Identification of similarity between protein sequences is an important component for the assignment of function. With ever-growing databases of genome sequence, this becomes an increasing challenge, and especially in the detection of relationships between distantly related sequences, which is frequently an issue with euglenids. The introduction of artificial intelligence tools to the prediction of protein structure has been, without exaggeration, revolutionary. In particular, AlphaFold3 (AF3), the latest iteration of the AI predictor from DeepMind, a Google subsidiary, offers a potent combination of speed, accuracy, and ease-of-use, all free of charge. Here I will describe a basic workflow for the detection of low similarity between proteins, that is otherwise cryptic, using AF3, discuss how to interpret the predictions, and highlight examples of bizarre predictions or hallucinations.

Biology Centre Czech Academy of Sciences Institute of Parasitology České Budějovice Czech Republic

School of Life Sciences University of Dundee Dundee UK

Zobrazit více v PubMed

Williamson K, Eme L, Baños H et al (2025) A robustly rooted tree of eukaryotes reveals their excavate ancestry. Nature 640(8060):974–981 PubMed DOI

Krissinel E (2007) On the relationship between sequence and structure similarities in proteomics. Bioinformatics 23(6):717–723. https://doi.org/10.1093/bioinformatics/btm006 . Epub 2007 Jan 22. PMID: 17242029 PubMed DOI

Chothia C, Lesk AM (1986) The relation between the divergence of sequence and structure in proteins. EMBO J 5(4):823–826 PubMed DOI PMC

Ramachandran GN, Ramakrishnan C, Sasisekharan V (1963) Stereochemistry of polypeptide chain configurations. J Mol Biol 7:95–99 PubMed DOI

Kyte J, Doolittle RF (1982) A simple method for displaying the hydropathic character of a protein. J Mol Biol 157(1):105–132 PubMed DOI

Powell HR, Islam SA, David A et al (2025) Phyre2.2: a community resource for template-based protein structure prediction. J Mol Biol 23:168960 DOI

Abramson J, Adler J, Dunger J et al (2024) Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630(8016):493–500 PubMed DOI PMC

Wee J, Wei GW. Benchmarking AlphaFold3's protein-protein complex accuracy and machine learning prediction reliability for binding free energy changes upon mutation. ArXiv [Preprint]. 2024 6:arXiv:2406.03979v1

Mifsud JCO, Lytras S, Oliver MR et al (2024) Mapping glycoprotein structure reveals Flaviviridae evolutionary history. Nature 633(8030):695–703 PubMed DOI PMC

Zhang Y, Skolnick J (2004) Scoring function for automated assessment of protein structure template quality. Proteins 57(4):702–710 PubMed DOI

Xu J, Zhang Y (2010) How significant is a protein structure similarity with TM-score = 0.5? Bioinformatics 26(7):889–895 PubMed DOI PMC

Upla P, Kim SJ, Sampathkumar P et al (2017) Molecular architecture of the major membrane ring component of the nuclear pore complex. Structure 25(3):434–445 PubMed DOI PMC

Butterfield ER, Obado SO, Scutts SR et al (2024) A lineage-specific protein network at the trypanosome nuclear envelope. Nucleus 15(1):2310452 PubMed DOI PMC

Meng EC, Goddard TD, Pettersen EF et al (2023) UCSF ChimeraX: tools for structure building and analysis. Protein Sci 32(11):e4792 PubMed DOI PMC

Mirdita M, Schütze K, Moriwaki Y et al (2022) ColabFold: making protein folding accessible to all. Nat Methods 19(6):679–682 PubMed DOI PMC

https://alphafold.com/

van Kempen M, Kim SS, Tumescheit C et al (2024) Fast and accurate protein structure search with FoldSeek. Nat Biotechnol 42(2):243–246 PubMed DOI

Elfmann C, Stülke J (2025) Cutting-edge tools for structural biology: bringing AlphaFold to the people. Trends Microbiol 33:S0966-842X(25)00110–6 PubMed DOI

https://www.ebi.ac.uk/training/online/courses/alphafold/

Padilla-Mejia NE, Koreny L, Holden J et al (2021) A hub-and-spoke nuclear lamina architecture in trypanosomes. J Cell Sci 134(12):jcs251264 PubMed DOI PMC