Bridging chemical space and biological efficacy: advances and challenges in applying generative models in structural modification of natural products

doi:10.1007/s13659-025-00521-y

Natural Products and Bioprospecting ›› 2025, Vol. 15 ›› Issue (4): 37-37.DOI: 10.1007/s13659-025-00521-y

• REVIEW • Previous Articles Next Articles

Bridging chemical space and biological efficacy: advances and challenges in applying generative models in structural modification of natural products

Chuan-Su Liu^1,2, Bing-Chao Yan², Han-Dong Sun², Jin-Cai Lu¹, Pema-Tenzin Puno²

1. School of Traditional Chinese Materia Medica, Shenyang Pharmaceutical University, Shenyang, 110016, Liaoning, China;
2. State Key Laboratory of Phytochemistry and Natural Medicines, Kunming Institute of Botany, Chinese Academy of Sciences, Kunming, 650201, Yunnan, China

Received:2025-04-13 Accepted:2025-05-13 Online:2025-06-06 Published:2025-08-23
Supported by:
This work was financially supported by the National Science Fund for Distinguished Young Scholars (82325047), Regional Innovation and Development Joint Fund of NSFC (U24A20807), Youth Innovation Promotion Association CAS (2023411), National Natural Science Foundation of China (22477123), Major Projects for Fundamental Research of Yunnan Province (202201BC070002), CAS “Light of West China” Program and CAS Interdisciplinary Innovation Team (xbzg-zdsys-202303), Yunnan Revitalization Talent Support Program: Yunling Scholar Project, Yunnan Province Science and Technology Department (202305AH340005).

Bridging chemical space and biological efficacy: advances and challenges in applying generative models in structural modification of natural products

Chuan-Su Liu^1,2, Bing-Chao Yan², Han-Dong Sun², Jin-Cai Lu¹, Pema-Tenzin Puno²

1. School of Traditional Chinese Materia Medica, Shenyang Pharmaceutical University, Shenyang, 110016, Liaoning, China;
2. State Key Laboratory of Phytochemistry and Natural Medicines, Kunming Institute of Botany, Chinese Academy of Sciences, Kunming, 650201, Yunnan, China

通讯作者: Jin-Cai Lu, E-mail:jincailu@126.com;Pema-Tenzin Puno, E-mail:punopematenzin@mail.kib.ac.cn
基金资助:
This work was financially supported by the National Science Fund for Distinguished Young Scholars (82325047), Regional Innovation and Development Joint Fund of NSFC (U24A20807), Youth Innovation Promotion Association CAS (2023411), National Natural Science Foundation of China (22477123), Major Projects for Fundamental Research of Yunnan Province (202201BC070002), CAS “Light of West China” Program and CAS Interdisciplinary Innovation Team (xbzg-zdsys-202303), Yunnan Revitalization Talent Support Program: Yunling Scholar Project, Yunnan Province Science and Technology Department (202305AH340005).

Abstract

Abstract: Natural products (NPs) are invaluable resources for drug discovery, characterized by their intricate scaffolds and diverse bioactivities. AI drug discovery & design (AIDD) has emerged as a transformative approach for the rational structural modification of NPs. This review examines a variety of molecular generation models since 2020, focusing on their potential applications in two primary scenarios of NPs structure modification: modifications when the target is identified and when it remains unidentified. Most of the molecular generative models discussed herein are open-source, and their applicability across different domains and technical feasibility have been evaluated. This evaluation was accomplished by integrating a limited number of research cases and successful practices observed in the molecular optimization of synthetic compounds. Furthermore, the challenges and prospects of employing molecular generation modeling for the structural modification of NPs are discussed.

Key words: Natural products, Artificial intelligence, Molecular generative models, Structural modification

摘要： Natural products (NPs) are invaluable resources for drug discovery, characterized by their intricate scaffolds and diverse bioactivities. AI drug discovery & design (AIDD) has emerged as a transformative approach for the rational structural modification of NPs. This review examines a variety of molecular generation models since 2020, focusing on their potential applications in two primary scenarios of NPs structure modification: modifications when the target is identified and when it remains unidentified. Most of the molecular generative models discussed herein are open-source, and their applicability across different domains and technical feasibility have been evaluated. This evaluation was accomplished by integrating a limited number of research cases and successful practices observed in the molecular optimization of synthetic compounds. Furthermore, the challenges and prospects of employing molecular generation modeling for the structural modification of NPs are discussed.

关键词: Natural products, Artificial intelligence, Molecular generative models, Structural modification

Chuan-Su Liu, Bing-Chao Yan, Han-Dong Sun, Jin-Cai Lu, Pema-Tenzin Puno. Bridging chemical space and biological efficacy: advances and challenges in applying generative models in structural modification of natural products[J]. Natural Products and Bioprospecting, 2025, 15(4): 37-37.

