Prospective analysis to determine model accuracy performance and boundaries in the post-AlphaFold2 environment

前瞻性分析以确定 AlphaFold2 后环境中的模型准确性性能和边界

• 批准号: 10672042
• 负责人: KRZYSZTOF A FIDELIS
• 金额: $ 29.79万
• 依托单位: UNIVERSITY OF CALIFORNIA AT DAVIS
• 依托单位国家: 美国
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-06-15 至 2025-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10672042
• 关键词: Active Sites; Address; Agreement; Amino Acid Sequence; Amino Acids; Antibodies; Area; Automobile Driving; Biological; Biological Process; Biology; Complementarity Determining Regions; Computer Models; Consumption; Crystallization; Data; Data Analyses; Data Set; Database Management Systems; Deposition; Development; Disease; Environment; Evaluation; Funding; Generations; Goals; Grain; Individual; Infrastructure; Knowledge; Length; Medicine; Methods; Modeling; Modification; Molecular Structure; Performance; Play; Procedures; Proline; Property; Proteins; Research; Rest; Role; Sequence Alignment; Set protein; Side; Structure; System; Techniques; Time; Uncertainty; Variant; Work; cost; data visualization; deep learning; experience; experimental study; falls; genome-wide; grasp; improved; learning strategy; method development; parent grant; programs; prospective; protein complex; protein structure; structural biology; tool

Experimental determination of protein structure often provides atomic accuracy models, but is inherently time- consuming, costly, and not always possible. Computational modeling offers an alternative. Recent application of deep learning methods to structure modeling now allows the generation of highly accurate models of structure for the great majority of single proteins. Progress in modeling accuracy for the modeling of protein complexes is also expected in the near term. These developments have dramatically expanded the utility of models in biology and medicine. However, having even high accuracy models at one’s disposal is not the same as an experimental result. While experimental structures come with established norms and procedures to ascertain accuracy, models are at best annotated with predictions of accuracy. The increased use of models underscores the need for similar knowledge, norms, and procedures for models. The Critical Assessment of Structure Prediction (CASP, funded by the parent grant), is already focused on assessing performance of modeling techniques and the performance of methods for estimating model accuracy, and to this end, extensive additional data are currently being acquired as part of the CASP15 experiment. But a detailed assessment of accuracy and accuracy prediction properties under an adequate range of conditions requires more extensive information than will be available through traditional CASP procedures. The release of close to a million models obtained with the AlphaFold2 method from DeepMind has created an opportunity to perform such an analysis. We will use these data to perform a prospective analysis of model accuracy and accuracy prediction performance. Specifically, we will compare structures released by the PDB with the corresponding previously deposited models. We will assess the agreement between these experimental and computed structures, both overall and at the individual amino acid level, and the agreement between the predicted and actual accuracy. Critically, we will examine these factors as a function of the relevant variables, particularly the quality and type of the experimental information, environmental effects such as crystal packing, function related structural features, rare structural features, protein interface regions, sequence length, and the depth of the available amino acid sequence alignment used to generate the model. We will also build tools to analyze and visualize the relationships and interdependencies between these data, to facilitate and expand our understanding of model accuracy performance. The overall goal of this work is to provide a fine-grained landscape of accuracy obtained with current modeling methods, and confidence limits on accuracy in each situation. Although the present analysis is restricted to AlphaFold2 models, identification of the most important variables should allow us to apply the procedures to the range of methods represented in the smaller data sets obtained in regular CASP experiments, and to new applications of deep learning methods in structural biology, for example the modeling of protein complexes. The infrastructure and expertise we already have in place, including the wide range of accuracy analysis tools, and our extensive experience with accuracy, accuracy estimation methods, and database management, make us the appropriate group to address this task. The proposed research falls well within the scientific scope of the current R01.

蛋白质结构的实验确定通常提供原子精度模型，但本质上是时间 - 消费，昂贵，并非总是可能的。计算建模提供了替代方案。最新应用 现在，学习结构建模的方法可以生成高度精确的结构模型 大多数单蛋白。在蛋白质复合物建模的建模准确性方面也有望在 近期。这些发展大大扩展了模型在生物学和医学中的效用。 但是，即使拥有高精度模型也与实验结果不同。尽管 实验结构具有确定准确性的既定规范和程序，模型充其量是注释 具有准确性的预测。增加模型的使用强调了对类似知识，规范和 模型的程序。结构预测的批判性评估（CASP，由父母赠款资助）已经是 专注于评估建模技术的性能和估计模型的方法的性能 准确性，为此，目前正在作为CASP15实验的一部分获取广泛的其他数据。 在适当范围的条件下，详细评估准确性和准确性预测属性需要更多 广泛的信息比传统的CASP程序可获得的信息。发布近一百万款 从DeepMind获得的AlphaFold2方法获得了进行此类分析的机会。 我们将使用这些数据对模型准确性和准确性预测性能进行前瞻性分析。 具体而言，我们将比较PDB发布的结构与相应的先前沉积模型。我们将 评估这些实验性和计算结构之间的一致性，无论是整体和单个氨基的 酸性水平，以及预测与实际准确之间的一致性。至关重要的是，我们将把这些因素视为 相关变量的功能，尤其是实验信息的质量和类型，环境影响 例如晶体堆积，功能相关的结构特征，稀有结构特征，蛋白质界面区域，序列 长度，以及用于生成模型的可用氨基酸序列比对的深度。我们还将构建工具 分析和可视化这些数据之间的关系和相互依存关系，以促进和扩展我们 了解模型准确性性能。这项工作的总体目标是提供一个细粒度的景观 通过当前的建模方法获得的精度，以及每种情况准确性的置信度限制。虽然 目前的分析仅限于AlphaFold2模型，对最重要变量的识别应允许我们应用 在常规CASP实验中获得的较小数据集中表示的方法范围的过程， 深度学习方法在结构生物学中的新应用，例如蛋白质复合物的建模。 我们已经拥有的基础架构和专业知识，包括广泛的准确分析工具，以及 我们具有准确性，准确性估计方法和数据库管理的丰富经验，使我们成为 适当的组来解决此任务。拟议的研究很好地属于当前R01的科学范围。