Development of a protein-ligand-binding site prediction method based on interaction energy and sequence conservation

Harnessing viral internal proteins to combat flu and beyond

This mini-review examines the strategy of combining viral protein sequence conservation with drug-binding potential to identify novel antiviral targets, focusing on internal proteins of influenza A and other RNA viruses. The importance of combating viral genetic variability and reducing the likelihood of resistance development is emphasised in the context of sequence redundancy in viral datasets. It covers recent structural and functional updates, as well as drug targeting efforts for three internal influenza A viral proteins: Basic Polymerase 2, Nuclear Export Protein, and Nucleoprotein. The review discusses new insights into protein interactions, potential inhibitors, and recent drug discovery efforts. Similar approaches beyond influenza including Hepatitis E, SARS-CoV-2, Dengue, and the HIV-1 virus are also covered briefly.

Protein ligand binding site prediction using graph transformer neural network

Ligand binding site prediction is a crucial initial step in structure-based drug discovery. Although several methods have been proposed previously, including those using geometry based and machine learning techniques, their accuracy is considered to be still insufficient. In this study, we introduce an approach that leverages a graph transformer neural network to rank the results of a geometry-based pocket detection method. We also created a larger training dataset compared to the conventionally used sc-PDB and investigated the correlation between the dataset size and prediction performance. Our findings indicate that utilizing a graph transformer-based method alongside a larger training dataset could enhance the performance of ligand binding site prediction.

Shape Theory Applied to Molecular Docking and Automatic Localization of Ligand Binding Pockets in Large Proteins

Automatic search of cavities and binding mode analysis between a ligand and a 3D protein receptor are challenging problems in drug design or repositioning. We propose a solution based on a shape theory theorem for an invariant coupled system of ligand-protein. The theorem provides a matrix representation with the exact formulas to be implemented in an algorithm. The method involves the following results: (1) exact formulae for the shape coordinates of a located-rotated invariant coupled system; (2) a parameterized search based on a suitable domain of van der Waals radii; (3) a scoring function for the discrimination of sites by measuring the distance between two invariant coupled systems including the atomic mass; (4) a matrix representation of the Lennard-Jones potential type 6-12 and 6-10 as the punctuation function of the algorithm for a molecular docking; and (5) the optimal molecular docking as a solution of an optimization problem based on the exploration of an exhaustive set of rotations. We apply the method in the xanthine oxidase protein with the following ligands: hypoxanthine, febuxostat, and chlorogenic acid. The results show automatic cavity detection and molecular docking not assisted by experts with meaningful amino acid interactions. The method finds better affinities than the expert software for known published cavities.

Applications of machine learning in computer-aided drug discovery

Machine learning (ML) has revolutionised the field of structure-based drug design (SBDD) in recent years. During the training stage, ML techniques typically analyse large amounts of experimentally determined data to create predictive models in order to inform the drug discovery process. Deep learning (DL) is a subfield of ML, that relies on multiple layers of a neural network to extract significantly more complex patterns from experimental data, and has recently become a popular choice in SBDD. This review provides a thorough summary of the recent DL trends in SBDD with a particular focus on de novo drug design, binding site prediction, and binding affinity prediction of small molecules.

DeepPocket: Ligand Binding Site Detection and Segmentation using 3D Convolutional Neural Networks

A structure-based drug design pipeline involves the development of potential drug molecules or ligands that form stable complexes with a given receptor at its binding site. A prerequisite to this is finding druggable and functionally relevant binding sites on the 3D structure of the protein. Although several methods for detecting binding sites have been developed beforehand, a majority of them surprisingly fail in the identification and ranking of binding sites accurately. The rapid adoption and success of deep learning algorithms in various sections of structural biology beckons the usage of such algorithms for accurate binding site detection. As a combination of geometry based software and deep learning, we report a novel framework, DeepPocket that utilizes 3D convolutional neural networks for the rescoring of pockets identified by Fpocket and further segments these identified cavities on the protein surface. Apart from this, we also propose another data set SC6K containing protein structures submitted in the Protein Data Bank (PDB) from January 1st, 2018, until February 28th, 2020, for ligand binding site (LBS) detection. DeepPocket's results on various binding site data sets and SC6K highlight its better performance over current state-of-the-art methods and good generalization ability over novel structures.

DeepSurf: A surface-based deep learning approach for the prediction of ligand binding sites on proteins

MOTIVATION

The knowledge of potentially druggable binding sites on proteins is an important preliminary step towards the discovery of novel drugs. The computational prediction of such areas can be boosted by following the recent major advances in the deep learning field and by exploiting the increasing availability of proper data.

RESULTS

In this paper, a novel computational method for the prediction of potential binding sites is proposed, called DeepSurf. DeepSurf combines a surface-based representation, where a number of 3 D voxelized grids are placed on the protein's surface, with state-of-the-art deep learning architectures. After being trained on the large database of scPDB, DeepSurf demonstrates superior results on three diverse testing datasets, by surpassing all its main deep learning-based competitors, while attaining competitive performance to a set of traditional non-data-driven approaches.

AVAILABILITY

The source code of the method along with trained models are freely available at https://github.com/stemylonas/DeepSurf.git.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Computational methods and tools for binding site recognition between proteins and small molecules: from classical geometrical approaches to modern machine learning strategies

In the current "genomic era" the number of identified genes is growing exponentially. However, the biological function of a large number of the corresponding proteins is still unknown. Recognition of small molecule ligands (e.g., substrates, inhibitors, allosteric regulators, etc.) is pivotal for protein functions in the vast majority of the cases and knowledge of the region where these processes take place is essential for protein function prediction and drug design. In this regard, computational methods represent essential tools to tackle this problem. A significant number of software tools have been developed in the last few years which exploit either protein sequence information, structure information or both. This review describes the most recent developments in protein function recognition and binding site prediction, in terms of both freely-available and commercial solutions and tools, detailing the main characteristics of the considered tools and providing a comparative analysis of their performance.

Docking study of flavonoid derivatives as potent inhibitors of influenza H1N1 virus neuraminidase

Influenza type A is considered as a severe public health concern. The mechanism of drugs applied for the control of this virus depends on two surface glycoproteins with antigenic properties, namely hemagglutinin (HA) and neuraminidase (NA). HA aids the virus to penetrate cells in the early stage of infection and NA is an enzyme with the ability to break glycoside bonds, which enables virion spread through the host cell membrane. Since NA contains a relatively preserved active site, it has been an important target in drug design. Oseltamivir is a common drug used for the treatment of influenza infections, for which cases of resistance have recently been reported, giving rise to health concerns. Flavonoids are natural polyphenolic compounds with potential blocking effects in the neuraminidase active site. Based on their antiviral effect, the flavonoids quercetin, catechin, naringenin, luteolin, hispidulin, vitexin, chrysin and kaempferol were selected in the present study and compared alongside oseltamivir on molecular docking, binding energy and active site structure, in order to provide insight on the potential of these compounds as targeted drugs for the control and treatment of influenza type A. The molecular characterization of flavonoids with binding affinity was performed using AutoDock Vina software. The results indicated that these compounds may effectively block the NA active site. Therefore, these natural compounds derived from fruits have the potential for development into drugs for controlling influenza, which may aid overcome the clinical challenge of the H1N1 strain epidemic.