Integrated One‐Against‐One Classifiers as Tools for Virtual Screening of Compound Databases: A Case Study with CNS Inhibitors

Abstract

A total of 21 833 inhibitors of the central nervous system (CNS) were collected from Binding-database and analyzed using discriminant analysis (DA) techniques. A combination of genetic algorithm and quadratic discriminant analysis (GA-QDA) was proposed as a tool for the classification of molecules based on their therapeutic targets and activities. The results indicated that the one-against-one (OAO) QDA classifiers correctly separate the molecules based on their therapeutic targets and are comparable with support vector machines. These classifiers help in charting the chemical space of the CNS inhibitors and finding specific subspaces occupied by particular classes of molecules. As a next step, the classification models were used as virtual filters for screening of random subsets of PUBCHEM and ZINC databases. The calculated enrichment factors together with the area under curve values of receiver operating characteristic curves showed that these classifiers are good candidates to speed up the early stages of drug discovery projects. The "relative distances" of the center of active classes of biosimilar molecules calculated by OAO classifiers were used as indices for sorting the compound databases. The results revealed that, the multiclass classification models in this work circumvent the definition inactive sets for virtual screening and are useful for compound retrieval analysis in Chemoinformatics.

Untargeted metabolomic profiling of seminal plasma in nonobstructive azoospermia men: A noninvasive detection of spermatogenesis

“…retention times), the GA‐QDA algorithm has been used for classification of the data. GA‐QDA is a supervised classification technique and tries to find the best subsets of discriminatory scan numbers for separating pre‐defined classes of samples, using the collection of methods inspired by the natural selection strategy (Jalali‐Heravi & Mani‐Varnosfaderani, ; Jalali‐Heravi et al, , ). The selected discriminatory scan numbers together with the accuracy, sensitivity, specificity and precision of the optimized QDA model are given in Table .…”

“…Actually, GA adapts the dimension of the data matrix to the classification problem using the natural evolution theorem. The GA would search to find the best collection of scan numbers by optimizing the objective function of the system (Jalali‐Heravi & Mani‐Varnosfaderani, ; Jalali‐Heravi, Mani‐Varnosfaderani, EftekharJahromi, Mahmoodi, & Taherinia, ; Jalali‐Heravi, Mani‐Varnosfaderani, & Valadkhani, ; Mani‐Varnosfaderani, Valadkhani, & Jalali‐Heravi, ). Defining an appropriate objective function, as a correct response of the system is an important task for a proper determination of the variables.…”

CS‐MINER: A Tool for Association Mining in Binding‐Database

“…The multi‐class classifiers compare the molecules according to their target types and measure the relative distances of active biosimilar molecules in chemical space 32. As an advantage, these classifiers do not need to inactive or decoy sets of molecules 32c. These classifiers help for finding some subspaces with considerable prior probabilities for inhibitors of a particular biological target.…”

Getting the most out of PubChem for virtual screening

“…12 PubChem was also screened using various predictive models to identify compounds with desired bioactivity. 13-20 Importantly, many studies 21-35 used bioactivity data archived in PubChem to develop bioactivity or toxicity prediction models. 24-35 In addition, PubChem data were used to build computational models to predict adverse drug reactions.…”