Application of image moments in MIA‐QSAR. (10th November 2017)

• Record Type: Journal Article
• Authors: Xu, Min Li; Wang, Xue; Li, Bao Qiong; Zhai, Hong Lin; Lu, Shao Hua
• Other Names: Yu Ru–Qin guestEditor.
• Is Part Of: Journal of chemometrics. Volume 32:Number 11(2018)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2017-11-10
• Subjects: image processing -- modeling -- molecular structure -- quantitative structure‐activity relationship (QSAR) -- Tchebichef moments; Chemistry -- Mathematics -- Periodicals; Chemistry -- Statistical methods -- Periodicals; 542.85
• DOI: 10.1002/cem.2958
• Languages: English
• ISSNs: 0886-9383

Abstract

Abstract: Owing to the presence of some significant chemical information, the conventional images of molecular structures have been used in the studies of quantitative structure‐activity relationship by multivariate image analysis (MIA‐QSAR). In this contribution, we suggest that the Tchebichef moments (TMs) calculated directly from the grayscale images of molecular structures are used as molecular descriptors to build linear QSAR models by stepwise regression. The proposed approach was applied to QSAR research on a series of HIV‐1 non‐nucleoside reverse transcriptase inhibitors, and satisfactory results were obtained. Compared with several published methods, the results indicate that the TM method possesses higher accuracy and reliability. The TMs effectively decompose the image information of molecular structures at different levels without any pretreatment owing its very favorable multiresolution, holographic, and inherent invariance properties. Our study successfully extends the application of image moments to MIA‐QSAR research. Abstract : The Tchebichef image moments calculated directly from the grayscale molecular images were introduced to establish the linear quantitative structure‐activity relationship models.