EUVIMEDOpdag EUVIMED
Open access · CC BY-NC-ND 4.0

Ankh‐Score Produces Better Sequence Alignments Than AlphaFold3

Julia Malec, Karina Rusen, G Brian Golding, Lucian Ilie

Proteins: Structure, Function, and Bioinformatics · 2026

DOI: 10.1002/prot.70143 ↗

At a glance

Journal article in Proteins: Structure, Function, and Bioinformatics, 2026. Written by Julia Malec and 3 co-authors. Institution: Department of Computer Science, University of Western Ontario, London, Ontario, Canada. Major MEDLINE topics: Sequence Alignment, Software, Proteins, Computational Biology. Cited 2 times so far (Crossref); 36 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery, Natural Sciences and Engineering Research Council of Canada.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Protein sequence alignment is one of the most fundamental procedures in bioinformatics. Due to its many downstream applications, improvements to this procedure are of great importance. We consider two revolutionary concepts that emerged recently as candidates for improving the state‐of‐the‐art alignment methods: AlphaFold and protein language models such as Ankh, ProtT5, or ESM‐C. Alignment improvements can come from the structural alignment of AlphaFold‐predicted structures or the scoring based on the similarity of protein embeddings produced by the protein language models. Thorough comparison on many domains from BAliBASE and CDD demonstrates that the Ankh‐score method produces much better sequence alignments than the structural alignments using US‐align of AlphaFold3‐predicted structures. Both are better than the traditional method using BLOSUM matrices. This suggests that Ankh embeddings may possess certain information that is not available in the AlphaFold3‐predicted structures. The alignment software is freely available as a web server at e‐score.csd.uwo.ca and as source code at github.com/lucian‐ilie/E‐score .

Subjects

MeSH terms (MEDLINE)

Sequence AlignmentSoftwareProteinsComputational BiologyAlgorithmsSequence Analysis, ProteinModels, MolecularAmino Acid SequenceDatabases, ProteinProtein Folding

Author keywords

AlphaFoldAnkhUS‐alignprotein embeddingprotein language modelprotein sequence alignment

Substances

Proteins

Authors and institutions

  • Department of Computer Science, University of Western Ontario, London, Ontario, Canada.
  • School of Rehabilitation Science, McMaster University, Hamilton, Ontario, Canada.
  • Department of Biology, McMaster University, Hamilton, Ontario, Canada.

Funding

  • Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery
  • Natural Sciences and Engineering Research Council of Canada

Cite

APA

Malec, J., Rusen, K., Golding, G. B., & Ilie, L. (2026). Ankh‐Score Produces Better Sequence Alignments Than AlphaFold3. Proteins: Structure, Function, and Bioinformatics. https://doi.org/10.1002/prot.70143

Vancouver

Malec J, Rusen K, Golding GB, Ilie L. Ankh‐Score Produces Better Sequence Alignments Than AlphaFold3. Proteins: Structure, Function, and Bioinformatics. 2026. doi:10.1002/prot.70143

BibTeX
@article{Malec2026,
  author = {Malec, Julia and Rusen, Karina and Golding, G Brian and Ilie, Lucian},
  title = {Ankh‐Score Produces Better Sequence Alignments Than AlphaFold3},
  journal = {Proteins: Structure, Function, and Bioinformatics},
  year = {2026},
  doi = {10.1002/prot.70143}
}
Start for free →