Bayesian clustering of multivariate immunological data

Given a dataset of B cell subpopulation quantities, for aboutsix thousand patients, that is a cross-sectional immunological dataset,here we detect clusters representing models of immune system states inan unsupervised way (i.e., according only to their different statisticalproperties). Two time-evolving B cell networks are also generated fromdata-driven hidden Markov models, with four and five hidden states,respectively. Our interpretation from a biomedical viewpoint of the sta-tistical parameters of the Bayesian models confirms an age related declineof some types of B cell functions and finds out a class of old patients withunexpected B cell values.