Hybrid-genetic algorithm based descriptor optimization and QSAR models for predicting the biological activity of Tipranavir analogs for HIV protease inhibition

BrainPepPass: A Framework Based on Supervised Dimensionality Reduction for Predicting Blood-Brain Barrier-Penetrating Peptides

Peptides that pass through the blood-brain barrier (BBB) not only are implicated in brain-related pathologies but also are promising therapeutic tools for treating brain diseases, e.g., as shuttles carrying active medicines across the BBB. Computational prediction of BBB-penetrating peptides (B3PPs) has emerged as an interesting approach because of its ability to screen large peptide libraries in a cost-effective manner. In this study, we present BrainPepPass, a machine learning (ML) framework that utilizes supervised manifold dimensionality reduction and extreme gradient boosting (XGB) algorithms to predict natural and chemically modified B3PPs. The results indicate that the proposed tool outperforms other classifiers, with average accuracies exceeding 94% and 98% in 10-fold cross-validation and leave-one-out cross-validation (LOOCV), respectively. In addition, accuracy values ranging from 45% to 97.05% were achieved in the independent tests. The BrainPepPass tool is available in a public repository for academic use (https://github.com/ewerton-cristhian/BrainPepPass).

A novel hybrid method named electron conformational genetic algorithm as a 4D QSAR investigation to calculate the biological activity of the tetrahydrodibenzazosines

To understand the structure-activity correlation of a group of tetrahydrodibenzazocines as inhibitors of 17β-hydroxysteroid dehydrogenase type 3, we have performed a combined genetic algorithm (GA) and four-dimensional quantitative structure-activity relationship (4D-QSAR) modeling study. The computed electronic and geometry structure descriptors were regulated as a matrix and named as electron-conformational matrix of contiguity (ECMC). A chemical property-based pharmacophore model was developed for series of tetrahydrodibenzazocines by EMRE software package. GA was employed to choose an optimal combination of parameters. A model has been developed for estimating anticancer activity quantitatively. All QSAR models were established with 40 compounds (training set), then they were considered for selective capability with additional nine compounds (test set). A statistically valid 4D-QSAR ( R training 2 = 0.856 , R test 2 = 0.851 and q² = 0.650) with good external set prediction was obtained.

Filter feature selectors in the development of binary QSAR models

The application of machine learning methods to the construction of quantitative structure-activity relationship models is a complex computational problem in which dimensionality reduction of the representation of the molecular structure plays a fundamental role in predicting a target activity. The feature selection pre-processing approach has been indicated to be effective in dimensionality reduction for building simpler and more understandable models. In this paper, a performance comparative study of 13 state-of-the-art feature selection filter methods is conducted. Structure-activity relationship models are constructed using three widely used classifiers and a diverse collection of datasets. The comparative study utilizes robust statistical tests to compare the algorithms. According to the experimental results, there are substantial differences in performance among the evaluated feature selection methods. The methods that exhibit the best performance are correlation-based feature selection, fast clustering-based feature selection and the set cover method.

Literature Review of (Q)SAR Modelling of Nanomaterial Toxicity

Despite the clear benefits that nanotechnology can bring to various sectors of industry, there are serious concerns about the potential health risks associated with engineered nanomaterials (ENMs), intensified by the limited understanding of what makes ENMs toxic and how to make them safe. As the use of ENMs for commercial purposes and the number of workers/end-users being exposed to these materials on a daily basis increases, the need for assessing the potential adverse effects of multifarious ENMs in a time- and cost-effective manner becomes more apparent. One strategy to alleviate the problem of testing a large number and variety of ENMs in terms of their toxicological properties is through the development of computational models that decode the relationships between the physicochemical features of ENMs and their toxicity. Such data-driven models can be used for hazard screening, early identification of potentially harmful ENMs and the toxicity-governing physicochemical properties, and accelerating the decision-making process by maximising the use of existing data. Moreover, these models can also support industrial, regulatory and public needs for designing inherently safer ENMs. This chapter is mainly concerned with the investigation of the applicability of (quantitative) structure-activity relationship ((Q)SAR) methods to modelling of ENMs' toxicity. It summarizes the key components required for successful application of data-driven toxicity prediction techniques to ENMs, the published studies in this field and the current limitations of this approach.

