Machine Learning Prediction of Cancer Susceptibility
Our grant on "Machine Learning Prediction of Cancer Susceptibility" was renewed by the National Library of Medicine at the NIH for another five years of funding (R01 LM009012). This grant supports our work on the development of powerful machine learning and data mining algorithms for the detection and characterization of gene-gene interactions. Here is the project summary:
Susceptibility to sporadic forms of cancer is determined by numerous genetic factors that interact in a nonlinear manner in the context of an individual’s age and environmental exposure. This complex genetic architecture has important implications for the use of genome-wide association studies for identifying susceptibility genes. The assumption of a simple architecture supports a strategy of testing each single-nucleotide polymorphism (SNP) individually using traditional univariate statistics followed by a correction for multiple tests. However, a complex genetic architecture that is characteristic of most types of cancer requires analytical methods that specifically model combinations of SNPs and environmental exposures. While new and novel methods are available for modeling interactions, exhaustive testing of all combinations of SNPs is not feasible on a genome-wide scale because the number of comparisons is effectively infinite. Thus, it is critical that we develop intelligent strategies for selecting subsets of SNPs prior to combinatorial modeling. The objective of this renewal application is to continue the development of a research strategy for the detection, characterization, and interpretation of gene-gene and gene-environment interactions in genome-wide association studies of bladder cancer susceptibility. To accomplish this objective, we will continue developing and evaluating modifications and extensions to the ReliefF family of algorithms for selecting or filtering subsets of single-nucleotide polymorphisms (SNPs) for multifactor dimensionality reduction (MDR) analysis of gene-gene and gene-environment interactions (AIM 1). We will continue developing and evaluating a stochastic wrapper or search strategy for MDR analysis of interactions that utilizes ReliefF values as a heuristic (AIM 2). We will continue to make available ReliefF algorithms as part of our open-source MDR software package (AIM 3). Finally, we will apply the best ReliefF-MDR analysis strategies to the detection, characterization, and interpretation of gene-gene and gene-environment interactions in large genome-wide association studies of bladder cancer susceptibility (AIM 4). We anticipate the proposed machine learning methods will provide powerful new approaches for identifying genetic variations that are predictive of cancer susceptibility.