Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Bioinformatics
  4. Volume 19, Issue 10
  5. Article
Volume 19, Issue 10
  • ISSN: 1574-8936
  • E-ISSN: 2212-392X

Abstract

Background

Conventional approaches to drug discovery are often characterized by lengthy and costly processes. To expedite the discovery of new drugs, the integration of artificial intelligence (AI) in predicting drug-target binding affinity (DTA) has emerged as a crucial approach. Despite the proliferation of deep learning methods for DTA prediction, many of these methods primarily concentrate on the amino acid sequence of proteins. Yet, the interactions between drug compounds and targets occur within distinct segments within the protein structures, whereas the primary sequence primarily captures global protein features. Consequently, it falls short of fully elucidating the intricate relationship between drugs and their respective targets.

Objective

This study aims to employ advanced deep-learning techniques to forecast DTA while incorporating information about the secondary structure of proteins.

Methods

In our research, both the primary sequence of protein and the secondary structure of protein were leveraged for protein representation. While the primary sequence played the role of the overarching feature, the secondary structure was employed as the localized feature. Convolutional neural networks and graph neural networks were utilized to independently model the intricate features of target proteins and drug compounds. This approach enhanced our ability to capture drug-target interactions more effectively.

Results

We have introduced a novel method for predicting DTA. In comparison to DeepDTA, our approach demonstrates significant enhancements, achieving a 3.9% increase in the Concordance Index (CI) and a remarkable 34% reduction in Mean Squared Error (MSE) when evaluated on the KIBA dataset.

Conclusion

In conclusion, our results unequivocally demonstrate that augmenting DTA prediction with the inclusion of the protein's secondary structure as a localized feature yields significantly improved accuracy compared to relying solely on the primary structure.

© 2024 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cbio/10.2174/0115748936285519240110070209
2024-02-06
2024-11-22

