Nonlinear Quantitative Structure-activity Relationship Research Articles

A Linear and Nonlinear QSAR Analysis of Benzimidazole Derivative XY123 in Prostate Cancer Treatment

Background: Metastatic Castration-Resistant Prostate Cancer (mCRPC) represents a critical challenge in current prostate cancer treatment. Benzimidazole Derivative XY123 has emerged as a novel inhibitor for its treatment. Objective: This study aims to establish a robust Quantitative Structure-Activity Relationship (QSAR) model for predicting the activity of Benzimidazole Derivative XY123 derivatives, aiding the development of novel anti-prostate cancer drugs. Methods: Utilizing CODESSA software, descriptors were computed based on various moieties of Benzimidazole Derivative XY123 derivatives. Multiple linear regression models were constructed, and both linear and nonlinear QSAR models were developed using heuristics and gene expression programming. Results: The linear model with two descriptors demonstrated the best predictive capacity for inhibitor activity, while the nonlinear model generated through Gene Expression Programming (GEP) exhibited correlation coefficients of 0.83 and 0.82 for the training and test sets, respectively. The average errors were 0.03 and 0.05, indicating the stability and the improved predictive ability of the nonlinear model. Conclusion: The QSAR linear model has an advantage over the nonlinear model in optimizing Benzimidazole Derivative XY123, providing a direction for the development of effective drugs for mCRPC treatment.

QSAR Research of Novel Tetrandrine Derivatives against Human Hepatocellular Carcinoma.

The new tetrandrine derivative is an anti-human liver cancer cell inhibitor which can be used to design and develop anti-human-liver-cancer drugs. A quantitative structure-activity relationship (QSAR) model was established to predict the physical properties of new tetrandrine derivatives using their chemical structures. The best descriptors were selected through CODESSA software to build a multiple linear regression model. Then, gene expression programming (GEP) was used to establish a nonlinear quantitative QSAR model with descriptors to predict the activity of a series of novel tetrandrine chemotherapy drugs. The best active compound 31 was subjected to molecular docking experiments through SYBYL software with a small fragment of the protein receptor (PDB ID:2J6M). Four descriptors were selected to build a multiple linear regression model with correlation coefficients R2, R2CV and S2 with the values of 0.8352, 0.7806 and 0.0119, respectively. The training and test sets with a correlation coefficient of 0.85 and 0.83 were obtained via an automatic problem-solving program (APS) using the four selected operators as parameters, with a mean error of 1.49 and 1.08. Compound 31 had a good docking ability with an overall score of 5.8892, a collision rate of -2.8004 and an extreme value of 0.9836. The computer-constructed drug molecular model reveals the factors affecting the activity of human hepatocellular carcinoma cells, which provides directions and guidance for the development of highly effective anti-humanhepatocellular- carcinoma drugs in the future.

QSAR Study of Novel 1, 8-Naphthimide Derivatives Targeting Nuclear DNA.

1, 8-naphthimide is a novel tumor inhibitor targeting nuclear DNA, which can be used to design and develop anti-osteosarcoma drugs. Quantitative structure-activity relationship (QSAR) model was established to predict the physical properties of compounds. In this study, gene expression programming (GEP) was used to build a nonlinear quantitative structureactivity relationship (QSAR) model with descriptors and to predict the activity of a serials novel DNA-targeted chemotherapeutic agents. These descriptors were calculated in CODESSA software and selected from the descriptor pool based on heuristics. Three descriptors were selected to establish a multiple linear regression model. The best nonlinear QSAR model with a correlation coefficient of 0.89 and 0.82 and mean error of 0.02 and 0.06 for the training and test sets were obtained. The results showed that the model established by GEP had better stability and predictive ability. The small molecular docking experiment of 32 compounds was carried out in SYBYL software, and it was found that compound 7A had reliable molecular docking ability. The established model reveals the factors affecting the activity of DNA inhibitors and provides direction and guidance for the further design of highly effective DNA-targeting drugs for osteosarcoma.

Predicting Potent Compounds Using a Conditional Variational Autoencoder Based upon a New Structure-Potency Fingerprint.

