@article {14681398, title = {MODBASE, a database of annotated comparative protein structure models, and associated resources}, journal = {Nucleic Acids Res}, volume = {32}, number = {Database issue}, year = {2004}, note = {Pieper, Ursula Eswar, Narayanan Braberg, Hannes Madhusudhan, M S Davis, Fred P Stuart, Ashley C Mirkovic, Nebojsa Rossi, Andrea Marti-Renom, Marc A Fiser, Andras Webb, Ben Greenblatt, Daniel Huang, Conrad C Ferrin, Thomas E Sali, Andrej P41 RR01081/RR/NCRR NIH HHS/United States P50 GM62529/GM/NIGMS NIH HHS/United States R01 GM 54762/GM/NIGMS NIH HHS/United States R33 CA84699/CA/NCI NIH HHS/United States Research Support, Non-U.S. Gov{\textquoteright}t Research Support, U.S. Gov{\textquoteright}t, P.H.S. England Nucleic acids research Nucleic Acids Res. 2004 Jan 1;32(Database issue):D217-22.}, pages = {D217-22}, abstract = {MODBASE (http://salilab.org/modbase) is a relational database of annotated comparative protein structure models for all available protein sequences matched to at least one known protein structure. The models are calculated by MODPIPE, an automated modeling pipeline that relies on the MODELLER package for fold assignment, sequence-structure alignment, model building and model assessment (http:/salilab.org/modeller). MODBASE uses the MySQL relational database management system for flexible querying and CHIMERA for viewing the sequences and structures (http://www.cgl.ucsf.edu/chimera/). MODBASE is updated regularly to reflect the growth in protein sequence and structure databases, as well as improvements in the software for calculating the models. For ease of access, MODBASE is organized into different data sets. The largest data set contains 1,26,629 models for domains in 659,495 out of 1,182,126 unique protein sequences in the complete Swiss-Prot/TrEMBL database (August 25, 2003); only models based on alignments with significant similarity scores and models assessed to have the correct fold despite insignificant alignments are included. Another model data set supports target selection and structure-based annotation by the New York Structural Genomics Research Consortium; e.g. the 53 new structures produced by the consortium allowed us to characterize structurally 24,113 sequences. MODBASE also contains binding site predictions for small ligands and a set of predicted interactions between pairs of modeled sequences from the same genome. Our other resources associated with MODBASE include a comprehensive database of multiple protein structure alignments (DBALI, http://salilab.org/dbali) as well as web servers for automated comparative modeling with MODPIPE (MODWEB, http://salilab. org/modweb), modeling of loops in protein structures (MODLOOP, http://salilab.org/modloop) and predicting functional consequences of single nucleotide polymorphisms (SNPWEB, http://salilab. org/snpweb).}, keywords = {Amino Acid Sequence Animals Binding Sites *Computational Biology *Databases, Molecular Molecular Sequence Data Polymorphism, Protein Genomics Humans Internet Ligands Models, Single Nucleotide Protein Binding Protein Conformation Proteins/*chemistry/genetics Sequence Alignment Software User-Computer Interface}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=14681398}, author = {Pieper, U. and Eswar, N. and Braberg, H. and Madhusudhan, M. S. and Davis, F. P. and Stuart, A. C. and Mirkovic, N. and Rossi, A. and M. A. Marti-Renom and Fiser, A. and Webb, B. and Greenblatt, D. and Huang, C. C. and Ferrin, T. E. and Sali, A.} }