Artificial intelligence-guided biosynthesis and retrosynthesis in pharmacognosy: Toward the synthesis-oriented discovery of natural-product therapeutics

Kiarash Solouki; Niloufar Moharrer Navaei; Ayla Balkan

doi:10.53063/synsint.2026.62341

Kiarash Solouki ¹
Niloufar Moharrer Navaei ¹
Ayla Balkan ²

¹ Faculty of Pharmacy, Cyprus International University, Nicosia 99258, Northern Cyprus, Mersin 10, Turkey
² Faculty of Pharmacy, Bahçeşehir University, Nicosia 99258, Northern Cyprus, Mersin 10, Turkey

https://doi.org/10.53063/synsint.2026.62341

Abstract

Artificial intelligence is reshaping Pharmacognosy by connecting ethnobotanical knowledge, multi-omic data, Biosynthetic pathway prediction, Retrosynthetic planning, and medicinal chemistry optimization. Particular attention is given to AI-driven tools, including BioNavi-NP, graph-sequence-enhanced transformers, NAG2G, RSGPT, RetroExplainer, and human-in-the-loop systems such as DeepRetro. These platforms can reconstruct natural-product biosynthesis, predict plausible precursors, preserve molecular topology, suggest multi-step disconnections, and explore broad reaction spaces. They are especially relevant for metabolites with dense stereochemistry, unusual ring systems, multifunctional scaffolds, and enzyme-guided biosynthetic logic. Beyond route design, AI may help prioritize biosynthetic genes, optimize scarce plant-derived compounds, and guide the development of more drug-like analogues with improved potency, selectivity, pharmacokinetic behavior, and synthetic accessibility. However, important limitations remain, including limited plant-specific reaction datasets, weak reaction-condition prediction, incomplete stereochemical and regioselective modeling, benchmark weaknesses, and the need for expert validation. Overall, AI is best understood as a decision-support layer linking biodiversity, traditional knowledge, biosynthetic logic, and experimental synthesis for responsible future therapeutic discovery and validation across modern natural-product-based drug discovery pipelines.

Downloads

Download data is not yet available.

Keywords: Natural products, Pharmacognosy, Artificial intelligence, Biosynthetic pathway prediction, Retrosynthetic planning

References

[1] T. Adhikary, P. Basak, Interdisciplinary approaches incorporating computational intelligence in modern pharmacognosy to address biological problems, Electronic Systems and Intelligent Computing: Proceedings of ESIC 2020, Springer, Singapore. (2020) 11–19. https://doi.org/10.1007/978-981-15-7031-5_2.

[2] S. Banerjee, Introduction to Ethnobotany and Traditional Medicine, Traditional Resources and Tools for Modern Drug Discovery: Ethnomedicine and Pharmacology, Singapore: Springer Nature Singapore. (2024) 1–30. https://doi.org/10.1007/978-981-97-4600-2_1.

[3] M. Leonti, The relevance of quantitative ethnobotanical indices for ethnopharmacology and ethnobotany, J. Ethnopharmacol. 288 (2022) 115008. https://doi.org/10.1016/j.jep.2022.115008.

[4] C.C. Davis, P. Choisy, Medicinal plants meet modern biodiversity science, Curr. Biol. 34 (2024) R158–R173. https://doi.org/10.1016/j.cub.2023.12.038.

[5] P.M. Allard, T. Péresse, J. Bisson, K. Gindro, L. Marcourt, et al., Integration of molecular networking and in-silico MS/MS fragmentation for natural products dereplication, Anal. Chem. 88 (2016) 3317–3323. https://doi.org/10.1021/acs.analchem.5b04804.

[6] W. Bai, C. Li, W. Li, H. Wang, X. Han, et al., Machine learning assists prediction of genes responsible for plant specialized metabolite biosynthesis by integrating multi-omics data, BMC Genom. 25 (2024) 418. https://doi.org/10.1186/s12864-024-10258-6.

[7] H. Ali, Artificial intelligence in multi-omics data integration: Advancing precision medicine, biomarker discovery and genomic-driven disease interventions, Int. J. Sci. Res. Arch. 8 (2023) 1012–1030. https://doi.org/10.30574/ijsra.2023.8.1.0189.