Prediction of the potency of bioactive compounds generally relies on linear or nonlinear quantitative structure-activity relationship (QSAR) models. Nonlinear models are generated using machine learning methods. We introduce a novel approach for potency prediction that depends on a newly designed molecular fingerprint (FP) representation. This structure-potency fingerprint (SPFP) combines different modules accounting for the structural features of active compounds and their potency values in a single bit string, hence unifying structure and potency representation. This encoding enables the derivation of a conditional variational autoencoder (CVAE) using SPFPs of training compounds and apply the model to predict the SPFP potency module of test compounds using only their structure module as input. The SPFP-CVAE approach correctly predicts the potency values of compounds belonging to different activity classes with an accuracy comparable to support vector regression (SVR), representing the state-of-the-art in the field. In addition, highly potent compounds are predicted with very similar accuracy as SVR and deep neural networks.

Corrosion Inhibition Studies of 8-Hydroxyquinoline Derivatives for N80 Steel in a 1.0 M HCl Solution: Experimental, Computational Chemistry, and Quantitative Structure-Activity Relationship Studies.

Twelve kinds of 8-hydroxyquinoline derivatives were synthesized and characterized. The weight loss method was used to evaluate their inhibition efficiencies (IEs) in a 1.0 M HCl solution at 333 K. The results showed that the alkyl chain length, heteroatoms (S, N, and O), and number of benzene rings significantly affect the IE. Herein, the IE of 5-[(dodecylthio)methyl]-8-quinolinol reached 98.71%. Meanwhile, the potentiodynamic polarization results indicated that all 8-hydroxyquinoline derivatives were mixed-type inhibitors. Electrochemical impedance spectroscopy results revealed that 8-hydroxyquinoline derivatives can increase polarization resistance, supporting their adsorption on the N80 steel surface. Moreover, according to density functional theory (DFT), the frontier orbital distribution and quantum chemical parameters (EHOMO, ELUMO, dipole moment μ, etc.) were calculated, and the results confirmed that the substituents of protonated 8-hydroxyquinoline derivatives significantly influenced the frontier orbital distribution. Molecular dynamics simulation illustrated that all protonated 8-hydroxyquinoline derivatives were adsorbed parallel to the Fe(110) surface, and the interaction energy (Eint) evidenced that the molecular size would affect their strength of adsorption on the Fe(110) surface. The linear and nonlinear quantitative structure-activity relationship models were established by linear regression (LR) methods and BP neural networks (NN), respectively. The LR model was established by using Eint and μ, and the coefficient of determination (R2) was 0.934. In addition, the nonlinear NN model was obtained according to IE and all parameters (DFT parameters and Eint). Then, the two calculation inhibition efficiencies (IEcal) were obtained from the LR and NN models, and the R2 values of the linear correlation between the IEcal and the experimental IE were 0.940 and 0.951, respectively. In addition, the IE of the tested inhibitor was 51.86% and the IEcal values predicted by the LR and NN models were 52.68% and 53.06%, respectively. Our results demonstrate that both the LR and NN models have good fits and predictive ability.

Molecular docking, linear and nonlinear QSAR studies on factor Xa inhibitors

Factor Xa (FXa) enzyme has an important role in the blood coagulation system. Disruption in the enzyme function results in the production of blood clots. Therefore, inhibition of the factor Xa with anticoagulant drugs is an important target in thromboembolic therapy. Experimental design of new drugs is a time-consuming and expensive process. Application of molecular modeling is an essential step for designing new and high yield drugs to achieve better results. In this study, 36 aroylguanidine derivatives that inhibit destructive activities by binding to the FXa enzyme were selected. Quantitative Structure-Activity Relationships (QSAR) model was developed for predicting the IC50 parameter for factor Xa inhibitors. QSAR have been constructed by combining Genetic Algorithms with Multiple Linear Regressions (GA-MLR) and Support Vector Machine (SVM). The correlation coefficient (R2) and root mean square error (RMSE) for GA-MLR are 0.895, 0.142 and for SVM are 0.994, 0.032, respectively. The obtained results indicated that the SVM method is superior over the GA-MLR method. Also, molecular docking was used to examine the results more accurately, in which energy interactions were investigated. Molecular docking indicated the binding relationship between the receptor and the ligand. The results showed that reducing the parameters such as electronegativity, and the size of the atoms, as well as increasing the number of loops and groups attached to the structures, is effective in the model.

In Silico Prediction of Intestinal Permeability by Hierarchical Support Vector Regression.

