Boosting support vector regression in QSAR studies of bioactivities of chemical compounds

A QSPR analysis of physical properties of antituberculosis drugs using neighbourhood degree-based topological indices and support vector regression

Topological indices are molecular descriptors used in QSPR modelling to predict the physicochemical properties of molecules. Topological indices are used in numerous applications in drug design. In this work, we compute the neighbourhood degree-based topological indices of 15 antituberculosis drugs, we studied the QSPR analysis of these drugs using support vector regression. The efficiency of support vector regression is determined by comparing it with the classical linear regression. Our QSPR model further shows the superiority of the SVR model as a better predictive model in QSPR analysis of the physical properties of antituberculosis drugs. The findings in this study are a further contribution to the field of chemical graph theory and drug design, providing a deeper understanding of neighbourhood degree-based topological indices and their predictive capabilities in QSPR model.

Solubility of gaseous hydrocarbons in ionic liquids using equations of state and machine learning approaches

Ionic liquids (ILs) have emerged as suitable options for gas storage applications over the past decade. Consequently, accurate prediction of gas solubility in ILs is crucial for their application in the industry. In this study, four intelligent techniques including Extreme Learning Machine (ELM), Deep Belief Network (DBN), Multivariate Adaptive Regression Splines (MARS), and Boosting-Support Vector Regression (Boost-SVR) have been proposed to estimate the solubility of some gaseous hydrocarbons in ILs based on two distinct methods. In the first method, the thermodynamic properties of hydrocarbons and ILs were used as input parameters, while in the second method, the chemical structure of ILs and hydrocarbons along with temperature and pressure were used. The results show that in the first method, the DBN model with root mean square error (RMSE) and coefficient of determination (R²) values of 0.0054 and 0.9961, respectively, and in the second method, the DBN model with RMSE and R² values of 0.0065 and 0.9943, respectively, have the most accurate predictions. To evaluate the performance of intelligent models, the obtained results were compared with previous studies and equations of the state including Peng-Robinson (PR), Soave-Redlich-Kwong (SRK), Redlich-Kwong (RK), and Zudkevitch-Joffe (ZJ). Findings show that intelligent models have high accuracy compared to equations of state. Finally, the investigation of the effect of different factors such as alkyl chain length, type of anion and cation, pressure, temperature, and type of hydrocarbon on the solubility of gaseous hydrocarbons in ILs shows that pressure and temperature have a direct and inverse effect on increasing the solubility of gaseous hydrocarbons in ILs, respectively. Also, the evaluation of the effect of hydrocarbon type shows that increasing the molecular weight of hydrocarbons increases the solubility of gaseous hydrocarbons in ILs.

Towards cheminformatics-based estimation of drug therapeutic index: Predicting the protective index of anticonvulsants using a new quantitative structure-index relationship approach

The overall efficacy and safety profile of a new drug is partially evaluated by the therapeutic index in clinical studies and by the protective index (PI) in preclinical studies. In-silico predictive methods may facilitate the assessment of these indicators. Although QSAR and QSTR models can be used for predicting PI, their predictive capability has not been evaluated. To test this capability, we developed QSAR and QSTR models for predicting the activity and toxicity of anticonvulsants at accuracy levels above the literature-reported threshold (LT) of good QSAR models as tested by both the internal 5-fold cross validation and external validation method. These models showed significantly compromised PI predictive capability due to the cumulative errors of the QSAR and QSTR models. Therefore, in this investigation a new quantitative structure-index relationship (QSIR) model was devised and it showed improved PI predictive capability that superseded the LT of good QSAR models. The QSAR, QSTR and QSIR models were developed using support vector regression (SVR) method with the parameters optimized by using the greedy search method. The molecular descriptors relevant to the prediction of anticonvulsant activities, toxicities and PIs were analyzed by a recursive feature elimination method. The selected molecular descriptors are primarily associated with the drug-like, pharmacological and toxicological features and those used in the published anticonvulsant QSAR and QSTR models. This study suggested that QSIR is useful for estimating the therapeutic index of drug candidates.

