Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
5
pubmed:dateCreated
2010-2-25
pubmed:abstractText
MOTIVATION: The identification of catalytic residues is a key step in understanding the function of enzymes. While a variety of computational methods have been developed for this task, accuracies have remained fairly low. The best existing method exploits information from sequence and structure to achieve a precision (the fraction of predicted catalytic residues that are catalytic) of 18.5% at a corresponding recall (the fraction of catalytic residues identified) of 57% on a standard benchmark. Here we present a new method, Discern, which provides a significant improvement over the state-of-the-art through the use of statistical techniques to derive a model with a small set of features that are jointly predictive of enzyme active sites. RESULTS: In cross-validation experiments on two benchmark datasets from the Catalytic Site Atlas and CATRES resources containing a total of 437 manually curated enzymes spanning 487 SCOP families, Discern increases catalytic site recall between 12% and 20% over methods that combine information from both sequence and structure, and by >or=50% over methods that make use of sequence conservation signal only. Controlled experiments show that Discern's improvement in catalytic residue prediction is derived from the combination of three ingredients: the use of the INTREPID phylogenomic method to extract conservation information; the use of 3D structure data, including features computed for residues that are proximal in the structure; and a statistical regularization procedure to prevent overfitting.
pubmed:grant
pubmed:commentsCorrections
http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-10815774, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-11292355, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-11478868, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-11575940, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-11588250, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-11606719, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-12181318, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-12421562, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-12475199, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-12662930, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-12850142, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-1438297, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-14630653, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-14681372, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-14681376, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-14681391, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-14980020, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-15010543, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-15033369, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-15037084, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-15201051, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-15201400, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-15318951, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-15456910, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-1546324, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-1554694, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-15701681, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-15980475, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-16003488, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-16037208, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-16790052, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-16995956, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-17189479, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-17519246, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-18096640, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-18174181, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-18654633, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-18776193, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-19558703, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-275827, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-332063, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-6667333, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-7613462, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-7661899, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-7723011, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-7749921, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-8609611, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-8609628, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-9015368, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-9188684, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-9254694, http://linkedlifedata.com/resource/pubmed/commentcorrection/20080507-9719646
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:chemical
pubmed:status
MEDLINE
pubmed:month
Mar
pubmed:issn
1367-4811
pubmed:author
pubmed:issnType
Electronic
pubmed:day
1
pubmed:volume
26
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
617-24
pubmed:dateRevised
2010-9-28
pubmed:meshHeading
pubmed:year
2010
pubmed:articleTitle
Active site prediction using evolutionary and structural information.
pubmed:affiliation
Computer Science Division, University of California, Berkeley, USA.
pubmed:publicationType
Journal Article, Research Support, U.S. Gov't, Non-P.H.S., Research Support, N.I.H., Extramural