Student or educator? Sign up with your school email and get 6 months of Pro free.
PreprintCited by 2

The DOI matches its Crossref record; the references it cites are not checked yet.

A Multi-Property Optimizing Generative Adversarial Network for de novo Antimicrobial Peptide Design

Liu, Jiaming, Cui, Tao, Wang, Tao, Zeng, Xi, Niu, Yinbo, Jiao, Shaoqing, Lu, Dazhi, Wang, Jun, Xiao, Shuyuan, Xie, Dongna, Wang, Xuecheng, Wang, Yongtian, Shang, Xuequn, Wei, Zhongyu, Peng, Jiajie·2024

Preprint — published as 10.1002/advs.202503443

Abstract

Antimicrobial peptides (AMPs) play a crucial role in developing novel antiinfective drugs due to their broad-spectrum antimicrobial activity and lower likelihood of causing bacterial resistance. However, laboratory synthesis of AMPs is tedious and time-consuming. Existing computational methods have limited capability in optimizing multiple desired properties simultaneously. Here, we propose a Multi-Property Optimizing Generative Adversarial Network (MPOGAN), a feedback-loop framework that iteratively learns from data with multiple desired properties. This approach enables de novo design of AMPs with potent antimicrobial activity, reduced cytotoxicity, and diversity. Through extensive computational tests, MPOGAN exhibits superior performance in optimizing multiple desired properties of generated AMPs. Ten of the most promising candidates are chemically synthesized, with nine showing potent antimicrobial activity against three bacterial strains and low cytotoxicity against eukaryotic cells. MPOGAN offers a powerful computational approach for effective multi-property optimization of AMPs, thereby advancing the field of AI-aided drug discovery.

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 · 10.1101/2024.11.13.623386

