Skip to content
2000
Volume 20, Issue 1
  • ISSN: 1573-4099
  • E-ISSN: 1875-6697

Abstract

Background

There has been a growing interest in discovering a viable drug for the new coronavirus (SARS-CoV-2) since the beginning of the pandemic. Protein-ligand interaction studies are a crucial step in the drug discovery process, as it helps us narrow the search space for potential ligands with high drug-likeness. Derivatives of popular drugs like Remdesivir generated through tools employing evolutionary algorithms are usually considered potential candidates. However, screening promising molecules from such a large search space is difficult. In a conventional screening process, for each ligand-target pair, there are time-consuming interaction studies that use docking simulations before downstream tasks like thermodynamic, kinetic, and electrostatic-potential evaluation.

Objective

This work aims to build a model based on deep learning applied over the graph structure of the molecules to accelerate the screening process for novel potential candidates for SARS-CoV-2 by predicting the binding energy of the protein-ligand complex.

Methods

In this work, ‘Graph Convolutional Capsule Regression’ (GCCR), a model which uses Capsule Neural Networks (CapsNet) and Graph Convolutional Networks (GCN) to predict the binding energy of a protein-ligand complex is being proposed. The model’s predictions were further validated with kinetic and free energy studies like Molecular Dynamics (MD) for kinetic stability and MM/GBSA analysis for free energy calculations.

Results

The GCCR showed an RMSE value of 0.0978 for 81.3% of the concordance index. The RMSE of GCCR converged around the iteration of just 50 epochs scoring a lower RMSE than GCN and GAT. When training with Davis Dataset, GCCR gave an RMSE score of 0.3806 with a CI score of 87.5%.

Conclusion

The proposed GCCR model shows great potential in improving the screening process based on binding affinity and outperforms baseline machine learning models like DeepDTA, KronRLS, SimBoost, and other Graph Neural Networks (GNN) based models like Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT).

Loading

Article metrics loading...

/content/journals/cad/10.2174/1573409919666230331083953
2024-01-01
2025-06-12
Loading full text...

Full text loading...

