Influence of feature rankers in the construction of molecular activity prediction models
| Autor: | Nicolás García-Pedrajas, Gonzalo Cerruela-García, José Pérez-Parra Toledano, Aida de Haro-García |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Models
Molecular Quantitative structure–activity relationship Computer science Feature selection Machine learning computer.software_genre 01 natural sciences Consistency (database systems) 0103 physical sciences Drug Discovery Humans Physical and Theoretical Chemistry 010304 chemical physics business.industry Rankers 0104 chemical sciences Computer Science Applications 010404 medicinal & biomolecular chemistry Ranking Feature (computer vision) Learning to rank Artificial intelligence business computer Algorithms Software Predictive modelling |
| Zdroj: | Journal of Computer-Aided Molecular Design. 34:305-325 |
| ISSN: | 1573-4951 0920-654X |
| Popis: | In the construction of activity prediction models, the use of feature ranking methods is a useful mechanism for extracting information for ranking features in terms of their significance to develop predictive models. This paper studies the influence of feature rankers in the construction of molecular activity prediction models; for this purpose, a comparative study of fourteen rankings methods for feature selection was conducted. The activity prediction models were constructed using four well-known classifiers and a wide collection of datasets. The ranking algorithms were compared considering the performance of these classifiers using different metrics and the consistency of the ranked features. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink