DNA variation that results in a single amino-acid residue change in the protein product of a gene (missense mutant) may have a major impact on an individual’s susceptibility to disease and sensitivity to drugs. Many such variants occur at very low population frequencies, thus case/control and familial cosegregation studies are not sufficiently powered to discriminate between those which are pathogenic/high clinical significance vs. neutral/low clinical significance. A promising alternative approach is to integrate information derived from computational biology with clinical patient data and functional studies. I will describe work that applies protein homology modeling, sequence analysis, and machine learning to predict and rationalize the impact of missense mutations on protein stability and function. These predictions can complement information from patient pedigrees and help make sense of the results of functional assays. I will also discuss how the process can be automated and applied to large-scale datasets.