@inproceedings{zhang2012signedb,

title = {Signed network propagation for detecting differential gene expressions and DNA copy number variations},

author = {Wei Zhang and Nicholas Johnson and Baolin Wu and Rui Kuang},

url = {http://compbio.cs.umn.edu/wp-content/uploads/2017/10/SignedNP-1.pdf},

year  = {2012},

date = {2012-10-07},

booktitle = {Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine},

pages = {337--344},

organization = {ACM},

abstract = {Network propagation algorithms have proved useful for the analysis of high-dimensional genomic data. One limitation is that the current formulation only allows network propagation on positively weighted graphs. In this paper, we explore two signed network propagation algorithms and general optimization frameworks for detecting differential gene expressions and DNA copy number variations (CNV). The proposed algorithms consider both positive and negative relations in graphs to model gene up/down-regulation or amplification/deletion CNV events. The first algorithm (Signed-NP) integrates gene co-expressions and differential expressions for consistent and robust gene selection from microarray datasets by propagation on gene correlation graphs. The second algorithm (Signed-NPBi) identifies gene or CNV markers by propagation on sample-feature bipartite graphs to capture bi-clusters between samples and genomic features. Large scale experiments on several microarray gene expression datasets and CNV datasets validate that Signed-NP and Signed-NPBi perform better classification of gene expression and CNV data than standard network propagation. The experiments also demonstrate that Signed-NP is capable of selecting genes that are more biologically interpretable and consistent across multiple datasets, and Signed-NPBi can detect hidden CNV patterns in bi-clusters by smoothing on correlations between adjacent probes.},

keywords = {DNA Copy Number Variation, Gene Expression, Semi-supervised Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhang2010network,

title = {Network propagation models for gene selection},

author = {Wei Zhang and Baryun Hwang and Baolin Wu and Rui Kuang},

url = {http://compbio.cs.umn.edu/wp-content/uploads/2017/10/NP.pdf},

doi = {10.1109/GENSIPS.2010.5719689},

isbn = {978-1-61284-791-7},

year  = {2010},

date = {2010-10-12},

booktitle = {2010 IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS)},

publisher = {IEEE},

abstract = {In this paper, we explore several network propagation methods for gene selection from microarray gene expression datasets. The network propagation methods capture gene co-expression and differential expression with unified machine learning frameworks. Large scale experiments on five breast cancer datasets validated that the network propagation methods are capable of selecting genes that are more biologically interpretable and more consistent across multiple datasets, compared with the existing approaches.},

keywords = {Cancer Genomics, Gene Expression, Semi-supervised Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{fang2010subspace,

title = {Subspace differential coexpression analysis: problem definition and a general approach.},

author = {Gang Fang and Rui Kuang and Gaurav Pandey and Michael Steinbach and Chad L Myers and Vipin Kumar},

url = {http://compbio.cs.umn.edu/wp-content/uploads/2017/10/9789814295291_0017.pdf},

doi = {10.1142/9789814295291_0017},

year  = {2010},

date = {2010-01-04},

booktitle = {Pacific symposium on biocomputing},

volume = {15},

pages = {145--56},

abstract = {In this paper, we study methods to identify differential coexpression patterns in case-control gene expression data. A differential coexpression pattern consists of a set of genes that have substantially different levels of coherence of their expression profiles across the two sample-classes, i.e., highly coherent in one class, but not in the other. Biologically, a differential coexpression patterns may indicate the disruption of a regulatory mechanism possibly caused by disregulation of pathways or mutations of transcription factors. A common feature of all the existing approaches for differential coexpression analysis is that the coexpression of a set of genes is measured on all the samples in each of the two classes, i.e., over the full-space of samples. Hence, these approaches may miss patterns that only cover a subset of samples in each class, i.e., subspace patterns, due to the heterogeneity of the subject population and disease causes. In this paper, we extend differential coexpression analysis by defining a subspace differential coexpression pattern, i.e., a set of genes that are coexpressed in a relatively large percent of samples in one class, but in a much smaller percent of samples in the other class. We propose a general approach based upon association analysis framework that allows exhaustive yet efficient discovery of subspace differential coexpression patterns. This approach can be used to adapt a family of biclustering algorithms to obtain their corresponding differential versions that can directly discover differential coexpression patterns. Using a recently developed biclustering algorithm as illustration, we perform experiments on cancer datasets which demonstrates the existence of subspace differential coexpression patterns. Permutation tests demonstrate the statistical significance for a large number of discovered subspace patterns, many of which can not be discovered if they are measured over all the samples in each of the classes. Interestingly, in our experiments, some discovered subspace patterns have significant overlap with known cancer pathways, and some are enriched with the target gene sets of cancer-related microRNA and transcription factors. The source codes and datasets used in this paper are available at http://vk.cs.umn.edu/SDC/. 

