APDB: a novel measure for benchmarking sequence alignment methods without reference alignments

TitleAPDB: a novel measure for benchmarking sequence alignment methods without reference alignments
Publication TypeJournal Article
Year of Publication2003
AuthorsO'Sullivan O, Zehnder M, Higgins D, Bucher P, Grosdidier A, Notredame C
JournalBioinformatics
Volume19 Suppl 1
Paginationi215-21
Accession Number12855461
KeywordsAlgorithms, Amino Acid Sequence, Benchmarking/ methods, Molecular Sequence Data, Reference Standards, Reproducibility of Results, Sensitivity and Specificity, Sequence Alignment/ methods/standards, Sequence Analysis, DNA/ methods/standards, Sequence Analysis, Protein/ methods/standards, Sequence Homology, Software, Software Validation
Abstract

MOTIVATION: We describe APDB, a novel measure for evaluating the quality of a protein sequence alignment, given two or more PDB structures. This evaluation does not require a reference alignment or a structure superposition. APDB is designed to efficiently and objectively benchmark multiple sequence alignment methods. RESULTS: Using existing collections of reference multiple sequence alignments and existing alignment methods, we show that APDB gives results that are consistent with those obtained using conventional evaluations. We also show that APDB is suitable for evaluating sequence alignments that are structurally equivalent. We conclude that APDB provides an alternative to more conventional methods used for benchmarking sequence alignment packages.