Decomposition and model selection for large contingency tables.

Large contingency tables summarizing categorical variables arise in many areas. One example is in biology, where large numbers of biomarkers are cross-tabulated according to their discrete expression level. Interactions of the variables are of great interest and are generally studied with log-linear models. The structure of a log-linear model can be visually represented by a graph from which the conditional independence structure can then be easily read off. However, since the number of parameters in a saturated model grows exponentially in the number of variables, this generally comes with a heavy computational burden. Even if we restrict ourselves to models of lower-order interactions or other sparse structures, we are faced with the problem of a large number of cells which play the role of sample size. This is in sharp contrast to high-dimensional regression or classification procedures because, in addition to a high-dimensional parameter, we also have to deal with the analogue of a huge sample size. Furthermore, high-dimensional tables naturally feature a large number of sampling zeros which often leads to the nonexistence of the maximum likelihood estimate. We therefore present a decomposition approach, where we first divide the problem into several lower-dimensional problems and then combine these to form a global solution. Our methodology is computationally feasible for log-linear interaction models with many categorical variables each or some of them having many levels. We demonstrate the proposed method on simulated data and apply it to a bio-medical problem in cancer research.

Mining tissue microarray data to uncover combinations of biomarker expression patterns that improve intermediate staging and grading of clear cell renal cell cancer.

PURPOSE: Tumor stage and nuclear grade are the most important prognostic parameters of clear cell renal cell carcinoma (ccRCC). The progression risk of ccRCC remains difficult to predict particularly for tumors with organ-confined stage and intermediate differentiation grade. Elucidating molecular pathways deregulated in ccRCC may point to novel prognostic parameters that facilitate planning of therapeutic approaches. EXPERIMENTAL DESIGN: Using tissue microarrays, expression patterns of 15 different proteins were evaluated in over 800 ccRCC patients to analyze pathways reported to be physiologically controlled by the tumor suppressors von Hippel-Lindau protein and phosphatase and tensin homologue (PTEN). Tumor staging and grading were improved by performing variable selection using Cox regression and a recursive bootstrap elimination scheme. RESULTS: Patients with pT2 and pT3 tumors that were p27 and CAIX positive had a better outcome than those with all remaining marker combinations. A prolonged survival among patients with intermediate grade (grade 2) correlated with both nuclear p27 and cytoplasmic PTEN expression, as well as with inactive, nonphosphorylated ribosomal protein S6. By applying graphical log-linear modeling for over 700 ccRCC for which the molecular parameters were available, only a weak conditional dependence existed between the expression of p27, PTEN, CAIX, and p-S6, suggesting that the dysregulation of several independent pathways are crucial for tumor progression. CONCLUSIONS: The use of recursive bootstrap elimination, as well as graphical log-linear modeling for comprehensive tissue microarray (TMA) data analysis allows the unraveling of complex molecular contexts and may improve predictive evaluations for patients with advanced renal cancer.

Penalized likelihood for sparse contingency tables with an application to full-length cDNA libraries.

BACKGROUND: The joint analysis of several categorical variables is a common task in many areas of biology, and is becoming central to systems biology investigations whose goal is to identify potentially complex interaction among variables belonging to a network. Interactions of arbitrary complexity are traditionally modeled in statistics by log-linear models. It is challenging to extend these to the high dimensional and potentially sparse data arising in computational biology. An important example, which provides the motivation for this article, is the analysis of so-called full-length cDNA libraries of alternatively spliced genes, where we investigate relationships among the presence of various exons in transcript species. RESULTS: We develop methods to perform model selection and parameter estimation in log-linear models for the analysis of sparse contingency tables, to study the interaction of two or more factors. Maximum Likelihood estimation of log-linear model coefficients might not be appropriate because of the presence of zeros in the table's cells, and new methods are required. We propose a computationally efficient l1-penalization approach extending the Lasso algorithm to this context, and compare it to other procedures in a simulation study. We then illustrate these algorithms on contingency tables arising from full-length cDNA libraries. CONCLUSION: We propose regularization methods that can be used successfully to detect complex interaction patterns among categorical variables in a broad range of biological problems involving categorical variables.