A novel Chow-Liu algorithm and its application to gene differential analysis

详细信息    查看全文

• 作者：Joe Suzuki ^{suzuki@math.sci.osaka-u.ac.jp}
• 关键词：Mutual information ; Chow&ndash ; Liu algorithm ; Forest graphical model ; Gene differential analysis ; ANOVA
• 刊名：International Journal of Approximate Reasoning
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：80
• 期：Complete
• 页码：1-18
• 全文大小：2740 K
• 卷排序：80

文摘

A novel mutual information estimator for both discrete and continuous variables is proposed. The estimator takes a positive value for large n if and only if the two variables are independent. The estimation completes within a quasi-polynomial time of sample size. This paper demonstrates that it finds relations among the gene expressions and SNP values.