Improving Structure-Based Virtual Screening with Ensemble Docking and Machine Learning.

One of the main challenges of structure-based virtual screening (SBVS) is the incorporation of the receptor's flexibility, as its explicit representation in every docking run implies a high computational cost. Therefore, a common alternative to include the receptor's flexibility is the approach known as ensemble docking. Ensemble docking consists of using a set of receptor conformations and performing the docking assays over each of them. However, there is still no agreement on how to combine the ensemble docking results to obtain the final ligand ranking. A common choice is to use consensus strategies to aggregate the ensemble docking scores, but these strategies exhibit slight improvement regarding the single-structure approach. Here, we claim that using machine learning (ML) methodologies over the ensemble docking results could improve the predictive power of SBVS. To test this hypothesis, four proteins were selected as study cases: CDK2, FXa, EGFR, and HSP90. Protein conformational ensembles were built from crystallographic structures, whereas the evaluated compound library comprised up to three benchmarking data sets (DUD, DEKOIS 2.0, and CSAR-2012) and cocrystallized molecules. Ensemble docking results were processed through 30 repetitions of 4-fold cross-validation to train and validate two ML classifiers: logistic regression and gradient boosting trees. Our results indicate that the ML classifiers significantly outperform traditional consensus strategies and even the best performance case achieved with single-structure docking. We provide statistical evidence that supports the effectiveness of ML to improve the ensemble docking performance.

Molecular modeling simulation studies reveal new potential inhibitors against HPV E6 protein.

High-risk strains of human papillomavirus (HPV) have been identified as the etiologic agent of some anogenital tract, head, and neck cancers. Although prophylactic HPV vaccines have been approved; it is still necessary a drug-based treatment against the infection and its oncogenic effects. The E6 oncoprotein is one of the most studied therapeutic targets of HPV, it has been identified as a key factor in cell immortalization and tumor progression in HPV-positive cells. E6 can promote the degradation of p53, a tumor suppressor protein, through the interaction with the cellular ubiquitin ligase E6AP. Therefore, preventing the formation of the E6-E6AP complex is one of the main strategies to inhibit the viability and proliferation of infected cells. Herein, we propose an in silico pipeline to identify small-molecule inhibitors of the E6-E6AP interaction. Virtual screening was carried out by predicting the ADME properties of the molecules and performing ensemble-based docking simulations to E6 protein followed by binding free energy estimation through MM/PB(GB)SA methods. Finally, the top-three compounds were selected, and their stability in the E6 docked complex and their effect in the inhibition of the E6-E6AP interaction was corroborated by molecular dynamics simulation. Therefore, this pipeline and the identified molecules represent a new starting point in the development of anti-HPV drugs.