In silico de novo design of novel NNRTIs: a bio-molecular modelling approach

Six novel NNRTIs (DABO) with high efficacy are designed by assessing the interaction potential and structural requirements using chemometric analyses (SVM, BPNN and MLR) on structural descriptors.

Design of novel leads: ligand based computational modeling studies on non-nucleoside reverse transcriptase inhibitors (NNRTIs) of HIV-1

Researchers are on the constant lookout for new antiviral agents for the treatment of AIDS. In the present work, ligand based modeling studies are performed on analogues of substituted phenyl-thio-thymines, which act as non-nucleoside reverse transcriptase inhibitors (NNRTIs) and novel leads are extracted. Using alignment-dependent descriptors, based on group center overlap (SALL, HDALL, HAALL and RALL), an alignment-independent descriptor (S log P), a topological descriptor (Balaban index (J)) and a 3D descriptor dipole moment (μ) and shape based descriptors (Kappa 2 index ((2)κ)), a correlation is derived with inhibitory activity. Linear and non-linear techniques have been used to achieve the goal. Support Vector Machine (SVM, R = 0.929, R(2) = 0.863) and Back Propagation Neural Network (BPNN, R = 0.928, R(2) = 0.861) methods yielded near similar results and outperformed Multiple Linear Regression (MLR, R = 0.915, R(2) = 0.837). The predictive ability of the models are cross-validated using a test dataset (SVM: R = 0.846, R(2) = 0.716, BPNN: R = 0.841, R(2) = 0.707 and MLR: R = 0.833, R(2) = 0.694). It is concluded that the hydrophobicity (S log P) and the polarity (μ) of a ligand and the presence of hydrogen donor (HDALL) moieties are the deciding factors in improving antiviral activity and pharmaco-therapeutic properties. Based on the above findings, a virtual dataset is created to extract probable leads with reasonable antiviral activity as well as better pharmacophoric properties.

Efficient calculation of molecular properties from simulation using kernel molecular dynamics

Understanding the relationship between chemical structure and function is a ubiquitous problem within the fields of chemistry and biology. Simulation approaches attack the problem utilizing physics to understand a given process at the particle level. Unfortunately, these approaches are often too expensive for many problems of interest. Informatics approaches attack the problem with empirical analysis of descriptions of chemical structure. The issue in these methods is how to describe molecules in a manner that facilitates accurate and general calculation of molecular properties. Here, we present a novel approach that utilizes aspects of simulation and informatics in order to formulate structure-property relationships. We show how supervised learning can be utilized to overcome the sampling problem in simulation approaches. Likewise, we show how learning can be achieved based on molecular descriptions that are rooted in the physics of dynamic intermolecular forces. We apply the approach to three problems including the analysis of corticosteroid binding globulin ligand binding affinity, identification of formylpeptide receptor ligands, and identification of resveratrol analogues capable of inhibiting activation of transcription factor nuclear factor kappaB.

Prediction of toxicity of nitrobenzenes using ab initio and least squares support vector machines

A quantitative structure-property relationship (QSPR) study is suggested for the prediction of toxicity (IGC50) of nitrobenzenes. Ab initio theory was used to calculate some quantum chemical descriptors including electrostatic potentials and local charges at each atom, HOMO and LUMO energies, etc. Modeling of the IGC50 of nitrobenzenes as a function of molecular structures was established by means of the least squares support vector machines (LS-SVM). This model was applied for the prediction of the toxicity (IGC50) of nitrobenzenes, which were not in the modeling procedure. The resulted model showed high prediction ability with root mean square error of prediction of 0.0049 for LS-SVM. Results have shown that the introduction of LS-SVM for quantum chemical descriptors drastically enhances the ability of prediction in QSAR studies superior to multiple linear regression and partial least squares.