 

 

Read More: http://www.worldscientific.com/doi/abs/10.1142/9789814295291_0017},

keywords = {Gene Expression, Transcriptome},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mining2009integrative,

title = {Integrative Biomarker Discovery for Breast Cancer Metastasis from Gene Expression and Protein Interaction Data Using Error-tolerant Pattern Mining},

author = {Rohit Gupta and Smita Agrawal and Navneet Rao and Ze Tian and Rui Kuang and Vipin Kumar},

url = {http://compbio.cs.umn.edu/wp-content/uploads/2017/10/BICOB2010.pdf},

year  = {2009},

date = {2009-11-29},

publisher = {Citeseer},

abstract = {Biomarker discovery for complex diseases is a challenging 

problem. Most of the existing approaches identify 

individual genes as disease markers, thereby missing the 

interactions among genes. Moreover, often only single biological 

data source is used to discover biomarkers. These 

factors account for the discovery of inconsistent biomarkers. 

In this paper, we propose a novel error-tolerant pattern 

mining approach for integrated analysis of gene expression 

and protein interaction data. This integrated approach incorporates 

constraints from protein interaction network and 

efficiently discovers patterns (groups of genes) in a bottomup 

fashion from the gene-expression data. We call these 

patterns active sub-network biomarkers. To illustrate the 

efficacy of our proposed approach, we used four breast cancer 

gene expression data sets and a human protein interaction 

network and showed that active sub-network biomarkers 

are more biologically plausible and genes discovered 

are more reproducible across studies. Finally, through pathway 

analysis, we also showed a substantial enrichment for 

known cancer genes and hence were able to generate relevant 

hypotheses for understanding the molecular mechanisms 

of breast cancer metastasis.},

keywords = {Cancer Genomics, Gene Expression},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hwang2008learning,

title = {Learning on weighted hypergraphs to integrate protein interactions and gene expressions for cancer outcome prediction},

author = {TaeHyun Hwang and Ze Tian and Rui Kuang and Jean-Pierre Kocher},

url = {http://compbio.cs.umn.edu/wp-content/uploads/2017/10/HyperGene.pdf},

doi = {10.1109/ICDM.2008.37},

isbn = {978-0-7695-3502-9},

year  = {2008},

date = {2008-12-15},

booktitle = {2008 Eighth IEEE International Conference on Data Mining},

pages = {293--302},

organization = {IEEE},

abstract = {Abstract: 

Building reliable predictive models from multiple complementary genomic data for cancer study is a crucial step towards successful cancer treatment and a full understanding of the underlying biological principles. To tackle this challenging data integration problem, we propose a hypergraph-based learning algorithm called HyperGene to integrate microarray gene expressions and protein-protein interactions for cancer outcome prediction and biomarker identification. HyperGene is a robust two-step iterative method that alternatively finds the optimal outcome prediction and the optimal weighting of the marker genes guided by a protein-protein interaction network. Under the hypothesis that cancer-related genes tend to interact with each other, the HyperGene algorithm uses a protein-protein interaction network as prior knowledge by imposing a consistent weighting of interacting genes. Our experimental results on two large-scale breast cancer gene expression datasets show that HyperGene utilizing a curated protein-protein interaction network achieves significantly improved cancer outcome prediction. Moreover, HyperGene can also retrieve many known cancer genes as highly weighted marker genes.},

keywords = {Cancer Genomics, Gene Expression, Protein-Protein Interaction Network, Semi-supervised Learning},

pubstate = {published},

tppubtype = {inproceedings}

}