Accelerating Antimicrobial Peptide Discovery with Latent Structure

Danqing Wang, Zeyu Wen^†, Fei Ye^††, Lei Li^*, Hao Zhou^*¶,

UC Santa Barbara, †Huazhong University of Science and Technology,
††ByteDance Research, ¶Tsinghua University
KDD 2023
^*Indicates Equal Corresponding

Paper Video Code Slides

Abstract

Antimicrobial peptides (AMPs) are promising therapeutic approaches against drug-resistant pathogens. Recently, deep generative models are used to discover new AMPs. However, previous studies mainly focus on peptide sequence attributes and do not consider crucial structure information. In this paper, we propose a latent sequence-structure model for designing AMPs (LSSAMP). LSSAMP exploits multi-scale vector quantization in the latent space to represent secondary structures (e.g. alpha helix and beta sheet). By sampling in the latent space, LSSAMP can simultaneously generate peptides with ideal sequence attributes and secondary structures. Experimental results show that the peptides generated by LSSAMP have a high probability of antimicrobial activity. Our wet laboratory experiments verified that two of the 21 candidates exhibit strong antimicrobial activity.

Secondary structures are important to biological functions such as antimicrobial activities.

Model Overview. Here, we use 𝑁 = 4 pattern selectors to select local patterns with different scales and use the corresponding codebooks to obtain discrete latent variables 𝑧𝑖 for each position.

Generated peptides verified with antimicrobial activities in wet laboratory

LSSAMP outperforms baselines in biological attributes and comparable in AMP classifiers

LSSAMP generations share similar distribution as Real AMPs

Poster

BibTeX

@inproceedings{10.1145/3580305.3599249,
      author = {Wang, Danqing and Wen, Zeyu and Ye, Fei and Li, Lei and Zhou, Hao},
      title = {Accelerating Antimicrobial Peptide Discovery with Latent Structure},
      year = {2023},
      isbn = {9798400701030},
      publisher = {Association for Computing Machinery},
      address = {New York, NY, USA},
      url = {https://doi.org/10.1145/3580305.3599249},
      doi = {10.1145/3580305.3599249},
      booktitle = {Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
      pages = {2243–2255},
      numpages = {13},
      keywords = {generative model, peptide generation, drug discovery},
      location = {Long Beach, CA, USA},
      series = {KDD '23}
      }