RESEARCH QUESTION
Act as an expert in medical bacteriology and computational biology. Analyze how Generative AI is currently used to combat antimicrobial resistance (AMR) and discover novel antibiotics. Provide a concise summary of the 3 biggest successes so far, 2 major biological bottlenecks (such as wet-lab translation or toxicity), and 3 novel, publication-ready research gaps that combine computational AI models with wet-lab validation.
Sep 28, 2026 · 09:58 PARTIAL
30-SECOND VIEW
Final Research Answer
Read full answer
Executive summary
Generative AI is accelerating antibiotic discovery against antimicrobial resistance (AMR), with notable successes in designing novel antimicrobial peptides (AMPs) and small molecules validated in vitro and in vivo. Key achievements include HydrAMP’s generation of potent AMPs active across resistant strains, TargetGen-RNN’s discovery of SAK-2970 effective against drug-resistant *S. aureus*, and AI-guided identification of abaucin. However, critical bottlenecks remain: poor translation from computational predictions to wet-lab efficacy—especially for Gram-negative pathogens—and unpredictable mammalian toxicity due to non-specific membrane disruption. Emerging research gaps involve closing the design-validation loop through multi-omics feedback, embedding biophysical membrane constraints into generative models, and co-designing antibiotic-adjuvant pairs to preempt resistance evolution. These integrative approaches require tight coupling of explainable AI with high-fidelity experimental pipelines to yield clinically viable candidates.
Partial research available
semantic_scholar: Semantic Scholar retrieval failed (rate_limit). Retry
2-MINUTE VIEW
Key Findings
HydrAMP generated 15 novel AMPs with experimental validation against multidrug-resistant bacteria.
Support diagnostic: academically supported
View sources
HydrAMP generated 15 novel AMPs with experimental validation against multidrug-resistant bacteria.
The HydrAMP study [C187] used a conditional VAE to generate analogues of both active and inactive peptides, followed by preselection and molecular dynamics. Wet-lab testing confirmed high activity in 9 analogues of clinical prototypes and 6 from an inactive scaffold, demonstrating high experimental validation rates.
[C187] Discovering highly potent antimicrobial peptides with deep generative model HydrAMP Open source
TargetGen-RNN discovered SAK-2970, a novel antibiotic with in vivo efficacy against resistant S. aureus and low toxicity.
Support diagnostic: academically supported
View sources
TargetGen-RNN discovered SAK-2970, a novel antibiotic with in vivo efficacy against resistant S. aureus and low toxicity.
SAK-2970 showed bactericidal activity, biofilm inhibition, efficacy against ciprofloxacin-resistant strains, and improved survival in a mouse bacteremia model with minimal systemic toxicity [C186], representing one of the few generative AI designs validated in vivo.
[C186] TargetGen‐RNN model discovers novel antibiotic compound targeting drug‐resistant Staphylococcus aureus Open source
AI-discovered abaucin exemplifies successful virtual screening guided by machine learning.
Support diagnostic: academically supported
View sources
AI-discovered abaucin exemplifies successful virtual screening guided by machine learning.
While the original abaucin paper is not included, [C184] explicitly cites it as a key case study in AI-based antibiotic discovery, lending indirect academic support within the allowed evidence set.
[C184] Artificial Intelligence and the Discovery of Antibiotics: Reinventing with Opportunities, Challenges, and Clinical Translation Open source
Mammalian toxicity remains a major bottleneck due to non-specific membrane disruption by AI-generated AMPs.
Support diagnostic: academically supported
View sources
Mammalian toxicity remains a major bottleneck due to non-specific membrane disruption by AI-generated AMPs.
Multiple reviews note that balancing antimicrobial activity with low hemolytic or cytotoxic effects is challenging; [C188] reports only 9 out of many generated peptides were both active (MIC ≤10 µg/mL) and non-toxic, highlighting the difficulty.
[C183] AI-Driven Antimicrobial Peptide Discovery: Mining and Generation Open source
[C188] Biochemical-knowledge-driven machine learning pipeline for generating potent antimicrobial peptides Open source
Gram-negative penetration is poorly modeled in current generative frameworks.
Support diagnostic: weak support
View sources
Gram-negative penetration is poorly modeled in current generative frameworks.
Although not explicitly stated in all papers, [C185] and [C188] emphasize context-dependent activity and the need for biochemical constraints, implying inadequate modeling of complex Gram-negative envelopes. No study demonstrates successful de novo design optimized for porin transit or efflux evasion.
[C185] Harnessing Machine Learning Approaches for the Identification, Characterization, and Optimization of Novel Antimicrobial Peptides Open source
[C188] Biochemical-knowledge-driven machine learning pipeline for generating potent antimicrobial peptides Open source
Evidence Overview
8 valid sources · 0 conflicting findings · 0 disagreements · 19 papers reviewed
The metrics above describe saved evidence. Source associations and agreement between models are not independent verification.
Best Academic Evidence
Saved synthesis ranking where available; otherwise Consensus order. Retrieved papers are not automatically proof of a claim.
