Skip to content
2000
Volume 16, Issue 3
  • ISSN: 2210-3155
  • E-ISSN: 2210-3163

Abstract

The investigation of computational techniques to forecast the bioactivity of natural substances has been spurred by the growing interest in utilizing their medicinal potential. A branch of artificial intelligence called deep learning (DL) has been particularly useful for predicting outcomes in a variety of fields, such as bioactivity prediction and drug discovery, by evaluating large amounts of complex data. An overview of current developments in the application of deep learning techniques to the prediction of natural chemical bioactivity has been presented in this article. The advantages provided by deep learning approaches, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and graph neural networks (GNNs), have been highlighted, and the difficulties connected with conventional methods of bioactivity prediction have been examined. Moreover, a variety of molecular representations—such as molecular fingerprints, graph representations, and molecular descriptors—that are fed into deep learning models have been studied. Additionally, included in this study is the integration of many data sources, including omics data, chemical structures, and biological tests, to enhance the precision and resilience of bioactivity prediction models. Furthermore, this review covers the uses of deep learning in target prediction, virtual screening, and poly-pharmacology study of natural substances. The paper concludes by discussing the field's present issues and potential paths forward, such as the requirement for standardized benchmark datasets, the interpretability of deep learning models, and the incorporation of experimental validation techniques. All things considered, this study sheds light on the most recent developments in deep learning techniques for estimating the bioactivity of natural substances and their possible effects on drug development and discovery.

© 2026 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/npj/10.2174/0122103155332267241122143118
2025-01-10
2026-02-11

  • From This Site

    /content/journals/npj/10.2174/0122103155332267241122143118
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. PaulD. SanapG. ShenoyS. KalyaneD. KaliaK. TekadeR.K. Artificial intelligence in drug discovery and development.Drug Discov. Today2021261809310.1016/j.drudis.2020.10.010 33099022
     [Google Scholar]
  2. AshrafF.B. AkterS. MumuS.H. IslamM.U. UddinJ. Bio-activity prediction of drug candidate compounds targeting SARS-CoV-2 using machine learning approaches.PLoS One2023189e028805310.1371/journal.pone.0288053 37669264
     [Google Scholar]
  3. YooS. YangH.C. LeeS. ShinJ. MinS. LeeE. SongM. LeeD. A deep learning-based approach for identifying the medicinal uses of plant-derived natural compounds.Front. Pharmacol.20201158487510.3389/fphar.2020.584875 33519445
     [Google Scholar]
  4. ShinS.H. OhS.M. Yoon ParkJ.H. LeeK.W. YangH. OptNCMiner: A deep learning approach for the discovery of natural compounds modulating disease-specific multi-targets.BMC Bioinformatics202223121810.1186/s12859‑022‑04752‑5 35672685
     [Google Scholar]
  5. ParkJ. BeckB.R. KimH.H. LeeS. KangK. A brief review of machine learning-based bioactive compound research.Appl. Sci.2022126290610.3390/app12062906
     [Google Scholar]
  6. JainP. SharmaM. DhingraD. Bioactivity prediction in drug discovery.IRJMETS2022478725825208
     [Google Scholar]
  7. NothiasL.F. Nothias-EspositoM. da SilvaR. WangM. ProtsyukI. ZhangZ. SarvepalliA. LeyssenP. TouboulD. CostaJ. PaoliniJ. AlexandrovT. LitaudonM. DorresteinP.C. Bioactivity-based molecular networking for the discovery of drug leads in natural product bioassay-guided fractionation.J. Nat. Prod.201881475876710.1021/acs.jnatprod.7b00737 29498278
     [Google Scholar]
