Quantitative Structure−Activity Relationship Modeling of Juvenile Hormone Mimetic Compounds for Culex Pipiens Larvae, with a Discussion of Descriptor-Thinning Methods

Abstract

Quantitative structure-activity relationship (QSAR) modelers often encounter the problem of multicollinearity owing to the availability of large numbers of computable molecular descriptors. Sparsity of the variables while using descriptors such as atom pairs increases the complexity. Three different predictor-thinning methods, namely, a modified Gram-Schmidt algorithm, a marginal soft thresholding algorithm, and LASSO (least absolute shrinkage and selection operator), were utilized to reduce the number of descriptors prior to developing linear models. Juvenile hormone (JH) activity of 304 compounds on Culex pipiens larvae was taken as the model data set, and predictor trimming of a large number of diverse descriptors comprising 268 global molecular descriptors (topostructural, topochemical, and geometrical), 13 quantum chemical descriptors, and 915 atom pairs (substructural counts) was applied prior to linear regression by the ridge regression method. The data set (N = 304) was split into five calibration data sets of random samples of sizes 60/110/160/210/260, and the remaining 244/194/144/94/44 compounds were used for validations. LASSO was not found to be a very effective method in handling a large set of descriptors because the number of predictors retained could not exceed the number of observations. The results indicated that the modified Gram-Schmidt algorithm could be used to trim the number of predictors in the global molecular descriptor set where collinearity of the descriptors was the major concern. On the contrary, the soft thresholding approach was found to be an effective tool in subset selection from a diverse set of descriptors having both sparsity and multicollinearity, as in the case of the combined set of atom pairs and global molecular descriptors. The final model developed after variable selection was dominated more by atom pairs, which indicated the important structural moieties that affect JH activity of the compounds. The success of the method reiterates the fact that QSAR or quantitative structure-property relationship (QSPR) models can be developed for a diverse set of compounds using properly parametrized and diverse sets of descriptors, of course, with the selection of the appropriate statistical tools.

Alignment-Free Method to Predict Enzyme Classes and Subclasses

“…As a result, a proper FS method is essential to develop robust and reliable quantitative structure–activity relationship (QSAR) models. This is particularly the case when using ANNs, since QSAR models developed with a large set of MDs are really complex, vulnerable to overfitting and difficult to obtain a mechanistic interpretation from [38,39].…”

Molecular Determinants of Juvenile Hormone Action as Revealed by 3D QSAR Analysis in Drosophila

“…For example, very different dose-response curves and ID 50 or IC 50 values will be obtained when animals are given a tested compounds via a single direct topical application than via its continuous presence in food or the living environment ( e.g. in the water for aquatic insects [42]). Under conditions where a compound is continuously present, there is an increased chance that toxic effects will have prevalence over realistic biological activity.…”

“…In the Class I structures it is concentrated near electronegative, ether or epoxy oxygen whereas in Class II structures it is localized to the phenyl rings. Indeed, a similar protocol for subdividing compounds into two chemotypes for QSAR analyses was published recently for COX-2 inhibitors [41] and steroid hormones to reflect the unusual conformational adaptation of nuclear receptor ligand binding domains to agonist variety [42], [43]. Furthermore, the presence of an electron deficient moiety in the middle of the JH agonist molecule is essential for the very high biological activity seen in some synthetic JH agonists but not observed in natural JH (blue and cyan polyhedra regions in CoMFA and CoMSIA contour maps, respectively; see Figures 3 and 4A, B).…”

Finding Needles in a Haystack: Determining Key Molecular Descriptors Associated with the Blood‐brain Barrier Entry of Chemical Compounds Using Machine Learning

“…The second set of descriptors, used frequently by Basak et al, is calculated using the softwares POLLY and Triplet . We use 98 and 100 descriptors calculated by these softwares, respectively.…”