Biswas Diptomit, Benson Sara, Matunis Aidan, Gebretsadik Gebremichal, Wertz Adam, StPierre Ben J, Schacht Nathan, Yan Yue, Gebremichael Hanna Y, Wong Pak Kin, Baughn Anthony D, Medina Scott H
Department of Biomedical Engineering, Penn State University, University Park, Pennsylvania 16802, United States.
Huck Institutes of the Life Sciences, Penn State University, University Park, Pennsylvania 16802, United States.
Biomacromolecules. 2025 May 12;26(5):3167-3179. doi: 10.1021/acs.biomac.5c00244. Epub 2025 May 1.
Identifying host defense peptides (HDPs) that are effective against drug-resistant infections is challenging due to their vast sequence space. Artificial intelligence (AI)-guided design can accelerate HDP discovery, but it traditionally requires large data sets to operationalize. We report an AI workflow that utilizes limited data sets (∼100 peptides) to uncover potent, selective, and safe HDPs by informing selection through lead candidate mutational scanning. This approach, referred to as Lead Informed Machine Interrogation of Therapeutic Sequences (LIMITS), is applied against the exemplary pathogen . Experimental validation of predicted sequences shows nearly an order of magnitude improvement in potency, selectivity, and safety, relative to the initial template. Post hoc analysis suggests sequence length may be a unique and underappreciated driver of antitubercular HDP activity. These results demonstrate that, with continued development, the LIMITS approach can identify selective HDPs under data-limited conditions and elucidate structure-function-performance relationships previously hidden in biologic complexity.
由于宿主防御肽（HDPs）的序列空间巨大，识别对耐药性感染有效的HDPs具有挑战性。人工智能（AI）指导的设计可以加速HDPs的发现，但传统上它需要大量数据集才能运行。我们报告了一种AI工作流程，该流程利用有限的数据集（约100种肽），通过先导候选突变扫描来指导选择，从而发现强效、选择性和安全的HDPs。这种方法被称为治疗序列的先导信息机器 interrogatioN（LIMITS），用于针对典型病原体。对预测序列的实验验证表明，相对于初始模板，其效力、选择性和安全性提高了近一个数量级。事后分析表明，序列长度可能是抗结核HDP活性的一个独特且未被充分认识的驱动因素。这些结果表明，随着不断发展，LIMITS方法可以在数据有限的条件下识别选择性HDPs，并阐明以前隐藏在生物复杂性中的结构-功能-性能关系。
