Scholarlink

<p>This work presents Neural Optimization for Melting-temperature Enabled by Leveraging Translation (NOMELT), a novel approach for designing and ranking high-temperature stable proteins using neural machine translation. The model, trained on over 4 million protein homologous pairs from organisms adapted to different temperatures, demonstrates promising capability in targeting thermal stability. A designed variant of the <i>Drosophila melanogaster</i> Engrailed Homeodomain shows a melting temperature increase of 15.5&#xa0;K. Furthermore, NOMELT achieves zero-shot predictive capabilities in ranking experimental melting and half-activation temperatures across a number of protein families. It achieves this without requiring extensive homology data or massive training datasets as do existing zero-shot predictors by specifically learning thermophilicity, as opposed to all natural variation. These findings underscore the potential of leveraging organismal growth temperatures in context-dependent design of proteins for enhanced thermal stability.</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

Neural network conditioned to produce thermophilic protein sequences can increase thermal stability

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月23日

查看全文
  • Evan Komp,
  • Christian Phillips,
  • Lauren M. Lee,
  • Shayna M. Fallin,
  • Humood N. Alanzi,
  • Marlo Zorman,
  • Michelle E. McCully,
  • David A. C. Beck

摘要

This work presents Neural Optimization for Melting-temperature Enabled by Leveraging Translation (NOMELT), a novel approach for designing and ranking high-temperature stable proteins using neural machine translation. The model, trained on over 4 million protein homologous pairs from organisms adapted to different temperatures, demonstrates promising capability in targeting thermal stability. A designed variant of the Drosophila melanogaster Engrailed Homeodomain shows a melting temperature increase of 15.5 K. Furthermore, NOMELT achieves zero-shot predictive capabilities in ranking experimental melting and half-activation temperatures across a number of protein families. It achieves this without requiring extensive homology data or massive training datasets as do existing zero-shot predictors by specifically learning thermophilicity, as opposed to all natural variation. These findings underscore the potential of leveraging organismal growth temperatures in context-dependent design of proteins for enhanced thermal stability.