  8. AlbergaD. TrisciuzziD. MontaruliM. LeonettiF. MangiatordiG.F. NicolottiO. A new approach for drug target and bioactivity prediction: The multifingerprint similarity search algorithm (MuSSeL).J. Chem. Inf. Model.201959158659610.1021/acs.jcim.8b00698 30485097
     [Google Scholar]
  9. ZhangR. LiX. ZhangX. QinH. XiaoW. Machine learning approaches for elucidating the biological effects of natural products.Nat. Prod. Rep.202138234636110.1039/D0NP00043D 32869826
     [Google Scholar]
  10. van TilborgD. AlenichevaA. GrisoniF. Exposing the limitations of molecular machine learning with activity cliffs.J. Chem. Inf. Model.202262235938595110.1021/acs.jcim.2c01073 36456532
     [Google Scholar]
  11. GeY. ZhouC. MaY. WangZ. WangS. WangW. WuB. Advancing natural product discovery: A structure-oriented fractions screening platform for compound annotation and isolation.Anal. Chem.202496145399540610.1021/acs.analchem.3c05057 38523322
     [Google Scholar]
  12. MoretM. Pachon AngonaI. CotosL. YanS. AtzK. BrunnerC. BaumgartnerM. GrisoniF. SchneiderG. Leveraging molecular structure and bioactivity with chemical language models for de novo drug design.Nat. Commun.202314111410.1038/s41467‑022‑35692‑6 36611029
     [Google Scholar]
  13. AgarwalA. PrajapatiP. PrajapatiB.G. Chemical biology-based toolset for artificial intelligence usage in drug design.In: Artificial Intelligence in Bioinformatics and Chemoinformatics.CRC Press202310111510.1201/9781003353768‑6
     [Google Scholar]
  14. MuhasinaK.M. GhoshP. SwaroopA.K. SelvarajJ. PrajapatiB.G. DuraiswamyB. PalaniswamyD.S. Machine learning and data mining: Uses and challenges in bioinformatics.In: Artificial Intelligence in Bioinformatics and Chemoinformatics.CRC Press2024117138
     [Google Scholar]
  15. LeCunY. BengioY. HintonG. Deep learning.Nature2015521755343644410.1038/nature14539 26017442
     [Google Scholar]
  16. JanieschC. ZschechP. HeinrichK. Machine learning and deep learning.Electron. Mark.202131368569510.1007/s12525‑021‑00475‑2
     [Google Scholar]
  17. Madhava KrishnaG. Advanced machine learning and deep learning approaches for predicting avian influenza outbreaks. (IJRD)20249213010.36713/epra18191
     [Google Scholar]
  18. PaliwalS. SharmaA. JainS. SharmaS. Machine learning and deep learning in bioinformatics.In: Bioinformatics and Computational Biology.Boca RatonChapman and Hall/CRC2023637410.1201/9781003331247‑7
     [Google Scholar]
  19. AlzubaidiL. ZhangJ. HumaidiA.J. Al-DujailiA. DuanY. Al-ShammaO. SantamaríaJ. FadhelM.A. Al-AmidieM. FarhanL. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions.J. Big Data2021815310.1186/s40537‑021‑00444‑8 33816053
     [Google Scholar]
  20. SarkerI.H. Deep learning: A comprehensive overview on techniques, taxonomy, applications and research directions.SN Comput. Sci.20212642010.1007/s42979‑021‑00815‑1 34426802
     [Google Scholar]
  21. ZhangY. YeT. XiH. JuhasM. LiJ. Deep learning driven drug discovery: Tackling severe acute respiratory syndrome coronavirus 2.Front. Microbiol.20211273968410.3389/fmicb.2021.739684 34777286
     [Google Scholar]
  22. AskrH. ElgeldawiE. Aboul EllaH. ElshaierY.A.M.M. GomaaM.M. HassanienA.E. Deep learning in drug discovery: An integrative review and future challenges.Artif. Intell. Rev.20235675975603710.1007/s10462‑022‑10306‑1 36415536
     [Google Scholar]
  23. NagS. BaidyaA.T.K. MandalA. MathewA.T. DasB. DeviB. KumarR. Deep learning tools for advancing drug discovery and development.Biotech2022121210.1007/s13205‑022‑03165‑8
     [Google Scholar]
  24. Blanco-GonzálezA. CabezónA. Seco-GonzálezA. Conde-TorresD. Antelo-RiveiroP. PiñeiroÁ. Garcia-FandinoR. The role of AI in drug discovery: Challenges, opportunities, and strategies.Pharmaceuticals202316689110.3390/ph16060891 37375838
     [Google Scholar]
