• Corpus ID: 3783471

Network-based Distance Metric with Application to Discover Disease Subtypes in Cancer

@article{Qiang2017NetworkbasedDM,
  title={Network-based Distance Metric with Application to Discover Disease Subtypes in Cancer},
  author={Jipeng Qiang and Wei Ding and John Quackenbush and Ping Chen},
  journal={ArXiv},
  year={2017},
  volume={abs/1703.01900}
}
While we once thought of cancer as single monolithic diseases affecting a specific organ site, we now understand that there are many subtypes of cancer defined by unique patterns of gene mutations. These gene mutational data, which can be more reliably obtained than gene expression data, help to determine how the subtypes develop, evolve, and respond to therapies. Different from dense continuous-value gene expression data, which most existing cancer subtype discovery algorithms use, somatic… 

Figures and Tables from this paper

R-PathCluster: Identifying cancer subtype of glioblastoma multiforme using pathway-based restricted boltzmann machine
TLDR
A pathway-based clustering method using Restricted Boltzmann Machine (RBM), called R-PathCluster, for identifying unknown subtypes with pathway markers of gene expressions, which provides a solution to interpret the model in biological sense, since it takes pathway markers that represent biological process of pathways.

References

SHOWING 1-10 OF 40 REFERENCES
Network-based stratification of tumor mutations
TLDR
This work introduces network-based stratification (NBS), a method to integrate somatic tumor genomes with gene networks that allows for stratification of cancer into informative subtypes by clustering together patients with mutations in similar network regions.
Prioritizing candidate disease genes by network-based boosting of genome-wide association data.
TLDR
It is demonstrated that a functional network of human genes provides a valuable statistical framework for prioritizing candidate disease genes, both for candidate gene-based and GWAS-based studies.
Metagenes and molecular pattern discovery using matrix factorization
TLDR
Nonnegative matrix factorization is described, an algorithm based on decomposition by parts that can reduce the dimension of expression data from thousands of genes to a handful of metagenes, and found less sensitive to a priori selection of genes or initial conditions and able to detect alternative or context-dependent patterns of gene expression in complex biological systems.
Somatic mutations in cancer prognosis and prediction: lessons from TP53 and EGFR genes
TLDR
With the accumulation of knowledge on the predictive and prognostic value of somatic mutations, and with recent advances in large-scale sequencing techniques and reduction in cost of sequencing, sequencing several genes in human tumors is on the verge of becoming routine clinical practice.
Integrated Genomic Analyses of Ovarian Carcinoma
TLDR
It is reported that high-grade serous ovarian cancer is characterized by TP53 mutations in almost all tumours (96%); low prevalence but statistically recurrent somatic mutations in nine further genes including NF1, BRCA1,BRCA2, RB1 and CDK12; 113 significant focal DNA copy number aberrations; and promoter methylation events involving 168 genes.
Non-negative matrix factorization by maximizing correntropy for cancer clustering
TLDR
The proposed NMF-MCC method is significantly more accurate than the state-of-the-art methods in cancer clustering and maximizes the correntropy between the product of the two matrices and the original matrix.
Comprehensive molecular characterization of human colon and rectal cancer
TLDR
Integrative analyses suggest new markers for aggressive colorectal carcinoma and an important role for MYC-directed transcriptional activation and repression.
The STRING database in 2011: functional interaction networks of proteins, globally integrated and scored
TLDR
An update on the online database resource Search Tool for the Retrieval of Interacting Genes (STRING), which provides uniquely comprehensive coverage and ease of access to both experimental as well as predicted interaction information.
Gene expression profile of BRCAness that correlates with responsiveness to chemotherapy and with outcome in patients with epithelial ovarian cancer.
TLDR
The BRCAness profile correlates with responsiveness to platinum and PARP inhibitors and identifies a subset of sporadic patients with improved outcome and is validated in 70 patients enriched for sporadic disease.
Simultaneous Discovery of Common and Discriminative Topics via Joint Nonnegative Matrix Factorization
TLDR
A novel topic modeling method based on joint nonnegative matrix factorization, which simultaneously discovers common as well as discriminative topics given multiple document sets and is capable of utilizing only the most representative, thus meaningful, keywords in each topic through a novel pseudo-deflation approach.
...
...