A framework for generalized subspace pattern mining in high-dimensional datasets.

BACKGROUND: A generalized notion of biclustering involves the identification of patterns across subspaces within a data matrix. This approach is particularly well-suited to analysis of heterogeneous molecular biology datasets, such as those collected from populations of cancer patients. Different definitions of biclusters will offer different opportunities to discover information from datasets, making it pertinent to tailor the desired patterns to the intended application. This paper introduces 'GABi', a customizable framework for subspace pattern mining suited to large heterogeneous datasets. Most existing biclustering algorithms discover biclusters of only a few distinct structures. However, by enabling definition of arbitrary bicluster models, the GABi framework enables the application of biclustering to tasks for which no existing algorithm could be used. RESULTS: First, a series of artificial datasets were constructed to represent three clearly distinct scenarios for applying biclustering. With a bicluster model created for each distinct scenario, GABi is shown to recover the correct solutions more effectively than a panel of alternative approaches, where the bicluster model may not reflect the structure of the desired solution. Secondly, the GABi framework is used to integrate clinical outcome data with an ovarian cancer DNA methylation dataset, leading to the discovery that widespread dysregulation of DNA methylation associates with poor patient prognosis, a result that has not previously been reported. This illustrates a further benefit of the flexible bicluster definition of GABi, which is that it enables incorporation of multiple sources of data, with each data source treated in a specific manner, leading to a means of intelligent integrated subspace pattern mining across multiple datasets. CONCLUSIONS: The GABi framework enables discovery of biologically relevant patterns of any specified structure from large collections of genomic data. An R implementation of the GABi framework is available through CRAN (http://cran.r-project.org/web/packages/GABi/index.html).

Molecular subtypes of serous borderline ovarian tumor show distinct expression patterns of benign tumor and malignant tumor-associated signatures.

Borderline ovarian tumors show heterogeneity in clinical behavior. Most have excellent prognosis, although a small percentage show recurrence or progressive disease, usually to low-grade serous carcinoma. The aim of this study was to understand the molecular relationship between these entities and identify potential markers of tumor progression and therapeutic targets. We studied gene expression using Affymetrix HGU133plus2 GeneChip microarrays in 3 low-grade serous carcinomas, 13 serous borderline tumors and 8 serous cystadenomas. An independent data set of 18 serous borderline tumors and 3 low-grade serous carcinomas was used for validation. Unsupervised clustering revealed clear separation of benign and malignant tumors, whereas borderline tumors showed two distinct groups, one clustering with benign and the other with malignant tumors. The segregation into benign- and malignant-like borderline molecular subtypes was reproducible on applying the same analysis to an independent publicly available data set. We identified 50 genes that separate borderline tumors into their subgroups. Functional enrichment analysis of genes that separate borderline tumors to the two subgroups highlights a cell adhesion signature for the malignant-like subset, with Claudins particularly prominent. This is the first report of molecular subtypes of borderline tumors based on gene expression profiling. Our results provide the basis for identification of biomarkers for the malignant potential of borderline ovarian tumor and potential therapeutic targets for low-grade serous carcinoma.