Learning and modeling biosignatures from tissue images.

Ideally biosignatures can be detected at the early infection phase and used both for developing diagnostic patterns and for prognostic triage. Such biosignatures are important for vaccine validation and to provide risk stratification to a population such as for the identification of individuals who are exposed to biological or chemical agents and who are at high risk for developing an infection. The research goal is to detect broad based biosignature models and is initially focused on developing effective computer-augmented pathology tied to animal models developed at the University of New Mexico (UNM).

A Bayesian network classification methodology for gene expression data.

We present new techniques for the application of a Bayesian network learning framework to the problem of classifying gene expression data. The focus on classification permits us to develop techniques that address in several ways the complexities of learning Bayesian nets. Our classification model reduces the Bayesian network learning problem to the problem of learning multiple subnetworks, each consisting of a class label node and its set of parent genes.