融合多组学数据的胰腺癌体液标志物精准挖掘与机理研究

肿瘤标志物在癌症早期诊断及发生发展机理研究中具有重要作用；胰腺癌作为致死率和恶性程度高的癌症备受关注。随着多种组学技术迅猛发展，研究者已获得大量肿瘤相关多组学数据。如何利用系统生物学技术，融合海量异构数据精准挖掘胰腺癌高效特异的临床易检测体液标志物，揭示其内在机理，已成为当前肿瘤分子标志物研究的前沿课题，对我国胰腺癌诊断和个性化治疗具有重要科学和实际意义。.本项目基于计算智能、统计分析和系统生物学技术，与医学和肿瘤学家紧密合作，自主产生胰腺癌多组数据，并搜集整理已有相关肿瘤多组学数据，精准挖掘其中隐含的关联信息，预测胰腺癌特异肿瘤标志物；搭建新型预测分析模型，提取能够进入血液、尿液和唾液等易于临床检测的体液标志物；融合其它组学信息和生物医学知识，搭建针对特定代谢通路的基因功能模型，搜寻基因调控机制，分析胰腺癌发生发展的深层机理；最终尝试将分析结果在胰腺癌早期诊断和相关治疗领域中有所应用。

Cancer marker plays an important role in the detection of early stage of cancer as well as the mechanism of tumor occurrence and development. Meanwhile, pancreatic cancer attracts more attention for its low survival rate and the high degree of malignance. With the rapid development of transcriptome, single cell sequencing and other omics technologies, researchers have obtained a lot of cancer-related data and information on Multi-omics level. With this improvement, how to systematically and efficiently mine clinical body fluid markers which are easily detectable, highly sensitive and highly specific from vast amounts of data by System Biology technology, and reveal its internal mechanism, have become the hot topic in current studies. This research has a great scientific and significance in pancreatic cancer early diagnosis, control, prevention and personalized treatments in China..This project will focus on autonomously generating pancreatic cancer data and systematically collecting related cancer multi-omics data from public database at first. And then, we will precisely mine underlying information and predict specific biomarkers of pancreatic cancer for cancer diagnosis via computational intelligence, statistical analysis and system biology technology along with therapists and oncologists. These biomarkers will focus on pancreatic cancer rather than other cancer types or diseases. In the same time, we will build novel models for body fluid protein identification and study what kind of tumor biomarker's corresponding proteins could be secreted into blood/urine/saliva etc., and which may be applied in real clinical diagnosis easily. Meanwhile, with the multi-omics data and biomedical knowledge, we will build gene function models for specific metabolic pathways, search for gene regulation mechanisms, and reveal inner mechanism of the pancreatic cancer’s development. At last, we will try to implement the results in the field of pancreatic cancer early diagnosis and related treatments.