Controlled vocabularies in bioinformatics: a case study in the gene ontology Export

@article{citeulike:5486633, abstract = {The automatic integration of information resources in the life sciences is one of the most challenging goals facing biomedical informatics today. Controlled vocabularies have played an important role in realizing this goal, by making it possible to draw together information from heterogeneous sources secure in the knowledge that the same terms will also represent the same entities on all occasions of use. One of the most impressive achievements in this regard is the Gene Ontology (GO), which is rapidly acquiring the status of a de facto standard in the field of gene and gene product annotations, and whose methodology has been much intimated in attempts to develop controlled vocabularies for shared use in different domains of biology. The GO Consortium has recognized, however, that its controlled vocabulary as currently constituted is marked by several problematic features - features which are characteristic of much recent work in bioinformatics and which are destined to raise increasingly serious obstacles to the automatic integration of biomedical information in the future. Here, we survey some of these problematic features, focusing especially on issues of compositionality and syntactic regimentation.}, author = {Smith, B. and Kumar, A.}, citeulike-article-id = {5486633}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/S1741-8364(04)02424-2}, citeulike-linkout-1 = {http://linkinghub.elsevier.com/retrieve/pii/S1741836404024242}, doi = {10.1016/S1741-8364(04)02424-2}, issn = {17418364}, journal = {Drug Discovery Today: BIOSILICO}, keywords = {biology, classification, controlled, genetics, ontology, vocabularies}, month = {November}, number = {6}, pages = {246--252}, posted-at = {2009-08-19 14:29:23}, priority = {0}, title = {Controlled vocabularies in bioinformatics: a case study in the gene ontology}, url = {http://dx.doi.org/10.1016/S1741-8364(04)02424-2}, volume = {2}, year = {2004} }

TY - JOUR ID - citeulike:5486633 L3 - citeulike-article-id:5486633 N2 - The automatic integration of information resources in the life sciences is one of the most challenging goals facing biomedical informatics today. Controlled vocabularies have played an important role in realizing this goal, by making it possible to draw together information from heterogeneous sources secure in the knowledge that the same terms will also represent the same entities on all occasions of use. One of the most impressive achievements in this regard is the Gene Ontology (GO), which is rapidly acquiring the status of a de facto standard in the field of gene and gene product annotations, and whose methodology has been much intimated in attempts to develop controlled vocabularies for shared use in different domains of biology. The GO Consortium has recognized, however, that its controlled vocabulary as currently constituted is marked by several problematic features - features which are characteristic of much recent work in bioinformatics and which are destined to raise increasingly serious obstacles to the automatic integration of biomedical information in the future. Here, we survey some of these problematic features, focusing especially on issues of compositionality and syntactic regimentation. IS - 6 JF - Drug Discovery Today: BIOSILICO SN - 17418364 EP - 252 TI - Controlled vocabularies in bioinformatics: a case study in the gene ontology VL - 2 SP - 246 KW - biology KW - classification KW - controlled KW - genetics KW - ontology KW - vocabularies AU - Smith, B AU - Kumar, A PY - 2004/11// UR - http://dx.doi.org/10.1016/S1741-8364(04)02424-2 ER -