@article{kadaba15structural,

title = {Structural Neuroimaging Markers of NPH versus AD and PD, and chronic TBI-A Narrative Review},

author = {Sharada Kadaba Sridhar and Jen Dysterheft Robb and Rishabh Gupta and Rui Kuang and Uzma Samadani},

doi = {doi: 10.3389/fneur.2024.1347200},

year  = {2024},

date = {2024-03-14},

journal = {Frontiers in Neurology},

volume = {15},

pages = {1347200},

publisher = {Frontiers},

keywords = {},

pubstate = {forthcoming},

tppubtype = {article}

}

@article{sridhar2024ventriculomegaly,

title = {A ventriculomegaly feature computational pipeline to improve the screening of normal pressure hydrocephalus on CT},

author = {Sharada Kadaba Sridhar and Rui Kuang and Jen Dysterheft Robb and Uzma Samadani},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Journal of Neurosurgery},

volume = {1},

number = {aop},

pages = {1–11},

publisher = {American Association of Neurological Surgeons},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{GNTD,

title = {GNTD: Reconstructing Spatial Transcriptomes with Graph-guided Neural Tensor Decomposition Informed by Spatial and Functional Relations},

author = {Tianci Song and Charles Broadbent and Rui Kuang},

url = {https://www.nature.com/articles/s41467-023-44017-0},

year  = {2023},

date = {2023-04-01},

urldate = {2023-04-01},

journal = {Nature Communications},

volume = {14},

number = {8276},

keywords = {Protein-Protein Interaction Network, Spatial Transcriptomics, Tensor Completion},

pubstate = {published},

tppubtype = {article}

}

@article{spatialGCNNb,

title = {Detecting Spatially Co-expressed Gene Clusters with Functional Coherence by Graph-regularized Convolutional Neural Network},

author = {Tianci Song and Kathleen K. Markham and Zhuliu Li and Kristen E. Muller and Kathleen Greenham and Rui Kuang},

url = {https://academic.oup.com/bioinformatics/article/38/5/1344/6448221},

year  = {2022},

date = {2022-03-01},

urldate = {2021-11-30},

journal = {Bioinformatics},

volume = {38},

number = {5},

pages = {1344–1352},

keywords = {Spatial Transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{li2021imputation,

title = {Imputation of spatially-resolved transcriptomes by graph-regularized tensor completion},

author = {Zhuliu Li and Tianci Song and Jeongsik Yong and Rui Kuang},

url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1008218},

year  = {2021},

date = {2021-01-01},

journal = {PLoS computational biology},

volume = {17},

number = {4},

pages = {e1008218},

publisher = {Public Library of Science San Francisco, CA USA},

keywords = {Spatial Transcriptomics, Tensor Completion},

pubstate = {published},

tppubtype = {article}

}

@article{li2021scalable,

title = {Scalable Label Propagation for Multi-relational Learning on the Tensor Product of Graphs},

author = {Zhuliu Li and Raphael Petegrosso and Shaden Smith and David Sterling and George Karypis and Rui Kuang},

url = {https://ieeexplore.ieee.org/document/9369895/},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {IEEE Transactions on Knowledge and Data Engineering},

publisher = {IEEE},

keywords = {Multi-relational learning, Protein-Protein Interaction Network, Tensor Completion},

pubstate = {published},

tppubtype = {article}

}

@article{WeiZhang2020,

title = {Platform-integrated mRNA Isoform Quantification},

author = {Jiao Sun and Jae-Woong Chang and Teng Zhang and Jeongsik Yong and Rui Kuang and Wei Zhang

},

url = {https://academic.oup.com/bioinformatics/article-abstract/36/8/2466/5675495?redirectedFrom=fulltext},

year  = {2020},

date = {2020-04-15},

journal = {Bioinformatics},

volume = {36},

number = {8},

pages = {2466–2473},

keywords = {Isoform Quantification},

pubstate = {published},

tppubtype = {article}

}

@article{Petegrosso2020,

title = {Hierarchical Canonical Correlation Analysis Reveals Phenotype, Genotype, and Geoclimate Associations in Plants},

author = {Raphael Petegrosso and Tianci Song and Rui Kuang},

url = {https://spj.sciencemag.org/plantphenomics/2020/1969142/cta/},

doi = {10.34133/2020/1969142},

year  = {2020},

date = {2020-03-31},

journal = {Plant Phenomics},

volume = {2020},

number = {1969142},

keywords = {Phenome-genome Association},

pubstate = {published},

tppubtype = {article}

}

@article{nanostring,

title = {A large-scale comparative study of isoform expressions measured on four platforms},

author = {Wei Zhang and Raphael Petegrosso and Jae-Woong Chang and Jiao Sun and Jeongsik Yong and Jeremy Chien and Rui Kuang},

url = {https://bmcgenomics.biomedcentral.com/articles/10.1186/s12864-020-6643-8},

year  = {2020},

date = {2020-03-30},

journal = {BMC Bioinformatics},

volume = {21},

number = {272},

keywords = {Isoform Quantification},

pubstate = {published},

tppubtype = {article}

}

@article{roe2020accurate,

title = {Accurate and Efficient KIR Gene and Haplotype Inference from Genome Sequencing Reads with Novel K-mer Signatures},

author = {David Roe and Rui Kuang},

url = {https://www.frontiersin.org/articles/10.3389/fimmu.2020.583013/full},

year  = {2020},

date = {2020-01-01},

journal = {Frontiers in immunology},

volume = {11},

pages = {3102},

publisher = {Frontiers},

keywords = {KIR Haplotype Inference},

pubstate = {published},

tppubtype = {article}

}

@article{roe2020detailed,

title = {A Detailed View of KIR Haplotype Structures and Gene Families as Provided by a New Motif-based Multiple Sequence Alignment},

author = {David Roe and Cynthia Vierra-Green and Chul-Woo Pyo and Daniel E Geraghty and Stephen R Spellman and Martin Maiers and Rui Kuang},

url = {https://www.frontiersin.org/articles/10.3389/fimmu.2020.585731/full},

year  = {2020},

date = {2020-01-01},

journal = {Frontiers in immunology},

volume = {11},

publisher = {Frontiers Media SA},

keywords = {KIR Haplotype Inference},

pubstate = {published},

tppubtype = {article}

}

@article{roe2020efficient,

title = {Efficient Sequencing, Assembly, and Annotation of Human KIR Haplotypes},

author = {David Roe and Jonathan Williams and Keyton Ivery and Jenny Brouckaert and Nick Downey and Chad Locklear and Rui Kuang and Martin Maiers},

url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7581912/},

year  = {2020},

date = {2020-01-01},

journal = {Frontiers in immunology},

volume = {11},

publisher = {Frontiers Media SA},

keywords = {KIR Haplotype Inference},

pubstate = {published},

tppubtype = {article}

}

@article{petegrosso2019scrnaseq,

title = {Machine Learning and Statistical Methods for Clustering Single-cell RNA-sequencing Data},