ConsensusAI-Driven Antimicrobial Peptide Discovery: Mining and Generation
Paulina Szymczak, Wojciech Zarzecki, Jie-Jing Wang, Yiqian Duan, Jun Wang, Luís Pedro Coelho, César… · 2025 · Accounts of Chemical Research
The escalating threat of antimicrobial resistance (AMR) poses a significant global health crisis, potentially surpassing cancer as a leading cause of death by 2050. Traditional antibiotic discovery methods have not kept pace with the rapidly evolving resistance mechanisms of pathogens, highlighting…
Read paper details
Paulina Szymczak, Wojciech Zarzecki, Jie-Jing Wang, Yiqian Duan, Jun Wang, Luís Pedro Coelho, César de la Fuente-Núñez, Ewa Szczurek
The escalating threat of antimicrobial resistance (AMR) poses a significant global health crisis, potentially surpassing cancer as a leading cause of death by 2050. Traditional antibiotic discovery methods have not kept pace with the rapidly evolving resistance mechanisms of pathogens, highlighting the urgent need for novel therapeutic strategies. In this context, antimicrobial peptides (AMPs) represent a promising class of therapeutics due to their selectivity toward bacteria and slower induction of resistance compared to classical, small molecule antibiotics. However, designing effective AMPs remains challenging because of the vast combinatorial sequence space and the need to balance efficacy with low toxicity. Addressing this issue is of paramount importance for chemists and researchers dedicated to developing next-generation antimicrobial agents.Artificial intelligence (AI) presents a powerful tool to revolutionize AMP discovery. By leveraging AI, we can navigate the immense sequence space more efficiently, identifying peptides with optimal therapeutic properties. This Account explores the emerging application of AI in AMP discovery, focusing on two primary strategies: AMP mining, and AMP generation, as well as the use of discriminative methods as a valuable toolbox.AMP mining involves scanning biological sequences to identify potential AMPs. Discriminative models are then used to predict the activity and toxicity of these peptides. This approach has successfully identified numerous promising candidates, which were subsequently validated experimentally, demonstrating the potential of AI in AMP design and discovery.AMP generation, on the other hand, creates novel peptide sequences by learning from existing data through generative modeling. This class of models optimizes for desired properties, such as increased activity and reduced toxicity, potentially producing synthetic peptides that surpass naturally occurring ones. Despite the risk of generating unrealistic sequences, generative models hold the promise of accelerating the discovery of highly effective and highly novel and diverse AMPs.In this Account, we describe the technical challenges and advancements in these AI-based approaches. We discuss the importance of integrating various data sources and the role of advanced algorithms in refining peptide predictions. Additionally, we highlight the future potential of AI to not only expedite the discovery process but also to uncover peptides with unprecedented properties, paving the way for next-generation antimicrobial therapies.In conclusion, the synergy between AI and AMP discovery opens new frontiers in the fight against AMR. By harnessing the power of AI, we can design novel peptides that are both highly effective and safe, offering hope for a future where AMR is no longer a looming threat. Our paper underscores the transformative potential of AI in drug discovery, advocating for its continued integration into biomedical research.
DOI: 10.1021/acs.accounts.0c00594
Open source ↗Artificial Intelligence and the Discovery of Antibiotics: Reinventing with Opportunities, Challenges, and Clinical Translation
Bharat Kumar Reddy Sanapalli, Shrestha Palit, Ashwini Deshpande, Ramya Tokala, D. K. Sigalapalli, V… · 2026 · Antibiotics
Background: The outbreak and spreading of antimicrobial resistance (AMR) in a very short time has made most of the old-fashioned antibiotics ineffective, and thus new therapeutic substances have to be developed. The traditional methods of antibiotics discovery are defined by long periods of time, h…
Read paper details
Bharat Kumar Reddy Sanapalli, Shrestha Palit, Ashwini Deshpande, Ramya Tokala, D. K. Sigalapalli, Vidyasrilekha Sanapalli
Background: The outbreak and spreading of antimicrobial resistance (AMR) in a very short time has made most of the old-fashioned antibiotics ineffective, and thus new therapeutic substances have to be developed. The traditional methods of antibiotics discovery are defined by long periods of time, high levels of expenditure, and high rates of failure, which contributes to the necessity of new approaches. Artificial intelligence (AI) has become a disruptive technology that can be used to accelerate and optimize various steps of antibiotic discovery, such as target detection and virtual screening, new molecular design, and early-stage testing. Methods: This review provides an in-depth discussion of the role of AI methodologies in the form of machine learning, deep learning, natural language processing, and generative models in the discovery of small-molecule antibiotics and antimicrobial peptides (AMPs). The major areas that are discussed include virtual screening, pharmacokinetics optimization, resistance mechanism prediction, and AMPs design, which is accompanied by relevant case studies, including the AI-based discovery of Abaucin. Results: The article highlights how AI can be used in a synergistic relationship with synthetic biology, nanotechnology, and multi-omics data as a core component in the next generation of antimicrobial approaches, such as personalized therapy and predictive stewardship. The existing issues, i.e., the lack of data, bias in algorithms, and the translational divide between research and clinical use, are addressed, as well as suggested measures of responsible, collaborative, and ethical AI use. Conclusions: The combination of computational innovation with experimentation validation, AI-driven antibiotic discovery paves the way for a potent and scalable approach in addressing the rising threat of AMR.
DOI: 10.3390/antibiotics15020233
Open source ↗Harnessing Machine Learning Approaches for the Identification, Characterization, and Optimization of Novel Antimicrobial Peptides
Naveed Saleem, Naresh Kumar, E. El-Omar, Mark D. P. Willcox, Xiaotao Jiang · 2025 · Antibiotics
Antimicrobial resistance (AMR) has become a major health crisis worldwide, and it is expected to surpass cancer as one of the leading causes of death by 2050. Conventional antibiotics are struggling to keep pace with the rapidly evolving resistance trends, underscoring the urgent need for novel ant…
Read paper details
Naveed Saleem, Naresh Kumar, E. El-Omar, Mark D. P. Willcox, Xiaotao Jiang
Antimicrobial resistance (AMR) has become a major health crisis worldwide, and it is expected to surpass cancer as one of the leading causes of death by 2050. Conventional antibiotics are struggling to keep pace with the rapidly evolving resistance trends, underscoring the urgent need for novel antimicrobial therapeutic strategies. Antimicrobial peptides (AMPs) function through diverse, often membrane-disrupting mechanisms that can address the latest challenges to resistance. However, the identification, prediction, and optimization of novel AMPs can be impeded by several issues, including extensive sequence spaces, context-dependent activity, and the higher costs associated with wet laboratory screenings. Recent developments in artificial intelligence (AI) have enabled large-scale mining of genomes, metagenomes, and quantitative species-resolved activity prediction, i.e., MIC, and de novo AMPs designed with integrated stability and toxicity filters. The current review has synthesized and highlighted progress across different discriminative models, such as classical machine learning and deep learning models and transformer embeddings, alongside graphs and geometric encoders, structure-guided and multi-modal hybrid learning approaches, closed-loop generative methods, and large language models (LLMs) predicted frameworks. This review compares models' benchmark performances, highlighting AI-predicted novel hybrid approaches for designing AMPs, validated by in vitro and in vivo methods against clinical and resistant pathogens to increase overall experimental hit rates. Based on observations, multimodal paradigm strategies are proposed, focusing on identification, prediction, and characterization, followed by design frameworks, linking active-learning lab cycles, mechanistic interpretability, curated data resources, and uncertainty estimation. Therefore, for reproducible benchmarks and interoperable data, collaborative computational and wet lab experimental validations must be required to accelerate AI-driven novel AMP discovery to combat multidrug-resistant Gram-negative pathogens.