Cites

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

The citation lists haven’t been fetched yet

Cited by 2

Research works printed but not linked: 68

  1. 10.1111/cbdd.12988 · doi:10.1111/cbdd.12988
  2. 10.1007/s00726-017-2473-7 · DOI
  3. 10.1038/s41551-022-00991-2 · DOI · Paper page
  4. 10.1038/nbt1267 · DOI · Paper page
  5. 10.1080/07388551.2020.1796576 · DOI · Paper page
  6. 2023, Designing antimicrobial peptides using deep learning and molecular dynamic simulations, Briefings in Bioinformatics, 24, 058
  7. 10.1111/jam.15314 · DOI · Paper page
  8. 10.1016/j.mpmed.2017.07.006 · DOI · Paper page
  9. 10.1038/s41467-023-36994-z · DOI · Paper page
  10. 10.1038/s41551-021-00689-x · DOI · Paper page
  11. 10.1609/aaai.v38i1.27792 · DOI
  12. 10.7717/peerj.10555 · DOI
  13. 10.1038/s41598-018-19752-w · DOI · Paper page
  14. 10.1016/j.bbagen.2021.130070 · DOI
  15. 10.1093/bioinformatics/bty179 · DOI · Paper page
  16. 2022, Amplify: attentive deep learning model for discovery of novel antimicrobial peptides effective against who priority pathogens, BMC genomics, 23, 77, 10.1186/s12864-022-08310-4 · DOI · Paper page
  17. 10.1093/bib/bbac174 · DOI · Paper page
  18. 10.1002/pro.4529 · DOI
  19. 10.1038/s41587-022-01226-0 · DOI · Paper page
  20. Santos-Júnior, C.D. , Torres, M.D. , Duan, Y. , Del Rìo, Á.R. , Schmidt, T.S. , Chong, H. , Fullam, A. , Kuhn, M. , Zhu, C. , Houseman, A. , et al.: Discovery of antimicrobial peptides in the global microbiome with machine learning. Cell (2024) · DOI · Paper page
  21. 10.1186/s12859-021-04156-x · DOI · Paper page
  22. 10.1038/s41467-018-03746-3 · DOI · Paper page
  23. 10.1074/jbc.M117.805499 · DOI
  24. 10.3390/biom11030471 · DOI
  25. 10.1021/acs.jcim.7b00414 · DOI · Paper page
  26. 10.1039/D1SC01713F · DOI · Paper page
  27. 2018, Pepcvae: Semi-supervised targeted design of antimicrobial peptide sequences, arXiv preprint
  28. 10.3389/fmicb.2021.725727 · DOI · Paper page
  29. 10.1021/acsomega.0c00442 · DOI
  30. 10.1021/acs.jcim.0c01441 · DOI · Paper page
  31. 10.1021/acsomega.0c02088 · DOI
  32. 10.1038/s42256-019-0017-4 · DOI · Paper page
  33. 10.1016/j.sbi.2021.11.008 · DOI
  34. 2021, Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models, IEEE transactions on pattern analysis and machine intelligence, 44, 7327
  35. 10.3390/antibiotics11101451 · DOI
  36. 10.1038/s41598-020-73644-6 · DOI · Paper page
  37. 10.1038/s41467-023-42434-9 · DOI · Paper page
  38. 2014, Net charge, hydrophobicity and specific amino acids contribute to the activity of antimicrobial peptides, J. Health Transl. Med, 17, 1, 10.22452/jummec.vol17no1.1 · DOI
  39. 10.1093/nar/gkab651 · DOI · Paper page
  40. Yu, L. , Zhang, W. , Wang, J. , Yu, Y. : Seqgan: Sequence generative adversarial nets with policy gradient. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017) · DOI · Paper page
  41. 10.1126/science.ade2574 · doi:10.1126/science.ade2574 · Paper page
  42. 10.1093/bioinformatics/bts565 · DOI · Paper page
  43. 10.1093/bioinformatics/btaa917 · DOI
  44. 2020, Physicochemical features and peculiarities of interaction of antimicrobial peptides with the membrane, arXiv preprint
  45. 10.2174/0929866526666190228144219 · doi:10.2174/0929866526666190228144219
  46. Maaten, L. , Hinton, G. : Visualizing data using t-sne. Journal of machine learning research 9(11) (2008)
  47. 10.1371/journal.pbio.1001014 · DOI
  48. 10.1093/nar/gkn201 · DOI · Paper page
  49. 10.1002/WICS.101 · DOI · Paper page
  50. 10.1016/S0016-0032(96)00063-4 · DOI · Paper page
  51. 10.1093/nar/gkac1052 · DOI · Paper page
  52. 10.1016/j.cellimm.2012.11.009 · DOI · Paper page
  53. Abramson, J. , Adler, J. , Dunger, J. , Evans, R. , Green, T. , Pritzel, A. , Ronneberger, O. , Willmore, L. , Ballard, A.J. , Bambrick, J. , et al.: Accurate structure prediction of biomolecular interactions with alphafold 3. Nature, 1–3 (2024) · DOI · Paper page
  54. 10.1016/j.softx.2015.06.001 · DOI · Paper page
  55. 10.1016/j.bbagen.2018.06.011 · DOI
  56. 10.1093/nar/gkv1114 · DOI · Paper page
  57. 10.1093/nar/gkac933 · DOI · Paper page
  58. 10.1093/nar/gkab1080 · DOI · Paper page
  59. 2020, Lamp2: a major update of the database linking antimicrobial peptides, Database, 2020, 061
  60. 10.1109/MCI.2023.3245731 · DOI
  61. 2018, Bert: Pre-training of deep bidirectional transformers for language understanding, arXiv preprint
  62. 10.1093/bioinformatics/btu739 · DOI · Paper page
  63. 2018, Deep learning using rectified linear units (relu), arXiv preprint
  64. 10.3390/antibiotics9010024 · DOI · Paper page
  65. 2023, Deep class-incremental learning: A survey, arXiv preprint
  66. 2013, An empirical investigation of catastrophic forgetting in gradient-based neural networks, arXiv preprint
  67. 10.1093/bioinformatics/btn392 · DOI · Paper page
  68. 10.1093/bioinformatics/btx285 · DOI · Paper page

Metadata

Authors
Liu, J., Cui, T., Wang, T., Zeng, X., Niu, Y., Jiao, S., Lu, D., Wang, J., Xiao, S., Xie, D., Wang, X., Wang, Y., Shang, X., Wei, Z., & Peng, J.
Publisher
openRxiv
Published
2024-11-15
Cited by
2
Type
Preprint

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A Multi-Property Optimizing Generative Adversarial Network for de novo Antimicrobial Peptide Design. https://app.cochat.ai/papers/10.1101/2024.11.13.623386
The paper
Liu, J., Cui, T., Wang, T., Zeng, X., Niu, Y., Jiao, S., Lu, D., Wang, J., Xiao, S., Xie, D., Wang, X., Wang, Y., Shang, X., Wei, Z., & Peng, J. (2024). A Multi-Property Optimizing Generative Adversarial Network for de novo Antimicrobial Peptide Design. https://doi.org/10.1101/2024.11.13.623386

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.