KNN QSAR method

A Simple Example of the QSAR Technique—the kNN QSAR. For illustrative purposes, we describe here the kNN QSAR method, which is conceptually simple and quite effective in a variety of applications. Formally, the kNN QSAR technique implements the active analog principle that is used widely by the medicinal chemist. 

For illustration, we shall consider here one of the nonlinear variable selection methods that adopts a k-Nearest Neighbor (kNN) principle to QSAR [kNN-QSAR (49)]. Formally, this method implements the active analog principle that lies in the foundation of the modern medicinal chemistry. The kNN-QSAR method employs multiple topological (2D) or topographical (3D) descriptors of chemical structures and predicts biological activity of any compound as the average activity of k most similar molecules. This method can be used to analyze the structure-activity relationships (SAR) of a large number of compounds where a nonlinear SAR may predominate. 

Computational models to predict human intestinal absorption using sphere exclusion and kNN QSAR methods... 

Gunturi, S.B. and Narayanan, R. (2007) In silico ADME modeling. 3. Computational models to predict human intestinal absorption using sphere exclusion and kNN QSAR methods. QSAR el Combinatorial Science, 26, 653-668. 

When applied to QSAR studies, the activity of molecule u is calculated simply as the average activity of the K nearest neighbors of molecule u. An optimal K value is selected by the optimization through the classification of a test set of samples or by the leave-one-out cross-validation. Many variations of the kNN method have been proposed in the past, and new and fast algorithms have continued to appear in recent years. The automated variable selection kNN QSAR technique optimizes the selection of descriptors to obtain the best models [20]. 

Similarity Distance In the case of a nonlinear method such as the k Nearest Neighbor (kNN) QSAR [41], since the models are based on chemical similarity calculations, a large similarity distance could signal query compounds that are too dissimilar to the... 

Asikainen, A.H., Ruuskanen, J. and Tuppurainen, K.A. (2004) Consensus kNN QSAR a versatile method for predicting the estrogenic activity of organic compounds in silico. A comparative study with five estrogen receptors, and a large, diverse set of ligands. Environ. Sci. Technol, 38, 6724-6729. 

Besides stepwise multiple linear regression (MLR) analysis, other methods used for deriving QSAR models were E-state modeling [168], kNN based COMBINE [173] and VALIDATE [I8I], The VALIDATE method makes use of 3D-coordinates of known ligand-receptor complexes to calculate physicochemical parameters. It was one of the very few studies where QSAR was part of the design and synthetic efforts [181]. Several statistical techniques such as stepwise regression, EA-MLR, PCRA and PLS analysis were applied in a recent study [194] to identify the structural and physicochemical requirements for HIV protease inhibitory activity. 

We have applied kNN (Zheng and Tropsha 2000) and simulated annealing - partial least squares (SA-PLS) (Cho et al. 1998) QSAR approaches to a dataset of 48 chemically diverse functionalized amino acids (FAAs) with anticonvulsant activity that were synthesized previously, and successful QSAR models of FAA anticonvulsants have been developed (Shen et al. 2002). Both methods utilized multiple descriptors such as molecular connectivity indices or atom-pair descriptors, which are derived from two-dimensional molecular topology. QSAR models with high internal accuracy were generated, with leave-one-out cross-validated (q ) values rang-... 

---