AI-Powered De Novo Antibiotics Discovery: Is It The Answer to Overcome Antimicrobial Resistance? A Systematic Review of Preclinical Evidence Across In Vitro and In Vivo Studies
DOI:
https://doi.org/10.53366/jimki.vi.1046Keywords:
artificial intelligence, antibiotic discovery, antimicrobial resistance, preclinical evidenceAbstract
Introduction: Antimicrobial resistance (AMR) remains a critical global issue. By 2050, it is projected to cause around 10 million deaths if current trends persist. Traditional antimicrobial discovery struggles to keep up with rapidly evolving resistance due to its lengthy process, high cost, and high failure rate. Developing a single drug can take over a decade of research and cost millions of dollars. These challenges demand more efficient approaches, with artificial intelligence (AI) offering a promising path to accelerate and improve antibiotic development.
Methods: GoogleScholar, PubMed, ScienceDirect, and Scopus were systematically searched following the PRISMA 2020, yielding 13 eligible studies. All included in vitro validation, and four extended to in vivo investigations. Risk of bias was evaluated using the QUIN (in vitro) and the SYRCLE (in vivo) tools.
Discussion: Across studies, AI supported multiple stages of antibiotic discovery, including target identification, lead compound optimization, also enhancement of pre-clinical testing. In target identification, two studies revealed novel antibacterial targets distinct from classical pathways. During lead optimization, applied in most studies, AI-generated compounds demonstrated strong antimicrobial activity and low MIC values against broad-spectrum and multi-drug resistant bacteria. Four in vivo studies further showed that these de novo antibiotics exhibited superior antimicrobial efficacy to current standard therapies. Finally, in preclinical testing, AI models accurately predicted cytotoxicity and hemolysis, later confirmed experimentally.
Conclusion: AI has markedly improved efficiency and accuracy in antibiotic development. While continued model refinement, validation, and ethical oversight remain crucial, AI-integrated pharmaceutical research indicates growing maturity and transformative potential.
References
1. World Health Organization. Global Antimicrobial Resistance and Use Surveillance System (GLASS) Report 2025. Geneva: WHO; 2025.
2. World Bank. Drug-resistant infections: a threat to our economic future. Washington (DC): World Bank; 2017.
3. Naghavi M, et al. Global burden of bacterial antimicrobial resistance 1990–2021: a systematic analysis with forecasts to 2050. Lancet. 2024;404(10459):1199–1226.
4. Akhlaq U, Bajwa SZ, Shinwari ZK. Artificial intelligence in drug discovery and development: a comprehensive review. Drug Discov Today. 2022.
5. Khan SA, Shakoor A, Kanwal S. TargetGen-RNN model discovers novel antibiotic compound targeting drug-resistant Staphylococcus aureus. Interdiscip Med. 2025. doi:10.1002/inmd.70064
6. Ferreira FJN, Carneiro AS. AI-driven drug discovery: A comprehensive review. ACS Omega. 2025;10(23):23889–23903. doi:10.1021/acsomega.5c00549
7. Farghali H, Kutinová Canová N, Arora M. The potential applications of artificial intelligence in drug discovery and development. Physiol Res. 2021;70(Suppl 4):S715–S722. doi:10.33549/physiolres.934765
8. Krishnan A, Anahtar MN, Valeri JA, et al. A generative deep learning approach to de novo antibiotic design. Cell. 2025;S0092-8674(25):00855-4. doi:10.1016/j.cell.2025.00855-4
9. Das U. Generative AI for drug discovery and protein design: the next frontier in AI-driven molecular science. Med Drug Discov. 2025;27:100213. doi:10.1016/j.medidd.2025.100213
10. Arshia N, Khan MA, Naseem M, et al. Artificial intelligence for antimicrobial resistance prediction: A comprehensive review. Comput Biol Med. 2022 doi:10.3390/antibiotics12030523
11. Zhang H, Li Y, Nguyen T, et al. Predictive modeling of drug–drug interactions using deep learning: implications for antimicrobial therapy. Pharmacol Ther Res. 2025.
