Machine Learning Tools for Discovery and Analysis of Active Metabolic Pathways

用于发现和分析活跃代谢途径的机器学习工具

基本信息

批准号：
9899255
负责人：
ALI SHOJAIE
金额：
$ 33.69万
依托单位：
UNIVERSITY OF WASHINGTON
依托单位国家：
美国
项目类别：
财政年份：
2016
资助国家：
美国
起止时间：
2016-04-01 至 2022-03-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/9899255
关键词：
Address Adoption Anabolism Area Biochemical Pathway Biochemical Reaction Biological Biological Assay Cardiovascular Diseases Cell physiology Cells Characteristics Code Communities Complement Complex Computer software Computing Methodologies Data Data Analyses Data Coordinating Center Data Set Deposition Detection Development Diabetes Mellitus Disease Environment Environmental Risk Factor Equilibrium Funding Galaxy Homeostasis Knowledge Label Language Letters Linear Models Machine Learning Malignant Neoplasms Mass Spectrum Analysis Measurement Measures Metabolic Metabolic Pathway Metabolism Methodology Methods Names Network-based Nuclear Magnetic Resonance Pathway interactions Phase Phenotype Plug-in Procedures Process Prognostic Marker Proteomics Reaction Sampling Signal Transduction Software Tools System Technology Testing United States National Institutes of Health Visualization Work base biological systems biomarker discovery data warehouse diagnostic biomarker diverse data experimental study flexibility high dimensionality improved insight interest machine learning method metabolome metabolomics new technology novel novel diagnostics novel marker open source programs public health relevance rapid growth response small molecule statistical and machine learning targeted treatment tool transcriptomics

项目摘要

DESCRIPTION (provided by applicant): This project aims to develop new statistical machine learning methods for metabolomics data from diverse platforms, including targeted and unbiased/global mass spectrometry (MS), labeled MS experiments for measuring metabolic ﬂux and Nuclear Magnetic Resonance (NMR) platforms. Unbiased MS and NMR proﬁling studies result in identifying a large number of unnamed spectra, which cannot be directly matched to known metabolites and are hence often discarded in downstream analyses. The ﬁrst aim develops a novel kernel penalized regression method for analysis of data from unbiased proﬁling studies. It provides a systematic framework for extracting the relevant information from unnamed spectra through a kernel that highlights the similarities and differences between samples, and in turn boosts the signal from named metabolites. This results in improved power in identiﬁcation of named metabolites associated with the phenotype of interest, as well as improved prediction accuracy. An extension of this kernel-based framework is also proposed to allow for systematic integration of metabolomics data from diverse proﬁling studies, e.g. targeted and unbiased MS proﬁling technologies. The second aim pro- vides a formal inference framework for kernel penalized regression and thus complements the discovery phase of the ﬁrst aim. The third aim focuses on metabolic pathway enrichment analysis that tests both orchestrated changes in activities of steady state metabolites in a given pathway, as well as aberrations in the mechanisms of metabolic reactions. The fourth aim of the project provides a uniﬁed framework for network-based integrative analysis of static (based on mass spectrometry) and dynamic (based on metabolic ﬂux) metabolomics measurements, thus providing an integrated view of the metabolome and the ﬂuxome. Finally, the last aim implements the pro- posed methods in easy-to-use open-source software leveraging the R language, the capabilities of the Cytoscape platform and the Galaxy workﬂow system, thus providing an expandable platform for further developments in the area of metabolomics. The proposed software tool will also provide a plug-in to the Data Repository and Coordination Center (DRCC) data sets, where all regional metabolomics centers supported by the NIH Common Funds Metabolomics Program deposit curated data.

描述（由申请人提供）：该项目旨在为来自不同平台的代谢组学数据开发新的统计机器学习方法，包括有针对性和无偏/全局质谱（MS）、用于测量代谢通量和核磁共振（NMR）的标记MS实验无偏见的 MS 和 NMR 分析研究导致识别大量未命名的光谱，这些光谱无法直接与已知的代谢物匹配，因此经常在下游被丢弃。第一个目标是开发一种新的核惩罚回归方法，用于分析来自无偏分析研究的数据，它提供了一个用于从中提取相关信息的系统框架。通过核突出显示样品之间的相似性和差异，从而增强来自命名代谢物的信号，这提高了与感兴趣的表型相关的命名代谢物的识别能力，并提高了预测准确性。还提出了这个基于内核的框架，以允许系统地整合来自不同分析研究的代谢组学数据，例如有针对性的和公正的 MS 分析技术。用于核惩罚回归，从而补充第一个目标的发现阶段，重点是代谢途径富集分析，测试给定途径中稳态代谢物活性的精心安排的变化，以及代谢反应机制的畸变。该项目的第四个目标为静态（基于质谱）和动态（基于代谢通量）代谢组学测量的基于网络的综合分析提供一个统一的框架，从而提供一个综合视图。最后，最后一个目标是利用 R 语言、Cytoscape 平台和 Galaxy 工作流程系统的功能，在易于使用的开源软件中实现所提出的方法，从而提供一个可扩展的平台。拟议的软件工具还将为数据存储和协调中心（DRCC）数据集提供插件，其中所有区域代谢组学中心均由 NIH Common 支持。基金代谢组学计划存放精选数据。