Scholarlink

<p>Protein folding models have revolutionized structure prediction but struggle to capture conformational flexibility. Recent studies perturb inputs or parameters to sample alternative conformations, while diffusion-based approaches generate conformational ensembles directly. While individual generative models have been benchmarked against molecular dynamics (MD) data, a systematic comparison across diverse methodologies remains scarce, and validation of sub-domain dynamics is still limited. Here, we present a systematic benchmark of nine methods across 20 monomeric proteins with active and inactive states. We extend the pairwise aligned error metric to ensembles and reveal that protein identity exerts a non-negligible influence on model performance. Focusing on Adenylate Kinase, a well-studied enzyme with extensive MD data, we find that Chai-1 performs the best in recovering known conformations, identifying mobile regions, and capturing plausible intermediate conformations. These results highlight the potential of generative models as efficient alternatives to MD for exploring protein conformational dynamics and provide a rigorous benchmark for sampling the protein conformational landscape.</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

Exploring the conformational landscape of adenylate kinase and beyond with protein folding models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月1日

查看全文
  • Aryan Bhasin,
  • Antoine Delaunay,
  • Francesco Saccon,
  • Yunguan Fu

摘要

Protein folding models have revolutionized structure prediction but struggle to capture conformational flexibility. Recent studies perturb inputs or parameters to sample alternative conformations, while diffusion-based approaches generate conformational ensembles directly. While individual generative models have been benchmarked against molecular dynamics (MD) data, a systematic comparison across diverse methodologies remains scarce, and validation of sub-domain dynamics is still limited. Here, we present a systematic benchmark of nine methods across 20 monomeric proteins with active and inactive states. We extend the pairwise aligned error metric to ensembles and reveal that protein identity exerts a non-negligible influence on model performance. Focusing on Adenylate Kinase, a well-studied enzyme with extensive MD data, we find that Chai-1 performs the best in recovering known conformations, identifying mobile regions, and capturing plausible intermediate conformations. These results highlight the potential of generative models as efficient alternatives to MD for exploring protein conformational dynamics and provide a rigorous benchmark for sampling the protein conformational landscape.