[8] F.C. Wolters, E. Del Pup, K.S. Singh, K. Bouwmeester, M.E. Schranz, et al., Pairing omics to decode the diversity of plant specialized metabolism, Curr. Opin. Plant Biol. 82 (2024) 102657. https://doi.org/10.1016/j.pbi.2024.102657.

[9] J.M. Stokes, K. Yang, K. Swanson, W. Jin, A. Cubillos-Ruiz, et al., A deep learning approach to antibiotic discovery, Cell. 180 (2020) 688–702. https://doi.org/10.1016/j.cell.2020.01.021.

[10] G. Liu, D.B. Catacutan, K. Rathod, K. Swanson, W. Jin, et al., Deep learning-guided discovery of an antibiotic targeting Acinetobacter baumannii, Nat. Chem. Biol. 19 (2023) 1342–1350. https://doi.org/10.1038/s41589-023-01349-8.

[11] L. Yao, W. Guo, Z. Wang, S. Xiang, W. Liu, G. Ke, Node-aligned graph-to-graph: elevating template-free deep learning approaches in single-step retrosynthesis, JACS Au. 4 (2024) 992–1003. https://doi.org/10.1021/jacsau.3c00737.

[12] Y. Deng, X. Zhao, H. Sun, Y. Chen, X. Wang, et al., RSGPT: a generative transformer model for retrosynthesis planning pre-trained on ten billion datapoints, Nat. Commun. 16 (2025) 7012. https://doi.org/10.1038/s41467-025-62308-6.

[13] S. Zheng, T. Zeng, C. Li, B. Chen, C.W. Coley, et al., Deep learning driven biosynthetic pathways navigation for natural products with BioNavi-NP, Nat. Commun. 13 (2022) 3342. https://doi.org/10.1038/s41467-022-30970-9.

[14] D. Meijer, M.A. Beniddir, C.W. Coley, Y.M. Mejri, M. Öztürk, et al., Empowering natural product science with AI: leveraging multimodal data and knowledge graphs, Nat. Prod. Rep. 42 (2025) 654–662. https://doi.org/10.1039/d4np00008k.

[15] P. Palit, S.C. Mandal, Climate change, geographical location, and other allied triggering factors modulate the standardization and characterization of traditional medicinal plants: a challenge and prospect for phyto-drug development, Evidence based validation of traditional medicines: a comprehensive approach, Springer Singapore, Singapore. (2021) 359–369. https://doi.org/10.1007/978-981-15-8127-4_18.

[16] R. Bushuiev, A. Bushuiev, R. Samusevich, C. Brungs, J. Sivic, T. Pluskal, Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS, Nat. Biotechnol. (2025) 1–11. https://doi.org/10.1038/s41587-025-02663-3.

[17] N.J. Brittin, J.M. Anderson, D.R. Braun, S.R. Rajski, C.R. Currie, T.S. Bugni, Machine learning-based bioactivity classification of natural products using LC-MS/MS metabolomics, J. Nat. Prod. 88 (2025) 361–372. https://doi.org/10.1021/acs.jnatprod.4c01123.

[18] G.D. Hannigan, D. Prihoda, A. Palicka, J. Soukup, O. Klempir, et al., A deep learning genome-mining strategy for biosynthetic gene cluster prediction, Nucleic Acids Res. 47 (2019) e110–e110. https://doi.org/10.1093/nar/gkz654.

[19] R. Ancuceanu, B.E. Lascu, D. Drăgănescu, M. Dinu, In silico ADME methods used in the evaluation of natural products, Pharmaceutics. 17 (2025) 1002. https://doi.org/10.3390/pharmaceutics17081002.

[20] J.K. Reinhardt, D. Craft, J.K. Weng, Toward an integrated omics approach for plant biosynthetic pathway discovery in the age of AI, Trends Biochem. Sci. 50 (2025) 311–321. https://doi.org/10.1016/j.tibs.2025.01.010.

[21] B. Behsaz, E. Bode, A. Gurevich, Y.N. Shi, F. Grundmann, et al., Integrating genomics and metabolomics for scalable non-ribosomal peptide discovery, Nat. Commun. 12 (2021) 3225. https://doi.org/10.1038/s41467-021-23502-4.

