Journal article · 2026 · Open access
Evaluating deep learning based structure prediction methods on antibody–antigen complexes
Bioinformatics, 42(4) · Published 21 March 2026 · DOI 10.1093/bioinformatics/btag136
In brief
“Evaluating deep learning based structure prediction methods on antibody–antigen complexes” is a 2026 journal article by Samuel Fromm and 2 co-authors, published in Bioinformatics. OpenAlex counts 33 citations as of 19 November 2026, which puts it in the top 5% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Bioinformatics.
- Citations
- 33
- Most cited in
- 2026 (30)
- Field-weighted impact
- 33.78
- References
- 27
- Authors
- 3
Abstract
MOTIVATION: AlphaFold2 significantly improved the prediction of protein complex structures. However, its accuracy is lower for interactions without coevolutionary signals, such as host-pathogen and antibody-antigen interactions. Two strategies have been developed to address this limitation: massive sampling and replacing the evoformer with the pairformer, which does not rely on coevolution, as introduced in AlphaFold3, thereby enabling more structural reasoning by the network. RESULTS: In this study, we benchmark structure prediction methods on unseen antibody-antigen complexes. We found that increased sampling improves the chances of generating a correct protein model, roughly in a log-linear manner. However, the internal quality estimates by AlphaFold often cannot identify the best predicted structures for each target, resulting in a significant loss of performance for the top-ranked protein model compared with the best model. For all methods, a significant challenge remains the identification of the best model. We also show that AlphaFold3 outperforms AlphaFold2, Boltz-1, and Chai-1. Furthermore, AlphaFold3 performance declines significantly for complexes that lack structural similarity to the training set, indicating that it has to some extent learned to detect remote structural similarities. AVAILABILITY AND IMPLEMENTATION: All code is available from github.com/samuelfromm/abag-benchmark-set/ and all data from DOI: 10.5281/zenodo.17978681. The latter repository also contains the code.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Fromm, S., Ludaic, M., & Elofsson, A. (2026). Evaluating deep learning based structure prediction methods on antibody–antigen complexes. Bioinformatics, 42(4). https://doi.org/10.1093/bioinformatics/btag136
MLA 9
Fromm, Samuel, et al. “Evaluating deep learning based structure prediction methods on antibody–antigen complexes.” Bioinformatics, vol. 42, no. 4, 2026. https://doi.org/10.1093/bioinformatics/btag136.
Chicago
Fromm, Samuel, Marko Ludaic, and Arne Elofsson. 2026. “Evaluating deep learning based structure prediction methods on antibody–antigen complexes.” Bioinformatics 42 (4). https://doi.org/10.1093/bioinformatics/btag136.
Harvard
Fromm, S., Ludaic, M. and Elofsson, A. (2026) ‘Evaluating deep learning based structure prediction methods on antibody–antigen complexes’, Bioinformatics, 42(4). doi:10.1093/bioinformatics/btag136.
IEEE
S. Fromm, M. Ludaic, and A. Elofsson, “Evaluating deep learning based structure prediction methods on antibody–antigen complexes,” Bioinformatics, vol. 42, no. 4, 2026, doi: 10.1093/bioinformatics/btag136.
BibTeX
@article{fromm2026evaluating,
title = {{Evaluating deep learning based structure prediction methods on antibody–antigen complexes}},
author = {Fromm, Samuel and Ludaic, Marko and Elofsson, Arne},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {4},
doi = {10.1093/bioinformatics/btag136},
url = {https://doi.org/10.1093/bioinformatics/btag136}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
- immune complexes
- protein structure prediction
- AlphaFold2
- AlphaFold3
- benchmarking
- sampling strategy
- host-pathogen interaction
- model ranking
Work with this paper
Most-cited papers in Biochemistry, Genetics and Molecular Biology
- PROTEIN MEASUREMENT WITH THE FOLIN PHENOL REAGENTOliver H. Lowry, NiraJ. Rosebrough, A. Lewis Farr and 1 more · Journal of Biological Chemistry · 1951 · 316,470 citations
- A Rapid and Sensitive Method for the Quantitation of Microgram Quantities of Protein Utilizing the Principle of Protein-Dye BindingM Bradford · Analytical Biochemistry · 1976 · 256,780 citations
- Analysis of Relative Gene Expression Data Using Real-Time Quantitative PCR and the 2−ΔΔCT MethodKenneth J. Livak, Thomas D. Schmittgen · Methods · 2001 · 184,418 citations
- Molecular Cloning: A Laboratory ManualJoseph Sambrook, Elisabeth Fritsch, Tom Maniatis · UCLA - Biblioteca de Ciencias de la Salud · 1989 · 133,493 citations
- Basic Local Alignment Search ToolStephen F. Altschul, Warren R. Gish, Webb Miller and 2 more · Journal of Molecular Biology · 1990 · 100,529 citations
All highly cited Biochemistry, Genetics and Molecular Biology papers
Questions about this paper
How do I cite this paper in APA style?
Fromm, S., Ludaic, M., & Elofsson, A. (2026). Evaluating deep learning based structure prediction methods on antibody–antigen complexes. Bioinformatics, 42(4). https://doi.org/10.1093/bioinformatics/btag136
How many times has this paper been cited?
33 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Bioinformatics: sign in and open the full text from this page.
Who wrote this paper?
Samuel Fromm, Marko Ludaic, Arne Elofsson.
What is the DOI of this paper?
10.1093/bioinformatics/btag136, permanently at https://doi.org/10.1093/bioinformatics/btag136. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.