  • From This Site

    /content/journals/cbio/10.2174/0115748936285519240110070209
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. DiMasiJ.A. GrabowskiH.G. HansenR.W. Innovation in the pharmaceutical industry: New estimates of R&D costs.J. Health Econ.20164747203310.1016/j.jhealeco.2016.01.012 26928437
     [Google Scholar]
  2. MullardA. New drugs cost US$2.6 billion to develop.Nat. Rev. Drug Discov.20141312877710.1038/nrd4507 25435204
     [Google Scholar]
  3. DingY. TangJ. GuoF. Identification of drug–target interactions via dual laplacian regularized least squares with multiple kernel fusion.Knowl. Base. Syst.202020410625410.1016/j.knosys.2020.106254
     [Google Scholar]
  4. SunM. TiwariP. QianY. DingY. ZouQ. MLapSVM-LBS: Predicting DNA-binding proteins via a multiple Laplacian regularized support vector machine with local behavior similarity.Knowl. Base. Syst.202225010917410.1016/j.knosys.2022.109174
     [Google Scholar]
  5. DingY. TangJ. GuoF. Identification of drug–target interactions via fuzzy bipartite local model.Neural Comput. Appl.20203214103031031910.1007/s00521‑019‑04569‑z
     [Google Scholar]
  6. YamanishiY. KoteraM. KanehisaM. GotoS. Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework.Bioinformatics20102612i246i25410.1093/bioinformatics/btq176 20529913
     [Google Scholar]
  7. GohlkeH. KlebeG. Approaches to the description and prediction of the binding affinity of small-molecule ligands to macromolecular receptors.Angew. Chem. Int. Ed.200241152644267610.1002/1521‑3773(20020802)41:15<2644::AID‑ANIE2644>3.0.CO;2‑O 12203463
     [Google Scholar]
  8. TangJ. SzwajdaA. ShakyawarS. Making sense of large-scale kinase inhibitor bioactivity data sets: A comparative and integrative analysis.J. Chem. Inf. Model.201454373574310.1021/ci400709d 24521231
     [Google Scholar]
  9. FieldingL. NMR methods for the determination of protein–ligand dissociation constants.Prog. Nucl. Magn. Reson. Spectrosc.200751421924210.1016/j.pnmrs.2007.04.001
     [Google Scholar]
  10. CerR.Z. MudunuriU. StephensR. LebedaF.J. IC50-To-Ki: A web-based tool for converting IC50 to Ki values for inhibitors of enzyme activity and ligand binding.Nucleic Acids Res.200937W441-510.1093/nar/gkp253
     [Google Scholar]
  11. YangH. DingY. TangJ. GuoF. Drug–disease associations prediction via multiple Kernel-based dual graph regularized least squares.Appl. Soft Comput.202111210781110.1016/j.asoc.2021.107811
     [Google Scholar]
  12. DingY. TangJ. GuoF. Human protein subcellular localization identification via fuzzy model on kernelized neighborhood representation.Appl. Soft Comput.20209610659610.1016/j.asoc.2020.106596
     [Google Scholar]
  13. WuH. LingH. GaoL. Empirical potential energy function toward ab initio folding G protein-coupled receptors.IEEE/ACM Trans. Comput. Biol. Bioinformatics20211851752176210.1109/TCBB.2020.3008014 32750885
     [Google Scholar]
  14. KarimiM. WuD. WangZ. ShenY. Explainable deep relational networks for predicting compound–protein affinities and contacts.J. Chem. Inf. Model.2021611466610.1021/acs.jcim.0c00866 33347301
     [Google Scholar]
  15. DingY. TangJ. GuoF. Identification of drug-target interactions via multi-view graph regularized link propagation model.Neurocomputing202146161863110.1016/j.neucom.2021.05.100
     [Google Scholar]
  16. WeiningerD. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules.J. Chem. Inf. Model.19882813136
     [Google Scholar]
  17. DingY. TangJ. GuoF. Identification of drug-side effect association via semisupervised model and multiple kernel learning.IEEE J. Biomed. Health Inform.20192362619263210.1109/JBHI.2018.2883834 30507518
     [Google Scholar]
  18. ÖztürkH. ÖzgürA. OzkirimliE. DeepDTA: Deep drug–target binding affinity prediction.Bioinformatics20183417i821i82910.1093/bioinformatics/bty593 30423097
     [Google Scholar]
  19. ÖztürkH. OzkirimliE. ÖzgürA. WideDTA: Prediction of drug-target binding affinity.arXiv:1902041662019
     [Google Scholar]
  20. NguyenT. LeH. QuinnT.P. NguyenT. LeT.D. VenkateshS. GraphDTA: Predicting drug–target binding affinity with graph neural networks.Bioinformatics202037811401147 33119053
     [Google Scholar]
  21. XuK. HuW. LeskovecJ. JegelkaS. How powerful are graph neural networks?arXiv:1810008262019
     [Google Scholar]
  22. Veličković P, Cucurull G, Casanova A, Romero A, Pietro L, Bengio Y. Graph attention networks.arXiv:1710109032017
     [Google Scholar]
  23. KipfT.N. WellingM. Semi-supervised classification with graph convolutional networks.arXiv:1609029072017
     [Google Scholar]
  24. ChuZ. HuangF. FuH. Hierarchical graph representation learning for the prediction of drug-target binding affinity.Inf. Sci.202261350752310.1016/j.ins.2022.09.043
     [Google Scholar]
  25. YangZ. ZhongW. ZhaoL. Yu-ChianC.C. MGraphDTA: Deep multiscale graph neural network for explainable drug–target binding affinity prediction.Chem. Sci.202213381683310.1039/D1SC05180F
     [Google Scholar]
  26. KarimiM. WuD. WangZ. ShenY. DeepAffinity: interpretable deep learning of compound–protein affinity through unified recurrent and convolutional neural networks.Bioinformatics201935183329333810.1093/bioinformatics/btz111 30768156
     [Google Scholar]
  27. KhaQ.H. HoQ.T. LeN.Q.K. Identifying SNARE proteins using an alignment-free method based on multiscan convolutional neural network and PSSM profiles.J. Chem. Inf. Model.202262194820482610.1021/acs.jcim.2c01034 36166351
     [Google Scholar]
