Biomarker Indentification Using Bayesian Variable Selection Based on Marker-expression-proteomics Data

Finding genetic biomarkers and a search of geneticepidemiological factors, can be formulated as a statistical problem of variable selection, where from a large set of candidates a small number of trait-associated predictors are identified. We illustrate this by analyzing the data available for Chronic Fatigue Syndrome (CFS). CFS is a complex disease from several aspects, e.g. difficult to diagnose and difficult to quantify. From the clinical information subjects were classified in No-Fatigue (NF), Insufficient fatigue severity (IFS), Chronic Fatigue (CFS) and others. The additional clinical variables were used as stratifying factors to homogenize the study population. For identification of biomarkers microarray data and SELDI-TOF-based proteomics data were used. Genetic marker information for a large number of SNPs was also analyzed for an overlapping set of individuals. The objectives of the analyses were to identify markers specific to Fatigue which are also possibly exclusive to CFS. The WinBUGS software was used in implementation and parameter estimation of the proposed Bayesian models.