7-6Network-based,personalizedmethodsforaccuratepredictionofmetastasisinbreastcancer
发布时间 :2015-06-15  阅读次数 :1988

报告题目:Network-based, personalized methods for accurate prediction of metastasis in breast cancer

报 告 人:Jianhua Ruan, Associate Professor

Department of Computer Science and Leader of Computational Systems Biology Core at University of Texas, San Antonio

报告时间:7月6日 10:00-11:30

报告地点:闵行校区生物药学楼2-116

联 系 人:韦朝春 This e-mail address is being protected from spambots. You need JavaScript enabled to view it.

 

Abstract

Metastatic breast cancer is a leading cause of cancer-related deaths in women worldwide; on the other hand, over-treatment of non-metastatic breast cancer is very common and can have lethal side effects. An accurate model to predict metastasis risk for early-stage breast cancer is therefore urgently needed to help oncologists design better personalized treatment strategies. Recent studies showed that whole-genome based profiling methods such as DNA microarray and next-generation sequencing can have better prediction accuracy than conventional histological grading-based methods. However, their accuracy is still quite low, especially when the training patient cohort is different from the test patient cohort. The potential causes include (1) large number of genes being considered vs. small number of training patients available, (2) heterogeneity of breast cancer which includes many subtypes, and (3) complex functional relationship among genes, which is typically not considered by existing algorithms. In this talk I will present several novel machine learning algorithms to address these issues. Experimental results show that our methods have significantly improved the accuracy and stability of breast cancer prognosis models compared to the state of the art. In addition, we also identified several novel genes that may be used as potential therapeutic targets.

 

Speaker biography

Dr. Jianhua Ruan is currently Associate Professor in the Department of Computer Science and Leader of Computational Systems Biology Core at University of Texas San Antonio. He received his Ph.D. in Computer Science and Engineering from Washington University in St Louis (2007), a M.S. degree in Computer Science from California State University San Bernardino (2002), and a B.S. degree in Biology from the University of Science and Technology of China (1998). His research interests lie in the broad area of bioinformatics, computational systems biology, and data mining. He has published more than 40 papers in high impact journals and conferences such as Bioinformatics, PLoS Computational Biology, Genome Biology, ICDM and AAAI. He is on the editorial boards of several journals and has been on the program committees of over 10 scientific conferences. He received a Best Performer award in the Third Annual DREAM Reverse Engineering Challenges, 2008. His current research is sponsored by the National Institutes of Health and the National Science Foundation.