References

[1] Cragg GM, Newman DJ. Natural products: a continuing source of novel drug leads. Biochem Biophys Acta. 2013;1830:3670-95.
[2] Baker DD, Chu M, Oza U, Rajgarhia V. The value of natural products to future pharmaceutical discovery. Nat Prod Rep. 2007;24:1225-44.
[3] Newman DJ, Cragg GM. Natural products as sources of new drugs over the nearly four decades from 01/1981 to 09/2019. J Nat Prod. 2020;83:770-803.
[4] Brown DG, Lister T, May-Dracka TL. New natural products as new leads for antibacterial drug discovery. Bioorg Med Chem Let. 2014;24:413-8.
[5] Harvey AL, Edrada-Ebel R, Quinn RJ. The re-emergence of natural products for drug discovery in the genomics era. Nat Rev Drug Discov. 2015;14:111-29.
[6] Hai Q-X, Hu K, Chen S-P, Fu Y-Y, Li X-N, Sun H-D, He H-P, Puno P-T. Silvaticusins A-D: ent-kaurane diterpenoids and a cyclobutane-containing ent-kaurane dimer from Isodon silvaticus. Nat Prod Bioprospect. 2024;14:1-8.
[7] Rashad M, Sampò S, Cataldi A, Zara S. Biological activities of gastropods secretions: snail and slug slime. Nat Prod Bioprospect. 2023;13:1-9.
[8] Banerjee S, Cabrera-Barjas G, Tapia J, Fabi JP, Delattre C, Banerjee A. Characterization of Chilean hot spring-origin Staphylococcus sp. BSP3 produced exopolysaccharide as biological additive. Nat Prod Bioprospect. 2024;14:1-16.
[9] Eberhardt L, Kumar K, Waldmann H. Exploring and exploiting biologically relevant chemical space. Curr Drug Targets. 2011;12:1531-46.
[10] Chen J-C, Li W-L, Yao H-Q, Xu J-Y. Insights into drug discovery from natural products through structural modification. Fitoterapia. 2015;103:231-41.
[11] Rodrigues T, Reker D, Schneider P, Schneider G. Counting on natural products for drug design. Nat Chem. 2016;8:531-41.
[12] Yao H, Liu J-K, Xu S-T, Zhu Z-Y, Xu J-Y. The structural modification of natural products for novel drug discovery. Expert Opin Drug Discovery. 2017;12:121-40.
[13] Haynes RK, Fugmann B, Stetter J, Rieckmann K, Heilmann H-D, Chan H-W, Cheung M-K, Lam W-L, Wong H-N, Croft SL, Vivas L, Rattray L, Stewart L, Peters W, Robinson BL, Edstein MD, Kotecka B, Kyle DE, Beckermann B, Gerisch M, Radtke M, Schmuck G, Steinke W, Wollborn U, Schmeer K, Römer A. Artemisone—a highly active antimalarial drug of the artemisinin class. Angew Chem Int Ed. 2006;45:2082-8.
[14] Pereira AR, Strangman WK, Marion F, Feldberg L, Roll D, Mallon R, Hollander I, Andersen RJ. Synthesis of phosphatidylinositol 3-kinase (PI3K) inhibitory analogues of the sponge meroterpenoid liphagal. J Med Chem. 2010;53:8523-33.
[15] Wang S-Z, Dong G-Q, Sheng C-Q. Structural simplification of natural products. Chem Rev. 2019;119:4180-220.
[16] Gromiha MM, Harini K. Protein-nucleic acid complexes: docking and binding affinity. Curr Opin Struct Biol. 2025;90:1-9.
[17] Panigrahi D, Sahu SK, Panigrahi D, Sahu SK. Computational approaches: atom-based 3D-QSAR, molecular docking, ADME-Tox, MD simulation and DFT to find novel multi-targeted anti-tubercular agents. BMC Chem. 2025;19:1-28.
[18] Zhavoronkov A, Ivanenkov YA, Aliper A, Veselov MS, Aladinskiy VA, Aladinskaya AV, Terentiev VA, Polykovskiy DA, Kuznetsov MD, Asadulaev A, Volkov Y, Zholus A, Shayakhmetov RR, Zhebrak A, Minaeva LI, Zagribelnyy BA, Lee LH, Soll R, Madge D, Xing L, Guo T, Aspuru-Guzik A. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Nat Biotechnol. 2019;37:1038-40.
[19] Jiang D, Hsieh C-Y, Wu Z-X, Kang Y, Wang J, Wang E, Liao B, Shen C, Xu L, Wu J, Cao D-S, Hou T-J. Interactiongraphnet: a novel and efficient deep graph representation learning framework for accurate protein-ligand interaction predictions. J Med Chem. 2021;64:18209-32.