author = {Raphael Petegrosso and Zhuliu Li and Rui Kuang},

url = {https://doi.org/10.1093/bib/bbz063},

year  = {2019},

date = {2019-06-29},

journal = {Briefings in Bioinformatics},

abstract = {Single-cell RNAsequencing (scRNA-seq) technologies have enabled the large-scale whole-transcriptome profiling of each individual single cell in a cell population. A core analysis of the scRNA-seq transcriptome profiles is to cluster the single cells to reveal cell subtypes and infer cell lineages based on the relations among the cells. This article reviews the machine learning and statistical methods for clustering scRNA-seq transcriptomes developed in the past few years. The review focuses on how conventional clustering techniques such as hierarchical clustering, graph-based clustering, mixture models, $k$-means, ensemble learning, neural networks and density-based clustering are modified or customized to tackle the unique challenges in scRNA-seq data analysis, such as the dropout of low-expression genes, low and uneven read coverage of transcripts, highly variable total mRNAs from single cells and ambiguous cell markers in the presence of technical biases and irrelevant confounding biological variations. We review how cell-specific normalization, the imputation of dropouts and dimension reduction methods can be applied with new statistical or optimization strategies to improve the clustering of single cells. We will also introduce those more advanced approaches to cluster scRNA-seq transcriptomes in time series data and multiple cell populations and to detect rare cell types. Several software packages developed to support the cluster analysis of scRNA-seq data are also reviewed and experimentally compared to evaluate their performance and efficiency. Finally, we conclude with useful observations and possible future directions in scRNA-seq data analytics.



AVAILABILITY:

All the source code and data are available at https://github.com/kuanglab/single-cell-review},

keywords = {scRNA-Seq, scRNA-Seq Clustering},

pubstate = {published},

tppubtype = {article}

}

@article{song2019path,

title = {Path segmentation for movement trajectories with irregular sampling frequency using space-time interpolation and density-based spatial clustering},

author = {Ying Song and Tianci Song and Rui Kuang},

url = {https://doi.org/10.1111/tgis.12549},

year  = {2019},

date = {2019-06-05},

journal = {Transactions in GIS},

volume = {23},

number = {3},

pages = {558--578},

abstract = {Path segmentation methods have been developed to distinguish stops and moves along movement trajectories. However, most studies do not focus on handling irregular sampling frequency of the movement data. This article proposes a four‐step method to handle various time intervals between two consecutive records, including parameter setting, space‐time interpolation, density‐based spatial clustering, and integrating the geographic context. The article uses GPS tracking data provided by HOURCAR, a non‐profit car‐sharing service in Minnesota, as a case study to demonstrate our method and present the results. We also implement the DB‐SMoT algorithm as a comparison. The results show that our four‐step method can handle various time intervals between consecutive records, group consecutive stops close to each other, and distinguish different types of stops and their inferred activities. These results can provide novel insights into car‐sharing behaviors such as trip purposes and activity scheduling.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{scalable2019petegrosso,

title = {Scalable Remote Homology Detection and Fold Recognition in Massive Protein Networks},

author = {Raphael Petegrosso and Zhuliu Li and Molly A. Srour and Yousef Saad and Wei Zhang and Rui Kuang},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/prot.25669},

year  = {2019},

date = {2019-01-31},

journal = {PROTEINS: Structure, Function, and Bioinformatics},

volume = {87},

number = {6},

pages = {478-491},

abstract = {The global connectivities in very large protein similarity networks contain traces of evolution among the proteins for detecting protein remote evolutionary relations or structural similarities. To investigate how well a protein network captures the evolutionary information, a key limitation is the intensive computation of pairwise sequence similarities needed to construct very large protein networks. In this paper, we introduce Label Propagation on Low-rank Kernel Approximation (LP-LOKA) for searching massively large protein networks. LP-LOKA propagates initial protein similarities in a low-rank graph by Nystrom approximation without computing all pairwise similarities. With scalable parallel implementations based on distributed-memory using message-passing interface and Apache-Hadoop/Spark on cloud, LP-LOKA can search protein networks with one million proteins or more. In the experiments on Swiss-Prot/ADDA/CASP data, LP-LOKA significantly improved protein ranking over the widely used HMM-HMM or profile-sequence alignment methods utilizing large protein networks. It was observed that the larger the protein similarity network, the better the performance, especially on relatively small protein superfamilies and folds. The results suggest that computing massively large protein network is necessary to meet the growing need of annotating proteins from newly sequenced species and LP-LOKA is both scalable and accurate for searching massively large protein networks.},

keywords = {Protein Remote Homology Detection},

pubstate = {published},

tppubtype = {article}

}

@article{Hauck2018,

title = {Obesity-Induced Protein Carbonylation In Murine Adipose Tissue Regulates The DNA Binding Domain Of Nuclear Zinc-Finger Proteins},

author = {Amy K Hauck and Tong Zhou and Wendy S Hahn and Raphael Petegrosso and Rui Kuang and Yue Chen and David A Bernlohr},

url = {http://www.jbc.org/content/early/2018/07/16/jbc.RA118.003469.abstract},

doi = {doi: 10.1074/jbc.RA118.003469},

year  = {2018},

date = {2018-07-16},

journal = {Journal of Biological Chemistry},

abstract = {In obesity-linked insulin resistance, oxidative stress in adipocytes leads to lipid peroxidation and subsequent carbonylation of proteins by diffusible lipid electrophiles. Reduction in oxidative stress attenuates protein carbonylation and insulin resistance suggesting lipid modification of proteins may play a role in metabolic disease, but the mechanisms remain incompletely understood. Herein we show that in vivo, diet-induced obesity in mice surprisingly results in preferential carbonylation of nuclear proteins by 4-hydroxy-trans 2,3 nonenal (4-HNE) or 4-hydroxy-trans 2,3 hexenal (4-HHE). Proteomic and structural analyses revealed that residues in or around the sites of zinc coordination of zinc finger proteins, such as those containing the C2H2 or MATRIN, RING, C3H1, or N4-type DNA binding domains, are particularly susceptible to carbonylation by lipid aldehydes. These observations strongly suggest that carbonylation functionally disrupts protein secondary structure supported by metal coordination. Analysis of one such target, the nuclear protein estrogen-related receptor gamma (ERR-γ), showed that ERR-γ is modified by 4-HHE in the obese state. In vitro carbonylation decreased the DNA-binding capacity of ERR-γ and correlated with the obesity-linked down regulation of many key genes promoting mitochondrial bioenergetics. Taken together, these findings reveal a novel mechanistic connection between oxidative stress and metabolic dysfunction arising from carbonylation of nuclear zinc-finger proteins such as the transcriptional regulator ERR-γ.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{chang2018,

title = {An integrative model for alternative polyadenylation, IntMAP, delineates mTOR-modulated endoplasmic reticulum stress response},

author = {Chang, Jae-Woong; Zhang, Wei; Yeh, Hsin Sung; Park, Meeyeon; Yao, Chengguo; Shi, Yongsheng; Kuang, Rui# and Yong, Jeongsik#},

