PolyPhen-2 is a tool for predicting the impact of amino acid substitutions on human protein structure and function. It uses structural and evolutionary data to assess the likelihood of a missense mutation being damaging. The tool integrates with the UCSC Genome Browser and supports next-generation sequencing data analysis. It provides three basic protocols for use: (1) predicting the effect of a single-residue substitution, (2) analyzing a large number of SNPs in batch mode, and (3) searching a precomputed database of predictions for the entire human exome. It also includes support protocols for checking query status and updating built-in databases. Alternate protocols describe automated batch submission and standalone software installation. The standalone version requires Perl, BLAST+, and other tools, and involves downloading and installing databases. The analysis pipeline includes three components: MapSNPs for genomic SNP annotation, run_pph.pl for protein variant annotation, and run_weka.pl for probabilistic classification. The tool is used to predict the functional effect of SNPs, which is crucial for understanding genetic variation and its impact on human health.PolyPhen-2 is a tool for predicting the impact of amino acid substitutions on human protein structure and function. It uses structural and evolutionary data to assess the likelihood of a missense mutation being damaging. The tool integrates with the UCSC Genome Browser and supports next-generation sequencing data analysis. It provides three basic protocols for use: (1) predicting the effect of a single-residue substitution, (2) analyzing a large number of SNPs in batch mode, and (3) searching a precomputed database of predictions for the entire human exome. It also includes support protocols for checking query status and updating built-in databases. Alternate protocols describe automated batch submission and standalone software installation. The standalone version requires Perl, BLAST+, and other tools, and involves downloading and installing databases. The analysis pipeline includes three components: MapSNPs for genomic SNP annotation, run_pph.pl for protein variant annotation, and run_weka.pl for probabilistic classification. The tool is used to predict the functional effect of SNPs, which is crucial for understanding genetic variation and its impact on human health.