Empirical bayes methods in statistical genetics

该计划的目标是开发统计遗传学领域的统计工具。随着最近分子生物技术和仪器的发展，遗传和基因组数据现在几乎可以不受限制地从任何生物体中产生。统计遗传学旨在为这些数据提供有效和高效的分析和利用，因此已成为一个非常活跃和有前途的统计学领域。我研究的总体目标是在微阵列数据和系谱数据的背景下，为遗传和基因组研究开发一套理论模型和统计方法。微阵列技术是分子生物学中最新和最重要的实验突破之一，可以同时测量和比较数千个基因的表达水平。我对检测一个或多个细胞条件之间差异表达基因的方法的发展感兴趣。这种方法的应用非常广泛，可以用于癌症研究或药物开发等领域。我考虑的第二类遗传数据来自涉及大家庭的基因图谱研究。通过连锁分析，研究了疾病的遗传状态与遗传标记之间的共遗传模式。我感兴趣的是对这些研究的个体之间的依赖框架进行建模。

The goal of this program is the development of statistical tools in the field of statistical genetics. With the recent development of molecular biotechnologies and instruments, genetic and genomic data can now be generated from any organism almost with no limits. Statistical genetics, aimed to provide effective and efficient analyses and utilization of these data, has thus become a very active and promising area of statistics. The overall objective of my research is to develop a collection of theoretical models and statistical methods for genetic and genomic research in the context of microarray data and pedigree data. Microarray technology is one of the most recent and important experimental breakthroughs in molecular biology, allowing the measurement and comparison of expression level of thousands of genes simultaneously. I am interested in the development of methods leading to the detection of differentially expressed genes between one or more cell conditions. The applications of such methods are very wide, and can be used in the field of cancer research or drug development, for example. The second type of genetic data I consider comes from gene mapping studies involving large families. Co-inheritance patterns between the affection status of a disease and genetic markers are studied through linkage analysis. I am interested in modeling the dependence framework between individuals of such studies.