蛋白质语言模型拯救突变突出了临床相关基因的变异效应和结构
Protein language model rescue mutations highlight variant effects and structure in clinically relevant genes
摘要：
尽管是自我监督的，但蛋白质语言模型在基本生物任务中表现出了卓越的性能，例如预测遗传变异对蛋白质结构和功能的影响。这些模型在不同任务集上的有效性表明，它们学习了对下游临床应用有用的适应度景观的有意义的表示。在这里，我们询问使用这些语言模型在表征已知的致病突变策划，医学上可操作的基因，通过一个详尽的搜索推定的补偿突变对每个变体的遗传背景。对这些补偿突变的预测效应的系统分析揭示了蛋白质的未被重视的结构特征，这些特征被其他结构预测因子如AlphaFold所错过。虽然深度突变扫描实验提供了突变景观的无偏估计，但我们鼓励社区生成和策划救援突变实验，以设计更复杂的共掩蔽策略，并更有效地利用大语言模型进行下游临床预测任务。
英文摘要：
Despite being self-supervised, protein language models have shown remarkable performance in fundamental biological tasks such as predicting impact of genetic variation on protein structure and function. The effectiveness of these models on diverse set of tasks suggests that they learn meaningful representations of fitness landscape that can be useful for downstream clinical applications. Here, we interrogate the use of these language models in characterizing known pathogenic mutations in curated, medically actionable genes through an exhaustive search of putative compensatory mutations on each variant's genetic background. Systematic analysis of the predicted effects of these compensatory mutations reveal unappreciated structural features of proteins that are missed by other structure predictors like AlphaFold. While deep mutational scan experiments provide an unbiased estimate of the mutational landscape, we encourage the community to generate and curate rescue mutation experiments to inform the design of more sophisticated co-masking strategies and leverage large language models more effectively for downstream clinical prediction tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
