Evaporative cooling feature selection for genotypic data involving interactions

MOTIVATION The development of genome-wide capabilities for genotyping has led to the practical problem of identifying the minimum subset of genetic variants relevant to the classification of a phenotype. This challenge is especially difficult in the presence of attribute interactions, noise and small sample size. METHODS Analogous to the physical mechanism of evaporation, we introduce an evaporative cooling (EC) feature selection algorithm that seeks to obtain a subset of attributes with the optimum information temperature (i.e. the least noise). EC uses an attribute quality measure analogous to thermodynamic free energy that combines Relief-F and mutual information to evaporate (i.e. remove) noise features, leaving behind a subset of attributes that contain DNA sequence variations associated with a given phenotype. RESULTS EC is able to identify functional sequence variations that involve interactions (epistasis) between other sequence variations that influence their association with the phenotype. This ability is demonstrated on simulated genotypic data with attribute interactions and on real genotypic data from individuals who experienced adverse events following smallpox vaccination. The EC formalism allows us to combine information entropy, energy and temperature into a single information free energy attribute quality measure that balances interaction and main effects. AVAILABILITY Open source software, written in Java, is freely available upon request.

[1]  E. Jaynes.  Information Theory and Statistical Mechanics , 1957 .

[2]  Larry A. Rendell,et al.  A Practical Approach to Feature Selection , 1992, ML.

[3]  Wentian Li,et al.  A Complete Enumeration and Classification of Two-Locus Disease Models , 1999, Human Heredity.

[4]  N. Schork,et al.  Who's afraid of epistasis? , 1996, Nature Genetics.

[5]  William H. Press,et al.  Numerical Recipes in FORTRAN - The Art of Scientific Computing, 2nd Edition , 1987 .

[6]  David M. Reif,et al.  Machine Learning for Detecting Gene-Gene Interactions , 2006, Applied bioinformatics.

[7]  Gerhard W. Dueck,et al.  Threshold accepting: a general purpose optimization algorithm appearing superior to simulated anneal , 1990 .

[8]  David M. Reif,et al.  Cytokine expression patterns associated with systemic adverse events following smallpox immunization. , 2006, The Journal of infectious diseases.

[9]  Jonathan L Haines,et al.  Genetics, statistics and human disease: analytical retooling for complexity. , 2004, Trends in genetics : TIG.

[10]  Jason H. Moore,et al.  Tuning ReliefF for Genome-Wide Genetic Analysis , 2007, EvoBIO.

[11]  Jason H. Moore,et al.  Genome-Wide Analysis of Epistasis Using Multifactor Dimensionality Reduction: Feature Selection and Construction in the Domain of Human Genetics , 2009 .

[12]  Bruce A. Draper,et al.  Iterative Relief , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[13]  Igor Kononenko,et al.  ReliefF for estimation and discretization of attributes in classification, regression, and ILP probl , 1996 .

[14]  Igor Kononenko,et al.  Estimating Attributes: Analysis and Extensions of RELIEF , 1994, ECML.

[15]  Marylyn D. Ritchie,et al.  Data Simulation Software for Whole-Genome Association and Other Studies in Human Genetics , 2005, Pacific Symposium on Biocomputing.

[16]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[17]  Jason H. Moore,et al.  The Ubiquitous Nature of Epistasis in Determining Susceptibility to Common Human Diseases , 2003, Human Heredity.

[18]  Hess,et al.  Evaporative cooling of magnetically trapped and compressed spin-polarized hydrogen. , 1986, Physical review. B, Condensed matter.