Feature selection with interactions in logistic regression models using multivariate synergies for a GWAS application.

BACKGROUND: Genotype-phenotype association has been one of the long-standing problems in bioinformatics. Identifying both the marginal and epistatic effects among genetic markers, such as Single Nucleotide Polymorphisms (SNPs), has been extensively integrated in Genome-Wide Association Studies (GWAS) to help derive "causal" genetic risk factors and their interactions, which play critical roles in life and disease systems. Identifying "synergistic" interactions with respect to the outcome of interest can help accurate phenotypic prediction and understand the underlying mechanism of system behavior. Many statistical measures for estimating synergistic interactions have been proposed in the literature for such a purpose. However, except for empirical performance, there is still no theoretical analysis on the power and limitation of these synergistic interaction measures. RESULTS: In this paper, it is shown that the existing information-theoretic multivariate synergy depends on a small subset of the interaction parameters in the model, sometimes on only one interaction parameter. In addition, an adjusted version of multivariate synergy is proposed as a new measure to estimate the interactive effects, with experiments conducted over both simulated data sets and a real-world GWAS data set to show the effectiveness. CONCLUSIONS: We provide rigorous theoretical analysis and empirical evidence on why the information-theoretic multivariate synergy helps with identifying genetic risk factors via synergistic interactions. We further establish the rigorous sample complexity analysis on detecting interactive effects, confirmed by both simulated and real-world data sets.

[Modeling vocal-fold vibration via integrating two-mass model with finite-element method].

Modeling vocal-fold vibration is extremely significant in realizing the vibration properties of human vocal folds and investigating their physiological and pathological characteristics. A combined model presented is two mass-finite element (T-F) model, which integrates all merits of both the finite element method (FEM) model and the asymmetric two-mass model of vocal folds. The high-speed glottis graph (HGG) can also be synthesized by the model. The result shows that T-F model can simulate the vibration behavior of normal and pathological vocal folds in a more realistic way with competitively computational speed. Therefore, the T-F model is helpful to gaining a thorough understanding of the vibration properties of vocal folds.

An automatic method to quantify the vibration properties of human vocal folds via videokymography.

The study offers an automatical quantitative method to obtain vibration properties of human vocal folds via videokymography. The presented method is based on image processing, which combines an active contour model with a genetic algorithm to improve detecting precision and processing speed, can accurately extract the vibration wave in videokymograms and quantify the vibration properties in terms of eight typical parameters automatically. To verify the precision of the proposed algorithm, an indirect simulation setup of vocal folds has been performed. The verification result shows that the relative error of the entire simulation system is less than 5%. Applying the method to analyzing hundreds of videokymograms from 12 subjects, the result indicates that the vibration characteristics of vocal folds can be recognized more exactly, and diseases of the vocal folds can be diagnosed quantitatively.