One of the goals the post-genomic era is to use protein sequence and structure data to learn about the function of these proteins in normal and disease states. In the ¿omics¿ era, computational methods constitute a valuable tool, because they can easily process large amounts of data and provide useful and instant information relevant in biomedical research. This book described using computational approaches to study the effects of genetic mutations in proteins, with the general aim of correlating protein sequence, structure, and function. Our works focus on identifying whether genotype/phenotype relationship can be learned from protein sequence and structural information, whether protein structure prediction methods are accurate enough to provide useful information when the experimental structures are not available, and finally to combine this information to predict and understand the effect of mutations on clinical phenotype and drug responses. The approaches developed in this work enable a systematic, comprehensive, and quantitative analysis of disease-related mutations and establish a paradigm to study genotype/phenotype correlations.