CoChat

DeepProSite: structure-aware protein binding site prediction using ESMFold and pretrained language model

Open access
Fang, Yitian, Jiang, Yi, Wei, Leyi, Ma, Qin, Ren, Zhixiang, Yuan, Qianmu, Wei, Dong-Qing · 2023 · Bioinformatics
Cited by 100

The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.

Abstract

Motivation: Identifying the functional sites of a protein, such as the binding sites of proteins, peptides, or other biological components, is crucial for understanding related biological processes and drug design. However, existing sequence-based methods have limited predictive accuracy, as they only consider sequence-adjacent contextual features and lack structural information. Results: In this study, DeepProSite is presented as a new framework for identifying protein binding site that utilizes protein structure and sequence information. DeepProSite first generates protein structures from ESMFold and sequence representations from pretrained language models. It then uses Graph Transformer and formulates binding site predictions as graph node classifications. In predicting protein–protein/peptide binding sites, DeepProSite outperforms state-of-the-art sequence- and structure-based methods on most metrics. Moreover, DeepProSite maintains its performance when predicting unbound structures, in contrast to competing structure-based prediction methods. DeepProSite is also extended to the prediction of binding sites for nucleic acids and other ligands, verifying its generalization capability. Finally, an online server for predicting multiple types of residue is established as the implementation of the proposed DeepProSite. Availability and implementation: The datasets and source codes can be accessed at https://github.com/WeiLab-Biology/DeepProSite. The proposed DeepProSite can be accessed at https://inner.wei-group.net/DeepProSite/.

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 · 10.1093/bioinformatics/btad718

