Statistical Quality Of Models Research Articles

Interpretable SMILES-based QSAR Model of Inhibitory Activity of Sirtuins 1 and 2.

Sirtuin 1 (Sirt1) and sirtuin 2 (Sirt2) are NAD+-dependent histone deacetylases which play important functional roles in the removal of the acetyl group of acetyllysine substrates. Considering the dysregulation of Sirt1 and Sirt2 as etiological causes of diseases, Sirt1 and Sirt2 are lucrative target proteins for treatment, thus there has been great interest in the development of Sirt1 and Sirt2 inhibitors. This study compiled the bioactivity data of Sirt1 and Sirt2 for the construction of quantitative structure-activity relationship (QSAR) models in accordance with the OECD principles. Simplified molecular-input line-entry system (SMILES)-based molecular descriptors were used to characterize the molecular features of inhibitors while the Monte Carlo method of the CORAL software was employed for multivariate analysis. The dataset was subjected to 3 random splits in which each split separated the data into 4 subsets consisting of training, invisible training, calibration, and external sets. Statistical indices for the evaluation of QSAR models suggested the good statistical quality of models of Sirt1 and Sirt2 inhibitors. Furthermore, mechanistic interpretation of molecular substructures that are responsible for modulating the bioactivity (i.e., promoters of increase or decrease of bioactivity) was extracted via the analysis of correlation weights. It exhibited molecular features involved in Sirt1 and Sirt2 inhibitors. It is anticipated that QSAR models presented herein can be useful as guidelines in the rational design of potential Sirt1 and Sirt2 inhibitors for the treatment of Sirtuin-related diseases.

The index of ideality of correlation and the variety of molecular rings as a base to improve model of HIV-1 protease inhibitors activity

Computational prediction of HIV-1 protease inhibitor via quantitative structure–activity relationships (QSARs) is a popular study in the field of computational chemistry. The aim of the present study was building up of QSAR models for anti-HIV activity by means of the CORAL software ( http://www.insilico.eu/coral ). Applying of correlation weights for five and six-member molecular rings as components of the target function in the Monte Carlo optimization that is aimed to build up correlation between activity of HIV-1 protease inhibitors expressed as pIC50 = lg[1/(IC50 × 109)] and optimal descriptor improves the predictive potential. Simplified molecular input-line entry system (SMILES) is used as the representation of the molecular structure of HIV-1 protease inhibitors for the QSAR analysis. New criterion of predictive potential so-called index of ideality of correlation (IIC) has been appllied to improve the model for HIV-1 protease inhibitors activity. High correlation coefficients were observed between the experimental and predicted anti-HIV activity. Applying of special ring code as component of the Monte Carlo calculation significantly improves the statistical quality of the model. Furthermore, applying of the IIC as component of the Monte Carlo optimization improves the predictive potential of the CORAL models. The presence of the rings and the quality of these are very important molecular features which are able to improve statistical quality of model for anti-HIV activity. In addition, the ability of IIC to improve predictive potential of a model has been confirmed.

Semi-correlations as a tool to build up categorical (active/inactive) model of GABAA receptor modulator activity

The interpretation of mode of action for GABAA receptor modulator activity is an important task of medicinal chemistry. The computational elucidation of the modulator activity is one of the ways to solve the above task. So-called semi-correlation is a tool for prediction of GABAA receptor modulator activity. The semi-correlation is based on the Monte Carlo method. This approach is to build up categorical classification models into two classes: (i) active and (ii) inactive. The CORAL software ( http://www.insilico.eu/coral ) can be used to build up the semi-correlations. The statistical quality of models (for external validation sets) based on semi-correlation has the range of Matthews correlation coefficient (MCC) is 0.72–1.00 for 30 random splits of all available data (n = 210) into the training and validation sets. In contrast to existing approaches, the predictive CORAL models give prediction using solely data on molecular architecture (represented by simplified molecular input-line entry system = SMILES) and available experimental data on endpoints. Suggested models for prediction of GABAA receptor modulator activity are built up according to the OECD principles. Thus, the approach based on the semi-correlation can be a useful tool for studying of the GABAA receptor modulators activity.

Accurate statistical model of comparison between multiple sequence alignments

Comparison of multiple protein sequence alignments (MSA) reveals unexpected evolutionary relations between protein families and leads to exciting predictions of spatial structure and function. The power of MSA comparison critically depends on the quality of statistical model used to rank the similarities found in a database search, so that biologically relevant relationships are discriminated from spurious connections. Here, we develop an accurate statistical description of MSA comparison that does not originate from conventional models of single sequence comparison and captures essential features of protein families. As a final result, we compute E-values for the similarity between any two MSA using a mathematical function that depends on MSA lengths and sequence diversity. To develop these estimates of statistical significance, we first establish a procedure for generating realistic alignment decoys that reproduce natural patterns of sequence conservation dictated by protein secondary structure. Second, since similarity scores between these alignments do not follow the classic Gumbel extreme value distribution, we propose a novel distribution that yields statistically perfect agreement with the data. Third, we apply this random model to database searches and show that it surpasses conventional models in the accuracy of detecting remote protein similarities.

Computational studies on HIV-1 protease inhibitors: influence of calculated inhibitor-enzyme binding affinities on the statistical quality of 3D-QSAR CoMFA models.

A theoretical study was performed on a set of 38 human immunodeficiency type 1 (HIV-1) protease inhibitors that are structurally similar to the AIDS drug Indinavir. Comparison between the computed binding energies and experimental activity data (pIC(50)) found a high degree of correlation (r(2)() = 0.82). Three-dimensional quantitative structure-activity relationship (3D-QSAR) models using comparative molecular field analysis (CoMFA) yielded predicted activities that were in excellent agreement with the corresponding experimentally determined values. Inclusion of the calculated enzyme-inhibitor binding energy as an additional descriptor in the CoMFA model yielded a significant improvement in the internal predictive ability of our model (q(2)() = 0.45 to q(2)() = 0.69). Separate CoMFA models were constructed to evaluate the influence of different alignment schemes (Atom Fit and Field Fit) and different partial atomic charge assignment schemes (Discover CVFF, Gasteiger-Marsili, and AM1-ESP) on the statistical quality of the models.