Scholarlink

Protein structure prediction is essential for understanding biological functions and advancing drug development. Although experimental techniques like NMR, X-ray crystallography, and cryo-EM provide valuable insights, they are expensive and time-consuming, prompting reliance on computational approaches. AlphaFold2 revolutionized protein model predictions accuracy in 2020. However, it faces limitations in accurately predicting certain novel proteins, complex conformations, and mutations. To address these challenges, we leverage PDBMine and machine learning for advanced data analytics. This approach detects and corrects structural inaccuracies, and enhances model reliability, accelerating therapeutic breakthroughs by bridging gaps in current protein prediction capabilities.

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 Structure Validation Using PDBMine and Data Analytics Approaches

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Niharika Pandala,
  • Katherine G. Brown,
  • Homayoun Valafar

摘要

Protein structure prediction is essential for understanding biological functions and advancing drug development. Although experimental techniques like NMR, X-ray crystallography, and cryo-EM provide valuable insights, they are expensive and time-consuming, prompting reliance on computational approaches. AlphaFold2 revolutionized protein model predictions accuracy in 2020. However, it faces limitations in accurately predicting certain novel proteins, complex conformations, and mutations. To address these challenges, we leverage PDBMine and machine learning for advanced data analytics. This approach detects and corrects structural inaccuracies, and enhances model reliability, accelerating therapeutic breakthroughs by bridging gaps in current protein prediction capabilities.