CoChat
Sign Up
PreprintCited by 19Protein Structure and DynamicsEnzyme Structure and FunctionMachine Learning in Bioinformatics

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Fast protein structure searching using structure graph embeddings

Open access
Greener, Joe G, Jamali, Kiarash·2022·Bioinformatics Advances
DOI 10.1101/2022.11.28.518224PMC PMC11974391

Preprint — published as 10.1093/bioadv/vbaf042 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Comparing and searching protein structures independent of primary sequence has proved useful for remote homology detection, function annotation and protein classification. Fast and accurate methods to search with structures will be essential to make use of the vast databases that have recently become available, in the same way that fast protein sequence searching underpins much of bioinformatics. We train a simple graph neural network using supervised contrastive learning to learn a low-dimensional embedding of protein structure. The method, called Progres, is available as software at https://github.com/greener-group/progres and as a web server at https://progres.mrc-lmb.cam.ac.uk . It has accuracy comparable to the best current methods and can search the AlphaFold database TED domains in a tenth of a second per query on CPU.

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 · 10.1101/2022.11.28.518224

Cites

1 of 1 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: 66

  1. 10.1016/j.sbi.2009.04.003 · DOI
  2. 10.1002/prot.22458 · DOI
  3. 10.1038/s41467-023-44082-5 · DOI
  4. 10.1093/nar/gkaa1079 · DOI · Paper page
  5. 10.1093/nar/gkx366 · DOI · Paper page
  6. 10.1038/s41586-023-06510-w · DOI · Paper page
  7. 10.1038/s41586-023-06622-3 · DOI
  8. 10.1093/nar/gki524 · DOI · Paper page
  9. 10.1371/journal.pcbi.1007970 · DOI
  10. 10.1038/s42003-022-03261-8 · DOI · Paper page
  11. 10.1016/0022-2836(89)90084-3 · DOI
  12. 10.1093/bioinformatics/bty585 · DOI
  13. 10.1007/978-1-0716-0270-6_3 · DOI
  14. 10.1093/bioinformatics/btae064 · DOI · Paper page
  15. 10.1093/protein/11.9.739 · DOI
  16. 10.1093/NAR/GKAB1061 · DOI · Paper page
  17. 10.1126/science.ade2574 · DOI · Paper page
  18. 2023, Fast and accurate protein structure search with Foldseek, Nature Biotechnology, 42, 243
  19. VG Satorras , E Hoogeboom , and M Welling . E(n) equivariant graph neural networks, 2021. URL https://arxiv.org/abs/2102.09844. · arXiv
  20. 10.1093/nar/gky1134 · DOI
  21. 10.1371/journal.pcbi.1003926 · DOI · Paper page
  22. P Khosla , P Teterwak , C Wang , A Sarna , Y Tian , P Isola , A Maschinot , C Liu , and D Krishnan . Supervised contrastive learning, 2020. URL https://arxiv.org/abs/2004.11362. · arXiv
  23. SM Kandathil , AM Lau , and DT Jones . Foldclass and Merizo-search: embedding-based deep learning tools for protein domain segmentation, fold recognition and comparison. bioRxiv, 2024. URL https://www.biorxiv.org/content/early/2024/03/29/2024.03.25.586696. · DOI
  24. C Chen , Y Zha , D Zhu , K Ning , and X Cui . Hydrogen bonds meet self-attention: all you need for protein structure embedding. In 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 12–17, 2021. · DOI
  25. 10.1371/journal.pcbi.1009986 · DOI
  26. 2023, Contrastive learning of protein representations with graph neural networks for structural and functional annotations, Pac Symp Biocomput, 28, 109
  27. T Hamamsy , M Barot , JT Morton , M Steinegger , R Bonneau , and K Cho . Learning sequence, structure, and function representations of proteins with language models. bioRxiv, 2023. URL https://www.biorxiv.org/content/early/2023/11/26/2023.11.26.568742.
  28. A Villegas-Morcillo , V Sanchez , and AM Gomez . FoldHSphere: deep hyperspherical embeddings for protein fold recognition. BMC Bioinformatics, 22(490), 2021. · DOI
  29. 10.1038/s41467-021-23303-9 · DOI
  30. Z Zhang , M Xu , AR Jamasb , V Chenthamarakshan , A Lozano , P Das , and J Tang . Protein representation learning by geometric structure pretraining. In First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022, 2022.
  31. P Hermosilla and T Ropinski . Contrastive representation learning for 3D protein structures, 2022. URL https://arxiv.org/abs/2205.15675. · arXiv
  32. C Chen , J Zhou , F Wang , X Liu , and D Dou . Structure-aware protein self-supervised learning, 2022. URL https://arxiv.org/abs/2204.04213. · arXiv