  25. NaikN. HameedB.M.Z. ShettyD.K. SwainD. ShahM. PaulR. AggarwalK. IbrahimS. PatilV. SmritiK. ShettyS. RaiB.P. ChlostaP. SomaniB.K. Legal and ethical consideration in artificial intelligence in healthcare: Who takes responsibility?Front. Surg.2022986232210.3389/fsurg.2022.862322 35360424
     [Google Scholar]
  26. FarhudD.D. ZokaeiS. Ethical issues of artificial intelligence in medicine and healthcare.Iran. J. Public Health20215011iv10.18502/ijph.v50i11.7600 35223619
     [Google Scholar]
  27. AtanasovA.G. ZotchevS.B. DirschV.M. SupuranC.T. BanachM. RollingerJ.M. BarrecaD. WeckwerthW. BauerR. BayerE.A. MajeedM. BishayeeA. BochkovV. BonnG.K. BraidyN. BucarF. CifuentesA. D’OnofrioG. BodkinM. DiederichM. Dinkova-KostovaA.T. EfferthT. El BairiK. ArkellsN. FanT.P. FiebichB.L. FreissmuthM. GeorgievM.I. GibbonsS. GodfreyK.M. GruberC.W. HeerJ. HuberL.A. IbanezE. KijjoaA. KissA.K. LuA. MaciasF.A. MillerM.J.S. MocanA. MüllerR. NicolettiF. PerryG. PittalàV. RastrelliL. RistowM. RussoG.L. SilvaA.S. SchusterD. SheridanH. Skalicka-WoźniakK. SkaltsounisL. Sobarzo-SánchezE. BredtD.S. StuppnerH. SuredaA. TzvetkovN.T. VaccaR.A. AggarwalB.B. BattinoM. GiampieriF. WinkM. WolfenderJ.L. XiaoJ. YeungA.W.K. LizardG. PoppM.A. HeinrichM. Berindan-NeagoeI. StadlerM. DagliaM. VerpoorteR. SupuranC.T. Natural products in drug discovery: Advances and opportunities.Nat. Rev. Drug Discov.202120320021610.1038/s41573‑020‑00114‑z 33510482
     [Google Scholar]
  28. DzoboK. The role of natural products as sources of therapeutic agents for innovative drug discovery.In: Comprehensive Pharmacology.Elsevier202240842210.1016/B978‑0‑12‑820472‑6.00041‑4
     [Google Scholar]
  29. HarveyA. Natural products in drug discovery.Drug Discov. Today20081319-2089490110.1016/j.drudis.2008.07.004 18691670
     [Google Scholar]
  30. GeY. MaY. ZhaoM. WeiJ. WuX. ZhangZ. YangH. LeiH. WuB. Exploring gabosine and chlorogentisyl alcohol derivatives from a marine-derived fungus as EcGUS inhibitors with informatic assisted approaches.Eur. J. Med. Chem.202224211469910.1016/j.ejmech.2022.114699 36001934
     [Google Scholar]
  31. KoehnF.E. CarterG.T. The evolving role of natural products in drug discovery.Nat. Rev. Drug Discov.20054320622010.1038/nrd1657 15729362
     [Google Scholar]
  32. DiasD.A. UrbanS. RoessnerU. A historical overview of natural products in drug discovery.Metabolites20122230333610.3390/metabo2020303 24957513
     [Google Scholar]
  33. SimobenC.V. BabiakaS.B. MoumbockA.F.A. Namba-NzanguimC.T. EniD.B. Medina-FrancoJ.L. GüntherS. Ntie-KangF. SipplW. Challenges in natural product-based drug discovery assisted with in silico -based methods.RSC Advances20231345315783159410.1039/D3RA06831E 37908659
     [Google Scholar]
  34. Barba-OstriaC. Carrera-PachecoS.E. Gonzalez-PastorR. Heredia-MoyaJ. Mayorga-RamosA. Rodríguez-PólitC. Zúñiga-MirandaJ. Arias-AlmeidaB. GuamánL.P. Evaluation of biological activity of natural compounds: Current trends and methods.Molecules20222714449010.3390/molecules27144490 35889361
     [Google Scholar]
  35. AhmaduT. AhmadK. An introduction to bioactive natural products and general applications.In: Bioactive Natural Products for Pharmaceutical Applications.Springer2021419110.1007/978‑3‑030‑54027‑2_2
     [Google Scholar]
  36. SytarO. SmetanskaI. Special issue “Bioactive compounds from natural sources (2020, 2021)”.Molecules2022276192910.3390/molecules27061929 35335293
     [Google Scholar]
  37. Atas GuvenilirH. DoğanT. How to approach machine learning-based prediction of drug/compound–target interactions.J. Cheminform.20231511610.1186/s13321‑023‑00689‑w 36747300
     [Google Scholar]
  38. PeriwalV. BasslerS. AndrejevS. GabrielliN. PatilK.R. TypasA. PatilK.R. Bioactivity assessment of natural compounds using machine learning models trained on target similarity between drugs.PLOS Comput. Biol.2022184e101002910.1371/journal.pcbi.1010029 35468126
     [Google Scholar]
  39. BéquignonO.J.M. BongersB.J. JespersW. IJzermanA.P. van der WaterB. van WestenG.J.P. Papyrus: A large-scale curated dataset aimed at bioactivity predictions.J. Cheminform.2023151310.1186/s13321‑022‑00672‑x 36609528