[20] Cao D-H, Chen M-A, Zhang R-Z, Wang Z-K, Huang M-L, Yu J, Jiang X-Y, Fan Z-H, Zhang W, Zhou H, Li X-T, Fu Z-Y, Zhang S-L, Zheng M-Y. SurfDock is a surface-informed diffusion generative model for reliable and accurate protein-ligand complex prediction. Nat Methods. 2024;22:310-22.
[21] Zhang O, Lin H-T, Zhang H, Zhao H-F, Huang Y-F, Hsieh C-Y, Pan P-C, Hou T-J. Deep lead optimization: leveraging generative AI for structural modification. J Am Chem Soc. 2024;146:31357-70.
[22] Acharya A, Nagpure M, Roy N, Gupta V, Patranabis S, Guchhait SK. How to nurture natural products to create new therapeutics: strategic innovations and molecule-to-medicinal insights into therapeutic advancements. Drug Discov Today. 2024;29:1-19.
[23] Cross S, Cruciani G. FragExplorer: GRID-based fragment growing and replacement. J Chem Inf Model. 2022;62:1224-35.
[24] Schneider G, Neidhart W, Giller T, Schmid G. “Scaffold-Hopping” by topological pharmacophore search: a contribution to virtual screening. Angew Chem Int Ed. 1999;38:2894-6.
[25] Erlanson DA, McDowell RS, O’Brien T. Fragment-based drug discovery. J Med Chem. 2004;47:3463-82.
[26] Jhoti H, Williams G, Rees DC, Murray CW, Jhoti H, Williams G, Rees DC, Murray CW. The “rule of three” for fragment-based drug discovery: where are we now? Nat Rev Drug Discov. 2013;12:1-2.
[27] Gagare S, Patil P, Jain A. Natural product-inspired strategies towards the discovery of novel bioactive molecules. Future J Pharm Sci. 2024;10:1-23.
[28] Chen X, Varghese S, Zhang Z-Y, Du J-C, Ruan B-F, Baell JB, Liu X-H. Drug discovery and optimization based on the co-crystal structure of natural product with target. Eur J Med Chem. 2024;266:116-26.
[29] Sakano K, Furui K, Ohue M. NPGPT: natural product-like compound generation with GPT-based chemical language models. J Supercomput. 2024;81:1-16.
[30] Welsch ME, Snyder SA, Stockwell BR. Privileged scaffolds for library design and drug discovery. Curr Opin Chem Biol. 2010;14:347-61.
[31] Green H, Koes DR, Durrant JD. DeepFrag: a deep convolutional neural network for fragment-based lead optimization. Chem Sci. 2021;12:8036-47.
[32] Yang S, Hwang D, Lee S, Ryu S, Hwang SJ. Hit and lead discovery with explorative RL and fragment-based molecule generation. arXiv preprint arXiv: 2110.01219 [Online], 2023.
[33] Telepov A, Tsypin A, Khrabrov K, Yakukhnov S, Strashnov P, Zhilyaev P, Rumiantsev E, Ezhov D, Avetisian M, Popova O, Kadurin A. FREED++: improving RL agents for fragment-based molecule generation by thorough reproduction. arXiv preprint arXiv: 2401.09840 [Online], 2024.
[34] Imrie F, Hadfield TE, Bradley AR, Deane CM. Deep generative design with 3D pharmacophoric constraints. Chem Sci. 2021;12:14577-89.
[35] Hadfield TE, Imrie F, Merritt A, Birchall K, Deane CM. Incorporating target-specific pharmacophoric information into deep generative models for fragment elaboration. J Chem Inf Model. 2022;62:2280-92.
[36] Eguida M, Schmitt-Valencia C, Hibert M, Villa P, Rognan D. Target-focused library design by pocket-applied computer vision and fragment deep generative linking. J Med Chem. 2022;65:13771-83.
[37] Zhang Z-X, Liu Q. Learning subpocket prototypes for generalizable structure-based drug design. arXiv preprint arXiv: 2305.13997 [Online], 2023.
[38] Shen T, Seo S, Lee G, Pandey M, Smith JR, Cherkasov A, Kim WY, Ester M. TacoGFN: target-conditioned GFlowNet for structure-based drug design. arXiv preprint arXiv: 2310.03223 [Online], 2024
[39] Zhu H-M, Zhou R-Y, Cao D-S, Tang J, Li M. A pharmacophore-guided deep learning approach for bioactive molecular generation. Nat Commun. 2023;14:1-11.
[40] Powers AS, Yu HH, Suriana P, Koodli RV, Lu T, Paggi JM, Dror RO. Geometric deep learning for structure-based ligand design. ACS Cent Sci. 2023;9:2257-67.
