Quantitative Issues in Cancer Research Working Seminar

Andy Shi
Doctoral Student, Department of Biostatistics, Harvard University

“Multiple Phenotype – Multiple Genotype Testing with Multidimensional Scan Statistics”

ABSTRACT: The increasing popularity of large-scale genetic compendiums has driven a recent interest in (1) testing sets of genotypes against a single phenotype and (2) testing sets of phenotypes against a single genotype. Incorporating the information from these correlated sets of variants and outcomes can offer more power to detect novel associations, reduce the multiple testing burden in such massive datasets, and produce more interpretable conclusions about the genetic etiology of complex diseases by incorporating prior biological knowledge into set definitions. However, less work has focused on the testing problem when sets are formed for both genotypes and phenotypes. Inspired by this problem, in this work we study the problem of detecting a submatrix with larger-than-usual entries within a sparse and noisy larger matrix. We extend multidimensional scan statistics to handle the situation where the matrix entries are correlated, and we adapt a fast approximation algorithm to efficiently compute the test statistic. We investigate the properties of this test using simulations and theory.