Classifier ensemble based on feature selection and diversity measures for predicting the affinity of A(2B) adenosine receptor antagonists

A Novel Automated Framework for QSAR Modeling of Highly Imbalanced Leishmania High-Throughput Screening Data

In silico prediction of antileishmanial activity using quantitative structure-activity relationship (QSAR) models has been developed on limited and small datasets. Nowadays, the availability of large and diverse high-throughput screening data provides an opportunity to the scientific community to model this activity from the chemical structure. In this study, we present the first KNIME automated workflow to modeling a large, diverse, and highly imbalanced dataset of compounds with antileishmanial activity. Because the data is strongly biased toward inactive compounds, a novel strategy was implemented based on the selection of different balanced training sets and a further consensus model using single decision trees as the base model and three criteria for output combinations. The decision tree consensus was adopted after comparing its classification performance to consensuses built upon Gaussian-Naı̈ve-Bayes, Support-Vector-Machine, Random-Forest, Gradient-Boost, and Multi-Layer-Perceptron base models. All these consensuses were rigorously validated using internal and external test validation sets and were compared against each other using Friedman and Bonferroni-Dunn statistics. For the retained decision tree-based consensus model, which covers 100% of the chemical space of the dataset and with the lowest consensus level, the overall accuracy statistics for test and external sets were between 71 and 74% and 71 and 76%, respectively, while for a reduced chemical space (21%) and with an incremental consensus level, the accuracy statistics were substantially improved with values for the test and external sets between 86 and 92% and 88 and 92%, respectively. These results highlight the relevance of the consensus model to prioritize a relatively small set of active compounds with high prediction sensitivity using the Incremental Consensus at high level values or to predict as many compounds as possible, lowering the level of Incremental Consensus. Finally, the workflow developed eliminates human bias, improves the procedure reproducibility, and allows other researchers to reproduce our design and use it in their own QSAR problems.

Identification of new potent A1 adenosine receptor antagonists using a multistage virtual screening approach

The use of antagonists for each adenosine receptor (AR) subtype as potent clinical candidates is of growing interest due to their involvement in the treatment of various diseases. The recent resolution of several A₁ and A_2A ARs X-ray structures provides opportunities for structure-based drug design. In this study, we describe the discovery of novel A₁AR antagonists by applying a multistage virtual screening approach, which is based on random forest (RF), e-pharmacophore modeling and docking methods. A multistage virtual screening approach was applied to screen the ChemDiv library (1,492,362 compounds). Among the final hits, 22 compounds were selected for further radioligand binding assay analysis against human A₁AR, and 18 compounds (81.82% success) exhibited nanomolar or low micromolar binding potency (K_i). Then, we selected six compounds (pK_i > 6) to further evaluate their antagonist profile in a cAMP functional assay, and we found that they had low micromolar antagonistic activity (pIC₅₀ = 5.51-6.38) for the A₁AR. Particularly, four of six compounds (pK_i > 6) showed very good affinity (pK_i = 6.11-7.13) and selectively (>100-fold) for A₁AR over A_2AAR. Moreover, the novelty analysis suggested that four of six compounds (pK_i > 6) were dissimilar to existing A₁AR antagonists and hence represented novel A₁AR antagonists. Further molecular docking and molecular dynamics (MD) studies showed that the three selective compounds 15, 20 and 22 were stabilized (RMS_lig value ≤ 2 Å) inside the binding pocket of A₁AR with similar orientations to the docking pose in 100-ns MD simulations, whereas they escaped from the binding area of A_2AAR with larger values of RMS_lig (RMS_lig ≥ 2 Å). We hope that these findings provide new insights into the discovery of drugs targeting A₁AR and facilitate research on new drugs and treatments for A₁AR-related human pathologies.

Ensemble-Based Modeling of Chemical Compounds with Antimalarial Activity

Background:

Malaria or Paludism is a tropical disease caused by parasites of the Plasmodium genre and transmitted to humans through the bite of infected mosquitos of the Anopheles genre. This pathology is considered one of the first causes of death in tropical countries and, despite several existing therapies, they have a high toxicity. Computational methods based on Quantitative Structure- Activity Relationship studies have been widely used in drug design work flows.

