CoChat
Sign Up
PreprintCited by 67Protein Structure and DynamicsMachine Learning in BioinformaticsComputational Drug Discovery Methods

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

Deep graph learning of inter-protein contacts

Open access
Xie, Ziwei, Xu, Jinbo·2021·Bioinformatics
DOI 10.1101/2021.08.14.456342PMC PMC8796373

Preprint — published as 10.1093/bioinformatics/btab761 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Motivation: Inter-protein (interfacial) contact prediction is very useful for in silico structural characterization of protein-protein interactions. Although deep learning has been applied to this problem, its accuracy is not as good as intra-protein contact prediction. Results: We propose a new deep learning method GLINTER (Graph Learning of INTER-protein contacts) for interfacial contact prediction of dimers, leveraging a rotational invariant representation of protein tertiary structures and a pretrained language model of multiple sequence alignments (MSAs). Tested on the 13th and 14th CASP-CAPRI datasets, the average top L/10 precision achieved by GLINTER is 54.35% on the homodimers and 51.56% on all the dimers, much higher than 30.43% obtained by the latest deep learning method DeepHomo on the homodimers and 14.69% obtained by BIPSPI on all the dimers. Our experiments show that GLINTER-predicted contacts help improve selection of docking decoys. Contact: jinboxu@gmail.com

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 · 10.1101/2021.08.14.456342

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: 44

  1. 10.1371/journal.pone.0092721 · DOI
  2. Hopf, T. A. et al. Sequence co-evolution gives 3D contacts and structures of protein complexes. Elife 3, (2014). · DOI · Paper page
  3. 10.7554/eLife.02030 · DOI · Paper page
  4. 2020, iScore: a novel graph kernel-based function for scoring protein-protein docking models, Bioinformatics, 36, 112, 10.1093/bioinformatics/btz496 · DOI
  5. 10.1073/pnas.1615068114 · DOI
  6. 2015, Local Geometry and Evolutionary Conservation of Protein Surfaces Reveal the Multiple Recognition Patches in Protein-Protein Interactions, PLOS Computational Biology, 11, e1004580, 10.1371/journal.pcbi.1004580 · DOI
  7. Vangone, A. & Bonvin, A. M. Contacts-based prediction of binding affinity in protein–protein complexes. eLife vol. 4 (2015). · DOI
  8. 10.1073/pnas.0805923106 · DOI · Paper page
  9. 10.1038/msb4100203 · DOI
  10. 10.1126/science.aaw6718 · DOI · Paper page
  11. 10.1093/nar/gky420 · DOI
  12. 10.1073/pnas.1607570113 · DOI
  13. 10.1073/pnas.1606762113 · DOI
  14. 10.1101/2021.02.12.430858 · DOI · Paper page
  15. Rives, A. et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl. Acad. Sci. U. S. A. 118, (2021). · DOI · Paper page
  16. 10.1101/240754 · DOI · Paper page
  17. 10.1101/2020.11.09.373878 · DOI
  18. 10.1093/bib/bbab038 · DOI
  19. 10.1371/journal.pcbi.1005324 · DOI · Paper page
  20. Townshend, R. , Bedi, R. , Suriana, P. & Dror, R. End-to-End Learning on 3D Protein Structure for Interface Prediction. Adv. Neural Inf. Process. Syst. 32, (2019).
  21. 10.1101/738690 · DOI
  22. 2020, Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning, Nat. Methods, 17, 184, 10.1038/s41592-019-0666-6 · DOI
  23. 10.1101/2020.12.28.424589 · DOI
  24. 10.1093/bioinformatics/btab154 · DOI
  25. 10.1093/bioinformatics/btaa263 · DOI
  26. Fout, A. , Byrd, J. , Shariat, B. & Ben-Hur, A. Protein Interface Prediction using Graph Convolutional Networks. Adv. Neural Inf. Process. Syst. 30, (2017).
  27. 10.1073/pnas.1821309116 · DOI · Paper page
  28. Xu, J. , McPartlon, M. & Li, J. Improved protein structure prediction by deep learning irrespective of co-evolution information. Nature Machine Intelligence 1–9 (2021). · DOI
  29. 10.1101/2020.12.10.419994 · DOI
  30. 10.1093/nar/gkx407 · DOI
  31. 10.1093/bioinformatics/bty573 · DOI
  32. 10.1109/cvpr.2016.90 · DOI · Paper page
  33. 10.1101/2020.04.06.028266 · DOI
  34. 2019, Protein model quality assessment using 3D oriented convolutional neural networks, Bioinformatics, 35, 3313, 10.1093/bioinformatics/btz122 · DOI
  35. 10.1006/jmbi.1998.2401 · DOI
  36. 10.1002/(SICI)1097-0282(199603)38:3<305::AID-BIP4>3.0.CO;2-Y · DOI
  37. 10.1093/bioinformatics/btu500 · DOI
  38. 10.1186/s12859-019-3019-7 · DOI · Paper page
  39. 10.1093/bioinformatics/btaa003 · DOI
  40. 2020, Improved protein structure prediction using potentials from deep learning, Nature, 577, 706, 10.1038/s41586-019-1923-7 · DOI · Paper page
  41. 2020, High accuracy protein structure prediction using deep learning, Fourteenth Critical Assessment of Techniques for Protein Structure Prediction (Abstract Book), 22, 24
  42. 10.1371/journal.pcbi.0020155 · DOI
  43. 10.1093/nar/gki524 · DOI · Paper page
  44. 10.1093/nar/gkp318 · DOI

Metadata

Authors
Xie, Z., & Xu, J.
Affiliations
Toyota Technological Institute at Chicago (US)
Corresponding author
Xu, Jinbo
ORCID
Venue
Bioinformatics
Publisher
openRxiv
Published
2021-08-15
Volume
38
Issue
4
Pages
947-953
ISSN
1367-4803 (ISSN-L)
DOI
10.1101/2021.08.14.456342
PMC
PMC8796373
OpenAlex
W3211403530
Cited by
67
References
1
Citations by year
2026: 11 · 2025: 11 · 2024: 11 · 2023: 21 · 2022: 13
FWCI
3.53
Type
journal article
Language
en
Open access
Licence
cc-by-nc-nd
Locations
  • Bioinformatics (publishedVersion)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion)
  • PubMed (publishedVersion)
Funders
  • National Institutes of Health
  • National Institute of General Medical Sciences (R01GM089753)
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 › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
Keywords
protein-protein interaction, protein dimer, graph neural networks, homodimer
MeSH terms
Proteins, Software, Sequence Alignment, Computational Biology

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