Scholarlink

<p>Protease dysregulation, particularly involving matrix metalloproteinases (MMP-2 and MMP-9), plays a pivotal role in the progression and metastasis of tongue carcinoma. Antimicrobial peptides (AMPs) with protease inhibitory activity represent promising therapeutic candidates; however, natural peptides often require optimization for enhanced efficacy and selectivity. Here, we curated a comprehensive dataset of experimentally validated protease-inhibitory AMPs and applied machine learning models to identify key sequence and physicochemical features predictive of activity. Utilizing a genetic algorithm, we designed a novel series of anti-protease peptides, selecting GA-APP1 for synthesis and in vitro validation. GA-APP1 demonstrated potent inhibition of MMP-9 and MMP-2 with IC₅₀ values of 5.4 µM and 7.1 µM, respectively, alongside selective cytotoxicity against tongue carcinoma cell lines SCC-9 and CAL-27, while sparing normal oral keratinocytes. These findings validate the computational predictions and underscore the potential of machine learning-guided peptide design as a platform for developing targeted therapeutics against protease-driven cancers.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Design and Experimental Validation of Novel Anti-Protease Peptides Targeting Tongue Carcinoma

  • 期刊论文

  • 发表日期：

    2026年5月11日

查看全文
  • Andrej Jenča,
  • Elham Saberian,
  • Janka Jenčová,
  • Adriána Petrášová,
  • Hadi Zare-Zardini,
  • Eliška Kubíková,
  • Simona Dianišková,
  • Tetyana Pyndus

摘要

Protease dysregulation, particularly involving matrix metalloproteinases (MMP-2 and MMP-9), plays a pivotal role in the progression and metastasis of tongue carcinoma. Antimicrobial peptides (AMPs) with protease inhibitory activity represent promising therapeutic candidates; however, natural peptides often require optimization for enhanced efficacy and selectivity. Here, we curated a comprehensive dataset of experimentally validated protease-inhibitory AMPs and applied machine learning models to identify key sequence and physicochemical features predictive of activity. Utilizing a genetic algorithm, we designed a novel series of anti-protease peptides, selecting GA-APP1 for synthesis and in vitro validation. GA-APP1 demonstrated potent inhibition of MMP-9 and MMP-2 with IC₅₀ values of 5.4 µM and 7.1 µM, respectively, alongside selective cytotoxicity against tongue carcinoma cell lines SCC-9 and CAL-27, while sparing normal oral keratinocytes. These findings validate the computational predictions and underscore the potential of machine learning-guided peptide design as a platform for developing targeted therapeutics against protease-driven cancers.