Cites

16 of 16 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

Show all 16 references

Research works printed but not linked: 64

  1. Abdin, 2020, Sequence and structure based deep learning models for the identification of peptide binding sites, Adv Neural Inf Process Syst, 33
  2. Babu, 2011, Intrinsically disordered proteins: regulation and disease, Curr Opin Struct Biol, 21, 432, 10.1016/j.sbi.2011.03.011 · DOI · Paper page
  3. Batra, 2018, Protein interaction mapping identifies RBBP6 as a negative regulator of Ebola virus replication, Cell, 175, 1917, 10.1016/j.cell.2018.08.044 · DOI · Paper page
  4. Berman, 2000, The protein data bank, Nucleic Acids Res, 28, 235, 10.1093/nar/28.1.235 · DOI · Paper page
  5. Bertolazzi, 2014, Predicting protein-ligand and protein-peptide interfaces, Eur Phys J Plus, 129, 1, 10.1140/epjp/i2014-14132-1 · DOI
  6. Brettner, 2012, Protein stickiness, rather than number of functional protein-protein interactions, predicts expression noise and plasticity in yeast, BMC Syst Biol, 6, 1, 10.1186/1752-0509-6-128 · DOI
  7. Bruzzoni-Giovanelli, 2018, Interfering peptides targeting protein-protein interactions: the next generation of drugs?, Drug Discov Today, 23, 272, 10.1016/j.drudis.2017.10.016 · DOI
  8. Chen, 2017, Understand protein functions by comparing the similarity of local structural environments, Biochim Biophys Acta Proteins Proteom, 1865, 142, 10.1016/j.bbapap.2016.11.008 · DOI
  9. Chen, 2021, Structure-aware protein solubility prediction from sequence through graph convolutional network and predicted contact map, J Cheminform, 13, 7, 10.1186/s13321-021-00488-1 · DOI · Paper page
  10. Clare, 2004, Computational studies of protein–peptide interactions with systematic mutation of residues, Mol Phys, 102, 939, 10.1080/00268970410001704407 · DOI
  11. Davenport, 2020, Advances in therapeutic peptides targeting G protein-coupled receptors, Nat Rev Drug Discov, 19, 389, 10.1038/s41573-020-0062-z · DOI · Paper page
  12. De Las Rivas, 2012, Protein–protein interaction networks: unraveling the wiring of molecular machines within the cell, Brief Funct Genomics, 11, 489, 10.1093/bfgp/els036 · DOI
  13. Dhole, 2014, Sequence-based prediction of protein–protein interaction sites with L1-logreg classifier, J Theor Biol, 348, 47, 10.1016/j.jtbi.2014.01.028 · DOI
  14. Fosgerau, 2015, Peptide therapeutics: current status and future directions, Drug Discov Today, 20, 122, 10.1016/j.drudis.2014.10.003 · DOI · Paper page
  15. Gainza, 2020, Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning, Nat Methods, 17, 184, 10.1038/s41592-019-0666-6 · DOI · Paper page
  16. Guilliam, 2017, Molecular basis for PrimPol recruitment to replication forks by RPA, Nat Commun, 8, 15222, 10.1038/ncomms15222 · DOI
  17. Hermann, 2007, Structure-based activity prediction for an enzyme of unknown function, Nature, 448, 775, 10.1038/nature05981 · DOI · Paper page
  18. Hu, 2018, ATPbind: accurate protein–ATP binding site prediction by combining sequence-profiling and structure-based comparisons, J Chem Inf Model, 58, 501, 10.1021/acs.jcim.7b00397 · DOI · Paper page
  19. Hu, 2016, Recognizing metal and acid radical ion-binding sites by integrating ab initio modeling with template-based transferals, Bioinformatics, 32, 3260, 10.1093/bioinformatics/btw396 · DOI · Paper page
  20. Huynh, 2009, Metrics for 3D rotations: comparison and analysis, J Math Imaging Vis, 35, 155, 10.1007/s10851-009-0161-2 · DOI · Paper page
  21. Hwang, 2008, Protein–protein docking benchmark version 3.0, Prot Structure Funct Bioinform, 73, 705, 10.1002/prot.22106 · DOI · Paper page
  22. Ingraham, 2019, Generative models for graph-based protein design, Adv Neural Inf Process Syst, 32
  23. Kabsch, 1983, Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features, Biopolymers, 22, 2577, 10.1002/bip.360221211 · DOI · Paper page
  24. Kortemme, 2004, Computational redesign of protein-protein interaction specificity, Nat Struct Mol Biol, 11, 371, 10.1038/nsmb749 · DOI · Paper page
  25. Krapp, 2023, PeSTo: parameter-free geometric deep learning for accurate prediction of protein binding interfaces, Nat Commun, 14, 2175, 10.1038/s41467-023-37701-8 · DOI · Paper page
  26. Lavi, 2013, Detection of peptide-binding sites on protein surfaces: the first step toward the modeling and targeting of peptide-mediated interactions, Proteins, 81, 2096, 10.1002/prot.24422 · DOI · Paper page
  27. Lee, 2015, GalaxyPepDock: a protein–peptide docking tool based on interaction similarity and energy optimization, Nucleic Acids Res, 43, W431, 10.1093/nar/gkv495 · DOI · Paper page
  28. Li, 2021, DELPHI: accurate deep ensemble model for protein interaction sites prediction, Bioinformatics, 37, 896, 10.1093/bioinformatics/btaa750 · DOI · Paper page
  29. London, 2012, Modeling peptide-protein interactions, Methods Mol Biol, 857, 375, 10.1007/978-1-61779-588-6_17 · DOI · Paper page
  30. Murakami, 2010, Applying the naïve Bayes classifier with kernel density estimation to the prediction of protein–protein interaction sites, Bioinformatics, 26, 1841, 10.1093/bioinformatics/btq302 · DOI · Paper page
  31. Orengo, 1997, CATH—a hierarchic classification of protein domain structures, Structure, 5, 1093, 10.1016/S0969-2126(97)00260-8 · DOI · Paper page
  32. Pawson, 2003, Assembly of cell regulatory systems through protein interaction domains, Science, 300, 445, 10.1126/science.1083653 · DOI · Paper page
  33. Penna, 2007, Spontaneous and prostatic steroid binding protein peptide-induced autoimmune prostatitis in the nonobese diabetic mouse, J Immunol, 179, 1559, 10.4049/jimmunol.179.3.1559 · DOI
  34. Petsalaki, 2009, Accurate prediction of peptide binding sites on protein surfaces, PLoS Comput Biol, 5, e1000335, 10.1371/journal.pcbi.1000335 · DOI · Paper page
