Virtual Screening of Molecular Databases Using a Support Vector Machine
Citations Over TimeTop 1% of 2005 papers
Abstract
The Support Vector Machine (SVM) is an algorithm that derives a model used for the classification of data into two categories and which has good generalization properties. This study applies the SVM algorithm to the problem of virtual screening for molecules with a desired activity. In contrast to typical applications of the SVM, we emphasize not classification but enrichment of actives by using a modified version of the standard SVM function to rank molecules. The method employs a simple and novel criterion for picking molecular descriptors and uses cross-validation to select SVM parameters. The resulting method is more effective at enriching for active compounds with novel chemistries than binary fingerprint-based methods such as binary kernel discrimination.
Related Papers
- → An Effective Approach for Newspaper Article Classification using Multi-Class Support Vector Machine in Comparison with Binary Classifier to improve Accuracy(2023)1 cited
- Incremental Vector Support Vector Machine Learning Algorithm(2012)
- [발표논문] 인공신경망과 Support Vector Machine의 기업부도예측 성과 비교-Support Vector Machine의 유용성을 중심으로-(2004)
- Incremental Local Outlier Factor를 이용한 Support Vector Machine의 성능 개선에 관한 연구(2011)
- Learning and Performance Comparison of Multi-class Classification Problems based on Support Vector Machine(2008)