[41] Lin H-T, Huang Y-F, Zhang O, Wu L-R, Li S-Y, Chen Z-Y, Li SZ. Functional-group-based diffusion for pocket-specific molecule generation and elaboration. arXiv preprint arXiv: 2306.13769 [Online], 2024.
[42] Li X-Z, Wang P-L, Fu T-F, Gao W-H, Li C-T, Shi L-L, Liu J-H. AUTODIFF: autoregressive diffusion modeling for structure-based drug design. arXiv preprint arXiv: 2404.02003 [Online], 2024.
[43] Yang Y-W, Ouyang S-Q, Hu X-Y, Zheng M-Y, Zhou H, Li L. Structure-based drug design via 3D molecular generative pre-training and sampling. arXiv preprint arXiv: 2402.14315 [Online], 2024.
[44] McNaughton AD, Bontha MS, Knutson CR, Pope JA, Kumar N. De novo design of protein target specific scaffold-based inhibitors via reinforcement learning. arXiv preprint arXiv: 2205.10473 [Online], 2022.
[45] Xie J-J, Chen S, Lei J-P, Yang Y-D. DiffDec: structure-aware scaffold decoration with an end-to-end diffusion model. J Chem Inf Model. 2024;64:2554-64.
[46] Ghorbani M, Gendelev L, Beroza P, Keiser MJ. Autoregressive fragment-based diffusion for pocket-aware ligand design. arXiv preprint arXiv: 2401.05370 [Online], 2023
[47] Huang L, Xu T-Y, Yu Y, Zhao P-L, Chen X-J, Han J, Xie Z, Li H-L, Zhong W-G, Wong K-C, Zhang H-T. A dual diffusion model enables 3D molecule generation and lead optimization based on target pockets. Nat Commun. 2024;15:1-15.
[48] Zhung W, Kim H, Kim WY. 3D molecular generative framework for interaction-guided drug design. Nat Commun. 2024;15:1-12.
[49] Sako M, Yasuo N, Sekijima M. DiffInt: a diffusion model for structure-based drug design with explicit hydrogen bond interaction guidance. J Chem Inf Model. 2024;65:71-82.
[50] Xue Z, Sun C-W, Zheng W-H, Lv J-C, Liu X-G. TargetSA: adaptive simulated annealing for target-specific drug design. Bioinformatics. 2024;41:1-9.
[51] Chen S-C, Zhang O, Jiang C-R, Zhao H-F, Zhang X-J, Chen M-T, Liu Y, Su Q, Wu Z-X, Wang X-Y, Qu W-L, Ye Y-Y, Chai X, Wang N, Wang T-Y, An Y, Wu G-L, Yang Q-Q, Chen J-A, Xie W, Lin H-T, Li D, Hsieh C-Y, Huang Y, Kang Y, Hou T-J, Pan P-C. Deep lead optimization enveloped in protein pocket and its application in designing potent and selective ligands targeting LTK protein. Nat Mach Intell. 2025;7:448-58.
[52] Weller JA, Rohs R. Structure-based drug design with a deep hierarchical generative model. J Chem Inf Model. 2024;64:6450-63.
[53] Sommer K, Flachsenberg F, Rarey M. NAOMInext-synthetically feasible fragment growing in a structure-based design context. Eur J Med Chem. 2019;163:747-62.
[54] Chevillard F, Kolb P. SCUBIDOO: a large yet screenable and easily searchable database of computationally created chemical compounds optimized toward high likelihood of synthetic tractability. J Chem Inf Model. 2015;55:1824-35.
[55] Arús-Pous J, Patronov A, Bjerrum EJ, Tyrchan C, Reymond J-L, Chen H, Engkvist O. SMILES-based deep generative scaffold decorator for de-novo drug design. J Cheminform. 2020;12:1-18.
[56] Fialková V, Zhao J, Papadopoulos K, Engkvist O, Bjerrum EJ, Kogej T, Patronov A. LibINVENT: reaction-based generative scaffold decoration for in silico library design. J Chem Inf Model. 2021;62:2046-63.
[57] Langevin M, Minoux H, Levesque M, Bianciotto M. Scaffold-constrained molecular generation. J Chem Inf Model. 2020;60:5637-46.
[58] Loeffler HH, He J, Tibo A, Janet JP, Voronov A, Mervin LH, Engkvist O. Reinvent 4: modern AI-driven generative molecule design. J Cheminform. 2024;16:1-16.
[59] Noutahi E, Gabellini C, Craig M, Lim JSC, Tossou P. Gotta be SAFE: a new framework for molecular design. Digit Discov. 2024;3:796-804.
[60] Bagal V, Aggarwal R, Vinod PK, Priyakumar UD. MolGPT: molecular generation using a transformer-decoder model. J Chem Inf Model. 2021;62:2064-76.
[61] Kaitoh K, Yamanishi Y. Scaffold-retained structure generator to exhaustively create molecules in an arbitrary chemical space. J Chem Inf Model. 2022;62:2212-25.
