Accelerating Antimicrobial Peptide Discovery for WHO Priority Pathogens through Predictive and Interpretable Machine Learning Models

Cheng-Ting Tsai; Chia-Wei Lin; Gen-Lin Ye; Shao-Chi Wu; Philip Yao; Ching-Ting Lin; Lei Wan; Hui-Hsu Gavin Tsai

doi:10.1021/acsomega.3c08676

Accelerating Antimicrobial Peptide Discovery for WHO Priority Pathogens through Predictive and Interpretable Machine Learning Models

ACS Omega. 2024 Feb 13;9(8):9357-9374. doi: 10.1021/acsomega.3c08676. eCollection 2024 Feb 27.

Authors

Cheng-Ting Tsai¹, Chia-Wei Lin¹, Gen-Lin Ye¹, Shao-Chi Wu¹, Philip Yao², Ching-Ting Lin³, Lei Wan³, Hui-Hsu Gavin Tsai^{1

4}

Affiliations

¹ Department of Chemistry, National Central University, No. 300, Zhongda Road, Zhongli District, Taoyuan 32001, Taiwan.
² Aurora High School, 109 W Pioneer Trail, Aurora, Ohio 44202, United States.
³ School of Chinese Medicine, China Medical University, No. 91 Hsueh-Shih Road, Taichung 40402, Taiwan.
⁴ Research Center of New Generation Light Driven Photovoltaic Modules, National Central University, Taoyuan 32001, Taiwan.

Abstract

The escalating menace of multidrug-resistant (MDR) pathogens necessitates a paradigm shift from conventional antibiotics to innovative alternatives. Antimicrobial peptides (AMPs) emerge as a compelling contender in this arena. Employing in silico methodologies, we can usher in a new era of AMP discovery, streamlining the identification process from vast candidate sequences, thereby optimizing laboratory screening expenditures. Here, we unveil cutting-edge machine learning (ML) models that are both predictive and interpretable, tailored for the identification of potent AMPs targeting World Health Organization's (WHO) high-priority pathogens. Furthermore, we have developed ML models that consider the hemolysis of human erythrocytes, emphasizing their therapeutic potential. Anchored in the nuanced physical-chemical attributes gleaned from the three-dimensional (3D) helical conformations of AMPs, our optimized models have demonstrated commendable performance-boasting an accuracy exceeding 75% when evaluated against both low-sequence-identified peptides and recently unveiled AMPs. As a testament to their efficacy, we deployed these models to prioritize peptide sequences stemming from PEM-2 and subsequently probed the bioactivity of our algorithm-predicted peptides vis-à-vis WHO's priority pathogens. Intriguingly, several of these new AMPs outperformed the native PEM-2 in their antimicrobial prowess, thereby underscoring the robustness of our modeling approach. To elucidate ML model outcomes, we probe via Shapley Additive exPlanations (SHAP) values, uncovering intricate mechanisms guiding diverse actions against bacteria. Our state-of-the-art predictive models expedite the design of new AMPs, offering a robust countermeasure to antibiotic resistance. Our prediction tool is available to the public at https://ai-meta.chem.ncu.edu.tw/amp-meta.