Skip to content
2000
Volume 32, Issue 28
  • ISSN: 0929-8673
  • E-ISSN: 1875-533X

Abstract

Background

Drug research is a long process, taking more than 10 years and requiring considerable financial resources. Therefore, researchers and industrials aim to reduce time and cost. Thus, they use computational simulations like molecular docking to explore huge databases of compounds and extract the most promising ones for further tests. Structure-based molecular docking is a complex process mixing surface exploration and energy computation to find the minimal free energy of binding corresponding to the best interaction location.

Objective

Our work is developed in the ligand-protein context, where ligands are small compounds like drugs. In most cases, no information is known about where on the protein surface the ligand will bind. Thus, the whole protein surface must be explored, which takes a huge amount of time.

Methods

We have developed SGPocket (meaning Spherical Graph Pocket), a binding site prediction method. Our method allows us to reduce the explored protein surface using deep learning without any information about a ligand. SGPocket uses the spherical graph convolutional operator working on a spherical relative positioning of amino acids in the protein. Then, a final step of clustering extracts the binding sites.

Results

Tested and compared (with well-known binding site prediction methods) on a hand-made dataset, our method performed well and can reduce the docking computing time.

Conclusion

Thus, SGPocket allows the reduction of the exploration surface in the molecular docking process by restricting the simulation only to the site(s) predicted to be interesting.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cmc/10.2174/0109298673289137240304165758
2024-03-11
2025-10-22

