MOTIVATION: There is great interest in pathway-based methods for genomics data analysis in the research community. Although machine learning methods, such as random forests, have been developed to correlate survival outcomes with a set of genes, no study has assessed the abilities of these methods in incorporating pathway information for analyzing microarray data. In general, genes that are identified without incorporating biological knowledge are more difficult to interpret. Correlating pathway-based gene expression with survival outcomes may lead to biologically more meaningful prognosis biomarkers. Thus, a comprehensive study on how these methods perform in a pathway-based setting is warranted. RESULTS: In this article, we describe a pathway-based method using random forests to correlate gene expression data with survival outcomes and introduce a novel bivariate node-splitting random survival forests. The proposed method allows researchers to identify important pathways for predicting patient prognosis and time to disease progression, and discover important genes within those pathways. We compared different implementations of random forests with different split criteria and found that bivariate node-splitting random survival forests with log-rank test is among the best. We also performed simulation studies that showed random forests outperforms several other machine learning algorithms and has comparable results with a newly developed component-wise Cox boosting model. Thus, pathway-based survival analysis using machine learning tools represents a promising approach in dissecting pathways and for generating new biological hypothesis from microarray studies. AVAILABILITY: R package Pwayrfsurvival is available from URL: http://www.duke.edu/~hp44/pwayrfsurvival.htm. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: ChIP-chip data are routinely used to identify transcription factor binding targets. However, the presence of false positives and false negatives in ChIP-chip data complicates and hinders analyses, especially when the binding targets for a specific transcription factor are compared across conditions or species. RESULTS: We propose an Expectation Maximization based approach to infer the underlying true counts of "positives" and "negatives" from the observed counts. Based on this approach, we study the effect of false positives and false negatives on inferences related to transcription regulation. CONCLUSION: Our results indicate that if there is a significant degree of association among the binding targets across conditions/species (log odds ratio > 4), moderate values of false positive and false negative rates (0.005 and 0.4 respectively) would not change our inference qualitatively (i.e. the presence or absence of conservation) based on the observed experimental data despite a significant change in the observed counts. However, if the underlying association is marginal, with odds ratios close to 1, moderate to large values of false positive and false negative rates (0.01 and 0.2 respectively) could mask the underlying association.

MOTIVATION: Transcription factors regulate transcription in prokaryotes and eukaryotes by binding to specific DNA sequences in the regulatory regions of the genes. This regulation usually occurs in a coordinated manner involving multiple transcription factors. Genome-wide location data, also called ChIP-chip data, have enabled researchers to infer the binding sites for individual regulatory proteins. However, current methods to infer binding sites, such as simple thresholding based on p-values, are not optimal for a number of study objectives like combinatorial regulation, leading to potential loss of information. Hence, there is a need to develop more efficient statistical methods for analyzing such data. RESULTS: We propose to use log-linear models to study cooperative binding among transcription factors and have developed an Expectation-Maximization algorithm for statistical inferences. Our method is advantageous over simple thresholding methods both based on simulation and real data studies. We apply our method to infer the cooperative network of 204 regulators in Rich Medium and a subset of them in four different environmental conditions. Our results indicate that the cooperative network is condition specific; for a set of regulators, the network structure changes under different environmental conditions. AVAILABILITY: Our program is available at http://bioinformatics.med.yale.edu/TFcooperativity.