方海泉论文报告Detecting Novel Associations in Large Data Sets.pptVIP

MINE MIC captures relationship strength; MAS captures departure from monotonicity; MEV captures closeness to being a function; MCN captures complexity. How to use MINE Example java -jar MINE.jar?Spellman.csv 0 cv=0.7 6.Application of MINE to real data sets (1) Social, economic, health, and political indicators from the World Health Organization (WHO) and its partners. (2) Yeast gene expression profiles from a classic paper reporting genes whose transcript levels vary periodically with the cell cycle. 6. Application of MINE to real data sets 理解与心得 1. MIC具有广泛性，可以检测两个变量间是否有关系，不仅限于线性关系，还可以检测非线性关系，甚至是多种函数的叠加。 2. MIC具有公平性，对于不同关系类型，若噪声相同，则MIC值也相同。MIC近似等于R2,（这里R表示有噪声的数据与无噪声数据的相关系数。） 理解与心得 3. 对于广泛性，作者给出了严格的数学证明；对于公平性，作者通过数值模拟给出了直观的图像进行理解。 4. MIC属于MINE一个成员，作者提供了计算MINE的软件，可以快速计算出大数据集里变量间的关系。 5. 作者通过与其它方法进行对比，并且给出四个案例，显示出MINE的优越性。 评论 MINE可以快速准确找到大数据集里两个变量间是否有函数关系，不会漏检，具有抗干扰性，但是具体是什么关系还需要根据散点图观察，再用数学的方法计算出函数关系。（如一元线性回归和多元线性回归。） 应用展望 在生物医学、生物信息学领域，经常需要考察某两个变量间是否有影响，它们有什么关系，就可以用MINE对数据进行分析，得到的结果更准确，而且不会漏掉重要关系，这样才能真实地反映变量间的关系。 请多多指导 幻灯片放映结束！ O(∩_∩)O谢谢大家耐心观看！ 唐玄奘西天取经，西天为何方？ 取何经？ * Detecting Novel Associations in Large Data Sets David N. Reshef et al. Science 334, 1518 (2011); 方海泉 Imagine a data set with hundreds of variables, which may contain important, undiscovered relationships. There are tens of thousands of variable pairs-far too many to examine manually. Data sets of this size are increasingly common in fields as varied as genomics, physics, political science, and economics, making this question an important and growing challenge. 1. Two heuristic properties One way to begin exploring a large data set is to search for pairs of variables that are closely associated. To do this, we could calculate some measure of dependence for each pair, rank the pairs by their scores, and examine the top-scoring pairs.