References

  1. World Health OrganizationGlobal Situation of COVID-19.2022Available from: https://covid19.who.int/
  2. GuoY.R. CaoQ.D. HongZ.S. TanY.Y. ChenS.D. JinH.J. TanK.S. WangD.Y. YanY. The origin, transmission and clinical therapies on coronavirus disease 2019 (COVID-19) outbreak-An update on the status.Mil. Med. Res.2020711110.1186/s40779‑020‑00240‑0
    [Google Scholar]
  3. HillenH.S. KokicG. FarnungL. DienemannC. TegunovD. CramerP. Structure of replicating SARS-CoV-2 polymerase.Nature2020584781915415610.1038/s41586‑020‑2368‑832438371
    [Google Scholar]
  4. ZhouG. StewartL. ReggianoG. DiMaioF. Computational drug repurposing studies on SARS-CoV-2 protein targets.ChemRxiv202010.26434/chemrxiv.12315437.v1
    [Google Scholar]
  5. SelvarajJ. Sundar PS. RajanL. SelvarajD. PalanisamyD. Namboori PKK. MohankumarS.K. Identification of (2 R, 3 R)-2-(3,4-dihydroxyphenyl)chroman-3-yl-3,4,5-trihydroxy benzoate as multiple inhibitors of SARS-CoV-2 targets; a systematic molecular modelling approach.RSC Advances20211122130511306010.1039/D1RA01603B35423848
    [Google Scholar]
  6. PahikkalaT. AirolaA. PietiläS. ShakyawarS. SzwajdaA. TangJ. AittokallioT. Toward more realistic drug-target interaction predictions.Brief. Bioinform.201516232533710.1093/bib/bbu01024723570
    [Google Scholar]
  7. HeT. HeidemeyerM. BanF. CherkasovA. EsterM. SimBoost: A read-across approach for predicting drug-target binding affinities using gradient boosting machines.J. Cheminform.2017912410.1186/s13321‑017‑0209‑z29086119
    [Google Scholar]
  8. ÖztürkH. ÖzgürA. OzkirimliE. DeepDTA: Deep drug-target binding affinity prediction.Bioinformatics20183417i821i82910.1093/bioinformatics/bty59330423097
    [Google Scholar]
  9. IoannidisV.N. MarquesA.G. GiannakisG.B. Graph Neural Networks for Predicting Protein Functions.In. 2019 IEEE 8th International Workshop on Computational Advances in MultiSensor Adaptive Processing (CAMSAP)15-18 December 2019Le gosier, Guadeloupe 201922122510.1109/CAMSAP45676.2019.9022646
    [Google Scholar]
  10. ZhouJ. CuiG. HuS. ZhangZ. YangC. LiuZ. WangL. LiC. SunM. Graph neural networks: A review of methods and applications.AI Open20201578110.1016/j.aiopen.2021.01.001
    [Google Scholar]
  11. DavidL. ThakkarA. MercadoR. EngkvistO. Molecular representations in AI-driven drug discovery: A review and practical guide.J. Cheminform.20201215610.1186/s13321‑020‑00460‑533431035
    [Google Scholar]
  12. ScarselliF. GoriM. HagenbuchnerM. MonfardiniG. MonfardiniG. The graph neural network model.IEEE Trans. Neural Netw.2009201618010.1109/TNN.2008.200560519068426
    [Google Scholar]
  13. GilmerJ. SchoenholzS.S. RileyP.F. VinyalsO. DahlG.E. Neural Message Passing for Quantum Chemistry.International conference on machine learning.201712631272
    [Google Scholar]
  14. KipfT.N. WellingM. Semi-supervised classification with graph convolutional networks.arXiv201610.48550/arXiv.1609.02907
    [Google Scholar]
  15. BrunaJ. ZarembaW. SzlamA. LeCunY. Spectral networks and locally connected networks on graphs.arXiv201310.48550/arXiv.1312.6203
    [Google Scholar]
  16. DefferrardM. BressonX. VandergheynstP. Convolutional neural networks on graphs with fast localized spectral filtering.Adv. Neural Inf. Process. Syst.201629Available from: https://proceedings.neurips.cc/paper/2016/hash/04df4d434d481c5bb723be1b6df1ee65-Abstract.html
    [Google Scholar]
  17. HintonG.E. KrizhevskyA. WangS.D. Transforming Auto-encoders. HonkelaT. DuchW. GirolamiM. KaskiS. artificial neural networks and machine learning- ICANN 2011. ICANN 2011SpringerBerlin, Heidelberg2011445110.1007/978‑3‑642‑21735‑7_6
    [Google Scholar]
  18. SabourS. FrosstN. HintonG.E. Dynamic routing between capsules.Adv. Neural Inf. Process. Syst.201730
    [Google Scholar]
  19. ElnaggarA. HeinzingerM. DallagoC. RihawiG. WangY. JonesL. GibbsT. FeherT. AngererC. SteineggerM. ProtTrans: Towards cracking the language of Life’s code through self-supervised deep learning and high performance computing.arXiv202010.48550/arXiv.2007.06225
    [Google Scholar]
  20. DavisM.I. HuntJ.P. HerrgardS. CiceriP. WodickaL.M. PallaresG. HockerM. TreiberD.K. ZarrinkarP.P. Comprehensive analysis of kinase inhibitor selectivity.Nat. Biotechnol.201129111046105110.1038/nbt.199022037378
    [Google Scholar]
  21. PushkaranA.C. Nath ENP. MelgeA.R. PuthiyedathR. MohanC.G. A phytochemical-based medication search for the SARS-CoV-2 infection by molecular docking models towards spike glycoproteins and main proteases.RSC Advances20211120120031201410.1039/D0RA10458B35423778
    [Google Scholar]
  22. HaridasM. SasidharV. NathP. AbhithajJ. SabuA. RammanoharP. Compounds of citrus medica and zingiber officinale for COVID-19 inhibition: In silico evidence for cues from ayurveda.Futur. J. Pharm. Sci.202171910.1186/s43094‑020‑00171‑633457429
    [Google Scholar]
  23. NareshP. SelvarajA. Shyam SundarP. MurugesanS. SathianarayananS. NambooriP.K. Targeting a conserved pocket (n-octyl-β-D–glucoside) on the dengue virus envelope protein by small bioactive molecule inhibitors.J. Biomol. Struct. Dyn.202040114866487810.1080/07391102.2020.186270733345726
    [Google Scholar]
  24. SanderT. FreyssJ. von KorffM. RufenerC. DataWarrior: An open-source program for chemistry aware data visualization and analysis.J. Chem. Inf. Model.201555246047310.1021/ci500588j25558886
    [Google Scholar]
  25. KukolA. Molecular modeling of proteins.Totowa, New JerseySpringer200844310.1007/978‑1‑59745‑177‑2
    [Google Scholar]
  26. GaillardT. Evaluation of autodock and autodock vina on the CASF-2013 benchmark.J. Chem. Inf. Model.20185881697170610.1021/acs.jcim.8b0031229989806
    [Google Scholar]
  27. DengC. ZhangL. CenY. Retrieval of chemical oxygen demand through modified capsule network based on hyperspectral data.Appl. Sci.2019921462010.3390/app9214620
    [Google Scholar]
  28. SmithT.F. WatermanM.S. Identification of common molecular subsequences.J. Mol. Biol.1981147119519710.1016/0022‑2836(81)90087‑57265238
    [Google Scholar]
  29. KnutsonC. BonthaM. BilbreyJ.A. KumarN. Decoding the protein-ligand interactions using parallel graph neural networks.Sci. Rep.2022121762410.1038/s41598‑022‑10418‑235538084
    [Google Scholar]
  30. GonenM. HellerG. Concordance probability and discriminatory power in proportional hazards regression.Biometrika200592496597010.1093/biomet/92.4.965
    [Google Scholar]
/content/journals/cad/10.2174/1573409919666230331083953
Loading
/content/journals/cad/10.2174/1573409919666230331083953
Loading

Data & Media loading...

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