Scholarlink

<p>Folding stability is crucial for the vast majority of proteins. Computational methods suggested to date for the absolute folding stability (Δ<i>G</i>) prediction, including those driven from protein structure prediction AIs, show clear limitations in reproducing quantitative experimental values. Here we present IFUM, a deep neural network that jointly estimates Δ<i>G</i> and the equilibrium ensemble of folded and unfolded states represented by residue-pair distance probability distributions. This joint learning considerably enhances prediction accuracy compared to learning Δ<i>G</i> alone. Trained on a dataset including Mega-scale small proteins, disordered proteins, and wild-type natural proteins, IFUM is robust to various protein types and can accurately predict complex mutational effects like insertions or deletions. Here, we show that IFUM effectively guides real-world design challenges, exhibiting strong correlation with experimental melting temperatures in protein engineering and outperforming AlphaFold-based metrics in de novo design selection.</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

Protein folding stability estimation with explicit consideration of unfolded states

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月21日

查看全文
  • Heechan Lee,
  • Yugyeong Cho,
  • Jeongwon Yun,
  • Martin Steinegger,
  • Ho Min Kim,
  • Hahnbeom Park

摘要

Folding stability is crucial for the vast majority of proteins. Computational methods suggested to date for the absolute folding stability (ΔG) prediction, including those driven from protein structure prediction AIs, show clear limitations in reproducing quantitative experimental values. Here we present IFUM, a deep neural network that jointly estimates ΔG and the equilibrium ensemble of folded and unfolded states represented by residue-pair distance probability distributions. This joint learning considerably enhances prediction accuracy compared to learning ΔG alone. Trained on a dataset including Mega-scale small proteins, disordered proteins, and wild-type natural proteins, IFUM is robust to various protein types and can accurately predict complex mutational effects like insertions or deletions. Here, we show that IFUM effectively guides real-world design challenges, exhibiting strong correlation with experimental melting temperatures in protein engineering and outperforming AlphaFold-based metrics in de novo design selection.