结核病一直以来都是威胁人类健康的严重的公共卫生问题。对结核病转录组学大数据的挖掘，将有助于探索结核病的发病机制。本项目将以结核病相关的转录组学大数据为研究对象，利用前沿的大数据挖掘技术，同时结合生物实验，旨在从大数据中得出潜在的、有价值的信息，主要研究内容包括：（1）确定更多与结核病相关的重要宿主基因及其类别；（2）分析不同类别基因之间的交互作用及其影响；（3）预测未知基因表达量。本项目的研究将为与结核病相关的基因新功能的探索打下基础，为探索结核病的发病机制提供理论依据；为结核病的预防、诊断、控制和新药物的开发提供新思路。同时，项目研究可形成一套完整的并能沿用到其它类似疾病组学数据的大数据挖掘技术，为医学研究提供传统方法不能企及的数据挖掘技术手段。

Tuberculosis has long been a serious public health problem that threatens the health of human beings. Data mining of the transcriptomics of tuberculosis helps to explore the pathogenesis of tuberculosis. This project studies the transcriptional data of tuberculosis using dvanced data mining technology, combined with biological experiments, in order to draw potential and valuable information from big data. The main research contents include: (1) Identifying more tuberculosis related host genes and their categories; (2) Clearing the influence of the interaction between different types of genes; (3) Predicting of the unknown gene expression. Study on this project lays foundation for exploration of tuberculosis related novel gene functions. It also provides theoretical basis for exploring the pathogenesis of tuberculosis and provides new ideas for the prevention, diagnosis, control of tuberculosis and new drug development. At the same time, the methods in this project can be applied to data mining of omics data of some other similar diseases.