     [Google Scholar]
  40. TianT. LiS. ZhangZ. ChenL. ZouZ. ZhaoD. ZengJ. Benchmarking compound activity prediction for real-world drug discovery applications.Commun. Chem.20247112710.1038/s42004‑024‑01204‑4 38834746
     [Google Scholar]
  41. HuangY. GaoB. JiaY. MaH. MaW-Y. ZhangY-Q. LanY. SIU: A million-scale structural small molecule-protein interaction dataset for unbiased bioactivity prediction.Biomolecules2024116
     [Google Scholar]
  42. HuckvaleE.D. PowellC.D. JinH. MoseleyH.N.B. Benchmark dataset for training machine learning models to predict the pathway involvement of metabolites.Metabolites20231311112010.3390/metabo13111120 37999216
     [Google Scholar]
  43. Ó ConchúirS. BarlowK.A PacheR.A OllikainenN. KundertK. O’MearaM.J SmithC.A KortemmeT. A web resource for standardized benchmark datasets, metrics, and rosetta protocols for macromolecular modeling and design.PLoS One2015109e013043310.1371/journal.pone.0130433
     [Google Scholar]
  44. StokesJ.M. YangK. SwansonK. JinW. Cubillos-RuizA. DonghiaN.M. MacNairC.R. FrenchS. CarfraeL.A. Bloom-AckermannZ. TranV.M. Chiappino-PepeA. BadranA.H. AndrewsI.W. ChoryE.J. ChurchG.M. BrownE.D. JaakkolaT.S. BarzilayR. CollinsJ.J. A deep learning approach to antibiotic discovery.Cell20201804688702.e1310.1016/j.cell.2020.01.021 32084340
     [Google Scholar]
  45. YamashitaR. NishioM. DoR.K.G. TogashiK. Convolutional neural networks: An overview and application in radiology.Insights Imaging20189461162910.1007/s13244‑018‑0639‑9 29934920
     [Google Scholar]
  46. HuZ. TangJ. WangZ. ZhangK. ZhangL. SunQ. Deep learning for image-based cancer detection and diagnosis − A survey.Pattern Recognit.20188313414910.1016/j.patcog.2018.05.014
     [Google Scholar]
  47. MayrA. KlambauerG. UnterthinerT. HochreiterS. DeepTox: Toxicity prediction using deep learning.Front. Environ. Sci.2016310.3389/fenvs.2015.00080
     [Google Scholar]
  48. ZhangS. TongH. XuJ. MaciejewskiR. Graph convolutional networks: A comprehensive review.Comput. Soc. Netw.2019611110.1186/s40649‑019‑0069‑y 37915858
     [Google Scholar]
  49. SchmidtR.M. Recurrent neural networks (RNNs): A gentle introduction and overview.arXiv2019
     [Google Scholar]
  50. Van HoudtG. MosqueraC. NápolesG. A review on the long short-term memory model.Artif. Intell. Rev.20205385929595510.1007/s10462‑020‑09838‑1
     [Google Scholar]
  51. MichelucciU. An introduction to autoencoders.ArXiv2022
     [Google Scholar]
  52. XieL. XuL. KongR. ChangS. XuX. Improvement of prediction performance with conjoint molecular fingerprint in deep learning.Front. Pharmacol.20201160666810.3389/fphar.2020.606668 33488387
     [Google Scholar]
  53. HentabliH. BengherbiaB. SaeedF. SalimN. NafeaI. ToubalA. NasserM. Convolutional neural network model based on 2D fingerprint for bioactivity prediction.Int. J. Mol. Sci.202223211323010.3390/ijms232113230 36362018
     [Google Scholar]
  54. GaudeletT. DayB. JamasbA.R. SomanJ. RegepC. LiuG. HayterJ.B.R. VickersR. RobertsC. TangJ. RoblinD. BlundellT.L. BronsteinM.M. Taylor-KingJ.P. Utilizing graph machine learning within drug discovery and development.Brief. Bioinform.2021226bbab15910.1093/bib/bbab159 34013350
     [Google Scholar]
  55. El-AttarN.E. HassanM.K. AlghamdiO.A. AwadW.A. Deep learning model for classification and bioactivity prediction of essential oil-producing plants from Egypt.Sci. Rep.20201012134910.1038/s41598‑020‑78449‑1 33288845
     [Google Scholar]
  56. LiuR. LaxminarayanS. ReifmanJ. WallqvistA. Enabling data-limited chemical bioactivity predictions through deep neural network transfer learning.J. Comput. Aided Mol. Des.2022361286787810.1007/s10822‑022‑00486‑x 36272041
     [Google Scholar]
  57. RaschkaS. KaufmanB. Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition.Methods20201808911010.1016/j.ymeth.2020.06.016 32645448