Objective:

The main goal of the current research is to develop computational models for the identification of antimalarial hit compounds.

Materials and Methods:

For this, a data set suitable for the modeling of the antimalarial activity of chemical compounds was compiled from the literature and subjected to a thorough curation process. In addition, the performance of a diverse set of ensemble-based classification methodologies was evaluated and one of these ensembles was selected as the most suitable for the identification of antimalarial hits based on its virtual screening performance. Data curation was conducted to minimize noise. Among the explored ensemble-based methods, the one combining Genetic Algorithms for the selection of the base classifiers and Majority Vote for their aggregation showed the best performance.

Results:

Our results also show that ensemble modeling is an effective strategy for the QSAR modeling of highly heterogeneous datasets in the discovery of potential antimalarial compounds.

Conclusion:

It was determined that the best performing ensembles were those that use Genetic Algorithms as a method of selection of base models and Majority Vote as the aggregation method.

Exploring the structural determinants of novel xanthine derivatives as A2B adenosine receptor antagonists: a computational study

Adenosine is a ubiquitous endogenous nucleoside that controls numerous physiological functions via interacting with its specific G-coupled receptors. Activation of adenosine receptors (AdoRs), particularly A_2B AdoRs promotes the release of inflammatory cytokines; reduces vascular permeabilization and induces angiogenesis, thereby making A_2B AdoR becomes a potentially pharmacological target for drug development. Presently, for investigating the structural determinants of 164 xanthine derivatives as A_2B AdoR antagonists, we performed an in silico study integrating with 3D-QSAR, docking and molecular dynamics (MD) simulation. The obtained optimal model shows strong predictability (Q² = 0.647, R²_ncv = 0.955, and R²_pred = 0.848). Additionally, to explore the binding mode of the ligand with A_2B AdoR and to understand their binding mechanism, docking analysis, MD simulations (20 ns), and the calculation of binding free energy were also carried out. Finally, the structural determinants of these xanthine derivatives were identified and a total of 20 novel A_2B AdoR antagonists with improved potency were computationally designed, and their synthetic feasibility and selectivity were also evaluated. The information derived from the present study offers a better appreciation for exploring the interaction mechanism of the ligand with A_2B AdoR, which could be helpful for designing novel potent A_2B AdoR antagonists. Communicated by Ramaswamy H. Sarma.

Predicting Subtype Selectivity for Adenosine Receptor Ligands with Three-Dimensional Biologically Relevant Spectrum (BRS-3D)

Adenosine receptors (ARs) are potential therapeutic targets for Parkinson’s disease, diabetes, pain, stroke and cancers. Prediction of subtype selectivity is therefore important from both therapeutic and mechanistic perspectives. In this paper, we introduced a shape similarity profile as molecular descriptor, namely three-dimensional biologically relevant spectrum (BRS-3D), for AR selectivity prediction. Pairwise regression and discrimination models were built with the support vector machine methods. The average determination coefficient (r²) of the regression models was 0.664 (for test sets). The 2B-3 (A_2Bvs A₃) model performed best with q² = 0.769 for training sets (10-fold cross-validation), and r² = 0.766, RMSE = 0.828 for test sets. The models’ robustness and stability were validated with 100 times resampling and 500 times Y-randomization. We compared the performance of BRS-3D with 3D descriptors calculated by MOE. BRS-3D performed as good as, or better than, MOE 3D descriptors. The performances of the discrimination models were also encouraging, with average accuracy (ACC) 0.912 and MCC 0.792 (test set). The 2A-3 (A_2Avs A₃) selectivity discrimination model (ACC = 0.882 and MCC = 0.715 for test set) outperformed an earlier reported one (ACC = 0.784). These results demonstrated that, through multiple conformation encoding, BRS-3D can be used as an effective molecular descriptor for AR subtype selectivity prediction.