year  = {2018},

date = {2018-07-06},

journal = {Nucleic Acids Research},

volume = {46},

number = {12},

pages = {P5996–6008},

abstract = {3'-untranslated regions (UTRs) can vary through the use of alternative polyadenylation sites during pre-mRNA processing. Multiple publically available pipelines combining high profiling technologies and bioinformatics tools have been developed to catalog changes in 3'-UTR lengths. In our recent RNA-seq experiments using cells with hyper-activated mammalian target of rapamycin (mTOR), we found that cellular mTOR activation leads to transcriptome-wide alternative polyadenylation (APA), resulting in the activation of multiple cellular pathways. Here, we developed a novel bioinformatics algorithm, IntMAP, which integrates RNA-Seq and PolyA Site (PAS)-Seq data for a comprehensive characterization of APA events. By applying IntMAP to the datasets from cells with hyper-activated mTOR, we identified novel APA events that could otherwise not be identified by either profiling method alone. Several transcription factors including Cebpg (CCAAT/enhancer binding protein gamma) were among the newly discovered APA transcripts, indicating that diverse transcriptional networks may be regulated by mTOR-coordinated APA. The prevention of APA in Cebpg using the CRISPR/cas9-mediated genome editing tool showed that mTOR-driven 3'-UTR shortening in Cebpg is critical in protecting cells from endoplasmic reticulum (ER) stress. Taken together, we present IntMAP as a new bioinformatics algorithm for APA analysis by which we expand our understanding of the physiological role of mTOR-coordinated APA events to ER stress response. IntMAP toolbox is available at http://compbio.cs.umn.edu/IntMAP/.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kang2018,

title = {HRB2 and BBX21 interaction modulates Arabidopsis ABI5 locus and stomatal aperture},

author = {Xiaojun Kang and Gang Xu and Byungha Lee and Chen Chen and Huanan Zhang and Rui Kuang and Min Ni},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/pce.13336},

doi = {https://doi.org/10.1111/pce.13336},

year  = {2018},

date = {2018-05-10},

journal = {Plant, Cell & Environment},

number = {41},

pages = {1912-1925},

abstract = {Blue light triggers the opening of stomata in the morning to allow CO2 uptake and water loss through transpiration. During the day, plants may experience periodic drought and accumulate abscisic acid (ABA). ABA antagonizes blue light signalling through phosphatidic acid and reduces stomatal aperture. This study reveals a molecular mechanism by which two light signalling proteins interact to repress ABA signalling in the control of stomatal aperture. A hypersensitive to red and blue 2 (hrb2) mutant has a defective ATP‐dependent chromatin‐remodelling factor, PKL, in the chromodomain/helicase/DNA binding family. HRB2 enhances the light‐induced expression of a B‐box transcription factor gene, BBX21. BBX21 binds a T/G box in the ABI5 promoter and recruits HRB2 to modulate the chromatin structure at the ABI5 locus. Mutation in either HRB2 or BBX21 led to reduced water loss and ABA hypersensitivity. This hypersensitivity to ABA was well explained by the enhanced expression of the ABA signalling gene ABI5 in both mutants. Indeed, stomatal aperture was significantly reduced by ABI5 overexpression in the absence or presence of ABA under monochromatic light conditions. Overall, we present a regulatory loop in which two light signalling proteins repress ABA signalling to sustain gas exchange when plants experience periodic drou},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{multitask_zhang,

title = {A Multitask Clustering Approach for Single-cell RNA-Seq Analysis in Recessive Dystrophic Epidermolysis Bullosa},

author = {Huanan Zhang and Catherine A. A. Lee and Zhuliu Li and John R. Garbe and Cindy R. Eide and Raphael Petegrosso and Rui Kuang and Jakub Tolar},

url = {http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1006053},

doi = {https://doi.org/10.1371/journal.pcbi.1006053},

year  = {2018},

date = {2018-04-05},

journal = {PLOS Computational Biology},

volume = {14},

number = {4},

abstract = {Single-cell RNA sequencing (scRNA-seq) has been widely applied to discover new cell types by detecting sub-populations in a heterogeneous group of cells. 

Since scRNA-seq experiments have lower read coverage/tag counts and introduce more technical biases compared to bulk RNA-seq experiments, the limited number of sampled cells combined with the experimental biases and other dataset specific variations presents a challenge to cross-dataset analysis and discovery of relevant biological variations across multiple cell populations. In this paper, we introduce a method of variance-driven multitask clustering of single-cell RNA-seq data (scVDMC) that utilizes multiple single-cell populations from biological replicates or different samples. scVDMC clusters single cells in multiple scRNA-seq experiments of similar cell types and markers but varying expression patterns such that the scRNA-seq data are better integrated than typical pooled analyses which only increase the sample size. By controlling the variance among the cell clusters within each dataset and across all the datasets, scVDMC detects cell sub-populations in each individual experiment with shared cell-type markers but varying cluster centers among all the experiments. Applied to two real scRNA-seq datasets with several replicates  and one large-scale Drop-seq dataset on three patient samples, scVDMC more accurately detected cell populations and known cell markers than pooled clustering and other recently proposed scRNA-seq clustering methods. In the case study applied to in-house Recessive Dystrophic Epidermolysis Bullosa (RDEB) scRNA-seq data, scVDMC revealed several new cell types and unknown markers validated by flow cytometry.

},

keywords = {scRNA-Seq},

pubstate = {published},

tppubtype = {article}

}

@article{xiang2018vasodilator,

title = {Vasodilator-stimulated phosphoprotein promotes liver metastasis of gastrointestinal cancer by activating a β1-integrin-FAK-YAP1/TAZ signaling pathway},

author = {Xiaoyu Xiang and Yuanguo Wang and Hongbin Zhang and Jinhua Piao and Selvaraj Muthusamy and Lei Wang and Yibin Deng and Wei Zhang and Rui Kuang and Daniel D. Billadeau and Shengbing Huang and Jinping Lai and Raul Urrutia and Ningling Kang},

url = {https://www.nature.com/articles/s41698-017-0045-7},

doi = {10.1038/s41698-017-0045-7},

year  = {2018},

date = {2018-03-22},

journal = {npj Precision Oncology},

abstract = {Extracellular matrix (ECM)-induced β1-integrin-FAK signaling promotes cell attachment, survival, and migration of cancer cells in a distant organ so as to enable cancer metastasis. However, mechanisms governing activation of the β1-integrin-FAK signaling remain incompletely understood. Here, we report that vasodilator-stimulated phosphoprotein (VASP), an actin binding protein, is required for ECM–mediated β1-integrin-FAK-YAP1/TAZ signaling in gastrointestinal (GI) cancer cells and their liver metastasis. In patient-derived samples, VASP is upregulated in 53 of 63 colorectal cancers and 43 of 53 pancreatic ductal adenocarcinomas and high VASP levels correlate with liver metastasis and reduced patient survival. In a Matrigel-based 3-dimensional (3D) culture model, short hairpin RNA (shRNA)–mediated VASP knockdown in colorectal cancer cells (KM12L4, HCT116, and HT29) and pancreatic cancer cells (L3.6 and MIA PaCa-1) suppresses the growth of 3D cancer spheroids. Mechanistic studies reveal that VASP knockdown suppresses FAK phosphorylation and YAP1/TAZ protein levels, but not Akt or Erk-related pathways and that YAP1/TAZ proteins are enhanced by the β1-integrin-FAK signaling. Additionally, VASP regulates the β1-integrin-FAK-YAP1/TAZ signaling by at least two mechanisms: (1) promoting ECM-mediated β1-integrin activation and (2) regulating YAP1/TAZ dephosphorylation at downstream of RhoA to enhance the stability of YAP1/TAZ proteins. In agreement with these, preclinical studies with two experimental liver metastasis mouse models demonstrate that VASP knockdown suppresses GI cancer liver metastasis, β1-integrin activation, and YAP1/TAZ levels of metastatic cancer cells. Together, our data support VASP as a treatment target for liver metastasis of colorectal and pancreatic cancers.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kuang2017,

