| Attributs | Valeurs |
|---|
| type
| |
| Is Part Of
| |
| Subject
| |
| Title
| - Virtual Screening of Molecular Databases Using a Support Vector Machine
|
| has manifestation of work
| |
| related by
| |
| Author
| |
| Abstract
| - The Support Vector Machine (SVM) is an algorithm that derives a model used for the classification of datainto two categories and which has good generalization properties. This study applies the SVM algorithm tothe problem of virtual screening for molecules with a desired activity. In contrast to typical applications ofthe SVM, we emphasize not classification but enrichment of actives by using a modified version of thestandard SVM function to rank molecules. The method employs a simple and novel criterion for pickingmolecular descriptors and uses cross-validation to select SVM parameters. The resulting method is moreeffective at enriching for active compounds with novel chemistries than binary fingerprint-based methodssuch as binary kernel discrimination.
|
| article type
| |
| is part of this journal
| |