DOI: 10.3390/antibiotics14121263
Open source ↗View all papers (19)
ConsensusTargetGen‐RNN model discovers novel antibiotic compound targeting drug‐resistant Staphylococcus aureus
Shakeel Ahmad Khan, Adnan Shakoor, S. Kanwal · 2025 · Interdisciplinary Medicine
The escalating threat of antibacterial resistance demands innovative approaches for the discovery of novel antibiotics. Identifying hit and lead compounds with unique scaffolds during the early phases of drug development remains a significant challenge. Although various generative models have been …
Read paper details
Shakeel Ahmad Khan, Adnan Shakoor, S. Kanwal
The escalating threat of antibacterial resistance demands innovative approaches for the discovery of novel antibiotics. Identifying hit and lead compounds with unique scaffolds during the early phases of drug development remains a significant challenge. Although various generative models have been proposed to create drug‐like molecules, their capacity to design wet‐lab‐validated target‐specific compounds with novel scaffolds has been scarcely validated. Herein, we propose TargetGen‐recurrent neural network (RNN), a state‐of‐the‐art deep generative learning model designed to explore chemical space and generate novel tailor‐made virtual compound libraries for specific biological targets. By leveraging a combination of transfer learning, temperature‐modulated sampling, and stringent chemical validation, TargetGen‐RNN was trained on 5.7 million drug‐like compounds from the ZINC database and fine‐tuned with 82 known Staphylococcus aureus DHFR inhibitors, yielding 28,708 structurally diverse and chemically viable novel, tailor‐made molecules. Virtual screening, including QSAR analysis, pharmacophore mapping, molecular docking, molecular dynamic simulations, and multi‐criteria decision analysis against the generated tailor‐made compound library, led to the discovery of a potent antibiotic compound (SAK‐2970) with a novel scaffold with high predicted antibiotic activity, binding affinity, and favorable ADMET profiles. SAK‐2970 demonstrated remarkable in vitro bactericidal activity against S. aureus, strong biofilm inhibition and eradication capabilities, and exceptional efficacy against ciprofloxacin resistant S. aureus. In a mouse model of drug‐resistant bacteremia, SAK‐2970 significantly reduced bacterial load and improved survival rates with minimal systemic toxicity, underscoring its biocompatibility and therapeutic potential. These findings validate SAK‐2970 as a promising candidate for developing antibiotic treatments targeting resistant bacterial infections and highlight TargetGen‐RNN's powerful capability to generate hit compounds with novel scaffolds, advancing the frontier of antibiotic discovery.
DOI: 10.1002/inmd.70064
Open source ↗Discovering highly potent antimicrobial peptides with deep generative model HydrAMP
Paulina Szymczak, Marcin Możejko, Tomasz Grzegorzek, Radosław Jurczak, Marta Bauer, Damian Neubauer… · 2023 · Nature Communications
Antimicrobial peptides emerge as compounds that can alleviate the global health hazard of antimicrobial resistance, prompting a need for novel computational approaches to peptide generation. Here, we propose HydrAMP, a conditional variational autoencoder that learns lower-dimensional, continuous re…
Read paper details
Paulina Szymczak, Marcin Możejko, Tomasz Grzegorzek, Radosław Jurczak, Marta Bauer, Damian Neubauer, Karol Sikora, M. Michalski, J. Sroka, P. Setny, Wojciech Kamysz, Ewa Szczurek
Antimicrobial peptides emerge as compounds that can alleviate the global health hazard of antimicrobial resistance, prompting a need for novel computational approaches to peptide generation. Here, we propose HydrAMP, a conditional variational autoencoder that learns lower-dimensional, continuous representation of peptides and captures their antimicrobial properties. The model disentangles the learnt representation of a peptide from its antimicrobial conditions and leverages parameter-controlled creativity. HydrAMP is the first model that is directly optimized for diverse tasks, including unconstrained and analogue generation and outperforms other approaches in these tasks. An additional preselection procedure based on ranking of generated peptides and molecular dynamics simulations increases experimental validation rate. Wet-lab experiments on five bacterial strains confirm high activity of nine peptides generated as analogues of clinically relevant prototypes, as well as six analogues of an inactive peptide. HydrAMP enables generation of diverse and potent peptides, making a step towards resolving the antimicrobial resistance crisis. © 2023. The Author(s).