title = {Detecting Population-differentiation Copy Number Variants in Human Population Tree by Sparse Group Selection},

author = { Huanan Zhang and David Roe and Rui Kuang},

url = {http://ieeexplore.ieee.org/document/8168351/},

year  = {2017},

date = {2017-12-08},

journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics},

volume = {16},

number = {2},

pages = {538 - 549},

abstract = {Copy-number variants (CNVs) account for a substantial proportion of human genetic variations. Understanding the CNV diversities across populations is a computational challenge because CNV patterns are often present in several related populations and only occur in a subgroup of individuals within each of the population. This paper introduces a tree-guided sparse group selection algorithm (treeSGS) to detect population-differentiation CNV markers of subgroups across populations organized by a phylogenetic tree of human populations. The treeSGS algorithm detects CNV markers of populations associated with nodes from all levels of the tree such that the evolutionary relations among the populations are incorporated for more accurate detection of population-differentiation CNVs. We applied treeSGS algorithm to study the 1179 samples from the 11 populations in Hapmap3 CNV data. The treeSGS algorithm accurately identifies CNV markers of each population and the collection of populations organized under the branches of the human population tree, validated by consistency among family trios and SNP characterizations of the CNV regions. Further comparison between the detected CNV markers and other population-differentiation CNVs reported in 1000 genome data and other recent studies also shows that treeSGS can significantly improve the current annotations of population-differentiation CNV markers. TreeSGS package is available at http://compbio.cs.umn.edu/treesgs.},

keywords = {Sparse Group Learning},

pubstate = {published},

tppubtype = {article}

}

@article{networkreview2017,

title = {Network-based Machine Learning and Graph Theory Algorithms for Precision Oncology},

author = {Wei Zhang and Jeremy Chien and Jeongsik Yong and Rui Kuang},

url = {https://www.nature.com/articles/s41698-017-0029-7},

doi = {doi:10.1038/s41698-017-0029-7},

year  = {2017},

date = {2017-08-08},

journal = {NPJ Precision Oncology},

number = {25},

abstract = {Network-based analytics plays an increasingly important role in precision oncology. Growing evidence in recent studies suggests that cancer can be better understood through mutated or dysregulated pathways or networks rather than individual mutations and that the efficacy of repositioned drugs can be inferred from disease modules in molecular networks. This article reviews network-based machine learning and graph theory algorithms for integrative analysis of personal genomic data and biomedical knowledge bases to identify tumor-specific molecular mechanisms, candidate targets and repositioned drugs for personalized treatment. The review focuses on the algorithmic design and mathematical formulation of these methods to facilitate applications and implementations of network-based analysis in the practice of precision oncology. We review the methods applied in three scenarios to integrate genomic data and network models in different analysis pipelines, and we examine three categories of network-based approaches for repositioning drugs in drug-disease-gene networks. In addition, we perform a comprehensive subnetwork/pathway analysis of mutations in 31 cancer genome projects in the Cancer Genome Atlas (TCGA) and present a detailed case study on ovarian cancer. Finally, we discuss interesting observations, potential pitfalls and future directions in network-based precision oncology.},

keywords = {Phenome-genome Association, Protein-Protein Interaction Network},

pubstate = {published},

tppubtype = {article}

}

@article{huananplant2016b,

title = {Global analysis of canola genes targeted by SHORT HYPOCOTYL UNDER BLUE 1 during endosperm and embryo development},

author = {Huanan Zhang and Feng Cheng and Yuguo Xiao and Xiaojun Kang and Xiaowu Wang and Rui Kuang and Min Ni},

url = {http://onlinelibrary.wiley.com/doi/10.1111/tpj.13542/abstract},

year  = {2017},

date = {2017-07-01},

journal = {The Plant Journal},

volume = {91},

number = {1},

pages = {158-171},

abstract = {Seed development in dicots includes early endosperm proliferation followed by growth of the embryo to replace the endosperm. Endosperm proliferation in dicots not only provides nutrient supplies for subsequent embryo development but also enforces a space limitation, influencing final seed size. Overexpression of Arabidopsis SHORT HYPOCOTYL UNDER BLUE1::uidA (SHB1:uidA) in canola produces large seeds. We performed global analysis of the canola genes that were expressed and influenced by SHB1 during early endosperm proliferation at 8 days after pollination (DAP) and late embryo development at 13 DAP. Overexpression of SHB1 altered the expression of 973 genes at 8 DAP and 1035 genes at 13 DAP. We also surveyed the global SHB1 association sites, and merging of these sites with the RNA sequencing data identified a set of canola genes targeted by SHB1. The 8-DAP list includes positive and negative genes that influence endosperm proliferation and are homologous to Arabidopsis MINI3, IKU2, SHB1, AGL62, FIE and AP2. We revealed a major role for SHB1 in canola endosperm development based on the dynamics of SHB1-altered gene expression, the magnitude of SHB1 chromatin immunoprecipitation enrichment and the over-representation of eight regulatory genes for endosperm development. Our studies focus on an important agronomic trait in a major crop for global agriculture. The datasets on stage-specific and SHB1-induced gene expression and genes targeted by SHB1 also provide a useful resource in the field of endosperm development and seed size engineering. Our practices in an allotetraploid species will impact similar studies in other crop species.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{KIR2017,

title = {Revealing complete complex KIR haplotypes phased by long-read sequencing technology},

author = {David Roe and Cynthia Vierra-Green and C-W Pyo and K Eng and R Hall and Rui Kuang and Stephen Spellman and S Ranade and D E Geraghty and Martin Maiers},

url = {https://www.nature.com/gene/journal/vaop/ncurrent/full/gene201710a.html},

doi = {10.1038/gene.2017.10},

year  = {2017},

date = {2017-06-01},

journal = {Genes Immunity},

volume = {1-8},

abstract = {The killer cell immunoglobulin-like receptor (KIR) region of human chromosome 19 contains up to 16 genes for natural killer (NK) cell receptors that recognize human leukocyte antigen (HLA)/peptide complexes and other ligands. The KIR proteins fulfill functional roles in infections, pregnancy, autoimmune diseases and transplantation. However, their characterization remains a constant challenge. Not only are the genes highly homologous due to their recent evolution by tandem duplications, but the region is structurally dynamic due to frequent transposon-mediated recombination. A sequencing approach that precisely captures the complexity of KIR haplotypes for functional annotation is desirable. We present a unique approach to haplotype the KIR loci using single-molecule, real-time (SMRT) sequencing. Using this method, we have—for the first time—comprehensively sequenced and phased sixteen KIR haplotypes from eight individuals without imputation. The information revealed four novel haplotype structures, a novel gene-fusion allele, novel and confirmed insertion/deletion events, a homozygous individual, and overall diversity for the structural haplotypes and their alleles. These KIR haplotypes augment our existing knowledge by providing high-quality references, evolutionary informers, and source material for imputation. The haplotype sequences and gene annotations provide alternative loci for the KIR region in the human genome reference GrCh38.p8.},

