SSAlign: fast and sensitive protein structure search at scale

Abstract

Motivation: Predicted protein structure resources now contain hundreds of millions of models, turning structural comparison from a pairwise alignment task into a database-scale retrieval problem. Exhaustive structural aligners are computationally impractical at this scale, whereas fast structural-alphabet searches may discard remote or low-complexity homologs during prefiltering. Database-scale search therefore requires methods that combine rapid retrieval with sensitivity to global structural similarity.

Results: We present SSAlign, a protein structure search method that integrates SaProt sequence-structure embeddings, entropy-reduced dense retrieval, an SS-score predictor, and two-stage alignment refinement. In benchmarks on the Swiss-Prot, SCOPe40, and AFDB50 datasets, SSAlign showed competitive alignment quality and returned more TM-align-supported hits than Foldseek in recall-oriented evaluations. On AFDB50, 1000 queries against 53.7 million structures completed in 3150 s on CPUs and 2290 s with GPU prefiltering, corresponding to 103-fold and 142-fold speedups over Foldseek, respectively. On SCOPe40, SSAlign increased the area under the curve (AUC) by 20.2% at family level and 33.3% at superfamily level. In simple-fold antimicrobial peptide case studies, SSAlign retrieved candidates that were not returned by Foldseek under the tested settings, indicating its utility as a fast candidate-generation tool for proteome-scale structural search.

Availability and implementation: The source code for SSAlign is publicly available at https://github.com/ISYSLAB-HUST/SSAlign. The software version and test data used in this study are archived on Zenodo at https://doi.org/10.5281/zenodo.23432919. Datasets and prebuilt indices can be downloaded from http://bioinfo.isyslab.info/ssalign/download/section/ssalign/.

Phosphatidic Acid Vesicles Convert the Prion Protein into β-Sheet Fibrils with a Thermostable Structure but Temperature-Sensitive Packing
Cyntia Alves, Gabriela Assis-de-Lemos, Michel W. Jaworek +4
International journal of molecular sciences1 Oct 2026Peer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMCCrossref
Structural motif search across the protein universe with Folddisco
Hyunbin Kim, Rachel Seongeun Kim, Milot Mirdita +2
Nature Biotechnology5 Jun 2026Peer-reviewedLicence not statedFull text14 citedMolecular biology & gene regulationOpenAlex
Cryo-tides: synthetic peptides for cryo-EM grid preparation of multi-subunit protein complexes sensitive to the air-water interface
C. Alfieri, R. V. C. Young, A. J. S. McGeoch +2
bioRxiv30 Sep 2026PreprintCC BY-NC-NDFull textStructural biologybioRxiv
Near-infrared light-controlled catalytic hairpin assembly fluorescent biosensor for the sensitive and specific detection of fibroblast activation protein
Jiayi Wu, Xingchun Zheng, Jinhua Huang +1
Nanoscale Advances30 Sep 2026Peer-reviewedCC BY-NC 3.0Full textMolecular biology & gene regulationPMC
Novel hybrid protein scaffold gap filling using weighted machine learning ensemble, beam search, and mass-constrained reranking
Tahmid Enam Shrestha, Md. Manzurul Hasan, Md. Rafiqul Islam
arXiv1 Sep 2026PreprintarXiv licenceFull textBiophysicsarXiv

Cite

BibTeX RIS

BibTeX

@article{wang2026ssalign,
  title = {{SSAlign: fast and sensitive protein structure search at scale}},
  author = {Lei Wang and Xuchao Zhang and Yan Wang and Zhidong Xue},
  journal = {Bioinformatics},
  year = {2026},
  month = oct,
  doi = {10.1093/bioinformatics/btag789},
  url = {https://doi.org/10.1093/bioinformatics/btag789},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - SSAlign: fast and sensitive protein structure search at scale
AU  - Lei Wang
AU  - Xuchao Zhang
AU  - Yan Wang
AU  - Zhidong Xue
PY  - 2026
DA  - 2026/10/26
JO  - Bioinformatics
DO  - 10.1093/bioinformatics/btag789
UR  - https://doi.org/10.1093/bioinformatics/btag789
AB  - Motivation: Predicted protein structure resources now contain hundreds of millions of models, turning structural comparison from a pairwise alignment task into a database-scale retrieval problem. Exhaustive structural aligners are computationally impractical at this scale, whereas fast structural-alphabet searches may discard remote or low-complexity homologs during prefiltering. Database-scale search therefore requires methods that combine rapid retrieval with sensitivity to global structural similarity.  Results: We present SSAlign, a protein structure search method that integrates SaProt sequence-structure embeddings, entropy-reduced dense retrieval, an SS-score predictor, and two-stage alignment refinement. In benchmarks on the Swiss-Prot, SCOPe40, and AFDB50 datasets, SSAlign showed competitive alignment quality and returned more TM-align-supported hits than Foldseek in recall-oriented evaluations. On AFDB50, 1000 queries against 53.7 million structures completed in 3150 s on CPUs and 2290 s with GPU prefiltering, corresponding to 103-fold and 142-fold speedups over Foldseek, respectively. On SCOPe40, SSAlign increased the area under the curve (AUC) by 20.2% at family level and 33.3% at superfamily level. In simple-fold antimicrobial peptide case studies, SSAlign retrieved candidates that were not returned by Foldseek under the tested settings, indicating its utility as a fast candidate-generation tool for proteome-scale structural search.  Availability and implementation: The source code for SSAlign is publicly available at https://github.com/ISYSLAB-HUST/SSAlign. The software version and test data used in this study are archived on Zenodo at https://doi.org/10.5281/zenodo.23432919. Datasets and prebuilt indices can be downloaded from http://bioinfo.isyslab.info/ssalign/download/section/ssalign/.
SN  - 1367-4803
SN  - 1367-4811
ER  -

Abstract

Related

Cite