PANTHER: a library of protein families and subfamilies indexed by function. Export

@article{Thomas2003, abstract = {In the genomic era, one of the fundamental goals is to characterize the function of proteins on a large scale. We describe a method, PANTHER, for relating protein sequence relationships to function relationships in a robust and accurate way. PANTHER is composed of two main components: the PANTHER library (PANTHER/LIB) and the PANTHER index (PANTHER/X). PANTHER/LIB is a collection of "books," each representing a protein family as a multiple sequence alignment, a Hidden Markov Model (HMM), and a family tree. Functional divergence within the family is represented by dividing the tree into subtrees based on shared function, and by subtree HMMs. PANTHER/X is an abbreviated ontology for summarizing and navigating molecular functions and biological processes associated with the families and subfamilies. We apply PANTHER to three areas of active research. First, we report the size and sequence diversity of the families and subfamilies, characterizing the relationship between sequence divergence and functional divergence across a wide range of protein families. Second, we use the PANTHER/X ontology to give a high-level representation of gene function across the human and mouse genomes. Third, we use the family HMMs to rank missense single nucleotide polymorphisms (SNPs), on a database-wide scale, according to their likelihood of affecting protein function.}, address = {Protein Informatics, Celera Genomics, Foster City, California 94404, USA. paul.thomas@fc.celera.com}, author = {Thomas, P. D. and Campbell, M. J. and Kejariwal, A. and Mi, H. and Karlak, B. and Daverman, R. and Diemer, K. and Muruganujan, A. and Narechania, A.}, citeulike-article-id = {1187125}, citeulike-linkout-0 = {http://dx.doi.org/10.1101/gr.772403}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/12952881}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=12952881}, doi = {10.1101/gr.772403}, issn = {1088-9051}, journal = {Genome Res}, keywords = {database, family, hmm, method, protein}, month = {September}, number = {9}, pages = {2129--2141}, posted-at = {2009-04-06 18:23:19}, priority = {2}, title = {PANTHER: a library of protein families and subfamilies indexed by function.}, url = {http://dx.doi.org/10.1101/gr.772403}, volume = {13}, year = {2003} }

TY - JOUR ID - Thomas2003 L3 - citeulike-article-id:1187125 N2 - In the genomic era, one of the fundamental goals is to characterize the function of proteins on a large scale. We describe a method, PANTHER, for relating protein sequence relationships to function relationships in a robust and accurate way. PANTHER is composed of two main components: the PANTHER library (PANTHER/LIB) and the PANTHER index (PANTHER/X). PANTHER/LIB is a collection of "books," each representing a protein family as a multiple sequence alignment, a Hidden Markov Model (HMM), and a family tree. Functional divergence within the family is represented by dividing the tree into subtrees based on shared function, and by subtree HMMs. PANTHER/X is an abbreviated ontology for summarizing and navigating molecular functions and biological processes associated with the families and subfamilies. We apply PANTHER to three areas of active research. First, we report the size and sequence diversity of the families and subfamilies, characterizing the relationship between sequence divergence and functional divergence across a wide range of protein families. Second, we use the PANTHER/X ontology to give a high-level representation of gene function across the human and mouse genomes. Third, we use the family HMMs to rank missense single nucleotide polymorphisms (SNPs), on a database-wide scale, according to their likelihood of affecting protein function. IS - 9 JF - Genome Res SN - 1088-9051 AD - Protein Informatics, Celera Genomics, Foster City, California 94404, USA. paul.thomas@fc.celera.com EP - 2141 TI - PANTHER: a library of protein families and subfamilies indexed by function. VL - 13 SP - 2129 KW - database KW - family KW - hmm KW - method KW - protein AU - Thomas, PD AU - Campbell, MJ AU - Kejariwal, A AU - Mi, H AU - Karlak, B AU - Daverman, R AU - Diemer, K AU - Muruganujan, A AU - Narechania, A PY - 2003/09// UR - http://dx.doi.org/10.1101/gr.772403 ER -