keywords = {KIR Haplotype Inference},

pubstate = {published},

tppubtype = {article}

}

@article{petegrosso2016transfer,

title = {Transfer Learning across Ontologies for Phenome-Genome Association Prediction},

author = {Raphael Petegrosso and Sunho Park and Tae Hyun Hwang and Rui Kuang},

url = {http://bioinformatics.oxfordjournals.org/content/early/2016/10/20/bioinformatics.btw649.abstract},

doi = {10.1093/bioinformatics/btw649},

year  = {2016},

date = {2016-11-23},

journal = {Bioinformatics},

volume = {33},

number = {4},

pages = {529-536},

publisher = {Oxford Univ Press},

abstract = {Motivation: To better predict and analyze gene associations with the collection of phenotypes organized in a phenotype ontology, it is crucial to effectively model the hierarchical structure among the phenotypes in the ontology and leverage the sparse known associations with additional training information. In this paper, we first introduce Dual Label Propagation (DLP) to impose consistent associations with the entire phenotype paths in predicting phenotype-gene associations in Human Phenotype Ontology (HPO). DLP is then used as the base model in a transfer learning framework (tlDLP) to incorporate functional annotations in Gene Ontology (GO). By simultaneously reconstructing GO term-gene associations and HPO phenotype-gene associations for all the genes in a protein-protein interaction network, tlDLP benefits from the enriched training associations indirectly through relation with GO terms. 

 

Results: In the experiments to predict the associations between human genes and phenotypes in HPO based on human protein-protein interaction network, both DLP and tlDLP improved the prediction of gene associations with phenotype paths in HPO in cross-validation and the prediction of the most recent associations added after the snapshot of the training data. Moreover, the transfer learning through GO term-gene associations significantly improved association predictions for the phenotypes with no more specific known associations by a large margin. Examples are also shown to demonstrate how phenotype paths in phenotype ontology and transfer learning with gene ontology can improve the predictions. 

 

Availability: Source code is available at http://localhost/~raphaelpetegrosso/wpcb/ontophenome.},

keywords = {Phenome-genome Association, Transfer Learning},

pubstate = {published},

tppubtype = {article}

}

@article{vierra2016estimating,

title = {Estimating KIR Haplotype Frequencies on a Cohort of 10,000 Individuals: A Comprehensive Study on Population Variations, Typing Resolutions, and Reference Haplotypes},

author = {Cynthia Vierra-Green and David Roe and Jyothi Jayaraman and John Trowsdale and James Traherne and Rui Kuang and Stephen Spellman and Martin Maiers},

url = {http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0163973},

doi = {10.1371/journal.pone.0163973},

year  = {2016},

date = {2016-10-10},

journal = {PloS one},

volume = {11},

number = {10},

pages = {e0163973},

publisher = {Public Library of Science},

abstract = {The killer cell immunoglobulin-like receptors (KIR) mediate human natural killer (NK) cell cytotoxicity via activating or inhibiting signals. Although informative and functional haplotype patterns have been reported, most genotyping has been performed at resolutions that are structurally ambiguous. In order to leverage structural information given low-resolution genotypes, we performed experiments to quantify the effects of population variations, reference haplotypes, and genotyping resolutions on population-level haplotype frequency estimations as well as predictions of individual haplotypes. We genotyped 10,157 unrelated individuals in 5 populations (518 African American[AFA], 258 Asian or Pacific Islander[API], 8,245 European[EUR], 1,073 Hispanic[HIS], and 63 Native American[NAM]) for KIR gene presence/absence (PA), and additionally half of the AFA samples for KIR gene copy number variation (CNV). A custom EM algorithm was used to estimate haplotype frequencies for each population by interpretation in the context of three sets of reference haplotypes. The algorithm also assigns each individual the haplotype pairs of maximum likelihood. Generally, our haplotype frequency estimates agree with similar previous publications to within <5% difference for all haplotypes. The exception is that estimates for NAM from the U.S. showed higher frequency association of cB02 with tA01 (+14%) instead of tB01 (-8.5%) compared to a previous study of NAM from south of the U.S. The higher-resolution CNV genotyping on the AFA samples allowed unambiguous haplotype-pair assignments for the majority of individuals, resulting in a 22% higher median typing resolution score (TRS), which measures likelihood of self-match in the context of population-specific haplo- and geno-types. The use of TRS to quantify reduced ambiguity with CNV data clearly revealed the few individuals with ambiguous genotypes as outliers. It is observed that typing resolution and reference haplotype set influence haplotype frequency estimates. For example, PA resolution may be used with reference haplotype sets up to the point where certain haplotypes are gene-content subsets of others. At that point, CNV must be used for all genes.},

keywords = {KIR Haplotype Inference},

pubstate = {published},

tppubtype = {article}

}

@article{liang2015meta,

title = {Meta-Analysis of EMT Datasets Reveals Different Types of EMT.},

author = {Lining Liang and Hao Sun and Wei Zhang and Mengdan Zhang and Xiao Yang and Rui Kuang and Hui Zheng},

url = {http://journals.plos.org/plosone/article?id=10.1371%2Fjournal.pone.0156839},

doi = {10.1371/journal.pone.0156839},

year  = {2016},

date = {2016-06-03},

journal = {PloS one},

volume = {11},

number = {6},

pages = {e0156839--e0156839},

abstract = {As a critical process during embryonic development, cancer progression and cell fate conversions, epithelial-mesenchymal transition (EMT) has been extensively studied over the last several decades. To further understand the nature of EMT, we performed meta-analysis of multiple microarray datasets to identify the related generic signature. In this study, 24 human and 17 mouse microarray datasets were integrated to identify conserved gene expression changes in different types of EMT. Our integrative analysis revealed that there is low agreement among the list of the identified signature genes and three other lists in previous studies. Since removing the datasets with weakly-induced EMT from the analysis did not significantly improve the overlapping in the signature-gene lists, we hypothesized the existence of different types of EMT. This hypothesis was further supported by the grouping of 74 human EMT-induction samples into five distinct clusters, and the identification of distinct pathways in these different clusters of EMT samples. The five clusters of EMT-induction samples also improves the understanding of the characteristics of different EMT types. Therefore, we concluded the existence of different types of EMT was the possible reason for its complex role in multiple biological processes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Net-RSTQ,

title = {Network-based Isoform Quantification with RNA-Seq Data for Cancer Transcriptome Analysis},

author = {Wei Zhang and Jae-Woong Chang and Lilong Lin and Kay Minn and Baolin Wu and Jeremy Chien and Jeongsik Yong and Hui Zheng and Rui Kuang},

