Novel Variable Selection Quantitative Structure-Property Relationship Approach Based on the k-Nearest-Neighbor Principle

By Weifan Zheng, Alexander Tropsha. Journal of chemical information and computer sciences, 2000

423 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Recent advances in ligand-based drug design: relevance and utility of the conformationally sampled pharmacophore approach. (2011, methodology): “There are also other variable selection methods available such as genetic algorithms and Bayesian methods used in linear QSAR models; these have been discussed in detail in other review articles [34,43,44].”
Data Mining for Molecules with 2-D Neural Network Sensitivity Analysis (2003, methodology): “Examples of this approach are the use of genetic algorithms and simulated annealing (Wessel et al. 1998; Zheng and Tropsha 2000).”
Computational Methods in Drug Discovery (2014, methodology): “It can be applied with smaller sets of compounds than MLR. PLS combines MLR and PCA and extracts the dependent variable (biologic activity) into new components to optimize correlations (Zheng and Tropsha, 2000).”