The vast majority of marketed drugs are orally administrated. As such, drug absorption is one of the important drug metabolism and pharmacokinetics parameters that should be assessed in the process of drug discovery and development. A nonlinear quantitative structure–activity relationship (QSAR) model was constructed in this investigation using the novel machine learning-based hierarchical support vector regression (HSVR) scheme to render the extremely complicated relationships between descriptors and intestinal permeability that can take place through various passive diffusion and carrier-mediated active transport routes. The predictions by HSVR were found to be in good agreement with the observed values for the molecules in the training set (n = 53, r2 = 0.93, = 0.84, RMSE = 0.17, s = 0.08), test set (n = 13, q2 = 0.75–0.89, RMSE = 0.26, s = 0.14), and even outlier set (n = 8, q2 = 0.78–0.92, RMSE = 0.19, s = 0.09). The built HSVR model consistently met the most stringent criteria when subjected to various statistical assessments. A mock test also assured the predictivity of HSVR. Consequently, this HSVR model can be adopted to facilitate drug discovery and development.

A 2D/3D-QSAR STUDY ON BIOLOGICAL ACTIVITIES OF 1,2-ETHYLENDIAMINE DERIVATIVES AS ANTI-TUBERCULOSIS DRUGS

In this work quantitative structure-activity relationship (QSAR) study has been done on 1,2-ethylenediamine derivatives as anti-tuberculosis drugs. Genetic algorithm (GA), artificial neural network (ANN), multiple linear regressions (stepwise-MLR) and Imperialist Competitive Algorithm (ICA), were used to create the nonlinear and linear QSAR models. The root-mean square errors of the training set and the test set for GA–ANN models using the jack-knife method, were 0.1402, 0.1304 and Q2 = 0.94. Also, the R and R2 values 0.85, 0.73 in the gas phase were obtained from a GA-stepwise-MLR model. Q2 of training set for PLS was 0.52. The results obtained from this work indicate that ANN and ICA models are more effective than other statistical methods and exhibit reasonable prediction capabilities. The best descriptors are G3u, HATS2e, F02(C-N), GGI10, RDF040m, Mor22p, Mor05p, TIC4, H4e, H-052, G2m and G1e.

Theoretical Prediction of the Complex P-Glycoprotein Substrate Efflux Based on the Novel Hierarchical Support Vector Regression Scheme.

P-glycoprotein (P-gp), a membrane-bound transporter, can eliminate xenobiotics by transporting them out of the cells or blood–brain barrier (BBB) at the expense of ATP hydrolysis. Thus, P-gp mediated efflux plays a pivotal role in altering the absorption and disposition of a wide range of substrates. Nevertheless, the mechanism of P-gp substrate efflux is rather complex since it can take place through active transport and passive permeability in addition to multiple P-gp substrate binding sites. A nonlinear quantitative structure–activity relationship (QSAR) model was developed in this study using the novel machine learning-based hierarchical support vector regression (HSVR) scheme to explore the perplexing relationships between descriptors and efflux ratio. The predictions by HSVR were found to be in good agreement with the observed values for the molecules in the training set (n = 50, r2 = 0.96, = 0.94, RMSE = 0.10, s = 0.10) and test set (n = 13, q2 = 0.80–0.87, RMSE = 0.21, s = 0.22). When subjected to a variety of statistical validations, the developed HSVR model consistently met the most stringent criteria. A mock test also asserted the predictivity of HSVR. Consequently, this HSVR model can be adopted to facilitate drug discovery and development.

Quantitative Structure-Activity Relationship Model for HCVNS5B inhibitors based on an Antlion Optimizer-Adaptive Neuro-Fuzzy Inference System

The global prevalence of hepatitis C Virus (HCV) is approximately 3% and one-fifth of all HCV carriers live in the Middle East, where Egypt has the highest global incidence of HCV infection. Quantitative structure-activity relationship (QSAR) models were used in many applications for predicting the potential effects of chemicals on human health and environment. The adaptive neuro-fuzzy inference system (ANFIS) is one of the most popular regression methods for building a nonlinear QSAR model. However, the quality of ANFIS is influenced by the size of the descriptors, so descriptor selection methods have been proposed, although these methods are affected by slow convergence and high time complexity. To avoid these limitations, the antlion optimizer was used to select relevant descriptors, before constructing a nonlinear QSAR model based on the PIC50 and these descriptors using ANFIS. In our experiments, 1029 compounds were used, which comprised 579 HCVNS5B inhibitors (PIC50 < ~14) and 450 non-HCVNS5B inhibitors (PIC50 > ~14). The experimental results showed that the proposed QSAR model obtained acceptable accuracy according to different measures, where {{boldsymbol{R}}}^{{boldsymbol{2}}} was 0.952 and 0.923 for the training and testing sets, respectively, using cross-validation, while {{boldsymbol{R}}}_{{boldsymbol{L}}{boldsymbol{O}}{boldsymbol{O}}}^{{boldsymbol{2}}} was 0.8822 using leave-one-out (LOO).

