Department of Biochemistry, Eötvös Loránd University, Pázmány Péter stny 1/c, Budapest H-1117, Hungary.
Department of Biochemistry, Eötvös Loránd University, Pázmány Péter stny 1/c, Budapest H-1117, Hungary.
Curr Opin Struct Biol. 2024 Dec;89:102950. doi: 10.1016/j.sbi.2024.102950. Epub 2024 Nov 12.
Intrinsically disordered proteins (IDPs) lack a stable three-dimensional structure under physiological conditions, challenging traditional structure-based prediction methods. This review explores how modern deep learning approaches, which have revolutionized structure prediction for globular proteins, have impacted protein disorder predictions. We highlight the role of community-driven efforts in curating data and assessing state-of-the-art, which have been crucial in advancing the field. We also review state-of-the-art methods utilizing deep learning techniques, highlighting innovative approaches. We also address advancements in characterizing protein conformational ensembles directly from sequence data using novel machine learning methods.
无规卷曲蛋白质（IDPs）在生理条件下缺乏稳定的三维结构，这给基于结构的传统预测方法带来了挑战。本综述探讨了现代深度学习方法如何影响蛋白质无序性预测，这些方法已经彻底改变了球状蛋白质的结构预测。我们强调了社区驱动的努力在整理数据和评估最新技术方面的作用，这对推动该领域的发展至关重要。我们还回顾了利用深度学习技术的最新方法，突出了创新方法。我们还讨论了使用新的机器学习方法直接从序列数据中描述蛋白质构象集合的进展。