url = {http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1004465},

doi = {http://dx.doi.org/10.1371/journal.pcbi.1004465},

year  = {2015},

date = {2015-12-23},

journal = {PLoS Computational Biology},

volume = {e1004465},

abstract = {New sequencing technologies for transcriptome-wide profiling of RNAs have greatly promoted the interest in isoform-based functional characterizations of a cellular system. Elucidation of gene expressions at the isoform resolution could lead to new molecular mechanisms such as gene-regulations and alternative splicings, and potentially better molecular signals for phenotype predictions. However, it could be overly optimistic to derive the proportion of the isoforms of a gene solely based on short read alignments. Inherently, systematical sampling biases from RNA library preparation and ambiguity of read origins in overlapping isoforms pose a problem in reliability. The work in this paper exams the possibility of using protein domain-domain interactions as prior knowledge in isoform transcript quantification. We first made the observation that protein domain-domain interactions positively correlate with isoform co-expressions in TCGA data and then designed a probabilistic EM approach to integrate domain-domain interactions with short read alignments for estimation of isoform proportions. Validated by qRT-PCR experiments on three cell lines, simulations and classifications of TCGA patient samples in several cancer types, Net-RSTQ is proven a useful tool for isoform-based analysis in functional genomes and systems biology.},

keywords = {Isoform Quantification},

pubstate = {published},

tppubtype = {article}

}

@article{chang2015mrna,

title = {mRNA 3'-UTR shortening is a molecular signature of mTORC1 activation},

author = {Jae-Woong Chang and Wei Zhang and Hsin-Sung Yeh and Ebbing P de Jong and Semo Jun and Kwan-Hyun Kim and Sun S Bae and Kenneth Beckman and Tae Hyun Hwang and Kye-Seong Kim and others},

url = {http://www.nature.com/articles/ncomms8218},

doi = {10.1038/ncomms8218},

year  = {2015},

date = {2015-06-15},

journal = {Nature communications},

volume = {6},

publisher = {Nature Publishing Group},

abstract = {Mammalian target of rapamycin (mTOR) enhances translation from a subset of messenger RNAs containing distinct 5′-untranslated region (UTR) sequence features. Here we identify 3′-UTR shortening of mRNAs as an additional molecular signature of mTOR activation and show that 3′-UTR shortening enhances the translation of specific mRNAs. Using genetic or chemical modulations of mTOR activity in cells or mouse tissues, we show that cellular mTOR activity is crucial for 3′-UTR shortening. Although long 3′-UTR-containing transcripts minimally contribute to translation, 3-′UTR-shortened transcripts efficiently form polysomes in the mTOR-activated cells, leading to increased protein production. Strikingly, selected E2 and E3 components of ubiquitin ligase complexes are enriched by this mechanism, resulting in elevated levels of protein ubiquitination on mTOR activation. Together, these findings identify a previously uncharacterized role for mTOR in the selective regulation of protein synthesis by modulating 3′-UTR length of mRNAs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{xie2015network,

title = {Network-based Phenome-Genome Association Prediction by Bi-Random Walk},

author = {MaoQiang Xie and YingJie Xu and YaoGong Zhang and TaeHyun Hwang and Rui Kuang},

url = {http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0125138},

doi = {10.1371/journal.pone.0125138},

year  = {2015},

date = {2015-05-01},

journal = {PloS one},

volume = {10},

number = {5},

pages = {e0125138},

publisher = {Public Library of Science},

abstract = {The availability of ontologies and systematic documentations of phenotypes and their genetic associations has enabled large-scale network-based global analyses of the association between the complete collection of phenotypes (phenome) and genes. To provide a fundamental understanding of how the network information is relevant to phenotype-gene associations, we analyze the circular bigraphs (CBGs) in OMIM human disease phenotype-gene association network and MGI mouse phentoype-gene association network, and introduce a bi-random walk (BiRW) algorithm to capture the CBG patterns in the networks for unveiling human and mouse phenome-genome association. BiRW performs separate random walk simultaneously on gene interaction network and phenotype similarity network to explore gene paths and phenotype paths in CBGs of different sizes to summarize their associations as predictions.},

keywords = {Phenome-genome Association},

pubstate = {published},

tppubtype = {article}

}

@article{chien2015tp53,

title = {TP53 mutations, tetraploidy and homologous recombination repair defects in early stage high-grade serous ovarian cancer},

author = {Jeremy Chien and Hugues Sicotte and Jian-Bing Fan and Sean Humphray and Julie M Cunningham and Kimberly R Kalli and Ann L Oberg and Steven N Hart and Ying Li and Jaime I Davila and others},

url = {http://nar.oxfordjournals.org/content/43/14/6945},

doi = {10.1093/nar/gkv111},

year  = {2015},

date = {2015-02-02},

journal = {Nucleic acids research},

pages = {gkv111},

publisher = {Oxford Univ Press},

abstract = {To determine early somatic changes in high-grade serous ovarian cancer (HGSOC), we performed whole genome sequencing on a rare collection of 16 low stage HGSOCs. The majority showed extensive structural alterations (one had an ultramutated profile), exhibited high levels of p53 immunoreactivity, and harboured TP53 mutation, deletion or inactivation. BRCA1 and BRCA2 mutations were observed in two tumors, with nine showing evidence of a homologous recombination (HR) defect. Combined analysis with The Cancer Genome Atlas indicated that low and late stage HGSOCs have similar mutation and copy number profiles. We also found evidence that deleterious TP53 mutations are the earliest events, followed by deletions or loss of heterozygosity (LOH) of chromosomes carrying TP53, BRCA1 or BRCA2. Inactivation of HR appears to be an early event, as 62.5% of tumours showed a LOH pattern suggestive of HR defects. Three tumours with the highest ploidy had little genome-wide LOH, yet one of these had a homozygous somatic frame-shift BRCA2 mutation, suggesting that some carcinomas begin as tetraploid then descend into diploidy accompanied by genome-wide LOH. Lastly, we found evidence that structural variants (SV) cluster in HGSOC, but are absent in one ultramutated tumor, providing insights into the pathogenesis of low stage HGSOC.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{johnson2015subpatcnv,

title = {SubPatCNV: approximate subspace pattern mining for mapping copy-number variations},

author = {Nicholas Johnson and Huanan Zhang and Gang Fang and Vipin Kumar and Rui Kuang},

url = {https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-014-0426-7},

doi = {10.1186/s12859-014-0426-7},

issn = {1471-2105},

year  = {2015},

date = {2015-01-16},

journal = {BMC bioinformatics},

volume = {16},

number = {1},

pages = {1},

publisher = {BioMed Central},

abstract = {Background 

Many DNA copy-number variations (CNVs) are known to lead to phenotypic variations and pathogenesis. While CNVs are often only common in a small number of samples in the studied population or patient cohort, previous work has not focused on customized identification of CNV regions that only exhibit in subsets of samples with advanced data mining techniques to reliably answer questions such as “Which are all the chromosomal fragments showing nearly identical deletions or insertions in more than 30% of the individuals?”. 

