Featurization strategies for protein–ligand interactions and their applications in scoring function development

Xiong, Guo-Li; Shen, Chao; Yang, Ziyi; Jiang, Dejun; Shao, Lei; Lü, Aiping; Chen, Xiang; Hou, Tingjun; Cao, Dong‐Sheng

doi:10.1002/wcms.1567

Cited by 35 publications

(36 citation statements)

References 148 publications

(189 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The top-ranked poses were subjected for refinement and calculation of binding free energies (ΔG), which was evaluated by scoring function (GBVI/WSA dg) [ 45 ]. A reliable scoring scheme that results in the docking score of the correct binding poses was established by the number of molecular interactions (hydrogen, Pi, and hydrophobic interactions) [ 46 ]. The MOE database of the docked complex was visualized carefully to understand the mode of binding interactions of α-glucosidase inhibitors bound in the selected pocket of the target protein.…”

Section: Methodsmentioning

confidence: 99%

Preparation and Evaluation of Chitosan/PVA Based Hydrogel Films Loaded with Honey for Wound Healing Application

Chopra

Bibi

Kumar³

et al. 2022

Gels

105

View full text Add to dashboard Cite

In the present study, chitosan/polyvinyl alcohol (PVA)-based honey hydrogel films were developed for potential wound healing application. The hydrogel films were developed by a solvent-casting method and were evaluated in terms of thickness, weight variation, folding endurance, moisture content and moisture uptake. The water vapor transmission rate was found to range between 1650.50 ± 35.86 and 2698.65 ± 76.29 g/m2/day. The tensile strength and elongation at break were found to range between 4.74 ± 0.83 and 38.36 ± 5.39 N, and 30.58 ± 3.64 and 33.51 ± 2.47 mm, respectively, indicating significant mechanical properties of the films. SEM images indicated smooth surface morphology of the films. FTIR, DSC and in silico analysis were performed, which highlighted the docking energies of the protein–ligand complex and binding interactions such as hydrogen bonding, Pi–Pi bonding, and Pi–H bonding between the selected compounds and target proteins; hence, we concluded, with the three best molecules (lumichrome, galagin and chitosan), that there was wound healing potential. In vitro studies pointed toward a sustained release of honey from the films. The antimicrobial performance of the films was investigated against Staphylococcus aureus. Overall, the results signaled the potential application of chitosan/PVA based hydrogel films as wound dressings. Furthermore, in vivo experiments may be required to evaluate the clinical efficacy of honey-loaded chitosan/PVA hydrogel films in wound healing.

show abstract

Section: Methodsmentioning

confidence: 99%

Preparation and Evaluation of Chitosan/PVA Based Hydrogel Films Loaded with Honey for Wound Healing Application

Chopra

Bibi

Kumar³

et al. 2022

Gels

105

View full text Add to dashboard Cite

show abstract

“…It is also frequently applied in interpreting activity landscapes, supporting structural databases, and analyzing protein-ligand complexes to search for similarities, e.g., by calculating the Tanimoto coefficient of bit vectors. In rational drug discovery, SIFt supports processing virtual screening results [ 39 , 31 , 40 ] or developing new scoring functions [ 41 , 42 ]. With the growing importance of artificial intelligence methods in drug discovery, new applications of interaction fingerprints emerged.…”

Section: Introductionmentioning

confidence: 99%

fingeRNAt—A novel tool for high-throughput analysis of nucleic acid-ligand interactions

et al. 2022

View full text Add to dashboard Cite

Computational methods play a pivotal role in drug discovery and are widely applied in virtual screening, structure optimization, and compound activity profiling. Over the last decades, almost all the attention in medicinal chemistry has been directed to protein-ligand binding, and computational tools have been created with this target in mind. With novel discoveries of functional RNAs and their possible applications, RNAs have gained considerable attention as potential drug targets. However, the availability of bioinformatics tools for nucleic acids is limited. Here, we introduce fingeRNAt—a software tool for detecting non-covalent interactions formed in complexes of nucleic acids with ligands. The program detects nine types of interactions: (i) hydrogen and (ii) halogen bonds, (iii) cation-anion, (iv) pi-cation, (v) pi-anion, (vi) pi-stacking, (vii) inorganic ion-mediated, (viii) water-mediated, and (ix) lipophilic interactions. However, the scope of detected interactions can be easily expanded using a simple plugin system. In addition, detected interactions can be visualized using the associated PyMOL plugin, which facilitates the analysis of medium-throughput molecular complexes. Interactions are also encoded and stored as a bioinformatics-friendly Structural Interaction Fingerprint (SIFt)—a binary string where the respective bit in the fingerprint is set to 1 if a particular interaction is present and to 0 otherwise. This output format, in turn, enables high-throughput analysis of interaction data using data analysis techniques. We present applications of fingeRNAt-generated interaction fingerprints for visual and computational analysis of RNA-ligand complexes, including analysis of interactions formed in experimentally determined RNA-small molecule ligand complexes deposited in the Protein Data Bank. We propose interaction fingerprint-based similarity as an alternative measure to RMSD to recapitulate complexes with similar interactions but different folding. We present an application of interaction fingerprints for the clustering of molecular complexes. This approach can be used to group ligands that form similar binding networks and thus have similar biological properties. The fingeRNAt software is freely available at https://github.com/n-szulc/fingeRNAt.

show abstract

“…A more in-depth overview of featurization strategies for protein-ligand interactions that are commonly employed in the development of ML and DL SFs is given by Xiong et al (2021), while an overview of common molecular representations used in AI-driven drug discovery is provided by David et al (2020).…”

Section: Descriptorsmentioning

confidence: 99%

Scoring Functions for Protein-Ligand Binding Affinity Prediction Using Structure-based Deep Learning: A Review

2022

View full text Add to dashboard Cite

The rapid and accurate in silico prediction of protein-ligand binding free energies or binding affinities has the potential to transform drug discovery. In recent years, there has been a rapid growth of interest in deep learning methods for the prediction of protein-ligand binding affinities based on the structural information of protein-ligand complexes. These structure-based scoring functions often obtain better results than classical scoring functions when applied within their applicability domain. Here we review structure-based scoring functions for binding affinity prediction based on deep learning, focussing on different types of architectures, featurization strategies, data sets, methods for training and evaluation, and the role of explainable artificial intelligence in building useful models for real drug-discovery applications.

show abstract

Featurization strategies for protein–ligand interactions and their applications in scoring function development

Cited by 35 publications

References 148 publications

Preparation and Evaluation of Chitosan/PVA Based Hydrogel Films Loaded with Honey for Wound Healing Application

Preparation and Evaluation of Chitosan/PVA Based Hydrogel Films Loaded with Honey for Wound Healing Application

fingeRNAt—A novel tool for high-throughput analysis of nucleic acid-ligand interactions

Scoring Functions for Protein-Ligand Binding Affinity Prediction Using Structure-based Deep Learning: A Review

Contact Info

Product

Resources

About