DOI: 10.1038/s41467-023-36994-z
Open source ↗Biochemical-knowledge-driven machine learning pipeline for generating potent antimicrobial peptides
Deliang Yang, Yi-Fan Li, Chen-Xi Li, Qingpeng Zhang, Jian-Dong Huang, Xue Li, Peng Gao · 2026 · Briefings in Bioinformatics
The growing threat of antimicrobial resistance (AMR) necessitates the rapid discovery of novel antimicrobial peptides (AMPs) as alternative therapeutics. However, most computational approaches rely on binary AMP or non-AMP classification or permissive MIC thresholds (e.g. ≤128 μg/mL), offering limi…
Read paper details
Deliang Yang, Yi-Fan Li, Chen-Xi Li, Qingpeng Zhang, Jian-Dong Huang, Xue Li, Peng Gao
The growing threat of antimicrobial resistance (AMR) necessitates the rapid discovery of novel antimicrobial peptides (AMPs) as alternative therapeutics. However, most computational approaches rely on binary AMP or non-AMP classification or permissive MIC thresholds (e.g. ≤128 μg/mL), offering limited biological interpretability and translational value. We present CVAE-BIO, a biochemical-knowledge-driven, multi-module pipeline for the discovery of AMPs targeting drug-resistant Escherichia coli as a model pathogen yet generalisable to other bacterial targets. The model integrates a conditional variational autoencoder (CVAE) constrained by key biochemical properties (MIC≤10 μg/mL, net charge > + 2, peptide length < 40 residues, instability index <40, and Boman index <0) with a Random Forest classifier trained on 30 biochemical descriptors. In vitro validation showed that 18.5% of generated peptides exhibited strong activity (MIC≤10 μg/mL), with 38.9% reaching MIC ≤50 μg/mL while maintaining key biochemical properties. Most validated novel peptides are narrow-spectrum AMP targeting E. coli. Wet-lab results also showed that highly active cationic-amphipathic AMPs are characterized by significantly low counts of tiny and small residues, suggesting that avoiding using these residues or limiting them to a maximum of 2 and 3, respectively, might improve the activity of AMP. Taking both antimicrobial activity and hemolytic toxicity into account, 9 peptides were identified as non-toxic and active AMP candidates. This explainable framework enables efficient AMP discovery under biochemical constraints and yields experimentally validated candidates with translational potential. © The Author(s) 2026. Published by Oxford University Press.
DOI: 10.1093/bib/bbag115
Open source ↗Intelligent De Novo Design of Novel Antimicrobial Peptides against Antibiotic-Resistant Bacteria Strains
Tzu-Tang Lin, Li-yen Yang, Chung-Yen Lin, Ching-Tien Wang, Chia-Wen Lai, Chi-Fong Ko, Yang-Hsin Shi… · 2023 · International Journal of Molecular Sciences
Because of the growing number of clinical antibiotic resistance cases in recent years, novel antimicrobial peptides (AMPs) may be ideal for next-generation antibiotics. This study trained a Wasserstein generative adversarial network with gradient penalty (WGAN-GP) based on known AMPs to generate no…
Read paper details
Tzu-Tang Lin, Li-yen Yang, Chung-Yen Lin, Ching-Tien Wang, Chia-Wen Lai, Chi-Fong Ko, Yang-Hsin Shih, Shu-Hwa Chen
Because of the growing number of clinical antibiotic resistance cases in recent years, novel antimicrobial peptides (AMPs) may be ideal for next-generation antibiotics. This study trained a Wasserstein generative adversarial network with gradient penalty (WGAN-GP) based on known AMPs to generate novel AMP candidates. The quality of the GAN-designed peptides was evaluated in silico, and eight of them, named GAN-pep 1-8, were selected by an AMP Artificial Intelligence (AI) classifier and synthesized for further experiments. Disc diffusion testing and minimum inhibitory concentration (MIC) determinations were used to identify the antibacterial effects of the synthesized GAN-designed peptides. Seven of the eight synthesized GAN-designed peptides displayed antibacterial activity. Additionally, GAN-pep 3 and GAN-pep 8 presented a broad spectrum of antibacterial effects and were effective against antibiotic-resistant bacteria strains, such as methicillin-resistant Staphylococcus aureus and carbapenem-resistant Pseudomonas aeruginosa. GAN-pep 3, the most promising GAN-designed peptide candidate, had low MICs against all the tested bacteria. In brief, our approach shows an efficient way to discover AMPs effective against general and antibiotic-resistant bacteria strains. In addition, such a strategy also allows other novel functional peptides to be quickly designed, identified, and synthesized for validation on the wet bench.
DOI: 10.3390/ijms24076788
Open source ↗Designing antimicrobial peptides using deep learning and molecular dynamic simulations
Qiushi Cao, Cheng Ge, Xue-Jie Wang, P. Harvey, Zixuan Zhang, Yuan Ma, Xiang-Hong Wang, Xinying Jia,… · 2023 · Briefings in bioinformatics
With the emergence of multidrug-resistant bacteria, antimicrobial peptides (AMPs) offer promising options for replacing traditional antibiotics to treat bacterial infections, but discovering and designing AMPs using traditional methods is a time-consuming and costly process. Deep learning has been …
Read paper details
Qiushi Cao, Cheng Ge, Xue-Jie Wang, P. Harvey, Zixuan Zhang, Yuan Ma, Xiang-Hong Wang, Xinying Jia, M. Mobli, D. Craik, Tao Jiang, Jinbo Yang, Zhiqiang Wei, Yan Wang, Shan Chang, Rilei Yu
With the emergence of multidrug-resistant bacteria, antimicrobial peptides (AMPs) offer promising options for replacing traditional antibiotics to treat bacterial infections, but discovering and designing AMPs using traditional methods is a time-consuming and costly process. Deep learning has been applied to the de novo design of AMPs and address AMP classification with high efficiency. In this study, several natural language processing models were combined to design and identify AMPs, i.e. sequence generative adversarial nets, bidirectional encoder representations from transformers and multilayer perceptron. Then, six candidate AMPs were screened by AlphaFold2 structure prediction and molecular dynamic simulations. These peptides show low homology with known AMPs and belong to a novel class of AMPs. After initial bioactivity testing, one of the peptides, A-222, showed inhibition against gram-positive and gram-negative bacteria. The structural analysis of this novel peptide A-222 obtained by nuclear magnetic resonance confirmed the presence of an alpha-helix, which was consistent with the results predicted by AlphaFold2. We then performed a structure-activity relationship study to design a new series of peptide analogs and found that the activities of these analogs could be increased by 4-8-fold against Stenotrophomonas maltophilia WH 006 and Pseudomonas aeruginosa PAO1. Overall, deep learning shows great potential in accelerating the discovery of novel AMPs and holds promise as an important tool for developing novel AMPs. © The Author(s) 2023. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.
