Linked Life Data

17407280

Source:http://linkedlifedata.com/resource/pubmed/id/17407280

Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
3
pubmed:dateCreated
2007-5-29
pubmed:abstractText
Selecting a small subset of descriptors from a large pool to build a predictive quantitative structure-activity relationship (QSAR) model is an important step in the QSAR modeling process. In general, subset selection is very hard to solve, even approximately, with guaranteed performance bounds. Traditional approaches employ deterministic or stochastic methods to obtain a descriptor subset that leads to an optimal model of a single type (such as linear regression or a neural network). With the development of ensemble modeling approaches, multiple models of differing types are individually developed resulting in different descriptor subsets for each model type. However, it is advantageous, from the point of view of developing interpretable QSAR models, to have a single set of descriptors that can be used for different model types. In this paper, we describe an approach to the selection of a single, optimal, subset of descriptors for multiple model types. We apply this approach to three data sets, covering both regression and classification, and show that the constraint of forcing different model types to use the same set of descriptors does not lead to a significant loss in predictive ability for the individual models considered. In addition, interpretations of the individual models developed using this approach indicate that they encode similar structure-activity trends.
pubmed:grant
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:chemical
pubmed:status
MEDLINE
pubmed:issn
1549-9596
pubmed:author
pubmed:issnType
Print
pubmed:volume
47
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
989-97
pubmed:dateRevised
2007-12-3
pubmed:meshHeading
pubmed:articleTitle
Ensemble feature selection: consistent descriptor subsets for multiple QSAR models.
pubmed:affiliation
School of Informatics, Indiana University, Bloomington, Indiana 47406, USA.
pubmed:publicationType
Journal Article, Research Support, N.I.H., Extramural