SHEAR
SHEAR is a tool for next-generation sequencing data analysis that predicts somatic variants, accounts for heterogeneous variants by estimating their representative percentages, and generates personal genomic sequences to be used for downstream analysis. By utilizing structural variant detection algorithms, SHEAR also offers improved performance in the form of a stronger ability to handle difficult structural variant types and improved computational efficiency.
NetProp
Network Propagation is a novel graph-based semi-supervised feature classification algorithm to identify discriminative disease markers by learning on bipartite graphs. Two features of Network Propagation are 1) Network Propagation can identify highly replicable biomarkers across independent microarray or other high-thoughput datasets. 2) Network Propagation is capable of handling hundreds of thousands of features and thus, are particularly useful for biomarker identification from large-scale gene expressions and SNPs. In addition, although designed for classifying features, our algorithm can also simultaneously classify test samples for disease prognosis/diagnosis. [Joint work with Mayo Clinic and IBM TJ Watson research]
NTriPath
NTriPath (Network regularized non-negative TRI matrix factorization for PATHway identification) to integrate somatic mutation, gene-gene interaction networks andpathway databases to discover pathways altered by somatic mutations across cancers. NTriPath effectively utilizes mutation patterns that exist in only a subset of samples (or specific cancer types), thus revealing pathways altered by complex mutation patterns across cancer types.
HyperPrior
HyperPrior is a novel hypergraph-based semi-supervised algorithm to integrate genomic data with prior knowledge (e.g. microarray gene expression or copy number variation data with protein-protein interaction network) for cancer outcome prediction and biomarker discovery. HyperPrior could improve cancer outcome prediction compared with SVMs and the other baselines utilizing the same prior knowledge, and identified several cancer-related subnetworks, and CNV regions, both of which contain known oncogenes and tumor suppressor genes. [Joint work with Mayo Clinic]
rcNet
rcNet (Rank Coherence in Networks) web tool provides an online source to predict associations between disease phenotypes and gene sets. rcNet algorithms combine known disease-gene associations in OMIM with the topological information in the disease phenotype similarity network and the gene-gene interaction networks to analyze the association between a gene set and disease phenotypes. The networks provide richer and more reliable information for computing the association scores used to rank the phenotypes. rcNet algorithms could be applied to validate and analyze the candidate disease gene identified in GWAS, DNA copy number analysis, and Microarray gene expression profiling. rcNet code is available in here. [Joint work with Genentech Inc.]
Download 🡇
MinProp
Disease gene prioritization is the task of ranking candidate disease genes underlying each disease phenotype to prioritize the genes for further experimental validation. MINProp integrates disease similarity network, known disease-gene association, and gene-gene interaction networks to predict candidate disease genes for a query disease phenotype.