A Fuzzy System Classification Approach for QSAR Modeling of α-Amylase and α-Glucosidase Inhibitors

Introduction:

This report proposes the application of a new Machine Learning algorithm called Fuzzy Unordered Rules Induction Algorithm (FURIA)-C in the classification of drug-like compounds with antidiabetic inhibitory ability toward the main two pharmacological targets: α-amylase and α-glucosidase.

Methods:

The two obtained QSAR models were tested for classification capability, achieving satisfactory accuracy scores of 94.5% and 96.5%, respectively. Another important outcome was to achieve various α-amylase and α-glucosidase fuzzy rules with high Certainty Factor values. Fuzzy-Rules derived from the training series and active classification rules were interpreted. An important external validation step, comparing our method with those previously reported, was also included.

Results:

The Holm’s test comparison showed significant differences (p-value<0.05) between FURIA-C, Linear Discriminating Analysis (LDA), and Bayesian Networks, the former beating the two latter ones according to the relative ranking score of the Holm’s test.

Conclusion:

From these results, the FURIA-C algorithm could be used as a cutting-edge technique to predict (classify or screen) the α-amylase and α-glucosidase inhibitory activity of new compounds and hence speed up the discovery of new potent multi-target antidiabetic agents.

Beyond model interpretability using LDA and decision trees for α-amylase and α-glucosidase inhibitor classification studies

In this report are used two data sets involving the main antidiabetic enzyme targets α-amylase and α-glucosidase. The prediction of α-amylase and α-glucosidase inhibitory activity as antidiabetic is carried out using LDA and classification trees (CT). A large data set of 640 compounds for α-amylase and 1546 compounds in the case of α-glucosidase are selected to develop the tree model. In the case of CT-J48 have the better classification model performances for both targets with values above 80%-90% for the training and prediction sets, correspondingly. The best model shows an accuracy higher than 95% for training set; the model was also validated using 10-fold cross-validation procedure and through a test set achieving accuracy values of 85.32% and 86.80%, correspondingly. Additionally, the obtained model is compared with other approaches previously published in the international literature showing better results. Finally, we can say that the present results provided a double-target approach for increasing the estimation of antidiabetic chemicals identification aimed by double-way workflow in virtual screening pipelines.

Exploring the QSAR's predictive truthfulness of the novel N-tuple discrete derivative indices on benchmark datasets

Graph derivative indices (GDIs) have recently been defined over N-atoms (N = 2, 3 and 4) simultaneously, which are based on the concept of derivatives in discrete mathematics (finite difference), metaphorical to the derivative concept in classical mathematical analysis. These molecular descriptors (MDs) codify topo-chemical and topo-structural information based on the concept of the derivative of a molecular graph with respect to a given event (S) over duplex, triplex and quadruplex relations of atoms (vertices). These GDIs have been successfully applied in the description of physicochemical properties like reactivity, solubility and chemical shift, among others, and in several comparative quantitative structure activity/property relationship (QSAR/QSPR) studies. Although satisfactory results have been obtained in previous modelling studies with the aforementioned indices, it is necessary to develop new, more rigorous analysis to assess the true predictive performance of the novel structure codification. So, in the present paper, an assessment and statistical validation of the performance of these novel approaches in QSAR studies are executed, as well as a comparison with those of other QSAR procedures reported in the literature. To achieve the main aim of this research, QSARs were developed on eight chemical datasets widely used as benchmarks in the evaluation/validation of several QSAR methods and/or many different MDs (fundamentally 3D MDs). Three to seven variable QSAR models were built for each chemical dataset, according to the original dissection into training/test sets. The models were developed by using multiple linear regression (MLR) coupled with a genetic algorithm as the feature wrapper selection technique in the MobyDigs software. Each family of GDIs (for duplex, triplex and quadruplex) behaves similarly in all modelling, although there were some exceptions. However, when all families were used in combination, the results achieved were quantitatively higher than those reported by other authors in similar experiments. Comparisons with respect to external correlation coefficients (q²_ext) revealed that the models based on GDIs possess superior predictive ability in seven of the eight datasets analysed, outperforming methodologies based on similar or more complex techniques and confirming the good predictive power of the obtained models. For the q²_ext values, the non-parametric comparison revealed significantly different results to those reported so far, which demonstrated that the models based on DIVATI's indices presented the best global performance and yielded significantly better predictions than the 12 0-3D QSAR procedures used in the comparison. Therefore, GDIs are suitable for structure codification of the molecules and constitute a good alternative to build QSARs for the prediction of physicochemical, biological and environmental endpoints.

New antitrichomonal drug-like chemicals selected by bond (edge)-based TOMOCOMD-CARDD descriptors

Bond-based quadratic indices, new TOMOCOMD-CARDD molecular descriptors, and linear discriminant analysis (LDA) were used to discover novel lead trichomonacidals. The obtained LDA-based quantitative structure-activity relationships (QSAR) models, using nonstochastic and stochastic indices, were able to classify correctly 87.91% (87.50%) and 89.01% (84.38%) of the chemicals in training (test) sets, respectively. They showed large Matthews correlation coefficients of 0.75 (0.71) and 0.78 (0.65) for the training (test) sets, correspondingly. Later, both models were applied to the virtual screening of 21 chemicals to find new lead antitrichomonal agents. Predictions agreed with experimental results to a great extent because a correct classification for both models of 95.24% (20 of 21) of the chemicals was obtained. Of the 21 compounds that were screened and synthesized, 2 molecules (chemicals G-1, UC-245) showed high to moderate cytocidal activity at the concentration of 10 microg/ml, another 2 compounds (G-0 and CRIS-148) showed high cytocidal activity only at the concentration of 100 microg/ml, and the remaining chemicals (from CRIS-105 to CRIS-153, except CRIS-148) were inactive at these assayed concentrations. Finally, the best candidate, G-1 (cytocidal activity of 100% at 10 microg/ml) was in vivo assayed in ovariectomized Wistar rats achieving promising results as a trichomonacidal drug-like compound.