CoChat

Reaching alignment-profile-based accuracy in predicting protein secondary and tertiary structural properties without alignment

Open access
Singh, Jaspreet, Paliwal, Kuldip, Litfin, Thomas, Singh, Jaswinder, Zhou, Yaoqi · 2022 · Scientific Reports
Cited by 52

The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.

Abstract

Protein language models have emerged as an alternative to multiple sequence alignment for enriching sequence information and improving downstream prediction tasks such as biophysical, structural, and functional properties. Here we show that a method called SPOT-1D-LM combines traditional one-hot encoding with the embeddings from two different language models (ProtTrans and ESM-1b) for the input and yields a leap in accuracy over single-sequence-based techniques in predicting protein 1D secondary and tertiary structural properties, including backbone torsion angles, solvent accessibility and contact numbers for all six test sets (TEST2018, TEST2020, Neff1-2020, CASP12-FM, CASP13-FM and CASP14-FM). More significantly, it has a performance comparable to profile-based methods for those proteins with homologous sequences. For example, the accuracy for three-state secondary structure (SS3) prediction for TEST2018 and TEST2020 proteins are 86.7% and 79.8% by SPOT-1D-LM, compared to 74.3% and 73.4% by the single-sequence-based method SPOT-1D-Single and 86.2% and 80.5% by the profile-based method SPOT-1D, respectively. For proteins without homologous sequences (Neff1-2020) SS3 is 80.41% by SPOT-1D-LM which is 3.8% and 8.3% higher than SPOT-1D-Single and SPOT-1D, respectively. SPOT-1D-LM is expected to be useful for genome-wide analysis given its fast performance. Moreover, high-accuracy prediction of both secondary and tertiary structural properties such as backbone angles and solvent accessibility without sequence alignment suggests that highly accurate prediction of protein structures may be made without homologous sequences, the remaining obstacle in the post AlphaFold2 era.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1038/s41598-022-11684-w

Cites

19 of 19 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.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Research works printed but not linked: 24

  1. Wang, S., Peng, J., Ma, J. & Xu, J. Protein secondary structure prediction using deep convolutional neural fields. Sci. Rep. 6, 1–11 (2016). · DOI · Paper page
  2. Fang, C., Shang, Y. & Xu, D. MUFOLD-SS: New deep inception-inside-inception networks for protein secondary structure prediction. Proteins Struct. Funct. Bioinform. 86, 592–598 (2018). · DOI · Paper page
  3. Klausen, M. S. et al. NetSurfP-2.0: Improved prediction of protein structural features by integrated deep learning. Proteins Struct. Funct. Bioinform. 87, 520–527 (2019). · DOI · Paper page
  4. Hanson, J., Paliwal, K., Litfin, T., Yang, Y. & Zhou, Y. Improving prediction of protein secondary structure, backbone angles, solvent accessibility and contact numbers by using predicted contact maps and an ensemble of recurrent and residual convolutional neural networks. Bioinformatics 35, 2403–2410 (2019). · DOI · Paper page
  5. Xu, G., Wang, Q. & Ma, J. OPUS-TASS: A protein backbone torsion angles and secondary structure predictor based on ensemble neural networks. Bioinformatics 36, 5021 (2020). · DOI · Paper page
  6. Hanson, J., Paliwal, K., Litfin, T., Yang, Y. & Zhou, Y. Accurate prediction of protein contact maps by coupling residual two-dimensional bidirectional long short-term memory with convolutional neural networks. Bioinformatics 34, 4039–4045 (2018). · DOI · Paper page
  7. Pearson, W. R. An introduction to sequence similarity (“homology’’) searching. Curr. Protoc. Bioinform. 42, 3 (2013). · DOI · Paper page
  8. McGuffin, L. J., Bryson, K. & Jones, D. T. The PSIPRED protein structure prediction server. Bioinformatics 16, 404–405 (2000). · DOI · Paper page
  9. Heffernan, R. et al. Single-sequence-based prediction of protein secondary structures and solvent accessibility by deep whole-sequence learning. J. Comput. Chem. 39, 2210–2216 (2018). · DOI · Paper page
  10. Kotowski, K., Smolarczyk, T., Roterman-Konieczna, I. & Stapor, K. ProteinUnet: An efficient alternative to SPIDER3-single for sequence-based prediction of protein secondary structures. J. Comput. Chem. 42, 50 (2020). · DOI
  11. Chothia, C. Hydrophobic bonding and accessible surface area in proteins. Nature 248, 338–339 (1974). · DOI · Paper page
  12. Heffernan, R. et al. Highly accurate sequence-based prediction of half-sphere exposures of amino acid residues in proteins. Bioinformatics 32, 843–849 (2016). · DOI
  13. Schuster, M. & Paliwal, K. K. Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45, 2673–2681 (1997). · DOI · Paper page
  14. Elnaggar, A. et al. ProtTrans: Towards cracking the language of life’s code through self-supervised deep learning and high performance computing. arXiv preprintarXiv:2007.06225 (2020). · DOI · Paper page
  15. Mirdita, M. et al. Uniclust databases of clustered and deeply annotated protein sequences and alignments. Nucleic Acids Res. 45, D170–D176 (2017). · DOI · Paper page
  16. Bateman, A. et al. The pfam protein families database. Nucleic Acids Res. 32, D138–D141 (2004). · DOI · Paper page
  17. Jones, S. et al. Domain assignment for protein structures using a consensus approach: Characterization and analysis. Protein Sci. 7, 233–242 (1998). · DOI · Paper page
  18. Wang, Y., Zhang, H., Zhong, H. & Xue, Z. Protein domain identification methods and online resources. Comput. Struct. Biotechnol. J. 19, 1145 (2021). · DOI
  19. Wu, Q. et al. Protein contact prediction using metagenome sequence data and residual neural networks. Bioinformatics 36, 41–48 (2020). · DOI · Paper page
  20. Wang, W., Peng, Z. & Yang, J. Single-sequence protein structure prediction using supervised transformer protein language models. bioRxiv (2022). · DOI · Paper page
  21. Kabsch, W. & Sander, C. Dictionary of protein secondary structure: Pattern recognition of hydrogen-bonded and geometrical features. Biopolym. Orig. Res. Biomol. 22, 2577–2637 (1983). · DOI · Paper page
  22. Ioffe, S. & Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprintarXiv:1502.03167 (2015).
  23. Agarap, A. F. Deep learning using rectified linear units (relu). arXiv preprintarXiv:1803.08375 (2018).
  24. Benesty, J., Chen, J., Huang, Y. & Cohen, I. Pearson correlation coefficient. In Noise reduction in speech processing, 1–4 (Springer, 2009). · DOI · Paper page

Cited by

See all 52

Metadata

Authors
Singh, J., Paliwal, K., Litfin, T., Singh, J., & Zhou, Y.
Venue
Scientific Reports
Published
2022-05-09
Volume
12
Issue
1
Pages
7607-7607
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4229451461
Cited by
52
References
19
FWCI
3.04
Type
journal article
Language
en
Open access
gold
Licence
Funders
Australian Research Council (DP210101875)

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.