CoChat
Sign Up
Cited by 276Protein Structure and DynamicsMachine Learning in BioinformaticsComputational Drug Discovery Methods

The DOI matches its Crossref record; 100 of the 104 references it cites were found in a registry or an index.

ScanNet: an interpretable geometric deep learning model for structure-based protein binding site prediction

Open access
Tubiana, Jérôme, Schneidman-Duhovny, Dina, Wolfson, Haim J.·2022·Nature Methods
DOI 10.1038/s41592-022-01490-7

Published version of a preprint

Open this paper in CoChat — free account

Abstract

Predicting the functional sites of a protein from its structure, such as the binding sites of small molecules, other proteins or antibodies, sheds light on its function in vivo. Currently, two classes of methods prevail: machine learning models built on top of handcrafted features and comparative modeling. They are, respectively, limited by the expressivity of the handcrafted features and the availability of similar proteins. Here, we introduce ScanNet, an end-to-end, interpretable geometric deep learning model that learns features directly from 3D structures. ScanNet builds representations of atoms and amino acids based on the spatio-chemical arrangement of their neighbors. We train ScanNet for detecting protein-protein and protein-antibody binding sites, demonstrate its accuracy-including for unseen protein folds-and interpret the filters learned. Finally, we predict epitopes of the SARS-CoV-2 spike protein, validating known antigenic regions and predicting previously uncharacterized ones. Overall, ScanNet is a versatile, powerful and interpretable model suitable for functional site prediction tasks. A webserver for ScanNet is available from http://bioinfo3d.cs.tau.ac.il/ScanNet/ .

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 · 10.1038/s41592-022-01490-7

Cites

100 of 100 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

Research works printed but not linked: 14

  1. Esmaielbeiki, R. & Nebel, J.C. Unbiased Protein Interface Prediction Based on Ligand Diversity Quantification, in Proc. German Conference on Bioinformatics 119; 19-22 Sep 2012, Jena, Germany. (OASICS, no. Vol. 26) ISSN (print) 2190-6807 ISBN 9783939897446. Editors: S. Bocker, F. Hufsky, K. Scheubert, J. Schleicher and S. Schuster (2012).
  2. Ingraham, J., Riesselman, A., Sander, C. & Marks, D. Learning protein structure with a differentiable simulator, in Proc. International Conference on Learning Representations (2018). Venue: Vancouver, Canada. Editors: Y. Bengio, Y. LeCun, T. Saintath, I. Murray, M.A. Ranzato, O. Vinyals, A. Courville & H. Larochelle.
  3. Ingraham, J., Garg, V., Barzilay, R. & Jaakkola, T. Generative models for graph-based protein design. In. Proc. Advances in Neural Information Processing Systems 32 (NeurIPS, 2019).
  4. Wallach, I., Dzamba, M. & Heifets, A. Atomnet: a deep convolutional neural network for bioactivity prediction in structure-based drug discovery. Preprint at arXiv:1510.02855 (2015). · arXiv
  5. Eismann, S., Suriana, P., Jing, B., Townshend, R. J. & Dror, R. O. Protein model quality assessment using rotation-equivariant, hierarchical neural networks. Preprint at arXiv:2011.13557 (2020). · arXiv
  6. Bronstein, M. M., Bruna, J., Cohen, T. & Veličković, P. Geometric deep learning: grids, groups, graphs, geodesics, and gauges. Preprint at arXiv:2104.13478 (2021). · arXiv
  7. Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O. & Dahl, G. E. Neural message passing for quantum chemistry, in Proc. International Conference on Machine Learning 1263–1272 (PMLR, 2017). Venue: Sydney, Australia. Editors: D. Precup, Y. W. Teh
  8. Veličković, P. et al. Graph attention networks. Preprint at arXiv:1710.10903 (2017). · arXiv
  9. Posani, L. Inference and Modeling of Biological Networks: A Statistical-Physics Approach to Neural Attractors and Protein Fitness Landscapes. PhD thesis, Univ. Paris, sciences et lettres (2018).
  10. Qi, C. R., Su, H., Mo, K. & Guibas, L. J. Pointnet: deep learning on point sets for 3D classification and segmentation, in Proc. IEEE Conference on Computer Vision and Pattern Recognition 652–660 (IEEE, 2017). Venue: Honolulu, Hawai. Editors: R. Chellappa, Z. Zhang, A. Hoogs, J. Rehg, Y. Liu, Y. Wu & C. Taylor
  11. Qi, C. R., Yi, L., Su, H. & Guibas, L. J. Pointnet++: deep hierarchical feature learning on point sets in a metric space, Preprint at arXiv:1706.02413 (2017). · arXiv
  12. Ioffe S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift, in Proc. International Conference on Machine Learning 448–456 (PMLR, 2015). Venue: Lille, France. Editors: F. Bach, D. Blei
  13. Kingma, D. P. & Ba, J. ADAM: a method for stochastic optimization. Preprint at arXiv:1412.6980 (2014). · arXiv
  14. Abadi, M. et al. Tensorflow: a system for large-scale machine learning, in Proc. 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16). November 2–4, 2016, Savannah, GA, USA, 265–283 (USENIX, 2016).

Cited by

Sorted by citations

See all 276

Related

See all

Metadata

Authors
Tubiana, J., Schneidman-Duhovny, D., & Wolfson, H. J.
Affiliations
Tel Aviv University (IL)
Corresponding author
  • Tubiana, Jérôme
  • Wolfson, Haim J.
ORCID
Venue
Nature Methods
Publisher
Springer Science and Business Media LLC
Published
2022-05-30
Volume
19
Issue
6
Pages
730-739
ISSN
  • 1548-7091 (ISSN-L)
  • 1548-7105
DOI
10.1038/s41592-022-01490-7
OpenAlex
W4229031603
Cited by
274
References
104
Citations by year
2026: 70 · 2025: 75 · 2024: 69 · 2023: 48 · 2022: 11
FWCI
16.82
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Methods (publishedVersion)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • Research Square (acceptedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
Human Frontier Science Program (LT001058/2019-C)
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 binding site prediction, geometric deep learning, model interpretability, protein structure, protein-protein binding, epitope prediction, SARS-CoV-2 spike protein
MeSH terms
Deep Learning, COVID-19, SARS-CoV-2, Binding Sites, Humans, Protein Binding, Proteins, Spike Glycoprotein, Coronavirus

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