CoChat
Sign Up
PreprintCited by 0Antimicrobial Peptides and ActivitiesComputational Drug Discovery MethodsChemical Synthesis and Analysis

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Controllable generation of non-hemolytic antimicrobial peptides by multi-guided latent diffusion

Open access
Qin, Weihan, Wu, Yaling, Li, Chongyang, Cao, Sen, Guo, Jingjing, Ge, Yutong, Guo, Juan, Mo, Jisong, Zhu, Ning, Duan, Hongliang·2026·Journal of Cheminformatics
DOI 10.21203/rs.3.rs-9068112/v1

Preprint — published as 10.1186/s13321-026-01269-4

Open this paper in CoChat — free account

Abstract

Antimicrobial peptides (AMPs) are attractive anti-infective scaffolds, but their development is often constrained by hemolysis and by the narrow physicochemical separation between bacterial killing and host-cell damage. We developed NHAMP, a protein language model (PLM)-fused latent diffusion framework for generating peptides under explicit efficacy-safety constraints. NHAMP maps sequences into ESM-2 embeddings, denoises them with a conditional diffusion model that reuses PLM attention blocks, and decodes latent states with a noise-adapted masked-language-model head. During sampling, classifier-free guidance from antimicrobial, non-hemolytic and dual-property conditions is accumulated at each denoising step, allowing the model to search more directly for the overlap between activity and safety rather than maximise one property and filter later. Under a shared in silico evaluation pipeline, NHAMP maintained a high predicted AMP-positive rate (83.8%) while increasing the predicted non-hemolytic fraction to 71.4%, and ablation showed that combining all three guidance branches produced the strongest dual-objective yield among the tested settings ACCdual = 64.7%). Composition, physicochemical and embedding-space analyses showed a consistent shift toward more cationic, less hydrophobic and less aggregation-prone peptides. Overall, the results support the idea that introducing safety during denoising, rather than only after generation, can improve the practical yield of AMP libraries for downstream experimental prioritisation.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.21203/rs.3.rs-9068112/v1

