Our research goal is to develop, evaluate and apply novel computational methods and open-source software for identifying genetic and genomic biomarkers associated with human health and disease. Our focus is on methods that embrace, rather than ignore, the complexity of the genotype-to-phenotype mapping relationship due to phenomena such as epistasis and plastic reaction norms. Areas of interest include artificial intelligence, bioinformatics, biomedical informatics, complex systems, computational biology, genetic epidemiology, genomics, human genetics, machine learning, and visual analytics.
Our education goal is to provide interdisciplinary training and research experience to undergraduate, graduate, and postgraduate students. Our philosophy is that biomedical researchers of the future need to speak multiple languages to effectively collaborate with diverse teams of people focused on solving the hardest problems in health and healthcare.
"Exploratory Visual Analysis (EVA) is a database and GUI for the exploratory visual analysis of statistical results (not raw data) from high-throughput genetic and genomic experiments. The EVA system allows you to database statistical results with knowledge about each gene from public databases such as Entrez Gene. The GUI allows you to visually explore the p-values in the context of Gene Ontology, biochemical pathway, protein domain, chromosomal location, or phenotype thus facilitating biological interpretation."
"Multifactor Dimensionality Reduction (MDR) is a nonparametric and genetic model-free machine learning alternative to logistic regression for detecting and characterizing nonlinear interactions among discrete genetic and environmental attributes. The MDR method combines attribute selection, attribute construction, and classification with cross-validation and permutation testing to provide a comprehensive and powerful approach to detecting epistasis. MDR has been successfully applied to numerous different diseases and is currently being adapted to genome-wide association studies (GWAS)."
"The Symbolic Modeler (SyMod) software package provides two different methods. The first method, Symbolic Disciminant Analysis (SDA), was developed by our team as a nonlinear alternative to Fisher's Linear Discriminant Analysis (LDA). The goal of SDA is to identify the optimal combination of attributes and mathematical functions for predicting a discrete endpoint. The second method that is included in SyMod is symbolic regression. Symbolic regression is used for continuous endpoints."