  33. 2022, Contrastive learning on protein embeddings enlightens midnight zone, NAR Genomics and Bioinformatics, 4, lqac043, 10.1093/nargab/lqac043 · DOI
  34. T Hamamsy , JT Morton , R Blackwell , D Berenberg , N Carriero , V Gligorijevic , CEM Strauss , JK Leman , K Cho , and R Bonneau . Protein remote homology detection and structural alignment using deep learning. Nat Biotechnol, 2023. · DOI
  35. 10.1038/s41467-024-46808-5 · DOI · Paper page
  36. Y Liu and H-B Shen . FoldExplorer: Fast and Accurate Protein Structure Search with Sequence-Enhanced Graph Embedding, 2023. URL https://arxiv.org/abs/2311.18219. · arXiv
  37. J Zheng , G Wang , Y Huang , B Hu , S Li , C Tan , X Fan , and SZ Li . Lightweight contrastive protein structure-sequence transformation, 2023. URL https://arxiv.org/abs/2303.11783. · arXiv
  38. 10.1101/gr.279127.124 · DOI
  39. 2023, Bilingual language model for protein sequence and structure, NAR Genomics and Bioinformatics, 6, lqae150
  40. 10.1093/nar/gkz1064 · DOI
  41. A Vaswani , N Shazeer , N Parmar , J Uszkoreit , L Jones , AN Gomez , L Kaiser , and. I Polosukhin . Attention is all you need, 2017. URL https://arxiv.org/abs/1706.03762. · arXiv
  42. 10.1038/nbt.3988 · DOI · Paper page
  43. 10.1007/978-1-4939-0366-5_8 · DOI
  44. AM Lau , N Bordin , SM Kandathil , I Sillitoe , VP Waman , J Wells , CA Orengo , and DT Jones . Exploring structural diversity across the protein universe with The Encyclopedia of Domains. Science, 386(6721), 2024. · DOI · Paper page
  45. M Douze , A Guzhva , C Deng , J Johnson , G Szilvasy , P-E Mazaré , M Lomeli , L Hosseini , and H Jégou . The Faiss library, 2024. URL https://arxiv.org/abs/2401.08281. · arXiv
  46. 2008, Visualizing data using t-SNE, Journal of Machine Learning Research, 9, 2579
  47. 10.1093/nar/26.1.316 · DOI
  48. 10.1146/annurev-biophys-083012-130432 · DOI
  49. 10.1073/pnas.1403395111 · DOI
  50. 10.1038/s42003-023-04488-9 · DOI · Paper page
  51. 10.1093/bioinformatics/btae296 · DOI · Paper page
  52. 10.1038/s41467-023-43934-4 · DOI · Paper page
  53. 10.1093/nar/gkac370 · DOI
  54. X Guo , Y Du , S Tadepalli , L Zhao , and A Shehu . Generating tertiary protein structures via an interpretative variational autoencoder, 2020. URL https://arxiv.org/abs/2004.07119. · DOI
  55. J Ingraham , VK Garg , R Barzilay , and T Jaakkola . Generative models for graph-based protein design. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019.
  56. 10.1038/s41467-019-13633-0 · DOI · Paper page
  57. 10.1038/416657a · DOI
  58. 10.1371/journal.pcbi.1000957 · DOI
  59. 10.1073/pnas.0907683106 · DOI
  60. 10.1038/s41467-023-37896-w · DOI
  61. 10.1093/nar/gkh034 · DOI
  62. 10.1093/bioinformatics/btp163 · DOI · Paper page
  63. 10.1093/bioinformatics/btaa502 · DOI
  64. A Paszke , S Gross , F Massa , A Lerer , J Bradbury , G Chanan , T Killeen , Z Lin , N Gimelshein , L Antiga , A Desmaison , A Kopf , E Yang , Z DeVito , M Raison , A Tejani , S Chilamkurthy , B Steiner , L Fang , J Bai , and S Chintala . Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems 32, pages 8024–8035. 2019.
  65. D Hendrycks and K Gimpel . Gaussian error linear units (GELUs), 2016. URL https://arxiv.org/abs/1606.08415. · arXiv
  66. DP Kingma and J Ba . Adam: A method for stochastic optimization, 2014. URL https://arxiv.org/abs/1412.6980. · arXiv

Metadata

Authors
Greener, J. G., & Jamali, K.
Affiliations
MRC Laboratory of Molecular Biology (GB)
Corresponding author
Greener, Joe G
ORCID
Venue
Bioinformatics Advances
Publisher
openRxiv
Published
2022-11-28
Volume
5
Issue
1
Pages
vbaf042-vbaf042
ISSN
2635-0041 (ISSN-L)
DOI
10.1101/2022.11.28.518224
PMC
PMC11974391
OpenAlex
W4409217924
Cited by
19
References
1
Citations by year
2026: 6 · 2025: 7 · 2024: 4 · 2023: 2
FWCI
2.31
Type
journal article
Language
en
Open access
Licence
Locations
  • Bioinformatics Advances (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Apollo (University of Cambridge) (submittedVersion, cc-by)
Funders
  • UK Research and Innovation
  • Medical Research Council (MC_UP_A025_1013, MC_UP_1201/33)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Structural Biology › Enzyme Structure and Function
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
Keywords
protein structure search, graph neural networks, supervised contrastive learning, protein domains, remote homology detection, protein classification, AlphaFold, PROGRES

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