Artificial Intelligence Strategies for Alzheimer's Disease Research

阿尔茨海默病(AD)是一种常见疾病，部分原因是蛋白质错误折叠和 聚合。AD的研究是国家的优先事项，每年有550万美国人受到影响 耗资超过2500亿美元，而且没有可用的治疗方法。这是尽管在 在实验和基于人群的研究中收集不同的临床和生物学数据。 人工智能(AI)和机器学习有可能揭示临床和 使用标准方法尚未发现的多源大规模阿尔茨海默氏症数据。 我们在这里提出了一个全面的生物医学计算和健康信息学研究项目 开发和应用尖端的人工智能算法和生物医学软件来分析大型- 扩展AD数据。这个拟议的信息学项目的核心是PennAI方法和 用于通过可从先前学习的人工智能算法自动进行机器学习的软件 分析。这种方法消除了选择正确的机器学习算法的猜测工作 和参数设置，从而使这项计算技术对每个人都可用。 具体地说，我们将开发三种新的信息学方法来定制PennAI来分析 广告数据。首先，我们将开发一种多模式交互(M2I)特征选择算法，用于 确定预测阿尔茨海默病的遗传交互作用(目标1)。第二，我们将制定一项 面向人工智能的知识驱动多组学集成(KMI)算法 AD的分析(AIM 2)。第三，我们将开发一种多维脑成像Omics(MBio) 用于AD预测的多源大规模数据联合分析集成框架。 最后，我们将把所有三种生物医学信息学方法集成到我们的开源PennAI中 软件包，并将其应用于两个大规模的AD人群研究。我们预计PennAI 将揭示AD的新生物标记物，为更好的治疗和临床决策打开大门 支持。

Alzheimer's disease (AD) is a common disease that is partly due to protein misfolding and aggregation. Research on AD is a national priority with 5.5 million Americans affected at an annual cost of more than $250 billion and no available cure. This is despite heavy investments in the collection of diverse clinical and biological data in experimental and population-based studies. Artificial intelligence (AI) and machine learning have the potential to reveal patterns in clinical and multi-source large-scale Alzheimer’s data that have not been found using standard approaches. We propose here a comprehensive biomedical computing and health informatics research project to develop and apply cutting-edge AI algorithms and biomedical software for the analysis of large- scale AD data. At the heart of this proposed informatics program is the PennAI method and software for automating machine learning through an AI algorithm that can learn from prior analyses. This approach takes the guesswork out of picking the right machine learning algorithms and parameter settings thus making this computing technology accessible to everyone. Specifically, we will develop three novel informatics methods to tailor PennAI to the analysis of AD data. First, we will develop a Multi-Modal Interaction (M2I) feature selection algorithm for identifying genetic interactions that are predictive of AD (AIM 1). Second, we will develop a Knowledge-driven Multi-omics Integration (KMI) algorithm for combining omics features for AI analysis of AD (AIM 2). Third, we will develop a Multidimensional Brain Imaging Omics (MBIO) integration framework for the joint analysis of multi-source large-scale data for predicting AD. Finally, we will integrate all three biomedical informatics methods into our open-source PennAI software package and apply it to two large population-based studies of AD. We expect PennAI will reveal new biomarkers for AD that will open the door for better treatments and clinical decision support.