12. Page MJ, McKenzie JE, Bossuyt PM, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372:n71.
13. Pillai A, Nair SS, Ramakrishnan R. Development and validation of the QUIN risk-of-bias tool for in vitro studies. J Evid Based Dent Pract. 2022.
14. Hooijmans CR, Rovers MM, de Vries RBM, Leenaars M, Ritskes-Hoitinga M, Gooszen HG. SYRCLE’s risk of bias tool for animal studies. BMC Med Res Methodol. 2014;14:43.
15. Cesaro A, Hoffman SC, Das P, de la Fuente-Núñez C. Challenges and applications of artificial intelligence in infectious diseases and antimicrobial resistance. npj Antimicrobials Resist. 2025.
16. Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature. 1986;323:533–536. doi:10.1038/323533a0
17. AlGain S, Marra AR, Kobayashi T, et al. Can we rely on artificial intelligence to guide antimicrobial therapy? A systematic literature review. Antimicrob Steward Healthc Epidemiol. 2025.
18. Ochiai T, Inukai T, Akiyama M, Furui K, et al. Variational autoencoder-based chemical latent space for large molecular structures with 3D complexity. Commun Chem. 2023;6:54. doi:10.1038/s42004-023-01054-6
19. Titar RR, Ramanathan M. Variational autoencoders for generative modeling of drug dosing determinants in renal, hepatic, metabolic, and cardiac disease states. Clin Transl Sci. 2024;17(7):e13872. doi:10.1111/cts.13872
20. Odah, M.A.A. Artificial Intelligence Meets Drug Discovery: A Systematic Review on AI-Powered Target Identification and Molecular Design. Preprint. Preprints.org. 2025.
21. Lin T-T, Yang L-Y, et al. Intelligent de novo design of novel antimicrobial peptides against antibiotic-resistant bacteria strains. Int J Mol Sci. 2023;24(7):6788.
22. Alakhdar A, Poczos B, Washburn N. Diffusion models in de novo drug design. J Chem Inf Model. 2024;64(19):7238–7256. doi:10.1021/acs.jcim.4c01107
23. Dean SN, Alvarez JAE, Zabetakis D, et al. PepVAE: variational autoencoder framework for antimicrobial peptide generation and activity prediction. Front Microbiol. 2021;12:725727. doi:10.3389/fmicb.2021.725727.
24. Jiang J, Ke L, Chen L, Dou B, Zhu Y, Liu J, et al. Transformer technology in molecular science. WIREs Computational Molecular Science 2024;14(4):e1725.
25. Mswahili ME, Jeong YS. Transformer-based models for chemical SMILES representation: a comprehensive literature review. Heliyon 2024;10(20):e39038.
26. Chithrananda S, Grand G, Ramsundar B. ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction [Internet]. arXiv; 2020. Available from: https://arxiv.org/abs/2010.09885
27. Chandra A, Tünnermann L, Lofstedt T, Gratz R. Transformer-based deep learning for predicting protein properties in the life sciences. eLife 2023;18(12):e82819.
28. Boulougouri M, Vandergheynst P, Probst D. Molecular set representation learning. Nat Mach Intell. 2024;6:754–763. doi:10.1038/s42256-024-00856-0.
29. Strokach A, Kim PM. Deep generative modeling for peptide design. Patterns. 2022;3(6):100588. doi:10.1016/j.patter.2022.100588.
30. Gawehn E, Hiss JA, Schneider G. Deep learning in drug discovery. Mol Inform. 2016;35(1):3-14.
31. Ciao Q, Zhang Y, Chu Y, et al. Application of artificial intelligence in drug–target interactions prediction: a review. NPJ Biomed Innov. 2025;2:1. doi:10.1038/s44385-024-00003-9.
32. Pun FW, Ozerov IV, Zhavoronkov A. AI-powered therapeutic target discovery. Trends Pharmacol Sci. 2023;44(11):894–907. doi:10.1016/j.tips.2023.06.010.
33. Vetterli, S.U., Zerbe, K., Mu¨ller, M., Urfer, M., Mondal, M., Wang, S.-Y., Moehle, K., Zerbe, O., Vitale, A., Pessi, G., et al. (2018). Thanatin targets the intermembrane protein complexrequiredforlipopolysaccharide transport in Escherichia coli. Sci. Adv. 4, eaau2634. https://doi.org/10.1126/sciadv.aau2634.