 

Results 

We introduce a tool for mining CNV subspace patterns, namely SubPatCNV, which is capable of identifying all aberrant CNV regions specific to arbitrary sample subsets larger than a support threshold. By design, SubPatCNV is the implementation of a variation of approximate association pattern mining algorithm under a spatial constraint on the positional CNV probe features. In benchmark test, SubPatCNV was applied to identify population specific germline CNVs from four populations of HapMap samples. In experiments on the TCGA ovarian cancer dataset, SubPatCNV discovered many large aberrant CNV events in patient subgroups, and reported regions enriched with cancer relevant genes. In both HapMap data and TCGA data, it was observed that SubPatCNV employs approximate pattern mining to more effectively identify CNV subspace patterns that are consistent within a subgroup from high-density array data. 

 

Conclusions 

SubPatCNV available through http://sourceforge.net/projects/subpatcnv/is a unique scalable open-source software tool that provides the flexibility of identifying CNV regions specific to sample subgroups of different sizes from high-density CNV array data.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{cai2015predicting,

title = {Predicting and exploring network components involved in pathogenesis in the malaria parasite via novel subnetwork alignments},

author = {Cai, Hong and Lilburn, Timothy G and Hong, Changjin and Gu, Jianying and Kuang, Rui and Wang, Yufeng},

year  = {2015},

date = {2015-01-01},

journal = {BMC systems biology},

volume = {9},

number = {4},

pages = {1},

publisher = {BioMed Central},

keywords = {Protein-Protein Interaction Network},

pubstate = {published},

tppubtype = {article}

}

@article{cai2013novel,

title = {A novel subnetwork alignment approach predicts new components of the cell cycle regulatory apparatus in Plasmodium falciparum},

author = {Hong Cai and Changjin Hong and Timothy G Lilburn and Armando L Rodriguez and Sheng Chen and Jianying Gu and Rui Kuang and Yufeng Wang},

url = {http://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-14-S12-S2},

doi = {10.1186/1471-2105-14-S12-S2},

issn = {1471-2105},

year  = {2013},

date = {2013-09-24},

journal = {BMC bioinformatics},

volume = {14},

number = {12},

pages = {1},

publisher = {BioMed Central},

abstract = {Background 

According to the World Health organization, half the world's population is at risk of contracting malaria. They estimated that in 2010 there were 219 million cases of malaria, resulting in 660,000 deaths and an enormous economic burden on the countries where malaria is endemic. The adoption of various high-throughput genomics-based techniques by malaria researchers has meant that new avenues to the study of this disease are being explored and new targets for controlling the disease are being developed. Here, we apply a novel neighborhood subnetwork alignment approach to identify the interacting elements that help regulate the cell cycle of the malaria parasite Plasmodium falciparum. 

 

Results 

Our novel subnetwork alignment approach was used to compare networks in Escherichia coli and P. falciparum. Some 574 P. falciparum proteins were revealed as functional orthologs of known cell cycle proteins in E. coli. Over one third of these predicted functional orthologs were annotated as "conserved Plasmodium proteins" or "putative uncharacterized proteins" of unknown function. The predicted functionalities included cyclins, kinases, surface antigens, transcriptional regulators and various functions related to DNA replication, repair and cell division. 

 

Conclusions 

The results of our analysis demonstrate the power of our subnetwork alignment approach to assign functionality to previously unannotated proteins. Here, the focus was on proteins involved in cell cycle regulation. These proteins are involved in the control of diverse aspects of the parasite lifecycle and of important aspects of pathogenesis.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{chien2013platinumb,

title = {Platinum-sensitive recurrence in ovarian cancer: the role of tumor microenvironment},

author = {Jeremy Chien and Rui Kuang and Charles Landen and Viji Shridhar},

url = {http://journal.frontiersin.org/article/10.3389/fonc.2013.00251/full},

doi = {10.3389/fonc.2013.00251},

year  = {2013},

date = {2013-09-23},

journal = {Frontiers in oncology},

volume = {3},

pages = {251},

publisher = {Frontiers},

abstract = {Despite several advances in the understanding of ovarian cancer pathobiology, in terms of driver genetic alterations in high-grade serous cancer, histologic heterogeneity of epithelial ovarian cancer, cell-of-origin for ovarian cancer, the survival rate from ovarian cancer is disappointingly low when compared to that of breast or prostate cancer. One of the factors contributing to the poor survival rate from ovarian cancer is the development of chemotherapy resistance following several rounds of chemotherapy. Although unicellular drug resistance mechanisms contribute to chemotherapy resistance, tumor microenvironment and the extracellular matrix (ECM), in particular, is emerging as a significant determinant of a tumor’s response to chemotherapy. In this review, we discuss the potential role of the tumor microenvironment in ovarian cancer recurrence and resistance to chemotherapy. Finally, we propose an alternative view of platinum-sensitive recurrence to describe a potential role of the ECM in the process.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hwang2013large,

title = {Large-scale integrative network-based analysis identifies common pathways disrupted by copy number alterations across cancers},

author = {TaeHyun Hwang and Gowtham Atluri and Rui Kuang and Vipin Kumar and Timothy Starr and Kevin AT Silverstein and Peter M Haverty and Zemin Zhang and Jinfeng Liu},

url = {http://bmcgenomics.biomedcentral.com/articles/10.1186/1471-2164-14-440},

doi = {10.1186/1471-2164-14-440},

year  = {2013},

date = {2013-07-03},

journal = {BMC genomics},

volume = {14},

number = {1},

pages = {440},

publisher = {BioMed Central Ltd},

abstract = {Many large-scale studies analyzed high-throughput genomic data to identify altered pathways essential to the development and progression of specific types of cancer. However, no previous study has been extended to provide a comprehensive analysis of pathways disrupted by copy number alterations across different human cancers. Towards this goal, we propose a network-based method to integrate copy number alteration data with human protein-protein interaction networks and pathway databases to identify pathways that are commonly disrupted in many different types of cancer.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{zhang2013network,

title = {Network-based survival analysis reveals subnetwork signatures for predicting outcomes of ovarian cancer treatment},

author = {Wei Zhang and Takayo Ota and Viji Shridhar and Jeremy Chien and Baolin Wu and Rui Kuang},

