CoChat
Sign Up
Cited by 5Machine Learning in BioinformaticsGenomics and Phylogenetic StudiesProtein Structure and Dynamics

The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.

Evaluating the significance of embedding-based protein sequence alignment with clustering and double dynamic programming for remote homology

Open access
Spicer, Robert, Raychawdhary, Nilanjana, Danwada, Shivaram, Udomprasert, Priscilla, Seals, Cheryl, Bhattacharya, Sutanu·2025·Scientific Reports
DOI 10.1038/s41598-025-23319-xPMC PMC12612178

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Accurate detection of protein sequence homology is essential for understanding evolutionary relationships and predicting protein functions, particularly for detecting remote homology in the "twilight zone" (20-35% sequence similarity), where traditional sequence alignment methods often fail. Recent studies show that embeddings from protein language models (pLM) can improve remote homology detection over traditional methods. Alignment-based approaches, such as those combining pLMs with dynamic programming alignment, further improve performance but often suffer from noise in the resulting similarity matrices. To address this, we evaluate a newly developed embedding-based sequence alignment approach that refines residue-level embedding similarity using K-means clustering and double dynamic programming (DDP). We show that the incorporation of clustering and DDP consistently contributes to the improved performance in detecting remote homology. Experimental results demonstrate that our approach outperforms both traditional sequence-based methods and state-of-the-art embedding-based approaches on several benchmarks. Our study illustrates embedding-based alignment refined with clustering and DDP offers a powerful approach for identifying remote homology, with potential to evolve further as pLMs continue to advance.

Overview

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-025-23319-x

Cites

10 of 10 references verified0 citation errors · 0 not checkable

Statistics

Verification

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.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 53

