Scholarlink

<p>Liquid-liquid phase separation (LLPS) drives the formation of various membraneless organelles, which are crucial for biological processes and disease development. Despite the significant regulatory effects on LLPS of protein post-translational modifications (PTMs), specific data resource and predictor are still lacking. First, we constructed a well-curated database of PTM regulation on liquid-liquid Phase Separation (PTMPhaSe) (<a href="https://ptmphase.sjtu.edu.cn">https://ptmphase.sjtu.edu.cn</a>) that contains manually curated complete experimental evidence. Second, we developed graph neural network-based deep learning model (named <b>PhosLLPS</b>) to predict functional phosphorylation sites regulating LLPS, which achieved better identification performance (AUC = 0.9116) than four baseline models and the existing FuncPhos-SEQ method. Meanwhile, human proteome-scale predictions for functional phosphorylation sites were performed with PhosLLPS. PhosLLPS is now freely available in web server (<a href="https://ptmphase.sjtu.edu.cn/Predictor">https://ptmphase.sjtu.edu.cn/Predictor</a>). By bridging the gap between PTM regulation and LLPS, these resources could contribute to a better understanding of the molecular function of LLPS and facilitate further drug development for LLPS-related diseases.</p><p></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

Deep learning model of post-translational modification regulating liquid-liquid phase separation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月8日

查看全文
  • Xiaokun Hong,
  • Jiyang Lv,
  • Zhengxin Li,
  • Junjie Zhu,
  • Jiayi Li,
  • Mueed Ur Rahman,
  • Ting Wei,
  • Junxi Mu,
  • Hai-Feng Chen

摘要

Liquid-liquid phase separation (LLPS) drives the formation of various membraneless organelles, which are crucial for biological processes and disease development. Despite the significant regulatory effects on LLPS of protein post-translational modifications (PTMs), specific data resource and predictor are still lacking. First, we constructed a well-curated database of PTM regulation on liquid-liquid Phase Separation (PTMPhaSe) (https://ptmphase.sjtu.edu.cn) that contains manually curated complete experimental evidence. Second, we developed graph neural network-based deep learning model (named PhosLLPS) to predict functional phosphorylation sites regulating LLPS, which achieved better identification performance (AUC = 0.9116) than four baseline models and the existing FuncPhos-SEQ method. Meanwhile, human proteome-scale predictions for functional phosphorylation sites were performed with PhosLLPS. PhosLLPS is now freely available in web server (https://ptmphase.sjtu.edu.cn/Predictor). By bridging the gap between PTM regulation and LLPS, these resources could contribute to a better understanding of the molecular function of LLPS and facilitate further drug development for LLPS-related diseases.