AI2AMP-PD: Accelerating Parkinsons Diagnosis using Multi-omics and Artificial Intelligence

AI2AMP-PD：利用多组学和人工智能加速帕金森病的诊断 项目摘要和摘要 帕金森氏病(PD)影响着全球700多万人，生物标记物支持治疗 管道是迫切需要的。开发临床使用的生物标记物是一个需要评估的困难过程 多个大的队列，每个队列都增加了标记的信心。正在加速发展的医疗合作伙伴关系 帕金森氏病(AMP PD)联盟提供了一个前所未有的机会来迅速实现这一点 难以捉摸的目标。 我们假设一个强大的、由标准和先进机器驱动的多组学分类器 学习算法将在基因组水平上准确识别与PD相关的生物标记物。转录本和基因组 与帕金森病相关的分类器将在早期、未经治疗的多巴胺转运体患者中确定。 PPMI队列中有神经影像支持的诊断。成绩单和基因组分类器将是 在独立的PDBP和BioFIND队列中严格复制。多组学分类器同时使用PD- 相关的转录组变化和PD相关的基因组变体将用最先进的深度 学习技术(例如，变分自动编码器)。 这一分析将有力地描绘-首次-已知的和新的编码的全谱 以及与帕金森病相关的非编码RNA，并可在协调的大规模数据集的循环血细胞中检测到。 它将开发和测试高度创新的多组学分类器，并提供普遍有用的计算 大规模、无偏见的钯生物标志物发现框架。

AI2AMP-PD: Accelerating Parkinson’s Diagnosis using Multi-omics and Artificial Intelligence PROJECT SUMMARY AND ABSTRACT Parkinson’s disease (PD) affects more than 7 million people worldwide, and biomarkers to bolster the therapeutic pipeline are urgently needed. Developing biomarkers for clinical use is a difficult process that requires evaluation of multiple, large cohorts, each adding confidence to the marker. The Accelerating Medicine Partnership in Parkinson’s disease (AMP PD) consortium provides an unparalleled opportunity to rapidly achieve this previously elusive goal. We hypothesize that a powerful, multi-omics classifier powered by standard and advanced machine learning algorithms will accurately identify PD-associated biomarkers at genome scale. Transcripts and genomic classifiers associated with PD will be identified in early-stage, untreated, patients with Dopamine Transporter- neuroimaging-supported diagnosis represented in the PPMI cohort. Transcripts and genomic classifiers will be rigorously replicated in the independent PDBP and BioFIND cohorts. Multi-omics classifiers using both PD- associated transcriptome changes and PD-associated genomic variants will be built with state-of-the-art deep learning techniques (e.g. variational autoencoder). This analysis will powerfully delineate --- for the first time --- the full spectrum of known and novel, coding and noncoding RNAs linked to PD and detectable in circulating blood cells in a harmonized, large-scale data set. It will develop and test highly innovative multi-omics classifiers and provide a generally useful computational framework for large-scale, unbiased PD biomarker discovery.