Background: A high-throughput virtual screening pipeline has been extended from single energetically minimized structure Molecular Mechanics/Generalized Born Surface Area (MM/GBSA) rescoring to ensemble-average MM/GBSA rescoring. The correlation coefficient (R2) of calculated and experimental binding free energies for a series of antithrombin ligands has been improved from 0.36 to 0.69 when switching from the single-structure MM/GBSA rescoring to ensemble-average one. The electrostatic interactions in both solute and solvent are identified to play an important role in determining the binding free energy after the decomposition of the calculated binding free energy. The increasing negative charge of the compounds provides a more favorable electrostatic energy change but creates a higher penalty for the solvation free energy. Such a penalty is compensated by the electrostatic energy change, which results in a better binding affinity. A highly hydrophobic ligand is determined by the docking program to be a non-specific binder. Results: Our results have demonstrated that it is very important to keep a few top poses for rescoring, if the binding is non-specific or the binding mode is not well determined by the docking calculation.

Background: Virtual Screening (VS) methods can considerably aid clinical research, predicting how ligands interact with drug targets. Most VS methods suppose a unique binding site for the target, usually derived from the interpretation of the protein crystal structure. However, it has been demonstrated that in many cases, diverse ligands interact with unrelated parts of the target and many VS methods do not take into account this relevant fact. Results: We present BINDSURF, a novel VS methodology that scans the whole protein surface in order to find new hotspots, where ligands might potentially interact with, and which is implemented in last generation massively parallel GPU hardware, allowing fast processing of large ligand databases. Conclusions: BINDSURF is an efficient and fast blind methodology for the determination of protein binding sites depending on the ligand, that uses the massively parallel architecture of GPUs for fast pre-screening of large ligand databases. Its results can also guide posterior application of more detailed VS methods in concrete binding sites of proteins, and its utilization can aid in drug discovery, design, repurposing and therefore help considerably in clinical research.

De novo drug design is a stationary way to build novel ligands in the confined pocket of receptor by assembling the atoms or fragments, while molecular dynamics (MD) simulation is a dynamical way to study the interaction mechanism between the ligands and receptors based on the molecular force field. De novo drug design and MD simulation are effective tools for novel drug discovery. With the development of technology, deep learning methods, and interpretable machine learning (IML) have emerged in the research area of drug design. Deep learning methods and IML can be used further to improve the efficiency and accuracy of de novo drug design and MD simulations. The application summary of deep learning methods for de novo drug design, MD simulations, and IML can further promote the technical development of drug discovery. In this article, two major workflow methods and the related components of classical algorithm and deep learning are described for de novo drug design from a new perspective. The application progress of deep learning is also summarized for MD simulations. Furthermore, IML is introduced for the deep learning model interpretability of de novo drug design and MD simulations. Our paper deals with an interesting topic about deep learning applications of de novo drug design and MD simulations for the scientific community.This article is categorized under: Data Science > Chemoinformatics Data Science > Artificial Intelligence/Machine Learning

The optimal selection of chemical features (molecular descriptors) is an essential pre-processing step for the efficient application of computational intelligence techniques in virtual screening for identification of bioactive molecules in drug discovery. The selection of molecular descriptors has key influence in the accuracy of affinity prediction. In order to improve this prediction, we examined a Random Forest (RF)-based approach to automatically select molecular descriptors of training data for ligands of kinases, nuclear hormone receptors, and other enzymes. The reduction of features to use during prediction dramatically reduces the computing time over existing approaches and consequently permits the exploration of much larger sets of experimental data. To test the validity of the method, we compared the results of our approach with the ones obtained using manual feature selection in our previous study (Perez-Sanchez, Cano, and Garcia-Rodriguez, 2014).The main novelty of this work in the field of drug discovery is the use of RF in two different ways: feature ranking and dimensionality reduction, and classification using the automatically selected feature subset. Our RF-based method outperforms classification results provided by Support Vector Machine (SVM) and Neural Networks (NN) approaches.This work was partially supported by the Fundación Séneca del Centro de Coordinación de la Investigación de la Región de Murcia under Project 18946/JLI/13. This work has been funded by the Nils Coordinated Mobility under grant 012-ABEL-CM-2014A, in part financed by the European Regional Development Fund (ERDF)

The explosion of the data both in the biomedical research and in the healthcare systems demands urgent solutions. In particular, the research in omics sciences is moving from a hypothesis-driven to a data-driven approach. Healthcare is additionally always asking for a tighter integration with biomedical data in order to promote personalized medicine and to provide better treatments. Efficient analysis and interpretation of Big Data opens new avenues to explore molecular biology, new questions to ask about physiological and pathological states, and new ways to answer these open issues. Such analyses lead to better understanding of diseases and development of better and personalized diagnostics and therapeutics. However, such progresses are directly related to the availability of new solutions to deal with this huge amount of information. New paradigms are needed to store and access data, for its annotation and integration and finally for inferring knowledge and making it available to researchers. Bioinformatics can be viewed as the “glue” for all these processes. A clear awareness of present high performance computing (HPC) solutions in bioinformatics, Big Data analysis paradigms for computational biology, and the issues that are still open in the biomedical and healthcare fields represent the starting point to win this challenge.