design space. Human-engineered antibodies localize within the developability and sequence landscapes of natural antibodies, suggesting that human-engineered antibodies explore mere subspaces of the natural one. Our work quantifies the plasticity of antibody developability, providing a fundamental resource for multi-parameter therapeutic mAb design.
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.
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
Highly accurate protein structure prediction with AlphaFold
Jumper, J., Evans, R., Pritzel, A., Green, T., Figurnov, M., Ronneberger, O., Tunyasuvunakool, K., Bates, R., Žídek, A., Potapenko, A., et al. (2021) · Nature · doi:10.1038/s41586-021-03819-2 · Cited by 43,764 · see citing works
Protein complex prediction with AlphaFold-Multimer
Evans, R., O’Neill, M., Pritzel, A., Antropova, N., Senior, A., Green, T., Žídek, A., Bates, R., Blackwell, S., Yim, J., et al. (2021) · doi:10.1101/2021.10.04.463034 · Cited by 3,808 · see citing works
Unified rational protein engineering with sequence-based deep representation learning
Alley, E. C., Khimulya, G., Biswas, S., AlQuraishi, M., & Church, G. M. (2019) · Nature Methods · doi:10.1038/s41592-019-0598-1 · Cited by 1,131 · cited 2× · see citing works
“(ii ) The second embedding is an amino acid sequence encoding output produced by the protein language model (PLM) ESM-1v, which generates large semantically-rich digital representations of antibodies (high-dimensional embedding — order of magnitude ≈ 10 3 ) 74 – 76 .”
Large language models generate functional protein sequences across diverse families
Madani, A., Krause, B., Greene, E. R., Subramanian, S., Mohr, B. P., Holton, J. M., Olmos, J. L., Xiong, C., Sun, Z. Z., Socher, R., et al. (2023) · Nature Biotechnology · doi:10.1038/s41587-022-01618-2 · Cited by 1,078 · cited 2× · see citing works
“(ii ) The second embedding is an amino acid sequence encoding output produced by the protein language model (PLM) ESM-1v, which generates large semantically-rich digital representations of antibodies (high-dimensional embedding — order of magnitude ≈ 10 3 ) 74 – 76 .”
Advances in protein structure prediction and design
Kuhlman, B., & Bradley, P. (2019) · Nature Reviews Molecular Cell Biology · doi:10.1038/s41580-019-0163-x · Cited by 806 · see citing works
Biophysical properties of the clinical-stage antibody landscape
Jain, T., Sun, T., Durand, S., Hall, A., Houston, N. R., Nett, J. H., Sharkey, B., Bobrowicz, B., Caffry, I., Yu, Y., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1616408114 · Cited by 629 · cited 4× · see citing works
“Traditionally,developabilityscreeningisperformedthroughaseriesof laborious in vitro assays 17,22,23 .”
InfluentialProGen2: Exploring the boundaries of protein language models
Nijkamp, E., Ruffolo, J. A., Weinstein, E. N., Naik, N., & Madani, A. (2023) · Cell Systems · doi:10.1016/j.cels.2023.10.002 · Cited by 480 · see citing works
Mason, D. M., Friedensohn, S., Weber, C. R., Jordi, C., Wagner, B., Meng, S. M., Ehling, R. A., Bonati, L., Dahinden, J., Gainza, P., et al. (2021) · Nature Biomedical Engineering · doi:10.1038/s41551-021-00699-9 · Cited by 308 · see citing works
Kovaltsuk, A., Leem, J., Kelm, S., Snowden, J., Deane, C. M., & Krawczyk, K. (2018) · The Journal of Immunology · doi:10.4049/jimmunol.1800708 · Cited by 247 · see citing works
Self-citationComputational approaches to therapeutic antibody design: established methods and emerging trends
Norman, R. A., Ambrosetti, F., Bonvin, A. M. J. J., Colwell, L. J., Kelm, S., Kumar, S., & Krawczyk, K. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbz095 · Cited by 219 · cited 2× · see citing works
“These fi ndings emphasize the signi fi cance of structural consideration for therapeutic antibody design 3,8,25,97,98 .”
Self-citationThera-SAbDab: the therapeutic structural antibody database
Raybould, M. I. J., Marks, C., Lewis, A. P., Shi, J., Bujotzek, A., Taddese, B., & Deane, C. M. (2020) · Nucleic Acids Research · doi:10.1093/nar/gkz827 · Cited by 199 · cited 1× · see citing works
“A total of 782 therapeutic antibody sequences belonging to the “ whole mAb ” format were obtained from TheraSAbDAb as per July 2021 139 .”
Humanization of antibodies using a machine learning approach on large-scale repertoire data
Marks, C., Hummer, A. M., Chin, M., & Deane, C. M. (2021) · Bioinformatics · doi:10.1093/bioinformatics/btab434 · Cited by 124 · see citing works
In silico proof of principle of machine learning-based antibody design at unconstrained scale
Akbar, R., Robert, P. A., Weber, C. R., Widrich, M., Frank, R., Pavlović, M., Scheffer, L., Chernigovskaya, M., Snapkov, I., Slabodkin, A., et al. (2022) · mAbs · doi:10.1080/19420862.2022.2031482 · Cited by 94 · see citing works
Looking for therapeutic antibodies in next generation sequencing repositories
Krawczyk, K., Raybould, M., Kovaltsuk, A., & Deane, C. M. (2019) · doi:10.1101/572958 · Cited by 29 · see citing works
Self-citation
Flagged first, then by citations
- Authors
- Bashour, H., Smorodina, E., Pariset, M., Zhong, J., Akbar, R., Chernigovskaya, M., Lê Quý, K., Snapkow, I., Rawat, P., Krawczyk, K., Sandve, G. K., Gutierrez-Marcos, J., Gutierrez, D. N.-Z., Andersen, J. T., & Greiff, V.
- Affiliations
- Oslo University Hospital (NO)
- Norwegian Institute of Public Health (NO)
- University of Oslo (NO)
- Corresponding author
- Bashour, Habib
- Greiff, Victor
- ORCID
- Venue
- Communications Biology
- Published
- 2024-07-31
- Volume
- 7
- Issue
- 1
- Pages
- 922-922
- ISSN
- 2399-3642 (ISSN-L)
- PMC
- PMC11291509
- OpenAlex
- W4401165032
- Cited by
- 32
- References
- 14
- Citations by year
- 2026: 12 · 2025: 14 · 2024: 6
- FWCI
- 8.15
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Communications Biology (publishedVersion, cc-by-nc-nd)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Warwick Research Archive Portal (University of Warwick) (acceptedVersion, cc-by-nc-nd)
- Duo Research Archive (University of Oslo) (acceptedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Leona M. and Harry B. Helmsley Charitable Trust (#2019PG-T1D011)
- Stiftelsen Kristian Gerhard Jebsen (SKGJ‐MED‐017)
- Università degli Studi di Siena
- European Federation of Pharmaceutical Industries and Associations
- European Commission (101007799, HORIZON2020, 825821)
- Norges Forskningsråd (331890, 311341, 300 740)
- Biotechnology and Biological Sciences Research Council (BB/V011065/1)
- 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
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
- Keywords
- antibody developability, therapeutic monoclonal antibodies, natural antibodies, single-chain antibody
- MeSH terms
- Antibodies, Monoclonal, Humans, Protein Conformation, Protein Engineering, Single-Chain Antibodies
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