DOI: 10.1093/bib/bbad058
Open source ↗Accelerated antimicrobial discovery via deep generative models and molecular dynamics simulations
Payel Das, Tom Sercu, Kahini Wadhawan, Inkit Padhi, Sebastian Gehrmann, F. Cipcigan, Vijil Chentham… · 2021 · Nature Biomedical Engineering
The de novo design of antimicrobial therapeutics involves the exploration of a vast chemical repertoire to find compounds with broad-spectrum potency and low toxicity. Here, we report an efficient computational method for the generation of antimicrobials with desired attributes. The method leverage…
Read paper details
Payel Das, Tom Sercu, Kahini Wadhawan, Inkit Padhi, Sebastian Gehrmann, F. Cipcigan, Vijil Chenthamarakshan, H. Strobelt, Cícero Edinaldo dos Santos, Pin-Yu Chen, Yi Yan Yang, Jeremy P. K. Tan, J. Hedrick, J. Crain, A. Mojsilovic
The de novo design of antimicrobial therapeutics involves the exploration of a vast chemical repertoire to find compounds with broad-spectrum potency and low toxicity. Here, we report an efficient computational method for the generation of antimicrobials with desired attributes. The method leverages guidance from classifiers trained on an informative latent space of molecules modelled using a deep generative autoencoder, and screens the generated molecules using deep-learning classifiers as well as physicochemical features derived from high-throughput molecular dynamics simulations. Within 48 days, we identified, synthesized and experimentally tested 20 candidate antimicrobial peptides, of which two displayed high potency against diverse Gram-positive and Gram-negative pathogens (including multidrug-resistant Klebsiella pneumoniae) and a low propensity to induce drug resistance in Escherichia coli. Both peptides have low toxicity, as validated in vitro and in mice. We also show using live-cell confocal imaging that the bactericidal mode of action of the peptides involves the formation of membrane pores. The combination of deep learning and molecular dynamics may accelerate the discovery of potent and selective broad-spectrum antimicrobials.
DOI: 10.1038/s41551-021-00689-x
Open source ↗Generative AI for designing and validating easily synthesizable and structurally novel antibiotics
Kyle Swanson, Gary Liu, Denise B. Catacutan, Autumn Arnold, James Y. Zou, Jonathan M. Stokes · 2024 · Nature Machine Intelligence
The rise of pan-resistant bacteria is creating an urgent need for structurally novel antibiotics. Artificial intelligence methods can discover new antibiotics, but existing methods have notable limitations. Property prediction models, which evaluate molecules one-by-one for a given property, scale …
Read paper details
Kyle Swanson, Gary Liu, Denise B. Catacutan, Autumn Arnold, James Y. Zou, Jonathan M. Stokes
The rise of pan-resistant bacteria is creating an urgent need for structurally novel antibiotics. Artificial intelligence methods can discover new antibiotics, but existing methods have notable limitations. Property prediction models, which evaluate molecules one-by-one for a given property, scale poorly to large chemical spaces. Generative models, which directly design molecules, rapidly explore vast chemical spaces but generate molecules that are challenging to synthesize. Here we introduce SyntheMol, a generative model that designs new compounds, which are easy to synthesize, from a chemical space of nearly 30 billion molecules. We apply SyntheMol to design molecules that inhibit the growth of Acinetobacter baumannii, a burdensome Gram-negative bacterial pathogen. We synthesize 58 generated molecules and experimentally validate them, with six structurally novel molecules demonstrating antibacterial activity against A. baumannii and several other phylogenetically diverse bacterial pathogens. This demonstrates the potential of generative artificial intelligence to design structurally novel, synthesizable and effective small-molecule antibiotic candidates from vast chemical spaces, with empirical validation.
DOI: 10.1038/s42256-024-00809-7
Open source ↗A generative deep learning approach to de novo antibiotic design
Aarti Krishnan, Melis N. Anahtar, Jacqueline A. Valeri, Wengong Jin, Nina M. Donghia, Leif Sieben, … · 2025 · Cell
The antimicrobial resistance crisis necessitates structurally distinct antibiotics. While deep learning approaches can identify antibacterial compounds from existing libraries, structural novelty remains limited. Here, we developed a generative artificial intelligence framework for designing de nov…
Read paper details
Aarti Krishnan, Melis N. Anahtar, Jacqueline A. Valeri, Wengong Jin, Nina M. Donghia, Leif Sieben, Andreas Luttens, Yu Zhang, S. Modaresi, Andrew D. Hennes, Jenna C. Fromer, Parijat Bandyopadhyay, Jonathan C. Chen, Danyal Rehman, Ronak Desai, P. Edwards, Ryan S. Lach, M. Aschtgen, Margaux Gaborieau, Massimiliano Gaetani, Samantha G. Palace, Satotaka Omori, L. Khonde, Yurii S. Moroz, B. Blough, Chunyang Jin, Edmund Loh, Y. Grad, A. Saei, Connor W. Coley, Felix Wong, James J. Collins
The antimicrobial resistance crisis necessitates structurally distinct antibiotics. While deep learning approaches can identify antibacterial compounds from existing libraries, structural novelty remains limited. Here, we developed a generative artificial intelligence framework for designing de novo antibiotics through two approaches: a fragment-based method to comprehensively screen >107 chemical fragments in silico against Neisseria gonorrhoeae or Staphylococcus aureus, subsequently expanding promising fragments, and an unconstrained de novo compound generation, each using genetic algorithms and variational autoencoders. Of 24 synthesized compounds, seven demonstrated selective antibacterial activity. Two lead compounds exhibited bactericidal efficacy against multidrug-resistant isolates with distinct mechanisms of action and reduced bacterial burden in vivo in mouse models of N. gonorrhoeae vaginal infection and methicillin-resistant S. aureus skin infection. We further validated structural analogs for both compound classes as antibacterial. Our approach enables the generative deep-learning-guided design of de novo antibiotics, providing a platform for mapping uncharted regions of chemical space. Copyright © 2025 Elsevier Inc. All rights reserved.
