Integrative Predictive Modeling of Alzheimer's Disease

项目摘要 阿尔茨海默病(AD)是一种医疗紧急情况，到目前为止，已被证明是不可能战胜的。存在 能够在早期症状阶段准确预测疾病进展将对我们的领域起到至关重要的推动作用。 遵循显著疾病特征(例如，淀粉样蛋白沉积)的预测模型将在设计上提供狭窄的- 范围不断进步，而且总是缺乏准确的疾病建模和结果预测。这个 本申请提出了一种系统级、多模式的方法来识别有前景的成像遗传学 生物标志物将可靠地预测早期疾病阶段的认知能力下降。我们的长期研究目标是 开发一种经济高效的风险评估和预测建模方法，并将其应用于治疗 药物开发。这个应用程序的总体目标是开发一个综合的预测框架 基于生物标志物签名的轻度认知障碍(MCI)。我们的中心假设是我们的现状- ART统计和拓扑多模数据分析将显著提高诊断和预测能力 MCI的准确性，并有助于弥合这一AD发病机制的知识差距。为此，我们建议实现 使用现有的临床、认知、成像、基因组和转录组数据进行以下具体目标：1) 用持续时间研究MCI患者的基因表达模式和神经影像内表型 2)提出一种贝叶斯多核学习框架，用于MCI及其相关疾病的诊断预测 进展为阿尔茨海默病；以及3)估计不同数据模式的相对贡献 早期预测和诊断的有效性。本申请中提出的方法提供了重要的 利用当代最先进的分析方法，如Persistent 基于同调的拓扑面分析和贝叶斯多核学习框架。我们还将依靠 整合先验知识，从而用可解释的方式增强数据驱动方法的实力 领域专业知识。我们工作的积极影响是重大的，因为它将有助于增进我们的理解 在AD中几种生物标志物模式之间的复杂相互作用，导致对 用于AD风险评估的多模式生物标记物集，并可能发现新的关键疾病相关途径 这可能会导致发现新的治疗靶点。

Project Abstract Alzheimer’s disease (AD) is a medical emergency that has, to date, proven impossible to defeat. Being able to accurately predict disease progression in the early symptomatic stages will critically advance our field. Predictive models abiding to a salient disease feature (e.g. amyloid deposition) would, by design, offer narrow- scope advances and will invariably come short of accurate disease modeling and outcome prediction. The present application proposes a systems-level, multimodal approach to identify promising imaging-genetics biomarkers that will reliably predict cognitive decline at early disease stages. Our long-term research goal is to develop a method for cost-efficient risk assessment and predictive modeling and to implement it in therapeutic drug development. The overall objective of this application is to develop an integrative predictive framework for mild cognitive impairment (MCI) based on biomarker signatures. Our central hypothesis is that our state-of-the- art statistical and topological multimodal data analysis will significantly improve the diagnostic and predictive accuracy in MCI and help close this knowledge gap in AD pathogenesis. To this end, we propose to accomplish the following specific aims using existing clinical, cognitive, imaging, genomic and transcriptomic data: 1) Characterize the gene expression patterns and neuroimaging endophenotypes in MCI using persistent homology; 2) Develop a Bayesian multi-kernel learning framework for diagnostic prediction of MCI and its progression to AD dementia; and 3) Estimate the relative contribution of different data modalities in terms of their effectiveness regarding early prediction and diagnosis. The methods proposed in this application offer significant advances over the status-quo by utilizing contemporary state-of -the-art analytic approaches such as persistent homology-based topological surface analysis and Bayesian multi-kernel learning framework. We will also rely on the integration of prior knowledge, whereby augmenting the strength of data-driven methods with interpretable domain expertise. The positive impact of our work is significant because it will help advance our understanding of the complex interactions between several biomarker modalities in AD, lead to the identification of sensitive multimodal biomarker set for AD risk assessment and potentially uncover novel critical disease-related pathways that might result in the discovery of new therapeutic targets.