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 38

  1. Murray CJL et al (2022) Global Burden of Bacterial Antimicrobial Resistance in 2019: A Systematic Analysis. Lancet 399(10325):629–655. https://doi.org/10.1016/S0140-6736(21)02724-0 · DOI · Paper page
  2. Zasloff M (2002) Antimicrobial peptides of multicellular organisms. Nature 415:389–395. https://doi.org/10.1038/415389a · DOI · Paper page
  3. Hancock REW, Sahl H-G (2006) Antimicrobial and host-defense peptides as new anti-infective therapeutic strategies. Nat Biotechnol 24:1551–1557. https://doi.org/10.1038/nbt1267 · DOI
  4. Fjell CD, Hiss JA, Hancock REW, Schneider G (2012) Designing antimicrobial peptides: form follows function. Nat Rev Drug Discov 11:37–51. https://doi.org/10.1038/nrd3591 · DOI
  5. Mookherjee N, Anderson MA, Haagsman HP, Davidson DJ (2020) Antimicrobial host defence peptides: functions and clinical potential. Nat Rev Drug Discov 19:311–332. https://doi.org/10.1038/s41573-019-0058-8 · DOI · Paper page
  6. Magana M, Pushpanathan M, Santos AL et al (2020) The value of antimicrobial peptides in the age of resistance. Lancet Infect Dis 20:e216–e230. https://doi.org/10.1016/S1473-3099(20)30327-3 · DOI
  7. Matsuzaki K (2009) Control of cell selectivity of antimicrobial peptides. Biochimica et Biophysica Acta (BBA) -. Biomembranes 1788:1687–1692. https://doi.org/10.1016/j.bbamem.2008.09.013 · DOI
  8. Dathe M, Wieprecht T, Nikolenko H et al (1997) Hydrophobicity, hydrophobic moment and angle subtended by charged residues modulate antibacterial and haemolytic activity of amphipathic helical peptides. FEBS Lett 403:208–212. https://doi.org/10.1016/S0014-5793(97)00055-0 · DOI
  9. Nguyen LT, Haney EF, Vogel HJ (2011) The expanding scope of antimicrobial peptide structures and their modes of action. Trends Biotechnol 29:464–472. https://doi.org/10.1016/j.tibtech.2011.05.001 · DOI
  10. Wimley WC (2010) Describing the Mechanism of Antimicrobial Peptide Action with the Interfacial Activity Model. ACS Chem Biol 5:905–917. https://doi.org/10.1021/cb1001558 · DOI
  11. Wang G, Li X, Wang Z (2016) APD3: the antimicrobial peptide database as a tool for research and education. Nucleic Acids Res 44:D1087–D1093. https://doi.org/10.1093/nar/gkv1278 · DOI
  12. Pirtskhalava M, Amstrong AA, Grigolava M et al (2021) DBAASP v3: database of antimicrobial/cytotoxic activity and structure of peptides as a resource for development of new therapeutics. Nucleic Acids Res 49:D288–D297. https://doi.org/10.1093/nar/gkaa991 · DOI
  13. Shi G, Kang X, Dong F et al (2022) DRAMP 3.0: an enhanced comprehensive data repository of antimicrobial peptides. Nucleic Acids Res 50:D488–D496. https://doi.org/10.1093/nar/gkab651 · DOI
  14. Veltri D, Kamath U, Shehu A (2018) Deep learning improves antimicrobial peptide recognition. Bioinformatics 34:2740–2747. https://doi.org/10.1093/bioinformatics/bty179 · DOI
  15. Thomas S, Karnik S, Barai RS et al (2010) CAMP: a useful resource for research on antimicrobial peptides. Nucleic Acids Res 38:D774–D780. https://doi.org/10.1093/nar/gkp1021 · DOI · Paper page
  16. Lin T-T, Yang L-Y, Lu I-H et al (2021) AI4AMP: an Antimicrobial Peptide Predictor Using Physicochemical Property-Based Encoding Method and Deep Learning. mSystems 6:e0029921. https://doi.org/10.1128/mSystems.00299-21 · DOI
  17. Rathore AS, Kumar N, Choudhury S et al (2025) Prediction of hemolytic peptides and their hemolytic concentration. Commun Biol 8:176. https://doi.org/10.1038/s42003-025-07615-w · DOI
  18. Wan F, Wong F, Collins JJ, de la Fuente-Nunez C (2024) Machine learning for antimicrobial peptide identification and design. Nat Rev Bioeng 2:392–407. https://doi.org/10.1038/s44222-024-00152-x · DOI
  19. Szymczak P, Szczurek E (2023) Artificial intelligence-driven antimicrobial peptide discovery. Curr Opin Struct Biol 83:102733. https://doi.org/10.1016/j.sbi.2023.102733 · DOI
  20. Sidorczuk K, Gagat P, Pietluch F et al (2022) Benchmarks in antimicrobial peptide prediction are biased due to the selection of negative data. Brief Bioinform 23:bbac343. https://doi.org/10.1093/bib/bbac343 · DOI
  21. Wan F, Kontogiorgos-Heintz D, de la Fuente-Nunez C (2022) Deep generative models for peptide design. Digit Discovery 1:195–208. https://doi.org/10.1039/D1DD00024A · DOI
  22. Torres MDT, Cao J, Franco OL et al (2021) Synthetic Biology and Computer-Based Frameworks for Antimicrobial Peptide Discovery. ACS Nano 15:2143–2164. https://doi.org/10.1021/acsnano.0c09509 · DOI
  23. Szymczak P, Możejko M, Grzegorzek T et al (2023) Discovering highly potent antimicrobial peptides with deep generative model HydrAMP. Nat Commun 14:1453. https://doi.org/10.1038/s41467-023-36994-z · DOI · Paper page
  24. Yu H, Wang R, Qiao J, Wei L (2024) Multi-CGAN: Deep Generative Model-Based Multiproperty Antimicrobial Peptide Design. J Chem Inf Model 64:316–326. https://doi.org/10.1021/acs.jcim.3c01881 · DOI
  25. Wang X-F, Tang J-Y, Liang H et al (2024) ProT-Diff: A Modularized and Efficient Approach to De Novo Generation of Antimicrobial Peptide Sequences through Integration of Protein Language Model and Diffusion Model. 2024.02.22.581480.https://doi.org/10.1002/advs.202406305 · DOI
  26. Luo Z, Geng A, Wei L et al (2025) CPL-Diff: A Diffusion Model for De Novo Design of Functional Peptide Sequences with Fixed Length. Adv Sci 12:2412926. https://doi.org/10.1002/advs.202412926 · DOI
  27. Torres MDT, Chen LT, Wan F et al (2025) Generative latent diffusion language modeling yields anti-infective synthetic peptides. Cell Biomaterials 1:100183. https://doi.org/10.1016/j.celbio.2025.100183 · DOI
  28. Das P, Sercu T, Wadhawan K et al (2021) Accelerated antimicrobial discovery via deep generative models and molecular dynamics simulations. Nat Biomed Eng 5:613–623. https://doi.org/10.1038/s41551-021-00689-x · DOI
  29. Capecchi A et al (2021) Machine Learning Designs Non-Hemolytic Antimicrobial Peptides. Chem Sci 12(26):9221–9232. https://doi.org/10.1039/d1sc01713f · DOI
  30. Rives A, Meier J, Sercu T et al (2021) Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proceedings of the National Academy of Sciences 118:e2016239118. https://doi.org/10.1073/pnas.2016239118 · DOI · Paper page
  31. Lin Z, Akin H, Rao R et al (2023) Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379:1123–1130. https://doi.org/10.1126/science.ade2574 · DOI · Paper page
  32. Ho J, Jain A, Abbeel P (2020) Denoising Diffusion Probabilistic Models.https://doi.org/10.48550/arXiv.2006.11239 · DOI · Paper page
  33. Ho J, Salimans T (2022) Classifier-Free Diffusion Guidance.https://doi.org/10.48550/arXiv.2207.12598 · DOI · Paper page
  34. Sohl-Dickstein J, Weiss EA, Maheswaranathan N, Ganguli S (2015) Deep Unsupervised Learning using Nonequilibrium Thermodynamics.https://doi.org/10.48550/arXiv.1503.03585 · DOI · Paper page
  35. Nichol AQ, Dhariwal P (2020) Improved Denoising Diffusion Probabilistic Models.https://doi.org/10.48550/arXiv.2102.09672 · DOI · Paper page
  36. van der Maaten L, Hinton G (2008) Visualizing Data using t-SNE. J Mach Learn Res 9:2579–2605
  37. McInnes L, Healy J, Melville J (2020) UMAP: Uniform Manifold Approximation and Projection. https://doi.org/10.48550/arXiv.1802.03426. for Dimension Reduction. · DOI · Paper page
  38. Perez E, Strub F, de Vries H et al (2017) FiLM: Visual Reasoning with a General Conditioning Layer. https://doi.org/10.48550/arXiv.1709.07871 · DOI

