Brain tumor segmentation with Deep Neural Networks.

In this paper, we present a fully automatic brain tumor segmentation method based on Deep Neural Networks (DNNs). The proposed networks are tailored to glioblastomas (both low and high grade) pictured in MR images. By their very nature, these tumors can appear anywhere in the brain and have almost any kind of shape, size, and contrast. These reasons motivate our exploration of a machine learning solution that exploits a flexible, high capacity DNN while being extremely efficient. Here, we give a description of different model choices that we've found to be necessary for obtaining competitive performance. We explore in particular different architectures based on Convolutional Neural Networks (CNN), i.e. DNNs specifically adapted to image data. We present a novel CNN architecture which differs from those traditionally used in computer vision. Our CNN exploits both local features as well as more global contextual features simultaneously. Also, different from most traditional uses of CNNs, our networks use a final layer that is a convolutional implementation of a fully connected layer which allows a 40 fold speed up. We also describe a 2-phase training procedure that allows us to tackle difficulties related to the imbalance of tumor labels. Finally, we explore a cascade architecture in which the output of a basic CNN is treated as an additional source of information for a subsequent CNN. Results reported on the 2013 BRATS test data-set reveal that our architecture improves over the currently published state-of-the-art while being over 30 times faster.

Mixture model for sub-phenotyping in GWAS.

Genome Wide Association (GWA) studies resulted in discovery of genetic variants underlying several complex diseases including Chron's disease and age-related macular degeneration (AMD). Still geneticists find that in majority of studies the size of the effect even if it is significant tends to be very small. There are several factors contributing to this problem such as rare variants, complex relationships among SNPs (epistatic effect), and heterogeneity of the phenotype. In this work we focus on addressing phenotypic heterogeneity. We introduce the problem of identifying, from GWAS data, separate genotypic markers from overlapping mixtures of clinically indistinguishable phenotypes. We propose a generative model for this scenario and derive an expectation-maximization (EM) procedure to fit the model to data, as well as a novel screening procedure designed to identify skew specific to certain phenotypic regimes. We present results on several simulated datasets as well as preliminary findings in applying the model to type 2 diabetes dataset.

The GeneMANIA prediction server: biological network integration for gene prioritization and predicting gene function.

GeneMANIA (http://www.genemania.org) is a flexible, user-friendly web interface for generating hypotheses about gene function, analyzing gene lists and prioritizing genes for functional assays. Given a query list, GeneMANIA extends the list with functionally similar genes that it identifies using available genomics and proteomics data. GeneMANIA also reports weights that indicate the predictive value of each selected data set for the query. Six organisms are currently supported (Arabidopsis thaliana, Caenorhabditis elegans, Drosophila melanogaster, Mus musculus, Homo sapiens and Saccharomyces cerevisiae) and hundreds of data sets have been collected from GEO, BioGRID, Pathway Commons and I2D, as well as organism-specific functional genomics data sets. Users can select arbitrary subsets of the data sets associated with an organism to perform their analyses and can upload their own data sets to analyze. The GeneMANIA algorithm performs as well or better than other gene function prediction methods on yeast and mouse benchmarks. The high accuracy of the GeneMANIA prediction algorithm, an intuitive user interface and large database make GeneMANIA a useful tool for any biologist.

Dynamic modularity in protein interaction networks predicts breast cancer outcome.

Changes in the biochemical wiring of oncogenic cells drives phenotypic transformations that directly affect disease outcome. Here we examine the dynamic structure of the human protein interaction network (interactome) to determine whether changes in the organization of the interactome can be used to predict patient outcome. An analysis of hub proteins identified intermodular hub proteins that are co-expressed with their interacting partners in a tissue-restricted manner and intramodular hub proteins that are co-expressed with their interacting partners in all or most tissues. Substantial differences in biochemical structure were observed between the two types of hubs. Signaling domains were found more often in intermodular hub proteins, which were also more frequently associated with oncogenesis. Analysis of two breast cancer patient cohorts revealed that altered modularity of the human interactome may be useful as an indicator of breast cancer prognosis.

A critical assessment of Mus musculus gene function prediction using integrated genomic evidence.

BACKGROUND: Several years after sequencing the human genome and the mouse genome, much remains to be discovered about the functions of most human and mouse genes. Computational prediction of gene function promises to help focus limited experimental resources on the most likely hypotheses. Several algorithms using diverse genomic data have been applied to this task in model organisms; however, the performance of such approaches in mammals has not yet been evaluated. RESULTS: In this study, a standardized collection of mouse functional genomic data was assembled; nine bioinformatics teams used this data set to independently train classifiers and generate predictions of function, as defined by Gene Ontology (GO) terms, for 21,603 mouse genes; and the best performing submissions were combined in a single set of predictions. We identified strengths and weaknesses of current functional genomic data sets and compared the performance of function prediction algorithms. This analysis inferred functions for 76% of mouse genes, including 5,000 currently uncharacterized genes. At a recall rate of 20%, a unified set of predictions averaged 41% precision, with 26% of GO terms achieving a precision better than 90%. CONCLUSION: We performed a systematic evaluation of diverse, independently developed computational approaches for predicting gene function from heterogeneous data sources in mammals. The results show that currently available data for mammals allows predictions with both breadth and accuracy. Importantly, many highly novel predictions emerge for the 38% of mouse genes that remain uncharacterized.

GeneMANIA: a real-time multiple association network integration algorithm for predicting gene function.

BACKGROUND: Most successful computational approaches for protein function prediction integrate multiple genomics and proteomics data sources to make inferences about the function of unknown proteins. The most accurate of these algorithms have long running times, making them unsuitable for real-time protein function prediction in large genomes. As a result, the predictions of these algorithms are stored in static databases that can easily become outdated. We propose a new algorithm, GeneMANIA, that is as accurate as the leading methods, while capable of predicting protein function in real-time. RESULTS: We use a fast heuristic algorithm, derived from ridge regression, to integrate multiple functional association networks and predict gene function from a single process-specific network using label propagation. Our algorithm is efficient enough to be deployed on a modern webserver and is as accurate as, or more so than, the leading methods on the MouseFunc I benchmark and a new yeast function prediction benchmark; it is robust to redundant and irrelevant data and requires, on average, less than ten seconds of computation time on tasks from these benchmarks. CONCLUSION: GeneMANIA is fast enough to predict gene function on-the-fly while achieving state-of-the-art accuracy. A prototype version of a GeneMANIA-based webserver is available at http://morrislab.med.utoronto.ca/prototype.