Interpretable Machine Learning to Identify Alzheimer's Disease Therapeutic Targets

可解释的机器学习识别阿尔茨海默病的治疗目标

• 批准号: 10347341
• 负责人: Su-In Lee
• 金额: $ 58.2万
• 依托单位: UNIVERSITY OF WASHINGTON
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-02-15 至 2023-12-21
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10347341
• 关键词: Address; Affect; Algorithms; Alzheimer' s Disease; Alzheimer' s disease diagnosis; Alzheimer' s disease model; Alzheimer' s disease therapeutic; Amyloid beta-Protein; Animal Model; Award; Big Data; Biological; Biological Markers; Brain; Caenorhabditis elegans; Cause of Death; Cell physiology; Classification; Collaborations; Complex; Computer Models; Country; Data; Data Science; Data Set; Disease; Disease Progression; Drug Targeting; Educational workshop; Frequencies; Gene Expression; Genes; Genetic study; Heterogeneity; Human; Image; Individual; International; Intervention; Knowledge; Label; Lasso; Learning; Linear Models; Machine Learning; Measures; Methods; Modeling; Molecular; Molecular Chaperones; Multiomic Data; Nature; Nematoda; Network-based; Neurofibrillary Tangles; Oral; Orthologous Gene; Outcome; Paper; Pathogenesis; Pathologic; Pathology; Pathway interactions; Peptides; Phenotype; Play; Prevention; RNA Interference; Research Priority; Role; Selection Criteria; Senile Plaques; Signal Transduction; Statistical Models; Supervision; Techniques; Testing; Toxic effect; Training; Transgenic Organisms; Trees; United States; Validation; Variant; base; biomarker discovery; brain tissue; candidate marker; clinical practice; deep learning; deep learning model; direct application; disease heterogeneity; drug response prediction; effective therapy; experimental study; feature selection; gene function; gene interaction; gene network; high dimensionality; human data; improved; in vivo; interest; knock-down; machine learning algorithm; machine learning framework; machine learning method; molecular marker; novel; outcome prediction; phenotypic biomarker; precision medicine; predictive modeling; protective factors; proteostasis; rapid growth; response; success; tau Proteins; therapeutic target; therapy development

Project Summary Alzheimer’s disease (AD) is an urgent national and international research priority. Amyloid plaques and neurofibrillary tangles are the hallmark of AD. Their building blocks are Amyloid-β (Aβ) and tau, respectively. At present, we lack an understanding of the set of genes that affect formation of plaques and tangles along with protective and pathological responses to these toxic peptides. Biologists are now gathering gene expression data and Aβ and tau measures from human brain tissues. The current approach attempts to find a set of features (here, gene expression levels) that best predict an outcome (Aβ or tau level). The identified features, biomarkers, can help determine the molecular basis for plaques and tangles. Unfortunately, false positive biomarkers are very common, as evidenced by low success rates of replication in independent data and low success reaching clinical practice (less than 1%). We seek to radically shift the current paradigm in biomarker discovery by resolving three fundamental problems with the current approach using novel, theoretically well-founded machine learning (ML) methods to learn interpretable models from data. Aim 1. Learn an interpretable feature representation from publicly available, high-throughput brain data. High-dimensionality, hidden variables, and complex feature correlations create a discrepancy between predictability (i.e., observed statistical associations) and true biological interactions. To increase the chance to identify true positive biomarkers, we need new feature selection criteria to learn a model that better explains rather than simply predicts the outcome. To do so, our proposed ML algorithms will identify the genes that are likely to give a meaningful explanation of the outcome (Aβ or tau level) by inferring both the functions of genes in the cellular processes contributing to AD and the gene interaction network from many existing brain datasets. Aim 2. Make interpretable predictions using a unified framework to explain model predictions. Due to disease heterogeneity, complex models (e.g., deep learning or ensemble models) often more accurately describe relationships between genes and an outcome than simpler, linear models, but lack interpretability. We will develop a novel ML framework that interprets complex model predictions by estimating the importance of each feature to a specific prediction, which will identify features of high importance for each individual as personalized markers and classify subjects based on these importance estimates. Aim 3. Validate the identified candidate biomarkers using powerful worm models of AD. Analyzing observational data without doing interventional experiments cannot prove causal relationships. In collaboration with co-I Matt Kaeberlein, we will utilize powerful nematode models of AD to test our hypotheses on the role of certain genes as disease modifiers, and develop a new way to refine the models based on this knowledge. Successful completion of this project will result in previously unknown molecular basis for Aβ and tau levels, potential therapeutic targets, and general ML techniques widely applicable to many other data science problems.

项目概要 阿尔茨海默氏病（AD）是淀粉样斑块和淀粉样蛋白斑块的紧迫研究重点。 神经原纤维缠结是 AD 的标志，它们的组成部分分别是淀粉样蛋白 (Aβ) 和 tau。 目前，我们对影响斑块和缠结形成以及影响斑块和缠结形成的基因组缺乏了解。 对这些有毒肽的保护性和病理性反应。 生物学家现在正在收集人类脑组织的基因表达数据以及 Aβ 和 tau 蛋白测量值。 当前的方法试图找到一组最能预测结果的特征（此处为基因表达水平）（Aβ 或 tau 水平）。所识别的特征、生物标志物可以帮助确定斑块和缠结的分子基础。 不幸的是，假阳性生物标志物非常常见，复制成功率低就证明了这一点。 独立数据和临床实践的成功率较低（低于 1%）。 通过使用新颖的方法解决当前方法的三个基本问题，生物标志物发现的范例 理论上有充分依据的机器学习（ML）方法，用于从数据中学习可解释的模型。 目标 1. 从公开的、高通量的大脑数据中学习可解释的特征表示。 高维、隐藏变量和复杂的特征相关性造成了两者之间的差异 可预测性（即观察到的统计关联）和真实的生物相互作用。 识别真正的阳性生物标志物，我们需要新的特征选择标准来学习更好地解释的模型 为此，我们提出的机器学习算法将识别基因，而不是简单地预测结果。 通过推断基因的功能，可能对结果（Aβ 或 tau 水平）给出有意义的解释 来自许多现有大脑数据集的 AD 细胞过程和基因相互作用网络。 目标 2. 使用统一的框架来解释模型预测，从而做出可解释的预测。 疾病异质性，复杂模型（例如深度学习或集成模型）通常可以更准确地描述 基因和结果之间的关系比简单的线性模型更简单，但缺乏可解释性。 开发一种新颖的机器学习框架，通过估计每个模型的重要性来解释复杂的模型预测 特征到特定的预测，这将识别对每个人来说高度重要的特征作为个性化 标记并根据这些重要性估计对主题进行分类。 目标 3. 使用强大的 AD 蠕虫模型分析来验证已识别的候选生物标志物。 不进行介入实验的观察数据无法证明合作中的因果关系。 与合作者 Matt Kaeberlein 一起，我们将利用强大的 AD 线虫模型来检验我们对该作用的假设 某些基因作为疾病调节剂，并开发一种新的方法来基于这些知识来完善模型。 该项目的成功完成将带来以前未知的 Aβ 和 tau 水平的分子基础， 潜在的治疗目标，以及广泛适用于许多其他数据科学问题的通用机器学习技术。