PolyPhen-2 is a tool that predicts the functional impact of amino acid substitutions on human proteins using structural and evolutionary considerations. It performs functional annotation of single-nucleotide polymorphisms (SNPs), maps coding SNPs to gene transcripts, extracts protein sequence annotations and structural attributes, and builds conservation profiles to estimate the probability of a missense mutation being damaging. PolyPhen-2 features include a high-quality multiple protein sequence alignment pipeline and a machine-learning classification method. The software integrates UCSC Genome Browser annotations and MultiZ multiple alignments of vertebrate genomes with the human genome. It supports large datasets from next-generation sequencing projects through built-in support for high-performance computing environments like Grid Engine and Platform LSF. The article outlines three basic protocols for using PolyPhen-2 through its web interface: predicting the effect of a single-residue substitution or reference SNP, analyzing a large number of SNPs in batch mode, and searching a database of precomputed predictions for the whole human exome sequence space (WHESS.db). It also provides alternate protocols for installing and using the standalone version of the software on a Linux computer, as well as support protocols for checking the status of queries and updating built-in databases.PolyPhen-2 is a tool that predicts the functional impact of amino acid substitutions on human proteins using structural and evolutionary considerations. It performs functional annotation of single-nucleotide polymorphisms (SNPs), maps coding SNPs to gene transcripts, extracts protein sequence annotations and structural attributes, and builds conservation profiles to estimate the probability of a missense mutation being damaging. PolyPhen-2 features include a high-quality multiple protein sequence alignment pipeline and a machine-learning classification method. The software integrates UCSC Genome Browser annotations and MultiZ multiple alignments of vertebrate genomes with the human genome. It supports large datasets from next-generation sequencing projects through built-in support for high-performance computing environments like Grid Engine and Platform LSF. The article outlines three basic protocols for using PolyPhen-2 through its web interface: predicting the effect of a single-residue substitution or reference SNP, analyzing a large number of SNPs in batch mode, and searching a database of precomputed predictions for the whole human exome sequence space (WHESS.db). It also provides alternate protocols for installing and using the standalone version of the software on a Linux computer, as well as support protocols for checking the status of queries and updating built-in databases.