MODELING OF CARBONIC ANHYDRASE (II) INHIBITORY ACTIVITIES OF SULPHONILAMIDE SCHIFF BASES BY ARTIFICIAL NEURAL NETWORK TRAINED WITH DIFFERENT NUMERICAL TECHNIQUES

Objective: The aim of the present study was to develop robust linear and non-linear Quantitative Structure-Activity Relationship (QSAR) models for exploring the relationship between the structural features of a series of sulphanilamide Schiff bases and their CA (II) inhibition activities.Methods: QSAR modeling of carbonic anhydrase (II) inhibiting activities of a series of sulphanilamide Schiff bases as a function of theoretically derived molecular descriptors calculated by Dragon software was established linearly by stepwise multiple linear regression (SW-MLR) method and non-linearly by artificial neural network (ANN) method, trained with different numerical techniques namely, Scaled conjugate gradient (SCG), quasi-Newton (BFGS), and Levenberg-Marquardt (LM) algorithm. SW-MLR method was also used to select descriptors from large descriptor pool. After the selection of variables, best selected linear model was validated by Y-randomization test. The applicability domain was assessed by the normalized mean Euclidean distance value for each compound. The prediction quality of proposed non-linear QSAR models was tested externally using validation and test set.Results: The low value of R2average = 0.214 from the Y-randomization test and no significant correlation between the selected descriptors indicates that linear model is reliable, and robust. Applicability domain analysis has also revealed that the suggested model has acceptable predictability. To explore non-linear relationship between selected descriptors and the target property, ANN approach trained with three supervised algorithms (BFGS, SCG and LM) was used. Statistical comparison of the quality of models obtained using ANN method trained with above mentioned three algorithms with SW-MLR model shows that ANN with 4-3-1 architecture and trained with LM algorithm has better predictive power as indicated by low RMSEval (0.11), MAPEval (11.95) values and high R2val (0.96) value.Conclusion: The results of this work indicated the ANN trained with fastest Levenberg-Marqardt algorithm is a promising tool for establishing non-linear relationship between selected sulphanilamide Schiffbases and their CA (II) inhibition values.

Maximal Information Coefficient and Support Vector Regression Based Nonlinear Feature Selection and QSAR Modeling on Toxicity of Alcohol Compounds to Tadpoles of Rana temporaria

Efficient evaluation of biotoxicity of organics is of vital significance to resource utilization and environmental protection. In this study, toxicity of 110 alcohol compounds to tadpoles of Rana temporaria is adopted as the dependent variable and 1388 physiochemical parameters (features) calculated by PCLIENT are used for representing each compound. A feature selection pipeline with three steps is developed to refine the feature subset: 282 features that significantly correlated with biotoxicity of chemical compounds are preliminarily selected via the maximum information coefficient (MIC); 138 descriptors that have positive contribution to the model’s performance are reserved after a support vector regression (SVR) based backward elimination; 18 descriptors are finally selected via a forward selection process that integrated minimal redundancy maximal relevance (mRMR), MIC and SVR. In terms of feature subsets with different numbers of variables, quantitative structure activity relationship (QSAR) models are built using multiple linear regression (MLR), partial least square regression (PLS) and SVR, respectively. The independent prediction evaluation index, Q2, increases from -74.787, 0.824 and 0.868 to 0.892, 0.878 and 0.940, for the three regression models, respectively. Results suggest that nonlinear feature selection methods involved in MIC and SVR can effectively eliminate irrelevant descriptors. SVR outperforms classical statistical models to QSAR modeling on high-dimensional data containing nonlinear relationship between features. The methods proposed in this study have a potential application in the QSAR research field such as biotoxicity compounds.

Common SAR Derived from Linear and Non-linear QSAR Studies on AChE Inhibitors used in the Treatment of Alzheimer's Disease.