Quantitative structure-activity relationship study on BTK inhibitors by modified multivariate adaptive regression spline and CoMSIA methods

Bruton's tyrosine kinase (BTK) plays a crucial role in B-cell activation and development, and has emerged as a new molecular target for the treatment of autoimmune diseases and B-cell malignancies. In this study, two- and three-dimensional quantitative structure-activity relationship (2D and 3D-QSAR) analyses were performed on a series of pyridine and pyrimidine-based BTK inhibitors by means of genetic algorithm optimized multivariate adaptive regression spline (GA-MARS) and comparative molecular similarity index analysis (CoMSIA) methods. Here, we propose a modified MARS algorithm to develop 2D-QSAR models. The top ranked models showed satisfactory statistical results (2D-QSAR: Q(2) = 0.884, r(2) = 0.929, r(2)pred = 0.878; 3D-QSAR: q(2) = 0.616, r(2) = 0.987, r(2)pred = 0.905). Key descriptors selected by 2D-QSAR were in good agreement with the conclusions of 3D-QSAR, and the 3D-CoMSIA contour maps facilitated interpretation of the structure-activity relationship. A new molecular database was generated by molecular fragment replacement (MFR) and further evaluated with GA-MARS and CoMSIA prediction. Twenty-five pyridine and pyrimidine derivatives as novel potential BTK inhibitors were finally selected for further study. These results also demonstrated that our method can be a very efficient tool for the discovery of novel potent BTK inhibitors.

QSAR prediction of HIV-1 protease inhibitory activities using docking derived molecular descriptors

In this study, application of a new hybrid docking-quantitative structure activity relationship (QSAR) methodology to model and predict the HIV-1 protease inhibitory activities of a series of newly synthesized chemicals is reported. This hybrid docking-QSAR approach can provide valuable information about the most important chemical and structural features of the ligands that affect their inhibitory activities. Docking studies were used to find the actual conformations of chemicals in active site of HIV-1 protease. Then the molecular descriptors were calculated from these conformations. Multiple linear regression (MLR) and least square support vector machine (LS-SVM) were used as QSAR models, respectively. The obtained results reveal that statistical parameters of the LS-SVM model are better than the MLR model, which indicate that there are some non-linear relations between selected molecular descriptors and anti-HIV activities of interested chemicals. The correlation coefficient (R), root mean square error (RMSE) and average absolute error (AAE) for LS-SVM are: R=0.988, RMSE=0.207 and AAE=0.145 for the training set, and R=0.965, RMSE=0.403 and AAE=0.338 for the test set. Leave one out cross validation test was used for assessment of the predictive power and validity of models which led to cross-validation correlation coefficient QUOTE of 0.864 and 0.850 and standardized predicted relative error sum of squares (SPRESS) of 0.553 and 0.581 for LS-SVM and MLR models, respectively.

Systems biological approach of molecular descriptors connectivity: optimal descriptors for oral bioavailability prediction

BACKGROUND

Poor oral bioavailability is an important parameter accounting for the failure of the drug candidates. Approximately, 50% of developing drugs fail because of unfavorable oral bioavailability. In silico prediction of oral bioavailability (%F) based on physiochemical properties are highly needed. Although many computational models have been developed to predict oral bioavailability, their accuracy remains low with a significant number of false positives. In this study, we present an oral bioavailability model based on systems biological approach, using a machine learning algorithm coupled with an optimal discriminative set of physiochemical properties.

