Sensitivity improvement in molecular genetic analysis has led to increased detection of novel sequence variants of unknown clinical significance in disease related genes. These unclassified variants (UVs) can often induce pathogenesis by mutating the protein product of the gene. However, they can also manifest non-pathogenic or neutral effects, coding for amino acid changes which do not significantly affect the protein product. Diagnostic laboratories have great difficulty to identify whether an UV is pathogenic or not. Significant characterization of such variants represents a major challenge for medical management of patients in whom they are identified. Functional assays may help to prove whether an UV cause pathogenicity, but these analyses are tedious and laborious. Conversely, in silico prediction tools are very useful to perform a fast bioinformatics analysis which can predict the pathogenicity of a variant based on the change to an amino acid. Despite the amount of in silico tools, only a small number of these are regularly used by genetic testing laboratories. Practice guidelines at the Clinical Molecular Genetics Society for analysis of UVs (UK CMGS UV guidelines) recommend the use of AGVGD, SIFT and Polyphen, but it is unknown whether these are the most useful methods. The aim of the present study was the ability assessment of several in silico bioinformatics tools to accurately predict both pathogenic and neutral missense variants.