[62] Liao Z-R, Xie L, Mamitsuka H, Zhu S-F. Sc2Mol: a scaffold-based two-step molecule generator with variational autoencoder and transformer. Bioinformatics. 2023;39:1-9.
[63] Lim J, Hwang S-Y, Moon S, Kim S, Kim WY. Scaffold-based molecular design with a graph generative model. Chem Sci. 2020;11:1153-64.
[64] Liu X, Ye K, van Vlijmen HWT, IJzerman AP, van Westen GJP. DrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learning. J Cheminform. 2023;15:1-14.
[65] Xu M-Y, Chen H-M. Tree-Invent: a novel multipurpose molecular generative model constrained with a topological tree. J Chem Inf Model. 2023;63:7067-82.
[66] Maziarz K, Jackson-Flux H, Cameron P, Sirockin F, Schneider N, Stiefl N, Segler M, Brockschmidt M. Learning to extend molecular scaffolds with structural motifs. arXiv preprint arXiv: 2110.01219 [Online], 2024.
[67] Gao Z-X, Wang X-Y, Gaines BB, Shi X-T, Bi J-B, Song M-H. Fragment-based deep molecular generation using hierarchical chemical graph representation and multi-resolution graph variational autoencoder. Mol Inform. 2023;42:1-15.
[68] Joshi RP, Gebauer NWA, Bontha M, Khazaieli M, James RM, Brown JB, Kumar N. 3D-Scaffold: a deep learning framework to generate 3D coordinates of drug-like molecules with desired scaffolds. J Phys Chem. 2021;125:12166-76.
[69] Xu C, Liu R-D, Huang S-H, Li W-C, Li Z, Luo H-B. 3D-SMGE: a pipeline for scaffold-based molecular generation and evaluation. Brief Bioinform. 2023;24:1-11.
[70] Zheng S-J, Lei Z-R, Ai H-T, Chen H-M, Deng D-G, Yang Y-D. Deep scaffold hopping with multimodal transformer neural networks. J Cheminform. 2021;13:1-15.
[71] Yu Y, Xu T-Y, Li J-W, Qiu Y-P, Rong Y, Gong Z, Cheng X-M, Dong L-M, Liu W, Li J, Dou D-F, Huang J-Z. A novel scalarized scaffold hopping algorithm with graph-based variational autoencoder for discovery of JAK1 inhibitors. ACS Omega. 2021;6:22945-54.
[72] Hu C, Li S, Yang C-X, Chen J, Xiong Y, Fan G-S, Liu H, Hong L. ScaffoldGVAE: scaffold generation and hopping of drug molecules via a variational autoencoder based on multi-view graph neural networks. J Cheminform. 2023;15:1-17.
[73] Torge J, Harris C, Mathis SV, Lio P. DiffHopp: a graph diffusion model for novel drug design via scaffold hopping. arXiv preprint arXiv: 2308.07416 [Online], 2023.
[74] Igashov I, Stärk H, Vignac C, Schneuing A, Satorras VG, Frossard P, Welling M, Bronstein M, Correia B. Equivariant 3D-conditional diffusion model for molecular linker design. Nat Mach Intell. 2024;6:417-27.
[75] Imrie F, Bradley AR, Schaar MVD, Deane CM. Deep generative models for 3D linker design. J Chem Inf Model. 2020;60:1983-95.
[76] Yang Y-Y, Zheng S-J, Su S-M, Zhao C, Xu J, Chen H-M. SyntaLinker: automatic fragment linking with deep conditional transformer neural networks. Chem Sci. 2020;11:8312-22.
[77] Feng Y, Yang Y-Y, Deng W-B, Chen H-M, Ran T. SyntaLinker-Hybrid: a deep learning approach for target specific drug design. Artif Intell Life Sci. 2022;2:1-11.
[78] Tan Y-H, Dai L-X, Huang W-F, Guo Y-F, Zheng S-J, Lei J-P, Chen H-M, Yang Y-D. DRlinker: deep reinforcement learning for optimization in fragment linking design. J Chem Inf Model. 2022;62:5907-17.
[79] Zhang H, Huang J-C, Xie J-J, Huang W-F, Yang Y-D, Xu M-Y, Lei J-P, Chen H-M. GRELinker: a graph-based generative model for molecular linker design with reinforcement and curriculum learning. J Chem Inf Model. 2024;64:666-76.
[80] Guo J, Knuth F, Margreitter C, Janet JP, Papadopoulos K, Engkvist O, Patronov A. Link-INVENT: generative linker design with reinforcement learning. Digit Discov. 2023;2:392-408.
[81] Blaschke T, Arús-Pous J, Chen H-M, Margreitter C, Tyrchan C, Engkvist O, Papadopoulos K, Patronov A. REINVENT 2.0: an AI yool for de novo drug design. J Chem Inf Model. 2020;60:5918-22.