Background: Deficits in cholinergic neurotransmission due to the degeneration of cholinergic neurons in the brain are believed to be one of the major causes of the memory impairments associated with AD. Targeting acetyl cholinesterase (AChE) surfaced as a potential therapeutic target in the treatment of Alzheimer’s disease. The present study is pursued to develop quantitative structure activity relationship (QSAR) models to determine chemical descriptors responsible for AChE activity.Methods: Two different sets of AChE inhibitors, dataset-I (30 compounds) and dataset-II (20 compounds) were investigated through MLR aided linear and SVM aided non-linear QSAR models.Results: The obtained QSAR models were found statistically fit, stable and predictive on validation scales. These QSAR models were further investigated for their common structure-activity relationship in terms of overlapping molecular descriptors selection. Atomic mass weighted 3D Morse descriptors (MATS5m) and Radial Distribution Function (RDF045m) descriptors were found in common SAR for both the datasets. Electronegativity weighted (MATS5e, HATSe, and Mor17e) descriptors have also been identified in regulative roles towards endpoint values of dataset-I and dataset-II.Conclusion: The common SAR identified in these linear and non-linear QSAR models could be utilized to design novel inhibitors of AChE with improved biological activity.

Development of MLR and SVM Aided QSAR Models to Identify Common SAR of GABA Uptake Herbal Inhibitors used in the Treatment of Schizophrenia.

Background: Alterations in GABAnergic system are implicated in the pathophysiology of schizophrenia. Available antipsychotics that target GABA receptor form a desirable therapeutic strategy in the treatment regimen of schizophrenia, unfortunately, suffer serious setback due to their prolonged side effects. The present investigation focuses on developing QSAR models from the biological activity of herbal compounds and their derivatives that promise to be alternative candidates to GABA uptake inhibitors.Methods: Three sets of compounds were undertaken in the study to develop QSAR models. The first set consisted of nine compounds which included Magnolol, Honokiol and other GABA acting established compounds. The second set consisted of 16 derivatives of N-diarylalkenyl-piperidinecarboxylic acid. The third QSAR dataset was made up of thirty two compounds which were Magnolol and Honokiol derivatives. Multiple linear regressions (MLR) and support vector machine (SVM) supervised quantitative structure-activity relationship (QSAR) models were developed to predict the biological activity of these three sets. The purpose of taking three QSAR sets of diverse chemical structures but identical in their GABA targeting and pharmacological action was to identify common chemical structure features responsible for structure-activity relationship (SAR).Results: Linear and non-linear QSAR models confirmed that the three sets shared common structural descriptors derived from WHIM (Weighted Holistic Invariant Molecular descriptors), 3D-MoRSE and Eigenvalue classes.Conclusion: It was concluded that properties like electro negativity and polarizability play a crucial role in controlling the activity of herbal compounds against GABA receptor.

Study of quantitative structure-activity relationship (QSAR) of diarylaniline analogues as in vitro anti-HIV-1 agents in pharmaceutical interest

A study of quantitative structure-activity relationship (QSAR) is applied to a set of 24 molecules derived from diarylaniline to predict the anti-HIV-1 biological activity of the test compounds and find a correlation between the different physic-chemical parameters (descriptors) of these compounds and its biological activity, using principal components analysis (PCA), multiple linear regression (MLR), multiple non-linear regression (MNLR) and the artificial neural network (ANN). We accordingly proposed a quantitative model (non-linear and linear QSAR models), and we interpreted the activity of the compounds relying on the multivariate statistical analysis. The topological descriptors were computed with ACD/ChemSketch and ChemBioOffice14.0 programs. A correlation was found between the experimental activity and those obtained by MLR and MNLR such as (Rtrain = 0.886 ; R2train = 0.786) and (Rtrain = 0.925 ; R2train = 0.857) for the training set compounds, and (RMLR-test = 0.6) and (RMNLR-test = 0.7) for a randomly chosen test set of compounds, this result could be improved with ANN such as (R = 0.916 and R2 = 0.84) with an architecture ANN (6-1-1). To evaluate the performance of the neural network and the validity of our choice of descriptors selected by MLR and trained by MNLR and ANN, we used cross-validation method (CV) including (R = 0.903 and R2 = 0.815) with the procedure leave-one-out (LOO). The results showed that the MLR and MNLR have served to predict activities, but when compared with the results given by a 6-1-1 ANN model. We realized that the predictions fulfilled by the latter model were more effective than the other models. The statistical results indicated that this model is statistically significant and showing a very good stability towards the data variation in leave-one-out (LOO) cross validation.