Metadata

Authors
Qin, W., Wu, Y., Li, C., Cao, S., Guo, J., Ge, Y., Guo, J., Mo, J., Zhu, N., & Duan, H.
Affiliations
Macao Polytechnic University (MO)
Corresponding author
  • Zhu, Ning
  • Duan, Hongliang
ORCID
Venue
Journal of Cheminformatics
Publisher
Springer Science and Business Media LLC
Published
2026-04-01
ISSN
1758-2946 (ISSN-L)
DOI
10.21203/rs.3.rs-9068112/v1
OpenAlex
W7204036676
Cited by
0
References
1
FWCI
0.00
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Cheminformatics (publishedVersion, cc-by-nc-nd)
  • Research Square (acceptedVersion, cc-by)
Funders
Fundo para o Desenvolvimento das Ciências e da Tecnologia (0029/2025/RIB1)
Topics
  • Life Sciences › Immunology and Microbiology › Microbiology › Antimicrobial Peptides and Activities
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Physical Sciences › Chemistry › Organic Chemistry › Chemical Synthesis and Analysis
Keywords
antimicrobial peptides, peptide production, latent diffusion models, classifier-free guidance, protein language models, ESM-2 embeddings, peptide library design, cationic peptides, peptide physicochemical properties, in silico prediction, diffusion denoising

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review