sc-PDB: a 3D-database of ligandable binding sites—10 years on

Desaphy, Jérémy; Bret, Guillaume; Rognan, Didier; Kellenberger, Esther

doi:10.1093/nar/gku928

Cited by 232 publications

(212 citation statements)

References 27 publications

Supporting

Mentioning

211

Contrasting

Order By: Relevance

“…For training and validation of the model the sc-PDB [21] dataset was used. The database consists of known binding sites, accompanied with prepared protein structures.…”

Section: Datamentioning

confidence: 99%

Improving detection of protein-ligand binding sites with 3D segmentation

Stepniewska-Dziubinska

Zielenkiewicz

Siedlecki

2020

Sci Rep

109

View full text Add to dashboard Cite

In recent years machine learning (ML) took bioand cheminformatics fields by storm, providing new solutions for a vast repertoire of problems related to protein sequence, structure, and interactions analysis. ML techniques, deep neural networks especially, were proven more effective than classical models for tasks like predicting binding affinity for molecular complex.In this work we investigated the earlier stage of drug discovery process -finding druggable pockets on protein surface, that can be later used to design active molecules. For this purpose we developed a 3D fully convolutional neural network capable of binding site segmentation.Our solution has high prediction accuracy and provides intuitive representations of the results, which makes it easy to incorporate into drug discovery projects. The model's source code, together with scripts for most common use-cases is freely available at

show abstract

“…For training and validation of the model the sc-PDB [21] dataset was used. The database consists of known binding sites, accompanied with prepared protein structures.…”

Section: Datamentioning

confidence: 99%

Improving detection of protein-ligand binding sites with 3D segmentation

Stepniewska-Dziubinska

Zielenkiewicz

Siedlecki

2020

Sci Rep

109

View full text Add to dashboard Cite

show abstract

“…From all the available structures of human GSK3β in the Protein Data Bank (PDB), the 3-dimensional (3D) crystallographic structure 6B8J with the co-crystalized ligand 65C, was selected, and thus the protein structure modelling from it [47,48]. The meridianins and lignarenone B structures were modelled from the 2D chemical structure previously published [36][37][38][39].…”

Section: Target Selection and Modellingmentioning

confidence: 99%

Meridianins and Lignarenone B as Potential GSK3β Inhibitors and Inductors of Structural Neuronal Plasticity

et al. 2020

View full text Add to dashboard Cite

Glycogen Synthase Kinase 3 (GSK3) is an essential protein, with a relevant role in many diseases such as diabetes, cancer and neurodegenerative disorders. Particularly, the isoform GSK3β is related to pathologies such as Alzheimer's disease (AD). This enzyme constitutes a very interesting target for the discovery and/or design of new therapeutic agents against AD due to its relation to the hyperphosphorylation of the microtubule-associated protein tau (MAPT), and therefore, its contribution to neurofibrillary tangles (NFT) formation. An in silico target profiling study identified two marine molecular families, the indole alkaloids meridianins from the tunicate genus Aplidium, and lignarenones, the secondary metabolites of the shelled cephalaspidean mollusc Scaphander lignarius, as possible GSK3β inhibitors. The analysis of the surface of GSK3β, aimed to find possible binding regions, and the subsequent in silico binding studies revealed that both marine molecular families can act over the ATP and/or substrate binding regions. The predicted inhibitory potential of the molecules from these two chemical families was experimentally validated in vitro by showing ã 50% of increased Ser9 phosphorylation levels of the GSK3β protein. Furthermore, we determined that molecules from both molecular families potentiate structural neuronal plasticity in vitro. These results allow us to suggest that meridianins and lignarenone B could be used as possible therapeutic candidates for the treatment of GSK3β involved pathologies, such as AD.

show abstract

“…DeepSite is more accurate against the sc-PDB database of binding sites PickPocket: Pocket binding prediction for specific ligand families using neural networks. (40). However, fpocket is fast, and pocket descriptors data is easily retrieved from output files.…”

Section: Discussion and Perspectivesmentioning

confidence: 99%

PickPocket : Pocket binding prediction for specific ligands family using neural networks.

Viart

Lorenzi

Moriel‐Carretero³

et al. 2020

Preprint

View full text Add to dashboard Cite

Most of the protein biological functions occur through contacts with other proteins or ligands. The residues that constitute the contact surface of a ligand-binding pocket are usually located far away within its sequence.Therefore, the identification of such motifs is more challenging than the linear protein domains. To discover new binding sites, we developed a tool called PickPocket that focuses on a small set of user-defined ligands and PickPocket: Pocket binding prediction for specific ligand families using neural networks.uses neural networks to train a ligand-binding prediction model. We tested PickPocket on fatty acid-like ligands due to their structural similarities and their under-representation in the ligand-pocket binding literature.Our results show that for fatty acid-like molecules, pocket descriptors and secondary structures are enough to obtain predictions with accuracy >90% using a dataset of 1740 manually curated ligand-binding pockets. The trained model could also successfully predict the ligandbinding pockets using unseen structural data of two recently reported fatty acid-binding proteins. We think that the PickPocket tool can help to discover new protein functions by investigating the binding sites of specific ligand families. The source code and all datasets contained in this work are freely available at https://github.com/benjaminviart/PickPocket . Author Summary :Most of the protein biological functions are defined by its interactions with other proteins or ligands. The cavity of the protein structure that receives a ligand, also called a pocket, is made of residues that are usually located far away within its sequence. Therefore understanding the PickPocket: Pocket binding prediction for specific ligand families using neural networks.complementarity of pocket and ligand is a real challenge. To discover new binding sites, we developed a tool called PickPocket that focuses on a small set of user-defined ligands to train a prediction model. Our resultsshow that for fatty acid-like molecules, pocket descriptors ( such as volume, shape, hydrophobicity… ) and secondary structures are enough to obtain predictions with accuracy >90% using a dataset of 1740 manually curated ligand-binding pockets. The trained model could also successfully predict the ligand-binding pockets using unseen structural data of two recently reported fatty acid-binding proteins. We think that the PickPocket tool can help to discover new protein functions by investigating the binding sites of specific ligand families.

show abstract

sc-PDB: a 3D-database of ligandable binding sites—10 years on

Cited by 232 publications

References 27 publications

Improving detection of protein-ligand binding sites with 3D segmentation

Improving detection of protein-ligand binding sites with 3D segmentation

Meridianins and Lignarenone B as Potential GSK3β Inhibitors and Inductors of Structural Neuronal Plasticity

PickPocket : Pocket binding prediction for specific ligands family using neural networks.

Contact Info

Product

Resources

About