Building Highly Reliable Quantitative Structure–Activity Relationship Classification Models Using the Rivality Index Neighborhood Algorithm with Feature Selection

• Published in: Journal of chemical information and modeling Vol. 60; no. 1; pp. 133 - 151
• Main Authors: Ruiz, Irene Luque, Gómez-Nieto, Miguel Ángel
• Format: Journal Article
• Language: English
• Published: United States American Chemical Society 27.01.2020
• Subjects: Algorithms; Classification; Machine Learning; Model accuracy; Models, Molecular; Quantitative Structure-Activity Relationship; Reproducibility of Results; Selectivity

Dimensionality reduction of the data set representation for the construction of the quantitative structure–activity relationship classification models is an important research subject for the interpretability of the models and the computational cost efficiency of the classification algorithms. Featu...