CoChat
Sign Up
Cited by 5Protein Structure and DynamicsMachine Learning in BioinformaticsEnzyme Structure and Function

The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.

SAINT-Angle: self-attention augmented inception-inside-inception network and transfer learning improve protein backbone torsion angle prediction

Open access
Hasan, A K M Mehedi, Ahmed, Ajmain Yasar, Mahbub, Sazan, Rahman, M Saifur, Bayzid, Md Shamsuzzoha·2023·Bioinformatics Advances
DOI 10.1093/bioadv/vbad042PMC PMC10115468

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Motivation: Protein structure provides insight into how proteins interact with one another as well as their functions in living organisms. Protein backbone torsion angles (ϕ and ψ) prediction is a key sub-problem in predicting protein structures. However, reliable determination of backbone torsion angles using conventional experimental methods is slow and expensive. Therefore, considerable effort is being put into developing computational methods for predicting backbone angles. Results: We present SAINT-Angle, a highly accurate method for predicting protein backbone torsion angles using a self-attention-based deep learning network called SAINT, which was previously developed for the protein secondary structure prediction. We extended and improved the existing SAINT architecture as well as used transfer learning to predict backbone angles. We compared the performance of SAINT-Angle with the state-of-the-art methods through an extensive evaluation study on a collection of benchmark datasets, namely, TEST2016, TEST2018, TEST2020-HQ, CAMEO and CASP. The experimental results suggest that our proposed self-attention-based network, together with transfer learning, has achieved notable improvements over the best alternate methods. Availability and implementation: SAINT-Angle is freely available as an open-source project at https://github.com/bayzidlab/SAINT-Angle. Supplementary information: Supplementary data are available at Bioinformatics Advances online.

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 · 10.1093/bioadv/vbad042

Cites

12 of 12 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: 40

  1. Adhikari, 2012, De novo prediction of protein folding pathways and structure using the principle of sequential stabilization, Proc. Natl. Acad. Sci. USA, 109, 17442, 10.1073/pnas.1209000109 · DOI
  2. Altschul, 1997, Gapped BLAST and PSI-BLAST: a new generation of protein database search programs, Nucleic Acids Res, 25, 3389, 10.1093/nar/25.17.3389 · DOI · Paper page
  3. Bengio, 1994, Learning long-term dependencies with gradient descent is difficult, IEEE Trans. Neural Netw, 5, 157, 10.1109/72.279181 · DOI · Paper page
  4. Bystroff, 2000, HMMSTR: a hidden Markov model for local sequence–structure correlations in proteins, J. Mol. Biol, 301, 173, 10.1006/jmbi.2000.3837 · DOI
  5. Dor, 2007, Real-spine: an integrated system of neural networks for real-value prediction of protein structural properties, Proteins, 68, 76, 10.1002/prot.21408 · DOI
  6. Fang, 2018, MUFold-SS: new deep inception-inside-inception networks for protein secondary structure prediction, Proteins, 86, 592, 10.1002/prot.25487 · DOI
  7. Fang, 2018, Prediction of protein backbone torsion angles using deep residual inception neural networks, IEEE/ACM Trans. Comput. Biol. Bioinf, 16, 1020, 10.1109/TCBB.2018.2814586 · DOI
  8. Gao, 2018, RaptorX-Angle: real-value prediction of protein backbone dihedral angles through a hybrid method of clustering and deep learning, BMC Bioinformatics, 19, 73, 10.1186/s12859-018-2065-x · DOI
  9. Greener, 2019, Deep learning extends de novo protein modelling coverage of genomes using iteratively predicted structural constraints, Nat. Commun, 10, 1, 10.1038/s41467-019-11994-0 · DOI · Paper page
  10. Hanson, 2018, Accurate prediction of protein contact maps by coupling residual two-dimensional bidirectional long short-term memory with convolutional neural networks, Bioinformatics, 34, 4039, 10.1093/bioinformatics/bty481 · DOI
  11. Hanson, 2019, 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, 10.1093/bioinformatics/bty1006 · DOI
  12. Heffernan, 2015, Improving prediction of secondary structure, local backbone angles and solvent accessible surface area of proteins by iterative deep learning, Sci. Rep, 5, 1, 10.1038/srep11476 · DOI
  13. Heffernan, 2017, Capturing non-local interactions by long short-term memory bidirectional recurrent neural networks for improving prediction of protein secondary structure, backbone angles, contact numbers and solvent accessibility, Bioinformatics, 33, 2842, 10.1093/bioinformatics/btx218 · DOI
  14. Jiang, 2017, Protein secondary structure prediction: a survey of the state of the art, J. Mol. Graph. Modell, 76, 379, 10.1016/j.jmgm.2017.07.015 · DOI
  15. Karchin, 2003, Hidden Markov models that use predicted local structure for fold recognition: alphabets of backbone geometry, Proteins, 51, 504, 10.1002/prot.10369 · DOI
  16. Klausen, 2019, Netsurfp-2.0: improved prediction of protein structural features by integrated deep learning, Proteins, 87, 520, 10.1002/prot.25674 · DOI
  17. Ludwiczak, 2019, PiPred—a deep-learning method for prediction of π-helices in protein sequences, Sci. Rep, 9, 1, 10.1038/s41598-019-43189-4 · DOI
  18. Mahbub, 2022, EGRET: edge aggregated graph attention networks and transfer learning improve protein–protein interaction site prediction, Brief. Bioinf, 23, bbab578, 10.1093/bib/bbab578 · DOI
  19. Meiler, 2001, Generation and evaluation of dimension-reduced amino acid parameter representations by artificial neural networks, Mol. Model. Annu, 7, 360, 10.1007/s008940100038 · DOI
  20. Michaud, 2022, A language model beats alphafold2 on orphans, Nat. Biotechnol, 40, 1576, 10.1038/s41587-022-01466-0 · DOI
  21. Ramachandran, 1963, Stereochemistry of polypeptide chain configurations, J. Mol. Biol, 7, 95, 10.1016/S0022-2836(63)80023-6 · DOI
  22. Remmert, 2012, HHblits: lightning-fast iterative protein sequence searching by HMM–HMM alignment, Nat. Methods, 9, 173, 10.1038/nmeth.1818 · DOI · Paper page
  23. Schuster, 1997, Bidirectional recurrent neural networks, IEEE Trans. Signal Process, 45, 2673, 10.1109/78.650093 · DOI · Paper page
  24. Senior, 2020, Improved protein structure prediction using potentials from deep learning, Nature, 577, 706, 10.1038/s41586-019-1923-7 · DOI · Paper page
  25. Singh, 2021, SPOT-1D-Single: improving the single-sequence-based prediction of protein secondary structure, backbone angles, solvent accessibility and half-sphere exposures using a large training set and ensembled deep learning, Bioinformatics, 37, 3464, 10.1093/bioinformatics/btab316 · DOI
  26. Singh, 2022, SPOT-Contact-LM: improving single-sequence-based prediction of protein contact map using a transformer language model, Bioinformatics, 38, 1888, 10.1093/bioinformatics/btac053 · DOI
  27. Singh, 2022, Reaching alignment-profile-based accuracy in predicting protein secondary and tertiary structural properties without alignment, Sci. Rep, 12, 7607, 10.1038/s41598-022-11684-w · DOI
  28. Söding, 2005, Protein homology detection by HMM–HMM comparison, Bioinformatics, 21, 951, 10.1093/bioinformatics/bti125 · DOI
  29. Tian, 2020, Amino acid torsion angles enable prediction of protein fold classification, Sci. Rep, 10, 21773, 10.1038/s41598-020-78465-1 · DOI
  30. Uddin, 2020, SAINT: self-attention augmented inception-inside-inception network improves protein secondary structure prediction, Bioinformatics, 36, 4599, 10.1093/bioinformatics/btaa531 · DOI
  31. UniProt Consortium, 2007, The universal protein resource (UniProt), Nucleic Acids Res, 36, D190, 10.1093/nar/gkm895 · DOI
  32. Vaswani, 2017, Attention is all you need, Advances in Neural Information Processing Systems, 5998
  33. Wang, 2003, Pisces: a protein sequence culling server, Bioinformatics, 19, 1589, 10.1093/bioinformatics/btg224 · DOI
  34. Wang, 2016, Protein secondary structure prediction using deep convolutional neural fields, Sci. Rep, 6, 1
  35. Wilcoxon, 1970, Critical values and probability levels for the Wilcoxon rank sum test and the Wilcoxon signed rank test, Select. Tables Math. Stat, 1, 171
  36. Wu, 2008, ANGLOR: a composite machine-learning algorithm for protein backbone torsion angle prediction, PLoS ONE, 3, e3400, 10.1371/journal.pone.0003400 · DOI
  37. Xu, 2020, OPUS-TASS: a protein backbone torsion angles and secondary structure predictor based on ensemble neural networks, Bioinformatics, 36, 5021, 10.1093/bioinformatics/btaa629 · DOI
  38. Xu, 2019, Distance-based protein folding powered by deep learning, Proc. Natl. Acad. Sci. USA, 116, 16856, 10.1073/pnas.1821309116 · DOI · Paper page
  39. Xu, 2021, Accurate prediction of protein torsion angles using evolutionary signatures and recurrent neural network, Sci. Rep, 11, 1, 10.1038/s41598-021-00477-2 · DOI
  40. Yang, 2019, XLNet: generalized autoregressive pretraining for language understanding, Advances in Neural Information Processing Systems, 5753

Metadata

Authors
Hasan, A. K. M. M., Ahmed, A. Y., Mahbub, S., Rahman, M. S., & Bayzid, M. S.
Affiliations
Bangladesh University of Engineering and Technology (BD)
Corresponding author
Bayzid, Md Shamsuzzoha
ORCID
Venue
Bioinformatics Advances
Publisher
Oxford University Press (OUP)
Published
2023-01-01
Volume
3
Issue
1
Pages
vbad042-vbad042
ISSN
2635-0041 (ISSN-L)
DOI
10.1093/bioadv/vbad042
PMC
PMC10115468
OpenAlex
W4362605797
Cited by
5
References
12
Citations by year
2025: 2 · 2024: 2 · 2023: 1
FWCI
0.44
Type
journal article
Language
en
Open access
Licence
Locations
  • Bioinformatics Advances (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Greater South Information System
Funders
BUET (2021-01-016)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Structural Biology › Enzyme Structure and Function
Keywords
self-attention, saints, transfer learning, protein structure prediction

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