[82] Wang Z-L, Yang L-Y, Zhao X-E. Co-crystallization and structure determination: an effective direction for anti-SARS-CoV-2 drug discovery. Comput Struct Biotechnol J. 2021;19:4684-701.
[83] Wang Y-T, Long X-Y, Ding X, Fan S-R, Cai J-Y, Yang B-J, Zhang X-F, Luo R-H, Yang L, Ruan T, Ren J, Jing C-X, Zheng Y-T, Hao X-J, Chen D-Z. Novel nucleocapsid protein-targeting phenanthridine inhibitors of SARS-CoV-2. Eur J Med Chem. 2022;227:1-12.
[84] Xiang Z-R, Fan S-R, Ren J, Ruan T, Chen Y, Zhang Y-W, Wang Y-T, Yu Z-Z, Wang C-F, Sun X-L, Hao X-J, Chen D-Z. Utilizing artificial intelligence for precision exploration of N protein targeting phenanthridine SARS-CoV-2 inhibitors: a novel approach. Eur J Med Chem. 2024;279:1-19.
[85] Fortune JM, Osheroff N. Topoisomerase II as a target for anticancer drugs: when enzymes stop being nice. Prog Nucleic Acid Res Mol Biol. 2000;64:221-53.
[86] Pogorelčnik B, Brvar M, Zajc I, Filipič M, Solmajer T, Perdih A. Monocyclic 4-amino-6-(phenylamino)-1,3,5-triazines as inhibitors of human DNA topoisomerase IIα. Bioorg Med Chem Let. 2014;24:5762-8.
[87] Herlah B, Goričan T, Benedik NS, Grdadolnik SG, Sosič I, Perdih A. Simulation- and AI-directed optimization of 4,6-substituted 1,3,5-triazin-2(1H)-ones as inhibitors of human DNA topoisomerase IIα. Comput Struct Biotechnol J. 2024;23:2995-3018.
[88] Saini A, Patel R, Gaba S, Singh G, Gupta GD, Monga V. Adenosine receptor antagonists: recent advances and therapeutic perspective. Eur J Med Chem. 2022;227:1-29.
[89] Qin R, Zhang H, Huang W-F, Shao Z-L, Lei J-P. Deep learning-based design and screening of benzimidazole-pyrazine derivatives as adenosine A2B receptor antagonists. J Biomol Struct Dyn. 2023;43:3225-41
[90] Liu M-Y, Zhang J-F, Li X-X, Wang Y-X. Research progress of DDR1 inhibitors in the treatment of multiple human diseases. Eur J Med Chem. 2024;268:1-21.
[91] Wang Y-L, Dai Y, Wu X-W, Li F, Liu B, Li C-P, Liu Q-F, Zhou Y-Y, Wang B, Zhu M-R, Cui R-R, Tan X-Q, Xiong Z-P, Liu J, Tan M-J, Xu Y-C, Geng M-Y, Jiang H-L, Liu H, Ai J, Zheng M-Y. Discovery and development of a series of pyrazolo[3,4-d]pyridazinone compounds as the novel covalent fibroblast growth factor receptor inhibitors by the rational drug design. J Med Chem. 2019;62:7473-88.
[92] Tan X-Q, Li C-P, Yang R-R, Zhao S, Li F, Li X-T, Chen L-F, Wan X-Z, Liu X-H, Yang T-B, Tong X-C, Xu T-Y, Cui R-R, Jiang H-L, Zhang S-L, Liu H, Zheng M-Y. Discovery of pyrazolo[3,4-d]pyridazinone derivatives as selective DDR1 inhibitors via deep learning based design, synthesis, and biological evaluation. J Med Chem. 2022;65:103-19.
[93] Bachmaier K, Krawczyk C, Kozieradzki I, Kong Y-Y, Sasaki T, Oliveira-dos-Santos A, Mariathasan S, Bouchard D, Wakeham A, Itie A, Le J, Ohashi PS, Sarosi I, Nishina H, Lipkowitz S, Penninger JM. Negative regulation of lymphocyte activation and autoimmunity by the molecular adaptor Cbl-b. Nature. 2000;403:211-6.
[94] Quinn TR, Giblin KA, Thomson C, Boerth JA, Bommakanti G, Braybrooke E, Chan C, Chinn AJ, Code E, Cui C, Fan Y, Grimster NP, Kohara K, Lamb ML, Ma L, Mfuh AM, Robb GR, Robbins KJ, Schimpl M, Tang H, Ware J, Wrigley GL, Xue L, Zhang Y, Zhu H, Hughes SJ. Accelerated discovery of carbamate Cbl-b inhibitors using generative AI models and structure-based drug design. J Med Chem. 2024;67:14210-33.
[95] Lee J-H. Targeting the ATM pathway in cancer: opportunities, challenges and personalized therapeutic strategies. Cancer Treat Rev. 2024;129:1-14.
[96] Deng D, Yang Y-X, Zou Y-R, Liu K-J, Zhang C-F, Tang M-H, Yang T, Chen Y, Yuan X, Guo Y, Zhang S-J, Si W-T, Peng B, Xu Q, He W, Xu D-G, Xiang M-L, Chen L-J. Discovery and evaluation of 3-quinoxalin urea derivatives as potent, selective, and orally available ATM inhibitors combined with chemotherapy for the treatment of cancer via goal-oriented molecule generation and virtual screening. J Med Chem. 2023;66:9495-518.