  28. YuanQ. ChenK. YuY. LeN.Q.K. ChuaM.C.H. Prediction of anticancer peptides based on an ensemble model of deep learning and machine learning using ordinal positional encoding.Brief. Bioinform.2023241bbac63010.1093/bib/bbac630 36642410
     [Google Scholar]
  29. NguyenT.M. NguyenT. LeT.M. TranT. Gefa: early fusion approach in drug-target affinity prediction.IEEE/ACM Trans. Comput. Biol. Bioinformatics202219271872810.1109/TCBB.2021.3094217 34197324
     [Google Scholar]
  30. PandeyM. RadaevaM. MslatiH. Ligand binding prediction using protein structure graphs and residual graph attention networks.Molecules20222716511410.3390/molecules27165114 36014351
     [Google Scholar]
  31. DavisM.I. HuntJ.P. HerrgardS. Comprehensive analysis of kinase inhibitor selectivity.Nat. Biotechnol.201129111046105110.1038/nbt.1990 22037378
     [Google Scholar]
  32. GuermeurY. GeourjonC. GallinariP. DeléageG. Improved performance in protein secondary structure prediction by inhomogeneous score combination.Bioinformatics199915541342110.1093/bioinformatics/15.5.413 10366661
     [Google Scholar]
  33. CombetC. BlanchetC. GeourjonC. DeléageG. NPS@: network protein sequence analysis.Trends Biochem. Sci.200025314715010.1016/S0968‑0004(99)01540‑6 10694887
     [Google Scholar]
  34. GarnierJ. GibratJ.F. RobsonB. GOR method for predicting protein secondary structure from amino acid sequence.Methods Enzymol199626654055310.1016/S0076‑6879(96)66034‑0 8743705
     [Google Scholar]
  35. LevinJ.M. RobsonB. GarnierJ. An algorithm for secondary structure determination in proteins based on sequence similarity.FEBS Lett.1986205230330810.1016/0014‑5793(86)80917‑6 3743779
     [Google Scholar]
  36. GeourjonC. DeléageG. SOPMA: significant improvements in protein secondary structure prediction by consensus prediction from multiple alignments.Bioinformatics199511668168410.1093/bioinformatics/11.6.681 8808585
     [Google Scholar]
  37. WuH. WangK. LuL. XueY. LyuQ. JiangM. Deep conditional random field approach to transmembrane topology prediction and application to GPCR three-dimensional structure modeling.IEEE/ACM Trans. Comput. Biol. Bioinformatics20171451106111410.1109/TCBB.2016.2602872 27576262
     [Google Scholar]
  38. ChanW.K.B. ZhangH. YangJ. GLASS: A comprehensive database for experimentally validated GPCR-ligand associations.Bioinformatics201531183035304210.1093/bioinformatics/btv302 25971743
     [Google Scholar]
  39. ChouK.C. Prediction of protein cellular attributes using pseudo-amino acid composition.Proteins200143324625510.1002/prot.1035 11288174
     [Google Scholar]
  40. WangH. TangJ. DingY. GuoF. Exploring associations of non-coding RNAs in human diseases via three-matrix factorization with hypergraph-regular terms on center kernel alignment.Brief. Bioinform.2021225bbaa40910.1093/bib/bbaa409 33443536
     [Google Scholar]
  41. MikolovT. ChenK. CorradoG. DeanJ. Efficient estimation of word representations in vector space.arXiv:130137812013
     [Google Scholar]
  42. KabschW. SanderC. Dictionary of protein secondary structure: Pattern recognition of hydrogen-bonded and geometrical features.Biopolymers198322122577263710.1002/bip.360221211 6667333
     [Google Scholar]
  43. LandrumG. RDKit: A software suite for cheminformatics, computational chemistry, and predictive modeling.Greg Landrum2013831
     [Google Scholar]
  44. LiW. MatthewZ. SixinZ. Le CunY. FergusR. Regularization of neural networks using DropConnect.Proceedings of the 30th International Conference on Machine Learning, PMLR.201410581066
     [Google Scholar]
  45. KingmaD. BaJ. Adam: A Method for Stochastic Optimization.Comput. Sci.2014
     [Google Scholar]
  46. NairV. HintonG.E. Rectified linear units improve restricted boltzmann machines.Proceedings of the 27th International Conference on International Conference on Machine Learning (ICML-10)80714
     [Google Scholar]
  47. ChiccoD. WarrensM.J. JurmanG. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation.PeerJ Comput. Sci.20217e62310.7717/peerj‑cs.623 34307865
     [Google Scholar]
  48. BrentnallA.R. CuzickJ. Use of the concordance index for predictors of censored survival data.Stat. Methods Med. Res.20182782359237310.1177/0962280216680245 27920368
     [Google Scholar]
  49. ZhaoQ. XiaoF. YangM. LiY. WangJ. AttentionDTA: Prediction of drug–target binding affinity using attention model.2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).64910.1109/BIBM47256.2019.8983125
     [Google Scholar]
  50. TangZ. LiuX. LiZ. SpaRx: elucidate single-cell spatial heterogeneity of drug responses for personalized treatment.Brief. Bioinform.2023246bbad33810.1093/bib/bbad338 37798249
     [Google Scholar]
  51. TangZ. LiZ. HouT. SiGra: Single-cell spatial elucidation through an image-augmented graph transformer.Nat. Commun.2023141561810.1038/s41467‑023‑41437‑w 37699885
     [Google Scholar]
/content/journals/cbio/10.2174/0115748936285519240110070209
Loading
Enhancing Drug-Target Binding Affinity Prediction through Deep Learning and Protein Secondary Structure Integration
Curr Bioinform 19, 943 (2024); https://doi.org/10.2174/0115748936285519240110070209
/content/journals/cbio/10.2174/0115748936285519240110070209
/content/journals/cbio/10.2174/0115748936285519240110070209
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): convolutional neural network; deep learning; Drug-target binding affinity; graph neural network; protein primary sequence; protein secondary structure

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