  • From This Site

    /content/journals/cmc/10.2174/0109298673289137240304165758
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. SinhaS. VohoraD. Drug discovery and development: An overview.Pharmaceutical Medicine and Translational Clinical Research.Elsevier2018193210.1016/B978‑0‑12‑802103‑3.00002‑X
     [Google Scholar]
  2. WeinerP.K. KollmanP.A. AMBER : Assisted model building with energy refinement. A general program for modeling molecules and their interactions.J. Comput. Chem.19812328730310.1002/jcc.540020311
     [Google Scholar]
  3. van GunsterenW.F. BerendsenH.J.C. Computer simulation of molecular dynamics: Methodology, applications, and perspectives in chemistry.Angew. Chem. Int. Ed. Engl.1990299992102310.1002/anie.199009921
     [Google Scholar]
  4. CortesC. VapnikV. Support-vector networks.Mach. Learn.199520327329710.1007/BF00994018
     [Google Scholar]
  5. GardnerM.W. DorlingS.R. Artificial neural networks (the multilayer perceptron)-a review of applications in the atmospheric sciences.Atmos. Environ.19983214-152627263610.1016/S1352‑2310(97)00447‑0
     [Google Scholar]
  6. LiZ. LiuF. YangW. PengS. ZhouJ. A Survey of convolutional neural networks: Analysis, applications, and prospects.IEEE Trans. Neural Netw. Learn. Syst.202233126999701910.1109/TNNLS.2021.308482734111009
     [Google Scholar]
  7. WuZ. PanS. ChenF. LongG. ZhangC. YuP.S. A comprehensive survey on graph neural networks.IEEE Trans. Neural Netw. Learn. Syst.202012110.1109/TNNLS.2020.297838632217482
     [Google Scholar]
  8. CramponK. GiorkallosA. DeldossiM. BaudS. SteffenelL.A. Machine-learning methods for ligand-protein molecular docking.Drug Discov. Today202227115116410.1016/j.drudis.2021.09.00734560276
     [Google Scholar]
  9. CramponK. GiorkallosA. VigourouxX. BaudS. SteffenelL.A. Heterogeneous graph convolutional neural network for protein-ligand scoring.Explor Drug Sci202312613910.37349/eds.2023.00010
     [Google Scholar]
  10. Le GuillouxV. SchmidtkeP. TufferyP. Fpocket: An open source platform for ligand pocket detection.BMC Bioinformatics200910116810.1186/1471‑2105‑10‑16819486540
     [Google Scholar]
  11. LaurieA.T.R. JacksonR.M. Q-SiteFinder: An energy-based method for the prediction of protein-ligand binding sites.Bioinformatics20052191908191610.1093/bioinformatics/bti31515701681
     [Google Scholar]
  12. Stepniewska-DziubinskaM.M. ZielenkiewiczP. SiedleckiP. Improving detection of protein-ligand binding sites with 3D segmentation.Sci. Rep.2020101503510.1038/s41598‑020‑61860‑z32193447
     [Google Scholar]
  13. Stepniewska-DziubinskaM.M. ZielenkiewiczP. SiedleckiP. Development and evaluation of a deep learning model for protein-ligand binding affinity prediction.Bioinformatics201834213666367410.1093/bioinformatics/bty37429757353
     [Google Scholar]
  14. RonnebergerO. FischerP. BroxT. U-Net: Convolutional networks for biomedical image segmentation.International Conference on Medical image computing and computer-assisted intervention201523424110.1007/978‑3‑319‑24574‑4_28
     [Google Scholar]
  15. MylonasS.K. AxenopoulosA. DarasP. DeepSurf: A surface-based deep learning approach for the prediction of ligand binding sites on proteins.arXiv:2002.056432020
     [Google Scholar]
  16. HeK. ZhangX. RenS. SunJ. Deep residual learning for image recognition.2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)IEEELas Vegas, NV, USA201677077810.1109/CVPR.2016.90
     [Google Scholar]
  17. DesaphyJ. BretG. RognanD. KellenbergerE. sc-PDB: A 3D-database of ligandable binding sites-10 years on.Nucleic Acids Res.201543D1D399D40410.1093/nar/gku92825300483
     [Google Scholar]
  18. LiuZ. SuM. HanL. LiuJ. YangQ. LiY. WangR. Forging the basis for developing protein-ligand interaction scoring functions.Acc. Chem. Res.201750230230910.1021/acs.accounts.6b0049128182403
     [Google Scholar]
  19. IgashovI. PavlichenkoN. GrudininS. Spherical convolutions on molecular graphs for protein model quality assessment.Mach. Learning: Sci. Techno.20212404500510.1088/2632‑2153/abf856
     [Google Scholar]
  20. OlechnovičK. VenclovasČ. Voronota: A fast and reliable tool for computing the vertices of the Voronoi diagram of atomic balls.J. Comput. Chem.201435867268110.1002/jcc.2353824523197
     [Google Scholar]
  21. LeonS.J. BjörckÅ. GanderW. Gram-Schmidt orthogonalization: 100 years and more.Numer. Linear Algebra Appl.201320349253210.1002/nla.1839
     [Google Scholar]
  22. López-BlancoJ.R. ChacónP. KORP: Knowledge-based 6D potential for fast protein and loop modeling.Bioinformatics201935173013301910.1093/bioinformatics/btz02630649193
     [Google Scholar]
  23. EsterM. KriegelH.-P. XuX. A density-based algorithm for discovering clusters in large spatial databases with noise.KDD'96: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining1996226231
     [Google Scholar]
  24. Yizong Cheng Mean shift, mode seeking, and clustering.IEEE Trans. Pattern Anal. Mach. Intell.199517879079910.1109/34.400568
     [Google Scholar]
  25. FeyM. LenssenJ.E. Fast graph representation learning with pytorch geometric.arXiv:1903.024282019
     [Google Scholar]
  26. BernaschiM. AgostiniE. RossettiD. Benchmarking multi-GPU applications on modern multi-GPU integrated systems.Concurr. Comput.20213314e547010.1002/cpe.5470
     [Google Scholar]
  27. AkibaT. SanoS. YanaseT. OhtaT. KoyamaM. Optuna: A next-generation hyperparameter optimization framework.KDD ’19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining20192623263110.1145/3292500.3330701
     [Google Scholar]
  28. ChengT. LiX. LiY. LiuZ. WangR. Comparative assessment of scoring functions on a diverse test set.J. Chem. Inf. Model.20094941079109310.1021/ci900005319358517
     [Google Scholar]
/content/journals/cmc/10.2174/0109298673289137240304165758
Loading
SGPocket: A New Graph Convolutional Neural Network for Ligand-Protein Binding Site Prediction
Curr. Med. Chem. 32, 5996 (2025); https://doi.org/10.2174/0109298673289137240304165758
/content/journals/cmc/10.2174/0109298673289137240304165758
/content/journals/cmc/10.2174/0109298673289137240304165758
Loading

Data & Media loading...

Supplements

Supplementary material is available on the publisher’s website along with the published article.

file format download Download

  • Article Type:     Research Article
Keyword(s): artificial intelligence; binding site prediction; deep learning; graph neural network; Molecular docking; protein-ligand

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test