摘要
This paper describes the construction of a QSAR model to relate the structures of various derivatives of neocryptolepine to their anti-malarial activities. QSAR classification models were build using Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Classification and Regression Trees (CART), Partial Least Squares - Discriminant Analysis (PLS-DA), Orthogonal Projections to Latent Structures - Discriminant Analysis (OPLS-DA), and Support Vector Machines for Classification (SVM-C), using four sets of molecular descriptors as explanatory variables. Prior to classification, the molecules were divided into a training and a test set using the duplex algorithm. The different classification models were compared regarding their predictive ability, simplicity, and interpretability. Both binary and multi-class classification models were constructed. For classification into three classes. CART and One-Against-One (OAO)-SVM-C were found to be the best predictive methods, while for classification into two classes, LDA, QDA and CART were.
学科与关键词
- Development of QSAR models to predict and interpret the biological activity of artemisinin analoguesGuha, R; Jurs, PCJOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2004, 44(4): 1440-1449.被引 57
- Predicting the free radical scavenging activity of curcumin derivativesWorachartcheewan, Apilak; Nantasenamat, Chanin*; Isarankura-Na-Ayudhya, Chartchalerm; Prachayasittikul, Supaluk; Prachayasittikul, VirapongChemometrics and Intelligent Laboratory Systems, 2011, 109(2): 207-216.被引 56
- Exploring QSAR of antiamoebic agents of isolated natural products by MLR, ANN, and RTORamirez-Galicia, Guillermo; Martinez-Pacheco, Heidy; Garduno-Juarez, Ramon; Deeb, OmarMEDICINAL CHEMISTRY RESEARCH, 2012, 21(9): 2501-2516.被引 10
