Detection of gene-gene interactions using multistage sparse and low-rank regression.

Finding an efficient and computationally feasible approach to deal with the curse of high-dimensionality is a daunting challenge faced by modern biological science. The problem becomes even more severe when the interactions are the research focus. To improve the performance of statistical analyses, we propose a sparse and low-rank (SLR) screening based on the combination of a low-rank interaction model and the Lasso screening. SLR models the interaction effects using a low-rank matrix to achieve parsimonious parametrization. The low-rank model increases the efficiency of statistical inference and, hence, SLR screening is able to more accurately detect gene-gene interactions than conventional methods. Incorporation of SLR screening into the Screen-and-Clean approach (Wasserman and Roeder, 2009; Wu et al., 2010) is also discussed, which suffers less penalty from Boferroni correction, and is able to assign p-values for the identified variables in high-dimensional model. We apply the proposed screening procedure to the Warfarin dosage study and the CoLaus study. The results suggest that the new procedure can identify main and interaction effects that would have been omitted by conventional screening methods.

Matrix variate logistic regression model with application to EEG data.

Logistic regression has been widely applied in the field of biomedical research for a long time. In some applications, the covariates of interest have a natural structure, such as that of a matrix, at the time of collection. The rows and columns of the covariate matrix then have certain physical meanings, and they must contain useful information regarding the response. If we simply stack the covariate matrix as a vector and fit a conventional logistic regression model, relevant information can be lost, and the problem of inefficiency will arise. Motivated from these reasons, we propose in this paper the matrix variate logistic (MV-logistic) regression model. The advantages of the MV-logistic regression model include the preservation of the inherent matrix structure of covariates and the parsimony of parameters needed. In the EEG Database Data Set, we successfully extract the structural effects of covariate matrix, and a high classification accuracy is achieved.

Connective tissue growth factor activates pluripotency genes and mesenchymal-epithelial transition in head and neck cancer cells.

The epithelial-mesenchymal transition (EMT) is a key mechanism in both embryonic development and cancer metastasis. The EMT introduces stem-like properties to cancer cells. However, during somatic cell reprogramming, mesenchymal-epithelial transition (MET), the reverse process of EMT, is a crucial step toward pluripotency. Connective tissue growth factor (CTGF) is a multifunctional secreted protein that acts as either an oncoprotein or a tumor suppressor among different cancers. Here, we show that in head and neck squamous cell carcinoma (HNSCC), CTGF promotes the MET and reduces invasiveness. Moreover, we found that CTGF enhances the stem-like properties of HNSCC cells and increases the expression of multiple pluripotency genes. Mechanistic studies showed that CTGF induces c-Jun expression through αvß3 integrin and that c-Jun directly activates the transcription of the pluripotency genes NANOG, SOX2, and POU5F1. Knockdown of CTGF in TW2.6 cells was shown to reduce tumor formation and attenuate E-cadherin expression in xenotransplanted tumors. In HNSCC patient samples, CTGF expression was positively correlated with the levels of CDH1, NANOG, SOX2, and POU5F1. Coexpression of CTGF and the pluripotency genes was found to be associated with a worse prognosis. These findings are valuable in elucidating the interplay between epithelial plasticity and stem-like properties during cancer progression and provide useful information for developing a novel classification system and therapeutic strategies for HNSCC.