The SIFT (Sorting Intolerant from Tolerant) web server is a tool for predicting the effects of amino acid substitutions on protein function. First introduced in 2001, SIFT has become a standard tool for characterizing missense variation. The authors have updated the genome-wide prediction tool and added new features to the insertion/deletion (indel) tool. They also provide accuracy metrics on independent datasets. The SIFT web server is hosted at the Bioinformatics Institute of Singapore and can be accessed at http://sift-dna.org. The server offers various features, including a genome-wide database of predictions for nonsynonymous variants, variant annotation with dbSNP and 1000 Genomes, file format conversion, and an indel prediction tool. The performance of SIFT is assessed using external datasets, and the results show high sensitivity and specificity. The server also includes a standalone version available on the Amazon cloud.The SIFT (Sorting Intolerant from Tolerant) web server is a tool for predicting the effects of amino acid substitutions on protein function. First introduced in 2001, SIFT has become a standard tool for characterizing missense variation. The authors have updated the genome-wide prediction tool and added new features to the insertion/deletion (indel) tool. They also provide accuracy metrics on independent datasets. The SIFT web server is hosted at the Bioinformatics Institute of Singapore and can be accessed at http://sift-dna.org. The server offers various features, including a genome-wide database of predictions for nonsynonymous variants, variant annotation with dbSNP and 1000 Genomes, file format conversion, and an indel prediction tool. The performance of SIFT is assessed using external datasets, and the results show high sensitivity and specificity. The server also includes a standalone version available on the Amazon cloud.