  1. Altschul, S. F., Gish, W., Miller, W., Myers, E. W. & Lipman, D. J. Basic local alignment search tool. J. Mol. Biol. 215, 403–410 (1990). · DOI · Paper page
  2. Finn, R. D., Clements, J. & Eddy, S. R. HMMER web server: interactive sequence similarity searching. Nucleic Acids Res. 39, W29–W37 (2011). · DOI · Paper page
  3. Ashburner, M. et al. Gene ontology: tool for the unification of biology. Nat. Genet. 25, 25–29 (2000). · DOI · Paper page
  4. Finn, R. D. et al. The Pfam protein families database. Nucleic Acids Res. 36, D281–D288 (2008). · DOI
  5. Blum, M. et al. The interpro protein families and domains database: 20 years on. Nucleic Acids Res. 49, D344–D354 (2021). · DOI · Paper page
  6. Huerta-Cepas, J. et al. EggNOG 5.0: a hierarchical, functionally and phylogenetically annotated orthology resource based on 5090 organisms and 2502 viruses. Nucleic Acids Res. 47, D309–D314 (2019). · DOI
  7. Loewenstein, Y. et al. Protein function annotation by homology-based inference. Genome Biol. 10, 207 (2009). · DOI
  8. Greener, J. G., Kandathil, S. M. & Jones, D. T. Deep learning extends de Novo protein modelling coverage of genomes using iteratively predicted structural constraints. Nat. Commun. 10, 3977 (2019). · DOI · Paper page
  9. Senior, A. W. et al. Improved protein structure prediction using potentials from deep learning. Nature 577, 706–710 (2020). · DOI · Paper page
  10. Baker, K., Hughes, N. & Bhattacharya, S. An interactive visualization tool for educational outreach in protein contact map overlap analysis. Front Bioinforma 4, (2024). · DOI
  11. Bhattacharya, S., Roche, R., Moussad, B. & Bhattacharya, D. DisCovER: distance- and orientation-based covariational Threading for weakly homologous proteins. Proteins Struct. Funct. Bioinforma. 90, 579–588 (2022). · DOI · Paper page
  12. Bhattacharya, S. & Bhattacharya, D. Evaluating the significance of contact maps in low-homology protein modeling using contact-assisted Threading. Sci. Rep. 10, 2908 (2020). · DOI
  13. Bhattacharya, S. & Bhattacharya, D. Does inclusion of residue-residue contact information boost protein threading? Proteins Struct. Funct. Bioinforma. 87, 596–606 (2019). · DOI
  14. Bhattacharya, S., Roche, R., Shuvo, M. H. & Bhattacharya, D. Recent advances in protein homology detection propelled by Inter-Residue interaction map Threading. Front Mol. Biosci. 8, (2021). · DOI
  15. Shin, J. E. et al. Protein design and variant prediction using autoregressive generative models. Nat. Commun. 12, 2403 (2021). · DOI · Paper page
  16. Rost, B. Twilight zone of protein sequence alignments. Protein Eng. Des. Sel. 12, 85–94 (1999). · DOI · Paper page
  17. Zhang, Y. & Skolnick, J. TM-align: a protein structure alignment algorithm based on the TM-score. Nucleic Acids Res. 33, 2302–2309 (2005). · DOI · Paper page
  18. Holm, L., Kääriäinen, S., Wilton, C. & Plewczynski, D. Using Dali for structural comparison of proteins. Curr. Protoc. Bioinforma. 14, 551–5524 (2006). · DOI
  19. Zhu, J., Weng, Z. & FAST A novel protein structure alignment algorithm. Proteins Struct. Funct. Bioinforma. 58, 618–627 (2005). · DOI
  20. Ortiz, A. R., Strauss, C. E. M. & Olmea, O. MAMMOTH (Matching molecular models obtained from theory): an automated method for model comparison. Protein Sci. 11, 2606–2621 (2002). · DOI
  21. Mirdita, M. et al. ColabFold: making protein folding accessible to all. Nat. Methods. 19, 679–682 (2022). · DOI · Paper page
  22. Varadi, M. et al. AlphaFold protein structure database: massively expanding the structural coverage of protein-sequence space with high-accuracy models. Nucleic Acids Res. 50, D439–D444 (2022). · DOI · Paper page
  23. Richardson, L. et al. MGnify: the Microbiome sequence data analysis resource in 2023. Nucleic Acids Res. 51, D753–D759 (2023). · DOI
  24. Nordberg, H. et al. The genome portal of the department of energy joint genome institute: 2014 updates. Nucleic Acids Res. 42, D26–D31 (2014). · DOI
  25. Hamamsy, T. et al. Protein remote homology detection and structural alignment using deep learning. Nat. Biotechnol. 42, 975–985 (2024). · DOI
  26. Heinzinger, M. et al. Contrastive learning on protein embeddings enlightens midnight zone. NAR Genomics Bioinforma. 4, lqac043 (2022). · DOI
  27. Hie, B. L., Yang, K. K. & Kim, P. S. Evolutionary velocity with protein Language models predicts evolutionary dynamics of diverse proteins. Cell. Syst. 13, 274–285e6 (2022). · DOI
  28. Schütze, K., Heinzinger, M., Steinegger, M. & Rost, B. Nearest neighbor search on embeddings rapidly identifies distant protein relations. Front Bioinforma 2, (2022). · DOI
  29. Sillitoe, I. et al. CATH: increased structural coverage of functional space. Nucleic Acids Res. 49, D266–D273 (2021). · DOI · Paper page
  30. Pantolini, L. et al. Embedding-based alignment: combining protein Language models with dynamic programming alignment to detect structural similarities in the twilight-zone. Bioinformatics 40, btad786 (2024). · DOI · Paper page