RESULTS

The models were developed based on computationally derived 247 physicochemical descriptors from 2279 molecules, among which 969, 605 and 705 molecules were corresponds to oral bioavailability, intestinal absorption (HIA) and caco-2 permeability data set, respectively. The partial least squares discriminate analysis showed 49 descriptors of HIA and 50 descriptors of caco-2 are the major contributing descriptors in classifying into groups. Of these descriptors, 47 descriptors were commonly associated to HIA and caco-2, which suggests to play a vital role in classifying oral bioavailability. To determine the best machine learning algorithm, 21 classifiers were compared using a bioavailability data set of 969 molecules with 47 descriptors. Each molecule in the data set was represented by a set of 47 physiochemical properties with the functional relevance labeled as (+bioavailability/-bioavailability) to indicate good-bioavailability/poor-bioavailability molecules. The best-performing algorithm was the logistic algorithm. The correlation based feature selection (CFS) algorithm was implemented, which confirms that these 47 descriptors are the fundamental descriptors for oral bioavailability prediction.

CONCLUSION

The logistic algorithm with 47 selected descriptors correctly predicted the oral bioavailability, with a predictive accuracy of more than 71%. Overall, the method captures the fundamental molecular descriptors, that can be used as an entity to facilitate prediction of oral bioavailability.

Computational analysis of HIV-1 protease protein binding pockets

Mutations that arise in HIV-1 protease after exposure to various HIV-1 protease inhibitors have proved to be a difficult aspect in the treatment of HIV. Mutations in the binding pocket of the protease can prevent the protease inhibitor from binding to the protein effectively. In the present study, the crystal structures of 68 HIV-1 proteases complexed with one of the nine FDA approved protease inhibitors from the Protein Data Bank (PDB) were analyzed by (a) identifying the mutational changes with the aid of a developed mutation map and (b) correlating the structure of the binding pockets with the complexed inhibitors. The mutations of each crystal structure were identified by comparing the amino acid sequence of each structure against the HIV-1 wild-type strain HXB2. These mutations were visually presented in the form of a mutation map to analyze mutation patterns corresponding to each protease inhibitor. The crystal structure mutation patterns of each inhibitor (in vitro) were compared against the mutation patterns observed in in vivo data. The in vitro mutation patterns were found to be representative of most of the major in vivo mutations. We then performed a data mining analysis of the binding pockets from each crystal structure in terms of their chemical descriptors to identify important structural features of the HIV-1 protease protein with respect to the binding conformation of the HIV-1 protease inhibitors. Data mining analysis is performed using several classification techniques: Random Forest (RF), linear discriminant analysis (LDA), and logistic regression (LR). We developed two hybrid models, RF-LDA and RF-LR. Random Forest is used as a feature selection proxy, reducing the descriptor space to a few of the most relevant descriptors determined by the classifier. These descriptors are then used to develop the subsequent LDA, LR, and hierarchical classification models. Clustering analysis of the binding pockets using the selected descriptors used to produce the optimal classification models reveals conformational similarities of the ligands in each cluster. This study provides important information in understanding the structural features of HIV-1 protease which cannot be studied by other existing in vivo genomic data sets.

Consensus features of CP-MLR and GA in modeling HIV-1 RT inhibitory activity of 4-benzyl/benzoylpyridin-2-one analogues

The HIV-1 reverse transcriptase (RT) inhibitory activity of benzyl/benzoylpyridinones is modeled with molecular features identified in combinatorial protocol in multiple linear regression (CP-MLR) and genetic algorithm (GA). Among the features, nDB and LogP are found to be the most influential descriptors to modulate the activity. Although the coefficient of nDB suggested in favor of benzylpyridinones skeleton, the coefficient of LogP suggested the favorability of hydrophilic nature in compounds for better activity. The partial least squares analysis of the descriptors common to CP-MLR and GA has displayed their predictivity over the total descriptors identified in both the approaches. The back-propagation artificial neural networks model from the five most significant common descriptors (nDB, T(O..O), MATS8e, LogP, and BELp4) has explained 93.2% variance in the HIV-1 RT activity of the training set compounds and showed a test set r(2) of 0.89. The results suggest that the descriptors have the ability to identify the patterns in the compounds to predict potential analogues.