Journal article · 2022 · Open access

Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants

Rui Ming Yin, Brandon Y. Feng, Amitabh Varshney, Brian G. Pierce

Protein Science, 31(8), e4379 · Published 13 July 2022 · DOI 10.1002/pro.4379

Open PDFView at the publisherCite this paper

In brief

“Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants” is a 2022 journal article by Rui Ming Yin and 3 co-authors, published in Protein Science. OpenAlex counts 375 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at Protein Science.

Citations
375
Most cited in
2024 (121)
Field-weighted impact
19.75
References
81
Authors
4

Abstract

High-resolution experimental structural determination of protein-protein interactions has led to valuable mechanistic insights, yet due to the massive number of interactions and experimental limitations there is a need for computational methods that can accurately model their structures. Here we explore the use of the recently developed deep learning method, AlphaFold, to predict structures of protein complexes from sequence. With a benchmark of 152 diverse heterodimeric protein complexes, multiple implementations and parameters of AlphaFold were tested for accuracy. Remarkably, many cases (43%) had near-native models (medium or high critical assessment of predicted interactions accuracy) generated as top-ranked predictions by AlphaFold, greatly surpassing the performance of unbound protein-protein docking (9% success rate for near-native top-ranked models), however AlphaFold modeling of antibody-antigen complexes within our set was unsuccessful. We identified sequence and structural features associated with lack of AlphaFold success, and we also investigated the impact of multiple sequence alignment input. Benchmarking of a multimer-optimized version of AlphaFold (AlphaFold-Multimer) with a set of recently released antibody-antigen structures confirmed a low rate of success for antibody-antigen complexes (11% success), and we found that T cell receptor-antigen complexes are likewise not accurately modeled by that algorithm, showing that adaptive immune recognition poses a challenge for the current AlphaFold algorithm and model. Overall, our study demonstrates that end-to-end deep learning can accurately model many transient protein complexes, and highlights areas of improvement for future developments to reliably model any protein-protein interaction of interest.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

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

MLA 9

Yin, Rui Ming, et al. “Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants.” Protein Science, vol. 31, no. 8, 2022, p. e4379. https://doi.org/10.1002/pro.4379.

Chicago

Yin, Rui Ming, Brandon Y. Feng, Amitabh Varshney, and Brian G. Pierce. 2022. “Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants.” Protein Science 31 (8): e4379. https://doi.org/10.1002/pro.4379.

Harvard

Yin, R. M. et al. (2022) ‘Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants’, Protein Science, 31(8), p. e4379. doi:10.1002/pro.4379.

IEEE

R. M. Yin, B. Y. Feng, A. Varshney, and B. G. Pierce, “Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants,” Protein Science, vol. 31, no. 8, p. e4379, 2022, doi: 10.1002/pro.4379.

BibTeX

@article{yin2022benchmarking,
  title     = {{Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants}},
  author    = {Yin, Rui Ming and Feng, Brandon Y. and Varshney, Amitabh and Pierce, Brian G.},
  journal   = {Protein Science},
  year      = {2022},
  volume    = {31},
  number    = {8},
  pages     = {e4379},
  doi       = {10.1002/pro.4379},
  url       = {https://doi.org/10.1002/pro.4379}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201311
20222222
20238585
2024121121
20257575
20267171

Its field-weighted citation impact is 19.75: it has been cited 19.75 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics

  • AlphaFold
  • AlphaFold-Multimer
  • protein complex structure prediction
  • protein-protein interaction
  • immune complexes
  • protein-protein docking
  • benchmarking
  • multiple sequence alignment

Work with this paper

Most-cited papers in Biochemistry, Genetics and Molecular Biology

All highly cited Biochemistry, Genetics and Molecular Biology papers

Questions about this paper

How do I cite this paper in APA style?

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

How many times has this paper been cited?

375 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 Protein Science: sign in and open the PDF from this page.

Who wrote this paper?

Rui Ming Yin, Brandon Y. Feng, Amitabh Varshney, Brian G. Pierce.

What is the DOI of this paper?

10.1002/pro.4379, permanently at https://doi.org/10.1002/pro.4379. 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.