Scholarlink

<p>Chloride transport-related proteins play critical roles in coordinating ion cycling, maintaining cellular homeostasis, and enabling plants to dynamically adapt to environmental changes, particularly under salt stress conditions. Given the rapid accumulation of protein sequence data, the experimental identification of proteins is time-consuming and expensive. Therefore, efficient computational methods are urgently needed as a practical supplement to experimental research. Here, we present PCLPred, an SVM-based predictor that integrates reduced amino acid alphabets with N-peptide composition to represent protein sequences. We systematically evaluated 673 reduction schemes and selected an optimal encoding strategy for model training. PCLPred demonstrated superior performance compared to baseline models, achieving an overall accuracy of 95.10% and an AUC of 0.981 in nested cross-validation. Altogether, PCLPred provides an efficient and reliable tool for high-throughput screening of candidate plant chloride transport-related proteins, facilitating functional annotation and experimental validation.</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

PCLPred: identifying plant chloride transport-related proteins using reduced amino acid alphabets and N-peptide composition

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月8日

查看全文
  • Ge Bai,
  • Lijia Liu,
  • Hui Zhang,
  • Ruimei Geng,
  • Yong Li,
  • Dahai Yang,
  • Mingliang Fei,
  • Tao Pang,
  • Hao Wang,
  • Aiguo Yang,
  • He Xie,
  • Hao Eang

摘要

Chloride transport-related proteins play critical roles in coordinating ion cycling, maintaining cellular homeostasis, and enabling plants to dynamically adapt to environmental changes, particularly under salt stress conditions. Given the rapid accumulation of protein sequence data, the experimental identification of proteins is time-consuming and expensive. Therefore, efficient computational methods are urgently needed as a practical supplement to experimental research. Here, we present PCLPred, an SVM-based predictor that integrates reduced amino acid alphabets with N-peptide composition to represent protein sequences. We systematically evaluated 673 reduction schemes and selected an optimal encoding strategy for model training. PCLPred demonstrated superior performance compared to baseline models, achieving an overall accuracy of 95.10% and an AUC of 0.981 in nested cross-validation. Altogether, PCLPred provides an efficient and reliable tool for high-throughput screening of candidate plant chloride transport-related proteins, facilitating functional annotation and experimental validation.