Leveraging gene expression subgroups to classify DLBCL patients and select for clinical benefit from a novel agent.

Diffuse large B-cell lymphoma (DLBCL) is a heterogeneous disease, commonly described by cell-of-origin (COO) molecular subtypes. We sought to identify novel patient subgroups through an unsupervised analysis of a large public dataset of gene expression profiles from newly diagnosed de novo DLBCL patients, yielding 2 biologically distinct subgroups characterized by differences in the tumor microenvironment. Pathway analysis and immune deconvolution algorithms identified higher B-cell content and a strong proliferative signal in subgroup A and enriched T-cell, macrophage, and immune/inflammatory signals in subgroup B, reflecting similar biology to published DLBCL stratification research. A gene expression classifier, featuring 26 gene expression scores, was derived from the public dataset to discriminate subgroup A (classifier-negative, immune-low) and subgroup B (classifier-positive, immune-high) patients. Subsequent application to an independent series of diagnostic biopsies replicated the subgroups, with immune cell composition confirmed via immunohistochemistry. Avadomide, a CRL4CRBN E3 ubiquitin ligase modulator, demonstrated clinical activity in relapsed/refractory DLBCL patients, independent of COO subtypes. Given the immunomodulatory activity of avadomide and the need for a patient-selection strategy, we applied the gene expression classifier to pretreatment biopsies from relapsed/refractory DLBCL patients receiving avadomide (NCT01421524). Classifier-positive patients exhibited an enrichment in response rate and progression-free survival of 44% and 6.2 months vs 19% and 1.6 months for classifier-negative patients (hazard ratio, 0.49; 95% confidence interval, 0.280-0.86; P = .0096). The classifier was not prognostic for rituximab, cyclophosphamide, doxorubicin, vincristine, prednisone or salvage immunochemotherapy. The classifier described here discriminates DLBCL tumors based on tumor and nontumor composition and has potential utility to enrich for clinical response to immunomodulatory agents, including avadomide.

Predictive networks: a flexible, open source, web application for integration and analysis of human gene networks.

Genomics provided us with an unprecedented quantity of data on the genes that are activated or repressed in a wide range of phenotypes. We have increasingly come to recognize that defining the networks and pathways underlying these phenotypes requires both the integration of multiple data types and the development of advanced computational methods to infer relationships between the genes and to estimate the predictive power of the networks through which they interact. To address these issues we have developed Predictive Networks (PN), a flexible, open-source, web-based application and data services framework that enables the integration, navigation, visualization and analysis of gene interaction networks. The primary goal of PN is to allow biomedical researchers to evaluate experimentally derived gene lists in the context of large-scale gene interaction networks. The PN analytical pipeline involves two key steps. The first is the collection of a comprehensive set of known gene interactions derived from a variety of publicly available sources. The second is to use these 'known' interactions together with gene expression data to infer robust gene networks. The PN web application is accessible from http://predictivenetworks.org. The PN code base is freely available at https://sourceforge.net/projects/predictivenets/.

Refining gene signatures: a Bayesian approach.

BACKGROUND: In high density arrays, the identification of relevant genes for disease classification is complicated by not only the curse of dimensionality but also the highly correlated nature of the array data. In this paper, we are interested in the question of how many and which genes should be selected for a disease class prediction. Our work consists of a Bayesian supervised statistical learning approach to refine gene signatures with a regularization which penalizes for the correlation between the variables selected. RESULTS: Our simulation results show that we can most often recover the correct subset of genes that predict the class as compared to other methods, even when accuracy and subset size remain the same. On real microarray datasets, we show that our approach can refine gene signatures to obtain either the same or better predictive performance than other existing methods with a smaller number of genes. CONCLUSIONS: Our novel Bayesian approach includes a prior which penalizes highly correlated features in model selection and is able to extract key genes in the highly correlated context of microarray data. The methodology in the paper is described in the context of microarray data, but can be applied to any array data (such as micro RNA, for example) as a first step towards predictive modeling of cancer pathways. A user-friendly software implementation of the method is available.

Seeded Bayesian Networks: constructing genetic networks from microarray data.

BACKGROUND: DNA microarrays and other genomics-inspired technologies provide large datasets that often include hidden patterns of correlation between genes reflecting the complex processes that underlie cellular metabolism and physiology. The challenge in analyzing large-scale expression data has been to extract biologically meaningful inferences regarding these processes - often represented as networks - in an environment where the datasets are often imperfect and biological noise can obscure the actual signal. Although many techniques have been developed in an attempt to address these issues, to date their ability to extract meaningful and predictive network relationships has been limited. Here we describe a method that draws on prior information about gene-gene interactions to infer biologically relevant pathways from microarray data. Our approach consists of using preliminary networks derived from the literature and/or protein-protein interaction data as seeds for a Bayesian network analysis of microarray results. RESULTS: Through a bootstrap analysis of gene expression data derived from a number of leukemia studies, we demonstrate that seeded Bayesian Networks have the ability to identify high-confidence gene-gene interactions which can then be validated by comparison to other sources of pathway data. CONCLUSION: The use of network seeds greatly improves the ability of Bayesian Network analysis to learn gene interaction networks from gene expression data. We demonstrate that the use of seeds derived from the biomedical literature or high-throughput protein-protein interaction data, or the combination, provides improvement over a standard Bayesian Network analysis, allowing networks involving dynamic processes to be deduced from the static snapshots of biological systems that represent the most common source of microarray data. Software implementing these methods has been included in the widely used TM4 microarray analysis package.

An ensemble machine learning approach to predict survival in breast cancer.

Current breast cancer predictive signatures are not unique. Can we use this fact to our advantage to improve prediction? From the machine learning perspective, it is well known that combining multiple classifiers can improve classification performance. We propose an ensemble machine learning approach which consists of choosing feature subsets and learning predictive models from them. We then combine models based on certain model fusion criteria and we also introduce a tuning parameter to control sensitivity. Our method significantly improves classification performance with a particular emphasis on sensitivity which is critical to avoid misclassifying poor prognosis patients as good prognosis.

MeSHer: identifying biological concepts in microarray assays based on PubMed references and MeSH terms.

UNLABELLED: MeSHer uses a simple statistical approach to identify biological concepts in the form of Medical Subject Headings (MeSH terms) obtained from the PubMed database that are significantly overrepresented within the identified gene set relative to those associated with the overall collection of genes on the underlying DNA microarray platform. As a demonstration, we apply this approach to gene lists acquired from a published study of the effects of angiotensin II (Ang II) treatment on cardiac gene expression and demonstrate that this approach can aid in the interpretation of the resulting 'significant' gene set. AVAILABILITY: The software is available at http://www.tm4.org. SUPPLEMENTARY INFORMATION: Results from the analysis of significant genes from the published Ang II study.