Binding-Site Modeling with Multiple-Instance Machine-Learning

使用多实例机器学习的结合位点建模

• 批准号: 8436505
• 负责人: AJAY N JAIN
• 金额: $ 29.14万
• 依托单位: UNIVERSITY OF CALIFORNIA, SAN FRANCISCO
• 依托单位国家: 美国
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-01-01 至 2016-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8436505
• 关键词: Address; Affinity; Binding; Binding Sites; Biological Assay; Chemicals; Collaborations; Computer Assisted; Creativeness; Data; Data Set; Docking; Drug Design; Enzymes; Exercise; Foundations; Knowledge; Lead; Learning; Ligand Binding; Ligands; Machine Learning; Measures; Medical; Membrane; Methodology; Methods; Modeling; Molecular; Molecular Conformation; Paper; Pharmaceutical Chemistry; Pharmaceutical Preparations; Pharmacologic Substance; Physics; Population; Procedures; Process; Protein Binding; Proteins; Publishing; Quantitative Structure-Activity Relationship; Research; Series; Site; Solutions; Structure; System; Testing; Therapeutic; Training; Validation; Work; aging population; base; blind; chemical synthesis; computer framework; design; design and construction; drug discovery; falls; interest; novel; novel therapeutics; predictive modeling; process optimization; prospective; public health relevance; receptor binding; small molecule; virtual

DESCRIPTION (provided by applicant): This proposal is entitled "Binding-Site Modeling with Multiple-Instance Machine-Learning." One of the most challenging and longest studied problems in computer-aided drug design has been affinity prediction of small molecule ligands for their cognate protein targets. Despite decades of work, quantitative structure-activity re- lationship prediction (QSAR) approaches still suffer from poor accuracy, especially when predicting outside of closely related series of molecules. Even with high-quality structures of target proteins, approaches grounded in physics are also far from robust and accurate enough for reliable use in drug lead optimization. This proposal will build upon a foundation in multiple-instance machine learning applied to computer-aided drug design problems and develop a robust, accurate, and practically applicable affinity prediction methodology. The methodology requires only ligand structures and associated activity data for training, and it induces a virtual protein binding site composed of molecular fragments. The virtual binding pocket (or "pocketmol") is used in conjunction with a scoring function developed originally for molecular docking. The pocketmol configuration is chosen such that the optimal conformation and alignment of a ligand (based on the docking scoring function), yields scores for training ligands that are close to the known experimental values. Feasibility has been demon- strated in papers involving both membrane-bound receptors and enzymes. However, multiple challenges remain and are the subject of the proposed research. There are three key issues. First, there exist many pocketmols that satisfy the requirements of fitting the training data, so general solutions must be developed to address the inductive bias of the learning procedure as well as model selection after the procedure. Second, since any particular model is the product of a learning process, it will have some domain of applicability, with some new molecules likely to be predicted well and others poorly. Further, the model will be better informed by learning with certain new molecules but not others. We must develop solutions for estimating confidence of predictions for new molecules as well as for identifying particular molecules that will be highly informative. Third, the operational application of these methods involves model building, guided chemical synthesis, and iterative refinement of models. Convincing validation will require application on temporal series of molecules synthesized for multiple targets of pharmaceutical interest. The proposed work will develop novel methods to address these challenges and will establish extensive validation on multiple pharmaceutically relevant temporal series of small molecules that were the subject of real-world lead-optimization exercises.

描述（由申请人提供）：该提案的标题为“多实例机器学习的绑定站点建模”。“计算机辅助药物设计中最具挑战性和研究时间最长的问题之一是小分子配体对其同源蛋白质靶点的亲和力预测。尽管进行了数十年的工作，定量构效关系预测（QSAR）方法仍然存在准确性差的问题，特别是在预测密切相关的分子系列之外时。即使有高质量的靶蛋白结构，基于物理学的方法也远远不够稳健和准确，无法可靠地用于药物先导物优化。该提案将建立在应用于计算机辅助药物设计问题的多实例机器学习的基础上，并开发出一种稳健、准确且实用的亲和力预测方法。该方法只需要配体结构和相关的活性数据进行训练，它诱导了一个虚拟的 由分子片段组成的蛋白质结合位点。虚拟结合口袋（或“pocketmol”）与最初为分子对接开发的评分函数结合使用。选择pocketmol构型，使得配体的最佳构象和比对（基于对接评分函数）产生接近已知实验值的训练配体的评分。在涉及膜结合受体和酶的论文中已经证明了可行性。 然而，仍然存在多种挑战，这是拟议研究的主题。有三个关键问题。首先，存在许多满足拟合训练数据要求的pocketmols，因此必须开发通用解决方案来解决学习过程的归纳偏差以及过程后的模型选择。其次，由于任何特定的模型都是学习过程的产物，因此它将具有一定的适用范围，一些新分子可能预测得很好，而另一些则很差。此外，模型将通过学习某些新分子而不是其他分子来更好地了解情况。我们必须开发解决方案，以估计新分子预测的置信度，以及识别具有高度信息性的特定分子。第三，这些方法的操作应用涉及模型构建、指导化学合成和模型的迭代改进。令人信服的验证将需要应用于为多个药物目标合成的分子的时间序列。拟议的工作将开发新的方法来解决这些挑战，并将建立对多个药学相关的小分子时间序列的广泛验证，这些小分子是现实世界的铅优化练习的主题。