url = {http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1002975},

doi = {10.1371/journal.pcbi.1002975},

year  = {2013},

date = {2013-03-21},

journal = {PLoS Comput Biol},

volume = {9},

number = {3},

pages = {e1002975},

publisher = {Public Library of Science},

abstract = {Cox regression is commonly used to predict the outcome by the time to an event of interest and in addition, identify relevant features for survival analysis in cancer genomics. Due to the high-dimensionality of high-throughput genomic data, existing Cox models trained on any particular dataset usually generalize poorly to other independent datasets. In this paper, we propose a network-based Cox regression model called Net-Cox and applied Net-Cox for a large-scale survival analysis across multiple ovarian cancer datasets. Net-Cox integrates gene network information into the Cox's proportional hazard model to explore the co-expression or functional relation among high-dimensional gene expression features in the gene network. Net-Cox was applied to analyze three independent gene expression datasets including the TCGA ovarian cancer dataset and two other public ovarian cancer datasets. Net-Cox with the network information from gene co-expression or functional relations identified highly consistent signature genes across the three datasets, and because of the better generalization across the datasets, Net-Cox also consistently improved the accuracy of survival prediction over the Cox models regularized by L1-norm or L2-norm. This study focused on analyzing the death and recurrence outcomes in the treatment of ovarian carcinoma to identify signature genes that can more reliably predict the events. The signature genes comprise dense protein-protein interaction subnetworks, enriched by extracellular matrix receptors and modulators or by nuclear signaling components downstream of extracellular signal-regulated kinases. In the laboratory validation of the signature genes, a tumor array experiment by protein staining on an independent patient cohort from Mayo Clinic showed that the protein expression of the signature gene FBN1 is a biomarker significantly associated with the early recurrence after 12 months of the treatment in the ovarian cancer patients who are initially sensitive to chemotherapy. Net-Cox toolbox is available at http://localhost/~raphaelpetegrosso/wpcb/Net-Cox/.},

keywords = {Survival Analysis},

pubstate = {published},

tppubtype = {article}

}

@article{hwang2012co,

title = {Co-clustering phenome--genome for phenotype classification and disease gene discovery},

author = {TaeHyun Hwang and Gowtham Atluri and MaoQiang Xie and Sanjoy Dey and Changjin Hong and Vipin Kumar and Rui Kuang},

url = {http://nar.oxfordjournals.org/content/40/19/e146.short},

doi = {10.1093/nar/gks615},

year  = {2012},

date = {2012-06-26},

journal = {Nucleic acids research},

volume = {40},

number = {19},

pages = {e146--e146},

publisher = {Oxford Univ Press},

abstract = {Understanding the categorization of human diseases is critical for reliably identifying disease causal genes. Recently, genome-wide studies of abnormal chromosomal locations related to diseases have mapped >2000 phenotype–gene relations, which provide valuable information for classifying diseases and identifying candidate genes as drug targets. In this article, a regularized non-negative matrix tri-factorization (R-NMTF) algorithm is introduced to co-cluster phenotypes and genes, and simultaneously detect associations between the detected phenotype clusters and gene clusters. The R-NMTF algorithm factorizes the phenotype–gene association matrix under the prior knowledge from phenotype similarity network and protein–protein interaction network, supervised by the label information from known disease classes and biological pathways. In the experiments on disease phenotype–gene associations in OMIM and KEGG disease pathways, R-NMTF significantly improved the classification of disease phenotypes and disease pathway genes compared with support vector machines and Label Propagation in cross-validation on the annotated phenotypes and genes. The newly predicted phenotypes in each disease class are highly consistent with human phenotype ontology annotations. The roles of the new member genes in the disease pathways are examined and validated in the protein–protein interaction subnetworks. Extensive literature review also confirmed many new members of the disease classes and pathways as well as the predicted associations between disease phenotype classes and pathways.},

keywords = {Phenome-genome Association},

pubstate = {published},

tppubtype = {article}

}

@article{cai2011proteases,

title = {Proteases in malaria parasites-a phylogenomic perspective},

author = {Hong Cai and Rui Kuang and Jianying Gu and Yufeng Wang},

url = {http://www.ingentaconnect.com/content/ben/cg/2011/00000012/00000006/art00005},

doi = {10.2174/138920211797248565},

year  = {2011},

date = {2011-09-01},

journal = {Current genomics},

volume = {12},

number = {6},

pages = {417--427},

publisher = {Bentham Science Publishers},

abstract = {Malaria continues to be one of the most devastating global health problems due to the high morbidity and mortality it causes in endemic regions. The search for new antimalarial targets is of high priority because of the increasing prevalence of drug resistance in malaria parasites. Malarial proteases constitute a class of promising therapeutic targets as they play important roles in the parasite life cycle and it is possible to design and screen for specific protease inhibitors. In this mini-review, we provide a phylogenomic overview of malarial proteases. An evolutionary perspective on the origin and divergence of these proteases will provide insights into the adaptive mechanisms of parasite growth, development, infection, and pathogenesis.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hwang2011inferring,

title = {Inferring disease and gene set associations with rank coherence in networks},

author = {TaeHyun Hwang and Wei Zhang and Maoqiang Xie and Jinfeng Liu and Rui Kuang},

url = {http://bioinformatics.oxfordjournals.org/content/27/19/2692},

doi = {10.1093/bioinformatics/btr463},

year  = {2011},

date = {2011-08-02},

journal = {Bioinformatics},

volume = {27},

number = {19},

pages = {2692--2699},

publisher = {Oxford Univ Press},

abstract = {Motivation: To validate the candidate disease genes identified from high-throughput genomic studies, a necessary step is to elucidate the associations between the set of candidate genes and disease phenotypes. The conventional gene set enrichment analysis often fails to reveal associations between disease phenotypes and the gene sets with a short list of poorly annotated genes, because the existing annotations of disease-causative genes are incomplete. This article introduces a network-based computational approach called rcNet to discover the associations between gene sets and disease phenotypes. A learning framework is proposed to maximize the coherence between the predicted phenotype–gene set relations and the known disease phenotype-gene associations. An efficient algorithm coupling ridge regression with label propagation and two variants are designed to find the optimal solution to the objective functions of the learning framework. 

 

Results: We evaluated the rcNet algorithms with leave-one-out cross-validation on Online Mendelian Inheritance in Man (OMIM) data and an independent test set of recently discovered disease–gene associations. In the experiments, the rcNet algorithms achieved best overall rankings compared with the baselines. To further validate the reproducibility of the performance, we applied the algorithms to identify the target diseases of novel candidate disease genes obtained from recent studies of Genome-Wide Association Study (GWAS), DNA copy number variation analysis and gene expression profiling. The algorithms ranked the target disease of the candidate genes at the top of the rank list in many cases across all the three case studies.},

keywords = {Phenome-genome Association},

pubstate = {published},

tppubtype = {article}

}

@article{jacko2011community,

title = {Community engagement and outreach as curricular and pedagogical tools for consortial delivery of health informatics curricula},

author = {Julie A Jacko and Layne M Johnson and Terrence J Adam and Adel L Ali and Daniel Chan and Rui Kuang and Andrew F Nelson and Amy Watters and Bonnie Westra and Sally Fauchald and others},

url = {http://www.inderscienceonline.com/doi/abs/10.1504/IJIOME.2011.044616},

doi = {10.1504/IJIOME.2011.044616},

issn = {1744-2311},

year  = {2011},

date = {2011-01-01},

journal = {International Journal of Information and Operations Management Education},

volume = {4},

number = {3-4},

pages = {284--308},

publisher = {Inderscience Publishers},

abstract = {The objective of this paper is to identify and characterise two grand challenges in the consortial delivery of health informatics curricula: (a) challenges of curriculum and pedagogy and (b) challenges of community engagement. We discovered that we could broadly depict the first challenge along four dimensions and the second challenge along six dimensions. Solutions to these challenges are provided along with a depiction of how the solutions have been successfully implemented in the University Partnership for Health Informatics, a university-based training programme funded by the Office of the National Coordinator for Health Information Technology.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}