Optimization of biaryl piperidine and 4-amino-2-biarylurea MCH1 receptor antagonists using QSAR modeling, classification techniques and virtual screening

Abstract

This paper presents the results of an optimization study on biaryl piperidine and 4-amino-2-biarylurea MCH1 receptor antagonists, which was accomplished by using quantitative-structure activity relationships (QSARs), classification and virtual screening techniques. First, a linear QSAR model was developed using Multiple Linear Regression (MLR) Analysis, while the Elimination Selection-Stepwise Regression (ES-SWR) method was adopted for selecting the most suitable input variables. The predictive activity of the model was evaluated using an external validation set and the Y-randomization technique. Based on the selected descriptors, the Support Vector Machines (SVM) classification technique was utilized to classify data into two categories: "actives" or "non-actives". Several attempts were made to optimize the scaffold of most potent compounds by inducing various structural modifications. Potential derivatives with improved activities were identified, as they were classified "actives" by the SVM classifier. Their activities were estimated using the produced MLR model. A detailed analysis on the model applicability domain defined the compounds, whose estimations can be accepted with confidence.

COMPUTACIONAL STUDY OF 1H-IMIDAZOL-2-YL-PYRIMIDINE-4,6-DIAMINES FOR IDENTIFICATION OF POTENTIAL PARENT COMPOUNDS OF NEW ANTIMALARIAL AGENTS

“…Mesmo que a não interpretação de um modelo não impeça sua utilização para fins de predição, caso seja possível interpretá-lo, reforça a utilidade da equação obtida para explicar o problema em estudo. 23,[41][42][43][44] Outro fato importante a ser considerado neste estudo é que o mecanismo de ação dos compostos estudados contra o P. falciparum 3D7 não é conhecido. Assim, a interpretação mecanística pode ser baseada apenas nos descritores moleculares selecionados, seus significados gerais e por comparação com os resultados de outros estudos QSAR.…”

Structural investigations of CXCR2 receptor antagonists by CoMFA, CoMSIA and flexible docking studies

“…In other words, the in silico procedure minimizes the time and cost associated with identifying new leads. Virtual screening was performed by insertion, deletion and substitution of different substituents on the original molecules and the effects of structural modifications on the biological activity were investigated (19). Then, the domain of QSAR model application was defined for using the model for screening new compounds.…”

Study of Nematic Transition Temperatures in Themotropic Liquid Crystal Using Heuristic Method and Radial Basis Function Neural Networks and Support Vector Machine

“…To estimate the predictive power of a QSPR model, the following parameters were used [20]: (i) square correlation coefficient R 2 between the predicted and observed property; (ii) coefficients of determination (predicted vs. observed property R 2 0 , and observed vs. predicted property R' 2 0 ); (iii) slopes k and k' of regression lines (predicted vs. observed property, and observed vs. predicted property, with the intercept set to 0) through the origin. In addition, we calculated the r 2 m value for external validation of the RBFNNs model according to Roy and Roy [21].…”

“…A value of r 2 m > 0.5 may be taken as an indicator of good external predictability. We concluded that a QSPR model had an acceptable predictive capability if the following conditions were satisfied [20]: …”