Scholarlink

<p>The accuracy of enzyme kinetic parameters, particularly enzyme turnover numbers (<i>k</i><sub>cat</sub>), is critical for the predictive performance of enzyme-constrained genome-scale metabolic models. However, currently available kinetic datasets remain sparse and often fail to capture in vivo enzyme behavior, thereby limiting model accuracy. To address these limitations, we develop EnzymeTuning, a generative adversarial network-based framework for global <i>k</i><sub>cat</sub> optimization. By further incorporating literature-derived protein degradation constants, we infer protein synthesis rates and systematically assess their impact on model performance. Here, we show that EnzymeTuning substantially improves prediction accuracy and expands proteome-level coverage across diverse organisms, including <i>Saccharomyces cerevisiae</i>, <i>Kluyveromyces lactis</i>, <i>Kluyveromyces marxianus</i>, <i>Yarrowia lipolytica</i>, and <i>Escherichia coli</i>. Furthermore, EnzymeTuning reveals context-dependent enzyme usage patterns and adaptive catalytic resource allocation under diverse carbon- and nitrogen-limited chemostat conditions, underscoring the substantial potential of this framework for integrative multi-omics analyses.</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

EnzymeTuning improves enzyme-constrained metabolic modeling and proteome abundance prediction through deep learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月27日

查看全文
  • Xueting Wang,
  • Yongbo Wang,
  • Yingping Zhuang,
  • Guan Wang,
  • Hongzhong Lu

摘要

The accuracy of enzyme kinetic parameters, particularly enzyme turnover numbers (kcat), is critical for the predictive performance of enzyme-constrained genome-scale metabolic models. However, currently available kinetic datasets remain sparse and often fail to capture in vivo enzyme behavior, thereby limiting model accuracy. To address these limitations, we develop EnzymeTuning, a generative adversarial network-based framework for global kcat optimization. By further incorporating literature-derived protein degradation constants, we infer protein synthesis rates and systematically assess their impact on model performance. Here, we show that EnzymeTuning substantially improves prediction accuracy and expands proteome-level coverage across diverse organisms, including Saccharomyces cerevisiae, Kluyveromyces lactis, Kluyveromyces marxianus, Yarrowia lipolytica, and Escherichia coli. Furthermore, EnzymeTuning reveals context-dependent enzyme usage patterns and adaptive catalytic resource allocation under diverse carbon- and nitrogen-limited chemostat conditions, underscoring the substantial potential of this framework for integrative multi-omics analyses.