[22] S. Cong, M. Zhang, Y. Song, S. Chang, J. Tian, et al., Graph-sequence enhanced transformer for template-free prediction of natural product biosynthesis, Patterns. 6 (2025) 101259. https://doi.org/10.1016/j.patter.2025.101259.

[23] Y. Wang, C. Pang, Y. Wang, J. Jin, J. Zhang, et al., Retrosynthesis prediction with an interpretable deep-learning framework based on molecular assembly tasks, Nat. Commun. 14 (2023) 6155. https://doi.org/10.1038/s41467-023-41698-5.

[24] S.V. Sathyanarayana, S.D. Hiremath, S. Rahil Kirankumar, R. Panda, R. Jana, et al., DeepRetro discovers retrosynthetic pathways through iterative large language model reasoning, Sci. Rep. 16 (2026) 8448. https://doi.org/10.1038/s41598-026-38821-z.

[25] Y. Kwak, T. Kim, S.G. Kim, J. Park, READRetro web: A user-friendly platform for predicting plant natural product biosynthesis, Mol. Cells. 48 (2025) 100235. https://doi.org/10.1016/j.mocell.2025.100235.

[26] M. Orsi, J.L. Reymond, Assigning the stereochemistry of natural products by machine learning, J. Cheminform. 18 (2026) 76. https://doi.org/10.1186/s13321-026-01205-6.

[27] A.R. Bhat, S. Ahmed, Artificial intelligence (AI) in drug design and discovery: A comprehensive review, Silico Res. Biomed. 1 (2025) 100049. https://doi.org/10.1016/j.insi.2025.100049.

[28] E.S. Ozdemir, H. Jang, O. Keskin, A. Gursoy, R. Nussinov, Deep generative molecular design and its value in modern drug discovery, Expert Opin. Drug Discov. 21 (2026) 273–287. https://doi.org/10.1080/17460441.2026.2636192.

[29] D. Dekleva, A. Voronov, J.P. Janet, A. Ekborg, J. Borišek, et al., Synthesizability via reward engineering: expanding generative molecular design into synthetic space, Chem. Sci. 17 (2026) 10015–10028. https://doi.org/10.1039/D5SC09263A.

[30] A. Gangwal, A. Lavecchia, Artificial intelligence in natural product drug discovery: current applications and future perspectives, J. Med. Chem. 68 (2025) 3948–3969. https://doi.org/10.1021/acs.jmedchem.4c01257.

[31] R. Muthuraj, J. Chandrasekaran, Nature meets machine: the AI renaissance in natural product drug discovery, Nat. Prod. Bioprospect. 16 (2026) 37. https://doi.org/10.1007/s13659-025-00589-6.

[32] W. Yoo, Precision oncology in the age of AI: lessons from AI-driven drug discovery and clinical translation, BJC Rep. 4 (2026) 18. https://doi.org/10.1038/s44276-026-00221-1.

[33] J.J. Louwen, M.H. Medema, J.J. van der Hooft, Enhanced correlation-based linking of biosynthetic gene clusters to their metabolic products through chemical class matching, Microbiome. 11 (2023) 13. https://doi.org/10.1186/s40168-022-01444-3.

[34] Z.K. Othman, M.M. Ahmed, O. Kasimieh, S.S. Musa, F. Branda, et al., Artificial intelligence for natural product drug discovery and development: current landscape, applications, and future directions, Intell.-Based Med. 12 (2025) 100316. https://doi.org/10.1016/j.ibmed.2025.100316.

[35] B.K. Babu, Revolutionizing Herbal Medicine: The Role of E-health Informatics and Network Pharmacology in Personalized Herbal Therapies, Int. J. Pharm. Investig. 15 (2025) 219–227. https://doi.org/10.5530/ijpi.20251754.

[36] A. Mukherjee, S. Abraham, A. Singh, S. Balaji, K.S. Mukunthan, From data to cure: A comprehensive exploration of multi-omics data analysis for targeted therapies, Mol. Biotechnol. 67 (2025) 1269–1289. https://doi.org/10.1007/s12033-024-01133-6.

View more references

Cited By