High-dimensional QSAR modelling using penalized linear regression model with L1/2-norm

In high-dimensional quantitative structure–activity relationship (QSAR) modelling, penalization methods have been a popular choice to simultaneously address molecular descriptor selection and QSAR model estimation. In this study, a penalized linear regression model with L1/2-norm is proposed. Furthe...

Full description

Saved in:
Bibliographic Details
Main Authors: Algamal, Z. Y., Lee, M. H., Al-Fakih, A. M., Aziz, M.
Format: Article
Published: Taylor and Francis Ltd. 2016
Subjects:
Online Access:http://eprints.utm.my/id/eprint/72108/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84987643691&doi=10.1080%2f1062936X.2016.1228696&partnerID=40&md5=4d4834740f41f51ed40fd692c7811449
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Teknologi Malaysia
Description
Summary:In high-dimensional quantitative structure–activity relationship (QSAR) modelling, penalization methods have been a popular choice to simultaneously address molecular descriptor selection and QSAR model estimation. In this study, a penalized linear regression model with L1/2-norm is proposed. Furthermore, the local linear approximation algorithm is utilized to avoid the non-convexity of the proposed method. The potential applicability of the proposed method is tested on several benchmark data sets. Compared with other commonly used penalized methods, the proposed method can not only obtain the best predictive ability, but also provide an easily interpretable QSAR model. In addition, it is noteworthy that the results obtained in terms of applicability domain and Y-randomization test provide an efficient and a robust QSAR model. It is evident from the results that the proposed method may possibly be a promising penalized method in the field of computational chemistry research, especially when the number of molecular descriptors exceeds the number of compounds.