DOI: 10.1016/j.cell.2025.07.033
Open source ↗Antimicrobial resistance crisis: could artificial intelligence be the solution?
Guangyu Liu, Dan Yu, Meimei Fan, Xu Zhang, Ze-Yu Jin, Christoph M. Tang, Xiaofen Liu · 2024 · Military Medical Research
Antimicrobial resistance is a global public health threat, and the World Health Organization (WHO) has announced a priority list of the most threatening pathogens against which novel antibiotics need to be developed. The discovery and introduction of novel antibiotics are time-consuming and expensi…
Read paper details
Guangyu Liu, Dan Yu, Meimei Fan, Xu Zhang, Ze-Yu Jin, Christoph M. Tang, Xiaofen Liu
Antimicrobial resistance is a global public health threat, and the World Health Organization (WHO) has announced a priority list of the most threatening pathogens against which novel antibiotics need to be developed. The discovery and introduction of novel antibiotics are time-consuming and expensive. According to WHO's report of antibacterial agents in clinical development, only 18 novel antibiotics have been approved since 2014. Therefore, novel antibiotics are critically needed. Artificial intelligence (AI) has been rapidly applied to drug development since its recent technical breakthrough and has dramatically improved the efficiency of the discovery of novel antibiotics. Here, we first summarized recently marketed novel antibiotics, and antibiotic candidates in clinical development. In addition, we systematically reviewed the involvement of AI in antibacterial drug development and utilization, including small molecules, antimicrobial peptides, phage therapy, essential oils, as well as resistance mechanism prediction, and antibiotic stewardship. © 2024. The Author(s).
DOI: 10.1186/s40779-024-00510-1
Open source ↗Accelerating antibiotic discovery through artificial intelligence
Marcelo C. R. Melo, Jacqueline R. M. A. Maasch, César de la Fuente-Núñez · 2021 · Communications Biology
By targeting invasive organisms, antibiotics insert themselves into the ancient struggle of the host-pathogen evolutionary arms race. As pathogens evolve tactics for evading antibiotics, therapies decline in efficacy and must be replaced, distinguishing antibiotics from most other forms of drug dev…
Read paper details
Marcelo C. R. Melo, Jacqueline R. M. A. Maasch, César de la Fuente-Núñez
By targeting invasive organisms, antibiotics insert themselves into the ancient struggle of the host-pathogen evolutionary arms race. As pathogens evolve tactics for evading antibiotics, therapies decline in efficacy and must be replaced, distinguishing antibiotics from most other forms of drug development. Together with a slow and expensive antibiotic development pipeline, the proliferation of drug-resistant pathogens drives urgent interest in computational methods that promise to expedite candidate discovery. Strides in artificial intelligence (AI) have encouraged its application to multiple dimensions of computer-aided drug design, with increasing application to antibiotic discovery. This review describes AI-facilitated advances in the discovery of both small molecule antibiotics and antimicrobial peptides. Beyond the essential prediction of antimicrobial activity, emphasis is also given to antimicrobial compound representation, determination of drug-likeness traits, antimicrobial resistance, and de novo molecular design. Given the urgency of the antimicrobial resistance crisis, we analyze uptake of open science best practices in AI-driven antibiotic discovery and argue for openness and reproducibility as a means of accelerating preclinical research. Finally, trends in the literature and areas for future inquiry are discussed, as artificially intelligent enhancements to drug discovery at large offer many opportunities for future applications in antibiotic development. © 2021. The Author(s).
DOI: 10.1038/s42003-021-02586-0
Open source ↗A generative artificial intelligence approach for the discovery of antimicrobial peptides against multidrug-resistant bacteria
Yihui Wang, Lanlan Zhao, Zi-Yun Li, Yaxuan Xi, Yingmiao Pan, Guo-Ping Zhao, Lei Zhang · 2025 · Nature Microbiology
The discovery of novel antimicrobial peptides (AMPs) against clinical superbugs is urgently needed to address the ongoing antibiotic resistance crisis. AMPs are promising candidates due to their broad-spectrum activity, rapid bactericidal mechanisms and reduced likelihood of inducing resistance com…
Read paper details
Yihui Wang, Lanlan Zhao, Zi-Yun Li, Yaxuan Xi, Yingmiao Pan, Guo-Ping Zhao, Lei Zhang
The discovery of novel antimicrobial peptides (AMPs) against clinical superbugs is urgently needed to address the ongoing antibiotic resistance crisis. AMPs are promising candidates due to their broad-spectrum activity, rapid bactericidal mechanisms and reduced likelihood of inducing resistance compared with conventional antibiotics. Here, a pre-trained protein large language model (LLM), ProteoGPT, was established and further developed into multiple specialized subLLMs to assemble a sequential pipeline. This pipeline enables rapid screening across hundreds of millions of peptide sequences, ensuring potent antimicrobial activity and minimizing cytotoxic risks. Through transfer learning, we endowed the LLMs with different domain-specific knowledge to achieve high-throughput mining and generation of AMPs within a unified methodological framework. Notably, both mined and generated AMPs exhibited reduced susceptibility to resistance development in ICU-derived carbapenem-resistant Acinetobacter baumannii (CRAB) and methicillin-resistant Staphylococcus aureus (MRSA) in vitro. The AMPs also showed comparable or superior therapeutic efficacy in in vivo thigh infection mouse models compared with clinical antibiotics, without causing organ damage and disrupting gut microbiota. The mechanisms of action of these AMPs involve disruption of the cytoplasmic membrane and membrane depolarization. Overall, this study presents a generative artificial intelligence approach for the discovery of novel antimicrobials against multidrug-resistant bacteria, enabling efficient and extensive exploration of AMP space. © 2025. The Author(s).
DOI: 10.1038/s41564-025-02114-4
Open source ↗De novo design of self-assembling peptides with antimicrobial activity guided by deep learning.
Hua-Yang Liu, Zilin Song, Yu Zhang, Bihan Wu, Ding-Hao Chen, Ziao Zhou, Hong-Yan Zhang, Sangshuang … · 2025 · Nature materials
Bioinspired materials based on self-assembling peptides are promising for tackling various challenges in biomedical engineering. While contemporary data-driven approaches have led to the discovery of self-assembling peptides with various structures and properties, predicting the functionalities of …
Read paper details
Hua-Yang Liu, Zilin Song, Yu Zhang, Bihan Wu, Ding-Hao Chen, Ziao Zhou, Hong-Yan Zhang, Sangshuang Li, Xinping Feng, Jing Huang, Huaimin Wang
Bioinspired materials based on self-assembling peptides are promising for tackling various challenges in biomedical engineering. While contemporary data-driven approaches have led to the discovery of self-assembling peptides with various structures and properties, predicting the functionalities of these materials is still challenging. Here we describe the deep learning-guided de novo design of antimicrobial materials based on self-assembling peptides targeting bacterial membranes to address the emerging problem of bacterial drug resistance. Our approach integrates non-natural amino acids for enhanced peptide self-assembly and effectively predicts the functional activity of the self-assembling peptide materials with minimal experimental annotation. The designed self-assembling peptide leader displays excellent in vivo therapeutic efficacy against intestinal bacterial infection in mice. Moreover, it exhibits an enhanced biofilm eradication capability and does not induce acquired drug resistance. Mechanistic studies reveal that the designed peptide can self-assemble on bacterial membranes to form nanofibrous structures for killing multidrug-resistant bacteria. This work thus provides a strategy to discover functional peptide materials by customized design. © 2025. The Author(s), under exclusive licence to Springer Nature Limited.
DOI: 10.1038/s41563-025-02164-3
Open source ↗De Novo Multi‐Mechanism Antimicrobial Peptide Design via Multimodal Deep Learning
Xiaojuan Li, Haifan Gong, Yue Wang, Yinuo Zhao, Lixiang Li, Peijing Bao, Qing-Zhou Kong, Jialu Fu, … · 2024 · Advanced Science
Artificial intelligence (AI)-driven discovery of antimicrobial peptides (AMPs) is yet to fully utilize their three-dimensional (3D) structural characteristics, microbial species-specific antimicrobial activities, and mechanisms. Here, we constructed a QLAPD database comprising the sequence, structu…
Read paper details
Xiaojuan Li, Haifan Gong, Yue Wang, Yinuo Zhao, Lixiang Li, Peijing Bao, Qing-Zhou Kong, Jialu Fu, Boyao Wan, Yumeng Zhang, Jinghui Zhang, Jiekun Ni, Zhongxue Han, Xueping Nan, Kunping Ju, Longfei Sun, Yuerui Ma, Huijun Chang, Meng-Qi Zheng, Yanbo Yu, Xiaoyun Yang, Xiu-Li Zuo, Haina Wang, Yanqing Li
Artificial intelligence (AI)-driven discovery of antimicrobial peptides (AMPs) is yet to fully utilize their three-dimensional (3D) structural characteristics, microbial species-specific antimicrobial activities, and mechanisms. Here, we constructed a QLAPD database comprising the sequence, structures, and antimicrobial properties of 12 914 AMPs. QLAPD underlies a multimodal, multitask, multilabel, and conditionally controlled AMP discovery (M3-CAD) pipeline, proposed for the de novo design of multi-mechanism AMPs to combat multidrug-resistant organisms (MDROs). This pipeline integrates generation, regression, and classification modules, using an innovative 3D voxel coloring method to capture the nuanced physicochemical context of amino acids, thus enhancing structural characterizations. QLX-3DV-1 and QLX-3DV-2, identified through M3-CAD, were found to demonstrate multiple antimicrobial mechanisms, notable activity against MDROs, and low toxicity. In vivo experiments were used to validate their antimicrobial effects with limited local and systemic toxicity. Overall, integrating 3D features, species-specific antimicrobial activities, and mechanisms enhanced AI-driven AMP discovery, making the M3-CAD pipeline a viable tool for de novo AMP design. © 2026 The Author(s). Advanced Science published by Wiley‐VCH GmbH.
DOI: 10.1002/advs.202515835
Open source ↗Machine learning for antimicrobial peptide identification and design
Fang-Ping Wan, Felix Wong, James J. Collins, César de la Fuente-Núñez · 2024 · Nature reviews bioengineering
Artificial intelligence (AI) and machine learning (ML) models are being deployed in many domains of society and have recently reached the field of drug discovery. Given the increasing prevalence of antimicrobial resistance, as well as the challenges intrinsic to antibiotic development, there is an …
Read paper details
Fang-Ping Wan, Felix Wong, James J. Collins, César de la Fuente-Núñez
Artificial intelligence (AI) and machine learning (ML) models are being deployed in many domains of society and have recently reached the field of drug discovery. Given the increasing prevalence of antimicrobial resistance, as well as the challenges intrinsic to antibiotic development, there is an urgent need to accelerate the design of new antimicrobial therapies. Antimicrobial peptides (AMPs) are therapeutic agents for treating bacterial infections, but their translation into the clinic has been slow owing to toxicity, poor stability, limited cellular penetration and high cost, among other issues. Recent advances in AI and ML have led to breakthroughs in our abilities to predict biomolecular properties and structures and to generate new molecules. The ML-based modelling of peptides may overcome some of the disadvantages associated with traditional drug discovery and aid the rapid development and translation of AMPs. Here, we provide an introduction to this emerging field and survey ML approaches that can be used to address issues currently hindering AMP development. We also outline important limitations that can be addressed for the broader adoption of AMPs in clinical practice, as well as new opportunities in data-driven peptide design.
