Outcome-guided Bayesian Clustering for Disease Subtype Discovery Using High-dimensional Transcriptomic Data

by   Lingsong Meng, et al.

The discovery of disease subtypes is an essential step for developing precision medicine, and disease subtyping via omics data has become a popular approach. While promising, subtypes obtained from conventional approaches may not be necessarily associated with clinical outcomes. The collection of rich clinical data along with omics data has provided an unprecedented opportunity to facilitate the disease subtyping process and to discovery clinically meaningful disease subtypes. Thus, we developed an outcome-guided Bayesian clustering (GuidedBayesianClustering) method to fully integrate the clinical data and the high-dimensional omics data. A Gaussian mixed model framework was applied to perform sample clustering; a spike-and-slab prior was utilized to perform gene selection; a mixture model prior was employed to incorporate the guidance from a clinical outcome variable; and a decision framework was adopted to infer the false discovery rate of the selected genes. We deployed conjugate priors to facilitate efficient Gibbs sampling. Our proposed full Bayesian method is capable of simultaneously (i) obtaining sample clustering (disease subtype discovery); (ii) performing feature selection (select genes related to the disease subtype); and (iii) utilizing clinical outcome variable to guide the disease subtype discovery. The superior performance of the GuidedBayesianClustering was demonstrated through simulations and applications of breast cancer expression data.


page 19

page 20


Outcome-guided Sparse K-means for Disease Subtype Discovery via Integrating Phenotypic Data with High-dimensional Transcriptomic Data

The discovery of disease subtypes is an essential step for developing pr...

Outcome-Guided Disease Subtyping for High-Dimensional Omics Data

High-throughput microarray and sequencing technology have been used to i...

Bayesian outcome-guided multi-view mixture models with applications in molecular precision medicine

Clustering is commonly performed as an initial analysis step for uncover...

A Pipeline for Integrated Theory and Data-Driven Modeling of Genomic and Clinical Data

High throughput genome sequencing technologies such as RNA-Seq and Micro...

JigSaw: A tool for discovering explanatory high-order interactions from random forests

Machine learning is revolutionizing biology by facilitating the predicti...

Evaluation of network-guided random forest for disease gene discovery

Gene network information is believed to be beneficial for disease module...

Bayesian tensor factorization for predicting clinical outcomes using integrated human genetics evidence

The approval success rate of drug candidates is very low with the majori...

Please sign up or login with your details

Forgot password? Click here to reset