MOTIVATION: Recent technology developments have made it possible to generate various kinds of omics data, which provides opportunities to better solve problems such as disease subtyping or disease mapping using more comprehensive omics data jointly. Among many developed data-integration methods, the similarity network fusion (SNF) method has shown a great potential to identify new disease subtypes through separating similar subjects using multi-omics data. SNF effectively fuses similarity networks with pairwise patient similarity measures from different types of omics data into one fused network using both shared and complementary information across multiple types of omics data. RESULTS: In this article, we proposed an association-signal-annotation boosted similarity network fusion (ab-SNF) method, adding feature-level association signal annotations as weights aiming to up-weight signal features and down-weight noise features when constructing subject similarity networks to boost the performance in disease subtyping. In various simulation studies, the proposed ab-SNF outperforms the original SNF approach without weights. Most importantly, the improvement in the subtyping performance due to association-signal-annotation weights is amplified in the integration process. Applications to somatic mutation data, DNA methylation data and gene expression data of three cancer types from The Cancer Genome Atlas project suggest that the proposed ab-SNF method consistently identifies new subtypes in each cancer that more accurately predict patient survival and are more biologically meaningful. AVAILABILITY AND IMPLEMENTATION: The R package abSNF is freely available for downloading from https://github.com/pfruan/abSNF. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The molecular complexity of a tumor manifests itself at the genomic, epigenomic, transcriptomic and proteomic levels. Genomic profiling at these multiple levels should allow an integrated characterization of tumor etiology. However, there is a shortage of effective statistical and bioinformatic tools for truly integrative data analysis. The standard approach to integrative clustering is separate clustering followed by manual integration. A more statistically powerful approach would incorporate all data types simultaneously and generate a single integrated cluster assignment. METHODS: We developed a joint latent variable model for integrative clustering. We call the resulting methodology iCluster. iCluster incorporates flexible modeling of the associations between different data types and the variance-covariance structure within data types in a single framework, while simultaneously reducing the dimensionality of the datasets. Likelihood-based inference is obtained through the Expectation-Maximization algorithm. RESULTS: We demonstrate the iCluster algorithm using two examples of joint analysis of copy number and gene expression data, one from breast cancer and one from lung cancer. In both cases, we identified subtypes characterized by concordant DNA copy number changes and gene expression as well as unique profiles specific to one or the other in a completely automated fashion. In addition, the algorithm discovers potentially novel subtypes by combining weak yet consistent alteration patterns across data types. AVAILABILITY: R code to implement iCluster can be downloaded at http://www.mskcc.org/mskcc/html/85130.cfm

Abstract Motivation: The molecular complexity of a tumor manifests itself at the genomic, epigenomic, transcriptomic and proteomic levels. Genomic profiling at these multiple levels should allow an integrated characterization of tumor etiology. However, there is a shortage of effective statistical and bioinformatic tools for truly integrative data analysis. The standard approach to integrative clustering is separate clustering followed by manual integration. A more statistically powerful approach would incorporate all data types simultaneously and generate a single integrated cluster assignment. Methods: We developed a joint latent variable model for integrative clustering. We call the resulting methodology iCluster. iCluster incorporates flexible modeling of the associations between different data types and the variance–covariance structure within data types in a single framework, while simultaneously reducing the dimensionality of the datasets. Likelihood-based inference is obtained through the Expectation–Maximization algorithm. Results: We demonstrate the iCluster algorithm using two examples of joint analysis of copy number and gene expression data, one from breast cancer and one from lung cancer. In both cases, we identified subtypes characterized by concordant DNA copy number changes and gene expression as well as unique profiles specific to one or the other in a completely automated fashion. In addition, the algorithm discovers potentially novel subtypes by combining weak yet consistent alteration patterns across data types. Availability: R code to implement iCluster can be downloaded at http://www.mskcc.org/mskcc/html/85130.cfm Contact: [email protected] Supplementary information: Supplementary data are available at Bioinformatics online.

