Versini Raphaelle, Sritharan Sujith, Aykac Fas Burcu, Tubiana Thibault, Aimeur Sana Zineb, Henri Julien, Erard Marie, Nüsse Oliver, Andreani Jessica, Baaden Marc, Fuchs Patrick, Galochkina Tatiana, Chatzigoulas Alexios, Cournia Zoe, Santuz Hubert, Sacquin-Mora Sophie, Taly Antoine
Laboratoire de Biochimie Théorique, CNRS (UPR9080), Université Paris Cité, F-75005 Paris, France.
Université Paris-Saclay, CEA, CNRS, Institute for Integrative Biology of the Cell (I2BC), 91198 Gif-sur-Yvette, France.
J Chem Inf Model. 2024 Jan 8;64(1):26-41. doi: 10.1021/acs.jcim.3c01361. Epub 2023 Dec 20.
AlphaFold2 (AF2) and RoseTTaFold (RF) have revolutionized structural biology, serving as highly reliable and effective methods for predicting protein structures. This article explores their impact and limitations, focusing on their integration into experimental pipelines and their application in diverse protein classes, including membrane proteins, intrinsically disordered proteins (IDPs), and oligomers. In experimental pipelines, AF2 models help X-ray crystallography in resolving the phase problem, while complementarity with mass spectrometry and NMR data enhances structure determination and protein flexibility prediction. Predicting the structure of membrane proteins remains challenging for both AF2 and RF due to difficulties in capturing conformational ensembles and interactions with the membrane. Improvements in incorporating membrane-specific features and predicting the structural effect of mutations are crucial. For intrinsically disordered proteins, AF2's confidence score (pLDDT) serves as a competitive disorder predictor, but integrative approaches including molecular dynamics (MD) simulations or hydrophobic cluster analyses are advocated for accurate dynamics representation. AF2 and RF show promising results for oligomeric models, outperforming traditional docking methods, with AlphaFold-Multimer showing improved performance. However, some caveats remain in particular for membrane proteins. Real-life examples demonstrate AF2's predictive capabilities in unknown protein structures, but models should be evaluated for their agreement with experimental data. Furthermore, AF2 models can be used complementarily with MD simulations. In this Perspective, we propose a "wish list" for improving deep-learning-based protein folding prediction models, including using experimental data as constraints and modifying models with binding partners or post-translational modifications. Additionally, a meta-tool for ranking and suggesting composite models is suggested, driving future advancements in this rapidly evolving field.
AlphaFold2（AF2）和RoseTTaFold（RF）彻底改变了结构生物学，成为预测蛋白质结构的高度可靠且有效的方法。本文探讨了它们的影响和局限性，重点关注它们在实验流程中的整合以及在包括膜蛋白、内在无序蛋白（IDP）和寡聚体在内的多种蛋白质类别中的应用。在实验流程中，AF2模型有助于X射线晶体学解决相位问题，而与质谱和核磁共振数据的互补性则增强了结构测定和蛋白质柔韧性预测。由于难以捕捉构象集合以及与膜的相互作用，预测膜蛋白的结构对AF2和RF来说仍然具有挑战性。纳入膜特异性特征以及预测突变的结构效应方面的改进至关重要。对于内在无序蛋白，AF2的置信度评分（pLDDT）可作为一种有竞争力的无序预测指标，但提倡采用包括分子动力学（MD）模拟或疏水簇分析在内的综合方法来准确表示动力学。AF2和RF在寡聚体模型方面显示出有前景的结果，优于传统对接方法，其中AlphaFold-Multimer表现出更好的性能。然而，特别是对于膜蛋白仍存在一些注意事项。实际例子展示了AF2在未知蛋白质结构方面的预测能力，但模型应根据其与实验数据的一致性进行评估。此外，AF2模型可与MD模拟互补使用。在这篇观点文章中，我们提出了一份“愿望清单”，以改进基于深度学习的蛋白质折叠预测模型，包括将实验数据用作约束条件以及用结合伴侣或翻译后修饰来修改模型。此外，还建议开发一种用于对复合模型进行排名和推荐的元工具，以推动这一快速发展领域的未来进展。
