@article{Lopes2012, abstract = {<i>Aims:</i> Next-generation sequencing has opened the possibility of large-scale sequence-based disease association studies. A major challenge in interpreting whole-exome data is predicting which of the discovered variants are deleterious or neutral. To address this question in silico, we have developed a score called Combined Annotation scoRing toOL (CAROL), which combines information from 2 bioinformatics tools: PolyPhen-2 and SIFT, in order to improve the prediction of the effect of non-synonymous coding variants. <i>Methods:</i> We used a weighted <i>Z</i> method that combines the probabilistic scores of PolyPhen-2 and SIFT. We defined 2 dataset pairs to train and test CAROL using information from the dbSNP: ‘HGMD-PUBLIC’ and 1000 Genomes Project databases. The training pair comprises a total of 980 positive control (disease-causing) and 4,845 negative control (non-disease-causing) variants. The test pair consists of 1,959 positive and 9,691 negative controls.<i> Results:</i> CAROL has higher predictive power and accuracy for the effect of non-synonymous variants than each individual annotation tool (PolyPhen-2 and SIFT) and benefits from higher coverage. <i>Conclusion:</i> The combination of annotation tools can help improve automated prediction of whole-genome/exome non-synonymous variant functional consequences.}, author = {Lopes, Margarida C. and Joyce, Chris and Ritchie, Graham R. S. and John, Sally L. and Cunningham, Fiona and Asimit, Jennifer and Zeggini, Eleftheria}, doi = {10.1159/000334984}, journal = {Human Heredity}, month = {jan}, pages = {47-51}, title = {A Combined Functional Annotation Score for Non-Synonymous Variants}, url = {http://www.ncbi.nlm.nih.gov/pubmed/22261837}, volume = {73}, year = {2012} }