[97] Traves PG, Murray B, Campigotto F, Galien R, Meng A, Paolo JAD. JAK selectivity and the implications for clinical inhibition of pharmacodynamic cytokine signalling by filgotinib, upadacitinib, tofacitinib and baricitinib. Ann Rheum Dis. 2021;80:865-75.
[98] Xiang S, Song S-K, Tang H-T, Smaill JB, Wang A-Q, Xie H, Lu X-Y. TANK-binding kinase 1 (TBK1): an emerging therapeutic target for drug discovery. Drug Discov Today. 2021;26:2445-55.
[99] Song S-K, Tang H-T, Ran T, Fang F, Tong L-J, Chen H-M, Xie H, Lu X-Y. Application of deep generative model for design of pyrrolo[2,3-d] pyrimidine derivatives as new selective TANK binding kinase 1 (TBK1) inhibitors. Eur J Med Chem. 2023;247:1-15.
[100] Zhu Y-Y, Ouyang Z-J, Du H-J, Wang M-J, Wang J-J, Sun H-Y, Kong L-D, Xu Q, Ma H-Y, Sun Y. New opportunities and challenges of natural products research: when target identification meets single-cell multiomics. Acta Pharm Sin B. 2022;12:4011-39.
[101] Li J-S, Gong X-Q. Harnessing pre-trained models for accurate prediction of protein-ligand binding affinity. BMC Bioinf. 2025;26:1-21.
[102] Altae-Tran H, Ramsundar B, Pappu AS, Pande V. Low data drug discovery with one-shot learning. ACS Cent Sci. 2017;3:283-93.
[103] Moret M, Friedrich L, Grisoni F, Merk D, Schneider G. Generative molecular design in low data regimes. Nat Mach Intell. 2020;2:171-80.
[104] Bilodeau C, Jin W, Jaakkola T, Barzilay R, Jensen KF. Generative models for molecular discovery: recent advances and challenges. Wires Comput Mol Sci. 2022;12:1-17.
[105] Wang M-Y, Li S, Wang J-K, Zhang O, Du H-Y, Jiang D-J, Wu Z-X, Deng Y-F, Kang Y, Pan P-C, Li D, Wang X-R, Yao X-J, Hou T-J, Hsieh C-Y. ClickGen: directed exploration of synthesizable chemical space via modular reactions and reinforcement learning. Nat Commun. 2024;15:1-18.
[106] Nahal Y, Menke J, Martinelli J, Heinonen M, Kabeshov M, Janet JP, Nittinger E, Engkvist O, Kaski S. Human-in-the-loop active learning for goal-oriented molecule generation. J Cheminform. 2024;16:1-24.
[107] Lu W, Zhang J-X, Huang W-F, Zhang Z-Q, Jia X-Y, Wang Z-Y, Shi L-L, Li C-T, Wolynes PG, Zheng S-J. DynamicBind: predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model. Nat Commun. 2024;15:1-13.
[108] Cheng K-H, Liu C, Su Q-K, Wang J, Zhang L-W, Tang Y-N, Yao Y, Zhu S-Y, Qi Y. AlphaFolding: 4D diffusion for dynamic protein structure prediction with reference and motion guidance. arXiv preprint arXiv: 2408.12419 [Online], 2024
[109] Wu F, Jin S-T, Jiang Y-H, Jin X-R, Tang B-W, Niu Z-M, Liu X-R, Zhang Q, Zeng X-X, Li SZ. Pre-training of equivariant graph matching networks with conformation flexibility fordrug binding. Adv Sci. 2022;9:1-13.
[110] Schuh MG, Boldini D, Bohne AI, Sieber SA. Barlow twins deep neural network for advanced 1D drug-target interaction prediction. J Cheminform. 2025;17:1-14.
[111] Miglior L, Simone L, Podda M, Bacciu D. Towards efficient molecular property optimization with graph energy based models. arXiv preprint arXiv: 2502.12219 [Online], 2025.
[112] Li M-S, Zhang L, Zhu M-Z, Huang Z-L, Yu G, Fan J-Y, Chen T. Lightweight model pre-training via language guided knowledge distillation. IEEE Trans Multimedia. 2024;26:10720-30.
[113] Perera D, Tucker JW, Brahmbhatt S, Helal CJ, Chong A, Farrell W, Richardson P, Sach NW. A platform for automated nanomole-scale reaction screening and micromole-scale synthesis in flow. Science. 2018;359:429-34.
[114] Segler MHS, Preuss M, Waller MP. Planning chemical syntheses with deep neural networks and symbolic AI. Nature. 2018;555:604-10.

