Gene expression profiles are commonly utilized to infer disease subtypes and many clustering methods can be adopted for this task. However, existing clustering methods may not perform well when genes are highly correlated and many uninformative genes are included for clustering. To deal with these challenges, we develop a novel clustering method in the Bayesian setting. This method, called BCSub, adopts an innovative semiparametric Bayesian factor analysis model to reduce the dimension of the data to a few factor scores for clustering. Specifically, the factor scores are assumed to follow the Dirichlet process mixture model in order to induce clustering.
|Author||Jiehuan Sun [aut, cre], Joshua L. Warren [aut], and Hongyu Zhao [aut]|
|Date of publication||2017-01-20 10:46:47|
|Maintainer||Jiehuan Sun <firstname.lastname@example.org>|
BCSub: A Bayesian semiparametric factor analysis model for subtype...
calSim: Function to calculate the similarity matrix based on the...
dmvnrm_arma: Internal function to calculate the density of multivariate...
mvrnormArma: Internal function to sample from multivariate normal...
myfind: Internal function to find matched index.
polyurncpp: Internal function to sample cluster membership indicator
samEta: Internal function to sample eta
samLamV3Cpp: Internal function to sample Lambda
samMu: Internal function to sample cluster-specific means of eta
samRho2: Internal function to sample rho
samSig: Internal function to sample gene-specific variances
samSige: Internal function to sample variances for eta