DOI: 10.1038/s44222-024-00152-x
Open source ↗Discovery of antimicrobial peptides with notable antibacterial potency by an LLM-based foundation model
Ji-Ke Wang, Jianwen Feng, Yu Kang, P. Pan, Jingxuan Ge, Yan Wang, Mingyang Wang, Zhenxing Wu, Xingc… · 2025 · Science Advances
Large language models (LLMs) have shown remarkable advancements in chemistry and biomedical research, acting as versatile foundation models for various tasks. We introduce AMP-Designer, an LLM-based approach, for swiftly designing antimicrobial peptides (AMPs) with desired properties. Within 11 day…
Read paper details
Ji-Ke Wang, Jianwen Feng, Yu Kang, P. Pan, Jingxuan Ge, Yan Wang, Mingyang Wang, Zhenxing Wu, Xingcai Zhang, Jiameng Yu, Xujun Zhang, Tianyue Wang, Lirong Wen, Guangning Yan, Yafeng Deng, Hui Shi, Chang-Yu Hsieh, Zhihui Jiang, Tingjun Hou
Large language models (LLMs) have shown remarkable advancements in chemistry and biomedical research, acting as versatile foundation models for various tasks. We introduce AMP-Designer, an LLM-based approach, for swiftly designing antimicrobial peptides (AMPs) with desired properties. Within 11 days, AMP-Designer achieved the de novo design of 18 AMPs with broad-spectrum activity against Gram-negative bacteria. In vitro validation revealed a 94.4% success rate, with two candidates demonstrating exceptional antibacterial efficacy, minimal hemotoxicity, stability in human plasma, and low potential to induce resistance, as evidenced by significant bacterial load reduction in murine lung infection experiments. The entire process, from design to validation, concluded in 48 days. AMP-Designer excels in creating AMPs targeting specific strains despite limited data availability, with a top candidate displaying a minimum inhibitory concentration of 2.0 micrograms per milliliter against Propionibacterium acnes. Integrating advanced machine learning techniques, AMP-Designer demonstrates remarkable efficiency, paving the way for innovative solutions to antibiotic resistance.
DOI: 10.1126/sciadv.ads8932
Open source ↗Quantum Annealing Designs Nonhemolytic Antimicrobial Peptides in a Discrete Latent Space
A. Tučs, F. Berenger, Akiko Yumoto, Ryo Tamura, Takanori Uzawa, Koji Tsuda · 2023 · ACS Medicinal Chemistry Letters
Increasing the variety of antimicrobial peptides is crucial in meeting the global challenge of multi-drug-resistant bacterial pathogens. While several deep-learning-based peptide design pipelines are reported, they may not be optimal in data efficiency. High efficiency requires a well-compressed la…
Read paper details
A. Tučs, F. Berenger, Akiko Yumoto, Ryo Tamura, Takanori Uzawa, Koji Tsuda
Increasing the variety of antimicrobial peptides is crucial in meeting the global challenge of multi-drug-resistant bacterial pathogens. While several deep-learning-based peptide design pipelines are reported, they may not be optimal in data efficiency. High efficiency requires a well-compressed latent space, where optimization is likely to fail due to numerous local minima. We present a multi-objective peptide design pipeline based on a discrete latent space and D-Wave quantum annealer with the aim of solving the local minima problem. To achieve multi-objective optimization, multiple peptide properties are encoded into a score using non-dominated sorting. Our pipeline is applied to design therapeutic peptides that are antimicrobial and non-hemolytic at the same time. From 200 000 peptides designed by our pipeline, four peptides proceeded to wet-lab validation. Three of them showed high anti-microbial activity, and two are non-hemolytic. Our results demonstrate how quantum-based optimizers can be taken advantage of in real-world medical studies. © 2023 The Authors. Published by American Chemical Society.
DOI: 10.1021/acsmedchemlett.2c00487
Open source ↗Disagreements & Limitations
Disagreements
- No major disagreement identified.
Limitations
- No direct mention of halicin in the provided evidence—only abaucin is cited [C184]—so halicin cannot be counted as a supported success.
- Most studies focus on AMPs; fewer address small-molecule antibiotics beyond TargetGen-RNN [C186].
- In vivo validation remains rare; only [C186] reports animal model data among the provided sources.
- Lack of standardized benchmarks for generative models makes performance comparisons difficult across studies [C185].
- Several high-impact papers (e.g., on halicin, LLM-designed peptides) were omitted from the evidence set, limiting comprehensiveness.
Sources
Accounts of Chemical Research · 2025 · DOI: 10.1021/acs.accounts.0c00594
Open sourcehttps://consensus.app/papers/aidriven-antimicrobial-peptide-discovery-mining-and-szymczak-zarzecki/ed64743d22ab50538db31eb58c921e32/?utm_source=publicapiAntibiotics · 2026 · DOI: 10.3390/antibiotics15020233
Open sourcehttps://consensus.app/papers/artificial-intelligence-and-the-discovery-of-antibiotics-sanapalli-palit/48c251f439d75d3394f163bd34bb6188/?utm_source=publicapiAntibiotics · 2025 · DOI: 10.3390/antibiotics14121263
Open sourcehttps://consensus.app/papers/harnessing-machine-learning-approaches-for-the-saleem-kumar/f5697157dfa3547fbb334a8d2ab72ff4/?utm_source=publicapiInterdisciplinary Medicine · 2025 · DOI: 10.1002/inmd.70064
Open sourcehttps://consensus.app/papers/targetgenrnn-model-discovers-novel-antibiotic-compound-khan-shakoor/3c82db62b19b58b7b1c34c1a47e47260/?utm_source=publicapiNature Communications · 2023 · DOI: 10.1038/s41467-023-36994-z
Open sourcehttps://consensus.app/papers/discovering-highly-potent-antimicrobial-peptides-with-szymczak-moejko/4b5ec9fe6cf4539ea61b42edd560a231/?utm_source=publicapiBriefings in Bioinformatics · 2026 · DOI: 10.1093/bib/bbag115
Open sourcehttps://consensus.app/papers/biochemicalknowledgedriven-machine-learning-pipeline-yang-li/87e9df460a5351bea0b513106d6b06c1/?utm_source=publicapi