Predicting protein function from domain content

@article{citeulike:2946162, abstract = {Motivation: Computational assignment of protein function may be the single most vital application of bioinformatics in the post-genome era. These assignments are made based on various protein features, where one is the presence of identifiable domains. The relationship between protein domain content and function is important to investigate to understand how domain combinations encode complex functions. Results: Two different models are presented for how protein domain combinations yield specific functions: one rule-based and one probabilistic. We demonstrate how these are useful for Gene Ontology annotation transfer. The first is an intuitive generalization of the Pfam2GO mapping, and detects cases of strict functional implications of sets of domains. The second uses a probabilistic model to represent the relationship between domain content and annotation terms, and was found to be better suited for incomplete training sets. We implemented these models as predictors of Gene Ontology functional annotation terms. Both predictors were more accurate than conventional best BLAST-hit annotation transfer and more sensitive than a single-domain model on a large-scale dataset. We present a number of cases where combinations of Pfam-A protein domains predict functional terms that do not follow from the individual domains. Availability: Scripts and documentation are available for download at http://sonnhammer.sbc.su.se/multipfam2go\_source\_docs.tar Contact: Kristoffer.Forslund@sbc.su.se Supplementary Information: Table S1 10.1093/bioinformatics/btn312}, author = {Forslund, Kristoffer and Sonnhammer, Erik L. }, citeulike-article-id = {2946162}, doi = {10.1093/bioinformatics/btn312}, journal = {Bioinformatics}, keywords = {domain, prediction, protein}, month = {June}, pages = {btn312+}, posted-at = {2008-07-01 02:44:42}, priority = {3}, title = {Predicting protein function from domain content}, url = {http://dx.doi.org/10.1093/bioinformatics/btn312}, year = {2008} }

TY - JOUR ID - citeulike:2946162 L3 - citeulike-article-id:2946162 TI - Predicting protein function from domain content JF - Bioinformatics SP - btn312 N2 - Motivation: Computational assignment of protein function may be the single most vital application of bioinformatics in the post-genome era. These assignments are made based on various protein features, where one is the presence of identifiable domains. The relationship between protein domain content and function is important to investigate to understand how domain combinations encode complex functions. Results: Two different models are presented for how protein domain combinations yield specific functions: one rule-based and one probabilistic. We demonstrate how these are useful for Gene Ontology annotation transfer. The first is an intuitive generalization of the Pfam2GO mapping, and detects cases of strict functional implications of sets of domains. The second uses a probabilistic model to represent the relationship between domain content and annotation terms, and was found to be better suited for incomplete training sets. We implemented these models as predictors of Gene Ontology functional annotation terms. Both predictors were more accurate than conventional best BLAST-hit annotation transfer and more sensitive than a single-domain model on a large-scale dataset. We present a number of cases where combinations of Pfam-A protein domains predict functional terms that do not follow from the individual domains. Availability: Scripts and documentation are available for download at http://sonnhammer.sbc.su.se/multipfam2go_source_docs.tar Contact: Kristoffer.Forslund@sbc.su.se Supplementary Information: Table S1 10.1093/bioinformatics/btn312 KW - domain KW - prediction KW - protein AU - Forslund, Kristoffer AU - Sonnhammer, Erik PY - 2008/06/30/ UR - http://dx.doi.org/10.1093/bioinformatics/btn312 ER -