MOTIVATION: Tissue microarrays (TMAs) quantify tissue-specific protein expression of cancer biomarkers via high-density immuno-histochemical staining assays. Standard analysis approach estimates a sample mean expression in the tumor, ignoring the complex tissue-specific staining patterns observed on tissue arrays. METHODS: In this article, a cell mixture model (CMM) is proposed to reconstruct tumor expression patterns in TMA experiments. The concept is to assemble the whole-tumor expression pattern by aggregating over the subpopulation of tissue specimens sampled by needle biopsies. The expression pattern in each individual tissue element is assumed to be a zero-augmented Gamma distribution to assimilate the non-staining areas and the staining areas. A hierarchical Bayes model is imposed to borrow strength across tissue specimens and across tumors. A joint model is presented to link the CMM expression model with a survival model for censored failure time observations. The implementation involves imputation steps within each Markov chain Monte Carlo iteration and Monte Carlo integration technique. RESULTS: The model-based approach provides estimates for various tumor expression characteristics including the percentage of staining, mean intensity of staining and a composite meanstaining to associate with patient survival outcome. AVAILABILITY: R package to fit CMM model is available at http://www.mskcc.org/mskcc/html/85130.cfm

BACKGROUND: With the explosion in data generated using microarray technology by different investigators working on similar experiments, it is of interest to combine results across multiple studies. RESULTS: In this article, we describe a general probabilistic framework for combining high-throughput genomic data from several related microarray experiments using mixture models. A key feature of the model is the use of latent variables that represent quantities that can be combined across diverse platforms. We consider two methods for estimation of an index termed the probability of expression (POE). The first, reported in previous work by the authors, involves Markov Chain Monte Carlo (MCMC) techniques. The second method is a faster algorithm based on the expectation-maximization (EM) algorithm. The methods are illustrated with application to a meta-analysis of datasets for metastatic cancer. CONCLUSION: The statistical methods described in the paper are available as an R package, metaArray 1.8.1, which is at Bioconductor, whose URL is http://www.bioconductor.org/.

MOTIVATION: The nearest shrunken centroids classifier has become a popular algorithm in tumor classification problems using gene expression microarray data. Feature selection is an embedded part of the method to select top-ranking genes based on a univariate distance statistic calculated for each gene individually. The univariate statistics summarize gene expression profiles outside of the gene co-regulation network context, leading to redundant information being included in the selection procedure. RESULTS: We propose an Eigengene-based Linear Discriminant Analysis (ELDA) to address gene selection in a multivariate framework. The algorithm uses a modified rotated Spectral Decomposition (SpD) technique to select 'hub' genes that associate with the most important eigenvectors. Using three benchmark cancer microarray datasets, we show that ELDA selects the most characteristic genes, leading to substantially smaller classifiers than the univariate feature selection based analogues. The resulting de-correlated expression profiles make the gene-wise independence assumption more realistic and applicable for the shrunken centroids classifier and other diagonal linear discriminant type of models. Our algorithm further incorporates a misclassification cost matrix, allowing differential penalization of one type of error over another. In the breast cancer data, we show false negative prognosis can be controlled via a cost-adjusted discriminant function. AVAILABILITY: R code for the ELDA algorithm is available from author upon request.

BACKGROUND: Translational research requires taking basic science observations and developing them into clinically useful tests and therapeutics. We have developed a process to develop molecular biomarkers for diagnosis and prognosis by integrating tissue microarray (TMA) technology and an internet-database tool, Profiler. TMA technology allows investigators to study hundreds of patient samples on a single glass slide resulting in the conservation of tissue and the reduction in inter-experimental variability. The Profiler system allows investigator to reliably track, store, and evaluate TMA experiments. Here within we describe the process that has evolved through an empirical basis over the past 5 years at two academic institutions. RESULTS: The generic design of this system makes it compatible with multiple organ system (e.g., prostate, breast, lung, renal, and hematopoietic system,). Studies and folders are restricted to authorized users as required. Over the past 5 years, investigators at 2 academic institutions have scanned 656 TMA experiments and collected 63,311 digital images of these tissue samples. 68 pathologists from 12 major user groups have accessed the system. Two groups directly link clinical data from over 500 patients for immediate access and the remaining groups choose to maintain clinical and pathology data on separate systems. Profiler currently has 170 K data points such as staining intensity, tumor grade, and nuclear size. Due to the relational database structure, analysis can be easily performed on single or multiple TMA experimental results. The TMA module of Profiler can maintain images acquired from multiple systems. CONCLUSION: We have developed a robust process to develop molecular biomarkers using TMA technology and an internet-based database system to track all steps of this process. This system is extendable to other types of molecular data as separate modules and is freely available to academic institutions for licensing.