Bridging chemical space and biological efficacy: advances and challenges in applying generative models in structural modification of natural products

Bridging chemical space and biological efficacy: advances and challenges in applying generative models in structural modification of natural products

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Hesham R. El-Seedi, Mohamed S. Refaey, Nizar Elias, Mohamed F. El-Mallah, Faisal M. K. Albaqami, Ismail Dergaa, Ming Du, Mohamed F. Salem, Haroon Elrasheid Tahir, Maria Dagliaa, Nermeen Yosri, Hongcheng Zhang, Awg H. El-Seedi, Zhiming Guo, Shaden A. M. Khalifa. Marine natural products as a source of novel anticancer drugs: an updated review (2019-2023) [J]. Natural Products and Bioprospecting, 2025, 15(2): 13-13.
[2]	María I. Osella, Mario O. Salazar, Carlos M. Solís, Ricardo L. E. Furlan. New semisynthetic α-glucosidase inhibitor from a doubly-chemically engineered extract [J]. Natural Products and Bioprospecting, 2025, 15(1): 4-4.
[3]	Ahmed H. Elbanna, Xinhui Kou, Dilip V. Prajapati, Surasree Rakshit, Rebecca A. Butcher. Discovery of a parallel family of euglenatide analogs in Euglena gracilis [J]. Natural Products and Bioprospecting, 2025, 15(1): 10-10.
[4]	Song-Yu Hou, Bing-Chao Yan, Han-Dong Sun, Pema-Tenzin Puno. Recent advances in the application of [2+2] cycloaddition in the chemical synthesis of cyclobutane-containing natural products [J]. Natural Products and Bioprospecting, 2024, 14(5): 37-37.
[5]	Felaine Anne Sumang, Alan Ward, Jeff Errington, Yousef Dashti. Hibiscus acid and hydroxycitric acid dimethyl esters from Hibiscus flowers induce production of dithiolopyrrolone antibiotics by Streptomyces Strain MBN2-2 [J]. Natural Products and Bioprospecting, 2024, 14(5): 40-40.
[6]	Chunsong Hu. Marine natural products and human immunity: novel biomedical resources for anti-infection of SARS-CoV-2 and related cardiovascular disease [J]. Natural Products and Bioprospecting, 2024, 14(2): 2-2.
[7]	Shohreh Ariaeenejad, Javad Gharechahi, Mehdi Foroozandeh Shahraki, Fereshteh Fallah Atanaki, Jian-Lin Han, Xue-Zhi Ding, Falk Hildebrand, Mohammad Bahram, Kaveh Kavousi, Ghasem Hosseini Salekdeh. Precision enzyme discovery through targeted mining of metagenomic data [J]. Natural Products and Bioprospecting, 2024, 14(1): 7-7.
[8]	Daniel W. Armstrong, Alain Berthod. Occurrence of D-amino acids in natural products [J]. Natural Products and Bioprospecting, 2023, 13(6): 47-47.
[9]	Dalila Carbone, Carmela Gallo, Genoveffa Nuzzo, Giusi Barra, Mario Dell'Isola, Mario Affuso, Olimpia Follero, Federica Albiani, Clementina Sansone, Emiliano Manzo, Giuliana d'Ippolito, Angelo Fontana. Marine natural product lepadin A as a novel inducer of immunogenic cell death via CD91-dependent pathway [J]. Natural Products and Bioprospecting, 2023, 13(5): 34-34.
[10]	Phanankosi Moyo, Luke Invernizzi, Sephora M. Mianda, Wiehan Rudolph, Warren A. Andayi, Mingxun Wang, Neil R. Crouch, Vinesh J. Maharaj. Leveraging off higher plant phylogenetic insights for antiplasmodial drug discovery [J]. Natural Products and Bioprospecting, 2023, 13(5): 35-35.
[11]	Phanankosi Moyo, Luke Invernizzi, Sephora M. Mianda, Wiehan Rudolph, Andrew W. Andayi, Mingxun Wang, Neil R. Crouch, Vinesh J. Maharaj. Prioritised identification of structural classes of natural products from higher plants in the expedition of antimalarial drug discovery [J]. Natural Products and Bioprospecting, 2023, 13(5): 37-37.
[12]	Ji-Kai Liu. Natural products in cosmetics [J]. Natural Products and Bioprospecting, 2022, 12(6): 40-40.
[13]	Si-Yuan Luo, Jun-Yu Zhu, Ming-Feng Zou, Sheng Yin, Gui-Hua Tang. Mulberry Diels–Alder-type adducts: isolation, structure, bioactivity, and synthesis [J]. Natural Products and Bioprospecting, 2022, 12(5): 31-31.
[14]	Yulian Lv, Tian Tian, Yong-Jiang Wang, Jian-Ping Huang, Sheng-Xiong Huang. Advances in chemistry and bioactivity of the genus Erythroxylum [J]. Natural Products and Bioprospecting, 2022, 12(3): 15-15.
[15]	Ji-Kai Liu. Antiaging agents: safe interventions to slow aging and healthy life span extension [J]. Natural Products and Bioprospecting, 2022, 12(3): 18-18.