  31. Morton, J. T. et al. Protein Structural Alignments From Sequence. 11.03.365932 Preprint at (2020). https://doi.org/10.1101/2020.11.03.365932 (2020). · DOI
  32. Iovino, B. G. & Ye, Y. Protein embedding based alignment. BMC Bioinform. 25, 85 (2024). · DOI · Paper page
  33. Wang, G. & Dunbrack, R. L. Jr. PISCES: a protein sequence culling server. Bioinformatics 19, 1589–1591 (2003). · DOI
  34. Heinzinger, M. et al. Bilingual Language model for protein sequence and structure. NAR Genomics Bioinforma. 6, lqae150 (2024). · DOI · Paper page
  35. Rives, A. et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl. Acad. Sci. 118, e2016239118 (2021). · DOI · Paper page
  36. Vaswani, A. et al. Curran Associates Inc., Red Hook, NY, USA,. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems 6000–6010 (2017).
  37. Suzek, B. E. et al. UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches. Bioinformatics 31, 926–932 (2015). · DOI · Paper page
  38. Needleman, S. B. & Wunsch, C. D. A general method applicable to the search for similarities in the amino acid sequence of two proteins. J. Mol. Biol. 48, 443–453 (1970). · DOI · Paper page
  39. Bielińska-Wąż, D., Wąż, P. & Błaczkowska, A. 20D-Dynamic representation of protein sequences combined with K-means clustering. (2025). https://doi.org/10.2174/0113862073359729250220131623 · DOI
  40. Taylor, W. R. Protein structure comparison using iterated double dynamic programming. Protein Sci. 8, 654–665 (1999). · DOI
  41. Ovchinnikov, S. et al. Protein structure determination using metagenome sequence data. Science 355, 294–298 (2017). · DOI · Paper page
  42. Steinegger, M. et al. HH-suite3 for fast remote homology detection and deep protein annotation. BMC Bioinform. 20, 473 (2019). · DOI · Paper page
  43. Kaminski, K., Ludwiczak, J., Pawlicki, K., Alva, V. & Dunin-Horkawicz, S. pLM-BLAST: distant homology detection based on direct comparison of sequence representations from protein Language models. Bioinformatics 39, btad579 (2023). · DOI
  44. Henikoff, S. & Henikoff, J. G. Amino acid substitution matrices from protein blocks. Proc. Natl. Acad. Sci. 89, 10915–10919 (1992). · DOI · Paper page
  45. Steinegger, M. & Söding, J. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat. Biotechnol. 35, 1026–1028 (2017). · DOI · Paper page
  46. Mizuguchi, K., Deane, C. M., Blundell, T. L. & Overington, J. P. HOMSTRAD: A database of protein structure alignments for homologous families. Protein Sci. 7, 2469–2471 (1998). · DOI
  47. Holm, L. & Sander, C. Protein structure comparison by alignment of distance matrices. J. Mol. Biol. 233, 123–138 (1993). · DOI · Paper page
  48. Wang, S., Zheng, W. M. & CLePAPS Fast pair alignment of protein structures based on conformational letters. J. Bioinform Comput. Biol. 06, 347–366 (2008). · DOI
  49. Liu, W. et al. PLMSearch: protein Language model powers accurate and fast sequence search for remote homology. Nat. Commun. 15, 2775 (2024). · DOI · Paper page
  50. Hong, L. et al. Fast, sensitive detection of protein homologs using deep dense retrieval. Nat. Biotechnol. 43, 983–995 (2025). · DOI
  51. Nie, L. et al. Unveiling the black box of PLMs with semantic anchors: towards interpretable neural semantic parsing. Proc. AAAI Conf. Artif. Intell. 37, 13400–13408 (2023).
  52. Zhang, B. et al. Multi-label subcellular localization predict based on cluster balanced subspace partitioning method and multi-class contrastive representation learning. IEEE J. Biomed. Health Inf. 1–14. https://doi.org/10.1109/JBHI.2025.3537284 (2025). · DOI
  53. Li, X. et al. Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyond. Knowl. Inf. Syst. 64, 3197–3234 (2022). · DOI

Metadata

Authors
Spicer, R., Raychawdhary, N., Danwada, S., Udomprasert, P., Seals, C., & Bhattacharya, S.
Affiliations
  • Auburn University at Montgomery (US)
  • Auburn University (US)
Corresponding author
Bhattacharya, Sutanu
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2025-11-12
Volume
15
Issue
1
Pages
39601-39601
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-025-23319-x
PMC
PMC12612178
OpenAlex
W4416148377
Cited by
5
References
10
Citations by year
2026: 5
FWCI
1.50
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by-nc-nd)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Division of Information and Intelligent Systems (2435093)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
Keywords
remote homology detection, protein sequence alignment, protein language models, K-means clustering, twilight zone, sequence similarity, protein function prediction
MeSH terms
Dynamic Programming, Algorithms, Amino Acid Sequence, Proteins, Cluster Analysis, Sequence Alignment, Sequence Homology, Amino Acid, Computational Biology, Sequence Analysis, Protein

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