  35. Porollo, 2007, Prediction-based fingerprints of protein–protein interactions, Prot Struct Fun Bioinform, 66, 630, 10.1002/prot.21248 · DOI · Paper page
  36. Qiu, 2020, ProNA2020 predicts protein–DNA, protein–RNA, and protein–protein binding proteins and residues from sequence, J Mol Biol, 432, 2428, 10.1016/j.jmb.2020.02.026 · DOI · Paper page
  37. Rigden, 2009, From Protein Structure to Function with Bioinformatics, 10.1007/978-1-4020-9058-5 · doi:10.1007/978-1-4020-9058-5
  38. Rubinstein, 2009, Peptidic modulators of protein-protein interactions: progress and challenges in computational design, Biopolymers, 91, 505, 10.1002/bip.21164 · DOI · Paper page
  39. Shoemaker, 2007, Deciphering protein–protein interactions. Part I. Experimental techniques and databases, PLoS Comput Biol, 3, e42, 10.1371/journal.pcbi.0030042 · DOI · Paper page
  40. Taherzadeh, 2016, Sequence-based prediction of protein-peptide binding sites using support vector machine, J Comput Chem, 37, 1223, 10.1002/jcc.24314 · DOI · Paper page
  41. Taherzadeh, 2018, Structure-based prediction of protein-peptide binding regions using random Forest, Bioinformatics, 34, 477, 10.1093/bioinformatics/btx614 · DOI
  42. Terentiev, 2009, Dynamic proteomics in modeling of the living cell. Protein-protein interactions, Biochemistry (Mosc), 74, 1586, 10.1134/S0006297909130112 · DOI
  43. Valkov, 2016, Structure of the Dcp2-Dcp1 mRNA-decapping complex in the activated conformation, Nat Struct Mol Biol, 23, 574, 10.1038/nsmb.3232 · DOI
  44. Vaswani, 2017, Attention is all you need, Adv Neural Inf Process Syst, 30, 5998
  45. Vlieghe, 2010, Synthetic therapeutic peptides: science and market, Drug Discov Today, 15, 40, 10.1016/j.drudis.2009.10.009 · DOI · Paper page
  46. Wang, 2022, Predicting protein-peptide binding residues via interpretable deep learning, Bioinformatics, 38, 3351, 10.1093/bioinformatics/btac352 · DOI · Paper page
  47. Wang, 2022, RGN: residue-Based graph attention and convolutional network for protein–protein interaction site prediction, J Chem Inform Model, 62, 5961, 10.1021/acs.jcim.2c01092 · DOI · Paper page
  48. Wardah, 2020, Predicting protein-peptide binding sites with a deep convolutional neural network, J Theor Biol, 496, 110278, 10.1016/j.jtbi.2020.110278 · DOI
  49. Wells, 2007, Reaching for high-hanging fruit in drug discovery at protein–protein interfaces, Nature, 450, 1001, 10.1038/nature06526 · DOI · Paper page
  50. Wodak, 2013, Protein–protein interaction networks: the puzzling riches, Curr Opin Struct Biol, 23, 941, 10.1016/j.sbi.2013.08.002 · DOI
  51. Xia, 2020, Protein–ligand binding residue prediction enhancement through hybrid deep heterogeneous learning of sequence and structure data, Bioinformatics, 36, 3018, 10.1093/bioinformatics/btaa110 · DOI · Paper page
  52. Xia, 2021, GraphBind: protein structural context embedded rules learned by hierarchical graph neural networks for recognizing nucleic-acid-binding residues, Nucleic Acids Res, 49, e51, 10.1093/nar/gkab044 · DOI · Paper page
  53. Yang, 2013, BioLiP: a semi-manually curated database for biologically relevant ligand-protein interactions, Nucleic Acids Res, 41, D1096, 10.1093/nar/gks966 · DOI · Paper page
  54. Yang, 2013, Protein–ligand binding site recognition using complementary binding-specific substructure comparison and sequence profile alignment, Bioinformatics, 29, 2588, 10.1093/bioinformatics/btt447 · DOI · Paper page
  55. Yang, 2012, A new size-independent score for pairwise protein structure alignment and its application to structure classification and nucleic-acid binding prediction, Prot Struc Func Bioinform, 80, 2080, 10.1002/prot.24100 · DOI · Paper page
  56. Ying, 2021, Do transformers really perform badly for graph representation?, Adv Neural Inf Process Syst, 34, 28877
  57. Yu, 2013, Designing template-free predictor for targeting protein-ligand binding sites with classifier ensemble and spatial clustering, IEEE ACM Trans Comput Biol Bioinform, 10, 994, 10.1109/TCBB.2013.104 · DOI · Paper page
  58. Yuan, 2021, Structure-aware protein-protein interaction site prediction using deep graph convolutional network, Bioinformatics, 38, 125, 10.1093/bioinformatics/btab643 · DOI · Paper page
  59. Zeng, 2020, Protein–protein interaction site prediction through combining local and global features with deep neural networks, Bioinformatics, 36, 1114, 10.1093/bioinformatics/btz699 · DOI · Paper page
  60. Zhang, 2019, Sequence-based prediction of protein-protein interaction sites by simplified long short-term memory network, Neurocomputing, 357, 86, 10.1016/j.neucom.2019.05.013 · DOI · Paper page
  61. Zhang, 2019, SCRIBER: accurate and partner type-specific prediction of protein-binding residues from proteins sequences, Bioinformatics, 35, i343, 10.1093/bioinformatics/btz324 · DOI · Paper page
  62. Zhao, 2018, Improving sequence-based prediction of protein-peptide binding residues by introducing intrinsic disorder and a consensus method, J Chem Inf Model, 58, 1459, 10.1021/acs.jcim.8b00019 · DOI · Paper page
  63. Zheng, 2020, Predicting retrosynthetic reactions using self-corrected transformer neural networks, J Chem Inf Model, 60, 47, 10.1021/acs.jcim.9b00949 · DOI · Paper page
  64. Zhu, 2019, DNAPred: accurate identification of DNA-binding sites from protein sequence by ensembled hyperplane-distance-based support vector machines, J Chem Inf Model, 59, 3057, 10.1021/acs.jcim.8b00749 · DOI · Paper page

Metadata

Authors
Fang, Y., Jiang, Y., Wei, L., Ma, Q., Ren, Z., Yuan, Q., & Wei, D.-Q.
Venue
Bioinformatics
Published
2023-11-28
Volume
39
Issue
12
ISSN
  • 1367-4803 (ISSN-L)
  • 1367-4811
OpenAlex
W4389076414
Cited by
100
References
16
FWCI
7.47
Type
journal article
Language
en
Open access
gold
Funders
National Science Foundation of China (32070662, 61832019, 32030063)

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.