In silico investigation of agonist activity of a structurally diverse set of drugs to hPXR using HM-BSM and HM-PNN

The human pregnane X receptor (hPXR) plays a critical role in the metabolism, transport and clearance of xenobiotics in the liver and intestine. The hPXR can be activated by a structurally diverse of drugs to initiate clinically relevant drug-drug interactions. In this article, in silico investigation was performed on a structurally diverse set of drugs to identify critical structural features greatly related to their agonist activity towards hPXR. Heuristic method (HM)-Best Subset Modeling (BSM) and HM-Polynomial Neural Networks (PNN) were utilized to develop the linear and non-linear quantitative structure-activity relationship models. The applicability domain (AD) of the models was assessed by Williams plot. Statistically reliable models with good predictive power and explain were achieved (for HM-BSM, r (2)=0.881, q LOO (2) =0.797, q EXT (2) =0.674; for HM-PNN, r (2)=0.882, q LOO (2) =0.856, q EXT (2) =0.655). The developed models indicated that molecular aromatic and electric property, molecular weight and complexity may govern agonist activity of a structurally diverse set of drugs to hPXR.

Discovery of potent adenosine A2a antagonists as potential anti-Parkinson disease agents. Non-linear QSAR analyses integrated with pharmacophore modeling

Adenosine A2A receptor antagonists are of great interest in the treatment for Parkinson’s disease. In this study, we combined extensive pharmacophore modeling and quantitative structure-activity relationship (QSAR) analysis to explore the structural requirements for potent Adenosine A2A antagonists. Genetic function algorithm (GFA) joined with k nearest neighbor (kNN) analyses were applied to build predictive QSAR models. Successful pharmacophores were complemented with exclusion spheres to improve their receiver operating characteristic curve (ROC) profiles. Best QSAR models and their associated pharmacophore hypotheses were validated by identification of several novel Adenosine A2A antagonist leads retrieved from the National Cancer Institute (NCI) structural database. The most potent hit illustrated IC50 value of 545.7 nM.

Exploring Cellular Interactions of Liposomes Using Protein Corona Fingerprints and Physicochemical Properties

To control liposomes fate and transport upon contact with biofluids, it is essential to consider several parameters affecting the synthetic and biological identity of liposomes, as well as liposome-protein corona (PC) aspects. As a powerful tool in this data mining adventure, quantitative structure-activity relationship (QSAR) approach is used to correlate physicochemical properties of liposomes and their PC fingerprints to multiple quantified biological responses. In the present study, the relationship between cellular interactions of a set of structurally diverse liposomal formulations and their physicochemical and PC properties has been investigated via linear and nonlinear QSAR models. Significant parameters affecting cellular uptake and cell viability of liposomes in two important cancer cell lines (PC3 and HeLa) have been identified. The developed QSARs have the capacity to be implemented in advanced targeted delivery of liposomal drugs.

Studies on the IC50 of Trisubstituted Thiazoles as Cdc7 Kinase Inhibitors

In this study, a nonlinear quantitative structure-activity relationship model for the prediction of the IC50 of trisubstituted thiazoles as Cdc7 kinase inhibitors was developed by the gene expression programming (GEP). This model is based on five descriptors which were selected from the descriptors' pool by heuristic method (HM). GEP rendered a good correlation between the experimental and predicted log (IC50) values with a correlation coefficient and a mean error of 0.85 and 0.22 for the training set, 0.84 and 0.39 for the testing set, respectively. The results indicate that this QSAR model has good predictive capability and it points to further optimization opportunities for Cdc7 kinase inhibitors.

Radial basis function neural networks based on the projection pursuit and principal component analysis approaches: QSAR analysis of fullerene[C60]-based HIV-1 PR inhibitors

In this work, projection pursuit (PP) and principal component analysis (PCA) are combined with radial basis function networks (RBFNs) to perform the quantitative structure–activity relationship (QSAR) studies on the binding affinities (pEC50, i.e., minus decimal logarithm of the 50 % effective concentration) of 47 fullerene derivatives as inhibitors of the human immunodeficiency virus type 1 protease. RBFN is applied to construct the nonlinear QSAR models. The input of RBFN is the scores of PP or PCA, and genetic algorithm is used to select the centers of RBFN. The methods are called PP-GA-RBF and PCA-GA-RBF, respectively. The aim is the performance comparison of the proposed methods. To evaluate the performance of the methods, various statistical parameters such as \( Q_{F2}^{2} \) and \( r_{m}^{2} \) are calculated. The results demonstrated that the predictive performance of the proposed PP-GA-RBF is better than PCA-GA-RBF and previous studies. The applicability domain of the models is assessed by leverage and distance approaches.