|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
Probabilistic Methods in Cancer Biology
If you have a question about this talk, please contact Dr Jason Z JIANG.
In this talk I will discuss two specific problems in cancer biology, namely: Identifying the most informative features, and reverse-engineering genome-wide interaction networks. The first is a non-standard problem in machine learning, wherein the number of features is many times larger than the number of samples, the inverse of the usual situation in engineering. The second is a problem of constructing a minimal weighted directed graph that is consistent with the data. For each problem, I will discuss new and appropriate algorithms invented by my team, and their application/validation in three forms of cancer: lung, ovarian and endometrial. I will also suggest a broad framework through which engineers can make meaningful contributions to cancer biology, and suggest a few problems for future research.
This talk is part of the CUED Control Group Seminars series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsRussian Graduate Seminar Group (RUSSGRADS) Cambridge Language Sciences Twenty Years of Human Development: the past and the future of the Human Development Index
Other talksProbing the molecular and cellular basis of developmental morphogenesis Putting life into numbers – how statistical science has transformed health care Nano-particle polymer composites Pfizer Neusentis Graduate and Young Academics Symposium Understanding the mechanisms of Toll-like Receptor 7 induced immune pathologies Small Angle X-Ray Scattering (SAXS)