34. Simpson BW, Lazarus MB, Khalid S, et al. Lipopolysaccharide transport to the cell surface. Philosophical Transactions of the Royal Society B: Biological Sciences. 2015;370(1679):20150029. doi:10.1098/rstb.2015.0029
35. Alzain M, Daghistani H, Shamrani T, Almoghrabi Y, Daghistani Y, et al. Antimicrobial peptides: mechanisms, applications, and therapeutic potential. Infect Drug Resist. 2025;18:4385–4426. doi:10.2147/IDR.S514825.
36. Cao H, Torres MDT, Zhang J, Gao Z, Wu F, Gu C, Leskovec J, Choi Y, de la Fuente-Núñez C, Chen G, Heng P-A. A deep reinforcement learning platform for antibiotic discovery. bioRxiv. 2025. doi:10.1101/2025.09.23.678086.
37. Le, V. V. H.; Rakonjac, J. Nitrofurans: Revival of an “old” drug class in the fight against antibiotic resistance. PLoS Pathog. 2021, 17, No. e1009663.
38. Köllen MF, Schuh MG, Kretschmer R, Hesse J, Schum D, Chen J, Bohne AI, Halter DP, Sieber SA. Generative deep learning pipeline yields potent Gram-negative antibiotics. JACS Au. 2025;5(9):4249–4259. doi:10.1021/jacsau.5c00602.
39. Kim,S.Y.;Park,C.; Jang,H.-J.; Kim,B.-o.; Bae, H.-W.; Chung, I. Y.; Kim, E. S.; Cho, Y.-H. Antibacterial strategies inspired by the oxidative stress and response networks. J. Microbiol. 2019, 57, 203−212.
40. García-Ortegón M, Seal S, Geddes E, Littler JL, Guy CS, Whiteside J, Rasmussen C, Bender A, Bacallado S. Transfer learning enables discovery of sub-micromolar antibacterials for ESKAPE pathogens from ultra-large chemical spaces. Chem Sci. 2025; (in press). doi:10.1039/d5sc03055b.
41. Shen H, Li Y, Pi Q, Tian J, Xu X, Huang Z, Huang J, Pian C, Mao S. Unveiling novel antimicrobial peptides from the ruminant gastrointestinal microbiomes: a deep learning-driven approach yields an anti-MRSA candidate. J Adv Res. 2025;77:821–835. doi:10.1016/j.jare.2025.01.005
42. Durand H, Cardon T, Belkaid Y. Interorgan communication in immunity and homeostasis. Nat Rev Microbiol. 2024;22:704–718. doi:10.1038/s41579-024-01054-w.
43. Jin S, Zeng Z, Xiong X, et al. AMPGen: an evolutionary information-reserved and diffusion-driven generative model for de novo design of antimicrobial peptides. Commun Biol. 2025;8:839. doi:10.1038/s42003-025-08282-7.
44. Wang Y, Song M, Liu F, Liang Z, Hong R, Dong Y, Luan H, Fu X, Yuan W, Fang W, Li G, Lou H, Chang W. Artificial intelligence using a latent diffusion model enables the generation of diverse and potent antimicrobial peptides. Sci Adv. 2025;11:eADP7171. doi:10.1126/sciadv.adp7171.
45. Szymczak P, Możejko M, Grzegorzek T, Jurczak R, Bauer M, Neubauer D, Sikora K, Michalski M, Sroka J, Setny P, Kamysz W, Szczurek E. Discovering highly potent antimicrobial peptides with deep generative model HydrAMP. Nat Commun. 2023;14:1453. doi:10.1038/s41467-023-36994-z.
46. Torres MDT, Zeng Y, Wan F, Maus N, Gardner J, de la Fuente-Núñez C. A generative artificial intelligence approach for antibiotic optimization. bioRxiv. 2024. doi:10.1101/2024.11.27.625757.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Nabilah Nurul Iftitah, Nurfajrianty Jamaluddin, Alia Zhafira Agus
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.