     [Google Scholar]
  58. SturmN. MayrA. Le VanT. ChupakhinV. CeulemansH. WegnerJ. Golib-DzibJ.F. JeliazkovaN. VandriesscheY. BöhmS. CimaV. MartinovicJ. GreeneN. Vander AaT. AshbyT.J. HochreiterS. EngkvistO. KlambauerG. ChenH. Industry-scale application and evaluation of deep learning for drug target prediction.J. Cheminform.20201212610.1186/s13321‑020‑00428‑5 33430964
     [Google Scholar]
  59. BrownleeJ. Develop deep learning models on theano and tensorflow using keras.J. Chem. Inf. Model.20195316891699
     [Google Scholar]
  60. RuderS. An overview of gradient descent optimization algorithms.arXiv2016
     [Google Scholar]
  61. BergstraJ. BengioY. Random search for hyper-parameter optimization.J. Mach. Learn. Res.20121328130510.5555/2188385.2188395
     [Google Scholar]
  62. SrivastavaN. HintonG. KrizhevskyA. SutskeverI. SalakhutdinovR. Dropout: A simple way to prevent neural networks from overfitting.J. Mach. Learn. Res.2014151929195810.5555/2627435.2670313
     [Google Scholar]
  63. SokolovaM. LapalmeG. A systematic analysis of performance measures for classification tasks.Inf. Process. Manage.200945442743710.1016/j.ipm.2009.03.002
     [Google Scholar]
  64. LundbergS.M. LeeS-I. A unified approach to interpreting model predictions.Adv. Neural Inf. Process. Syst.201711010.5555/3295222.3295230
     [Google Scholar]
  65. Acuña-GuzmanV. Montoya-AlfaroM.E. Negrón-BallarteL.P. Solis-CaleroC. A machine learning approach for predicting caco-2 cell permeability in natural products from the biodiversity in Peru.Pharmaceuticals202417675010.3390/ph17060750 38931417
     [Google Scholar]
  66. GahlM. KimH.W. GlukhovE. GerwickW.H. CottrellG.W. PECAN predicts patterns of cancer cell cytostatic activity of natural products using deep learning.J. Nat. Prod.202487356757510.1021/acs.jnatprod.3c00879 38349959
     [Google Scholar]
  67. LaiJ. HuJ. WangY. ZhouX. LiY. ZhangL. LiuZ. Privileged scaffold analysis of natural products with deep learning‐based indication prediction model.Mol. Inform.20203911200005710.1002/minf.202000057 32406179
     [Google Scholar]
  68. LiuZ. HuangD. ZhengS. SongY. LiuB. SunJ. NiuZ. GuQ. XuJ. XieL. Deep learning enables discovery of highly potent anti-osteoporosis natural products.Eur. J. Med. Chem.202121011298210.1016/j.ejmech.2020.112982 33158578
     [Google Scholar]
  69. HamzaH. NasserM. SalimN. SaeedF. Bioactivity prediction using convolutional neural network.In: Emerging Trends in Intelligent Computing and Informatics.Springer202034135110.1007/978‑3‑030‑33582‑3_33
     [Google Scholar]
  70. KumariM. SubbaraoN. Deep learning model for virtual screening of novel 3C-like protease enzyme inhibitors against SARS coronavirus diseases.Comput. Biol. Med.202113210431710.1016/j.compbiomed.2021.104317 33721736
     [Google Scholar]
  71. TangH. Optimization model performance through pruning techniques.International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2023)2023435410.2991/978‑94‑6463‑370‑2_6
     [Google Scholar]
  72. GalushkaM. SwainC. BrowneF. MulvennaM.D. BondR. GrayD. Prediction of chemical compounds properties using a deep learning model.Neural Comput. Appl.20213320133451336610.1007/s00521‑021‑05961‑4
     [Google Scholar]
/content/journals/npj/10.2174/0122103155332267241122143118
Loading
Deep Learning Approaches for Predicting Bioactivity of Natural Compounds
Natural Products Journal, The 16, e22103155332267 (2026); https://doi.org/10.2174/0122103155332267241122143118
/content/journals/npj/10.2174/0122103155332267241122143118
/content/journals/npj/10.2174/0122103155332267241122143118
Loading

Data & Media loading...


  • Article Type:     Review Article
Keyword(s): bioactivity prediction; computational biology; Deep learning; drug discovery; natural compounds; neural networks

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