Integrating multiple biomedical data modalities to predict disease diagnosis

项目总结 我的实验室的研究目标是开发开放源码的集成计算工具，以执行 分析可公开获得的多组学生物、临床和环境暴露数据集以进行推断 上下文特定的调控相互作用和模块，并预测疾病相关基因和 患者特定的药物反应。随着生物学中高通量技术的最新进展， 数据生成的成本大大降低，这使得能够生成大量 多组学数据集，如基因表达、microRNA表达、拷贝数改变和DNA 甲基化。已经建立了许多国际和国家财团来产生这些 多组学数据集用于研究DNA、疾病和健康组织、表观遗传学中的调控元件 签名和药物反应。此外，正在进行的大型倡议，如英国生物库， Record Project和我们所有人的研究计划将带来来自 数百万人。因此，对能够集成的可扩展方法的需求非常大 来自不同背景的数百万人的不同层次的多组学数据集。这些 方法将产生对人类疾病的有价值的见解，并为精确铺平道路 医药。我的研究计划致力于通过以下方式经济高效地利用这些多组学数据集 开发开源、创新和综合的计算资源。我的实验室已经成功了 在开发集成这些数据集以推断基因的开源综合计算方法方面 监管相互作用和模块，并预测疾病驱动因素。在未来五年，我们的目标是 扩展我们最近和正在进行的工作，以推断特定于环境的监管交互作用和模块，并 预测疾病相关基因和患者特定的药物反应。我们将整合各种类型的 构建集成的、可扩展的计算工具的异质多组学数据集。这个 我们通过这项研究开发的计算工具将使我们能够阐明基因和 调控相互作用和药物反应的表观遗传结构与新疾病的发现 相关基因。我们的工具将适用于任何疾病类型，并将使研究人员能够 充分利用公开可用的多组学数据集，为实现精确度铺平道路 医药。通过这个研究项目，我将为毕业生和 本科生，特别是那些来自代表不足的群体的学生。

PROJECT SUMMARY My lab’s research goal is to develop open source integrative computational tools that perform secondary analysis of publicly available multi-omics biological, clinical and environmental exposure datasets to infer context-specific regulatory interactions and modules, and to predict disease associated genes and patient-specific drug response. With the recent advances in high-throughput technologies in biology, the cost of data generation has reduced tremendously, which enabled the generation of vast amounts of multi-omics datasets such as gene expression, microRNA expression, copy number alteration, and DNA methylation. Numerous international and national consortiums have been established to generate these multi-omics datasets to study regulatory elements in DNA, disease and healthy tissues, epigenetic signatures, and drug responses. Furthermore, ongoing large initiatives such as UK Biobank, Million Records Project, and the All of Us research program will bring vast amounts of multi-omics datasets from millions of individuals. Consequently, there is a tremendous need for scalable methods that can integrate different layers of multi-omics datasets across millions of individuals from different backgrounds. These methods would produce valuable insights into human diseases and pave the way towards precision medicine. My research program is devoted to utilizing these multi-omics datasets cost effectively by developing open-source innovative and integrative computational resources. My lab has been successful in developing open source integrative computational methods to integrate such datasets to infer gene regulatory interactions and modules and to predict disease drivers. In the next five years, we aim to extend our recent and ongoing work to infer context-specific regulatory interactions and modules, and to predict disease associated genes and patient-specific drug response. We will integrate various types of heterogenous multi-omics datasets to build integrative and scalable computational tools. The computational tools we develop through this research will enable us to elucidate the genetic and epigenetic architecture of regulatory interactions and drug response and discover novel disease associated genes. Our tools will be applicable for any disease type and will enable researchers to leverage publicly available multi-omics datasets to their full extent and pave the road towards precision medicine. Through this research program, I will create research opportunities for graduate and undergraduate students particularly those from under-represented groups.