Interpretation of ANN‐based QSAR models for prediction of antioxidant activity of flavonoids. Issue 16 (5th February 2018)

• Record Type: Journal Article
• Authors: Žuvela, Petar; David, Jonathan; Wong, Ming Wah
• Is Part Of: Journal of computational chemistry. Volume 39:Issue 16(2018)
• Page Start: 953
• Page End: 963
• Publication Date: 2018-02-05
• Subjects: antioxidants -- flavonoids -- QSAR -- ANNs -- ANN interpretation; Chemistry -- Data processing -- Periodicals; 542.85
• DOI: 10.1002/jcc.25168
• Languages: English
• ISSNs: 0192-8651

Abstract

Abstract : Quantitative structure–activity relationships (QSARs) built using machine learning methods, such as artificial neural networks (ANNs) are powerful in prediction of (antioxidant) activity from quantum mechanical (QM) parameters describing the molecular structure, but are usually not interpretable. This obvious difficulty is one of the most common obstacles in application of ANN‐based QSAR models for design of potent antioxidants or elucidating the underlying mechanism. Interpreting the resulting models is often omitted or performed erroneously altogether. In this work, a comprehensive comparative study of six methods (PaD, PaD2, weights, stepwise, perturbation and profile) for exploration and interpretation of ANN models built for prediction of Trolox‐equivalent antioxidant capacity (TEAC) QM descriptors, is presented. Sum of ranking differences (SRD) was used for ranking of the six methods with respect to the contributions of the calculated QM molecular descriptors toward TEAC. The results show that the PaD, PaD2 and profile methods are the most stable and give rise to realistic interpretation of the observed correlations. Therefore, they are safely applicable for future interpretations without the opinion of an experienced chemist or bio‐analyst. © 2018 Wiley Periodicals, Inc. Abstract : Machine learning methods, such as artificial neural networks (ANNs) are instructive for QSAR modeling because of the nonlinear relationships between molecular structure and activity. Regardless of the near‐perfect predictions ANNs yield, there is difficulty in their interpretation. Interpretations are often omitted or misleadingly reported. Thereby, in this work, six methods for interpretation of ANN‐based QSAR models are comprehensively evaluated and compared. Prediction of Trolox‐equivalent antioxidant capacity from QM descriptors is used as a case study.