scholarly journals PUResNet: prediction of protein-ligand binding sites using deep residual neural network

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Jeevan Kandel ◽  
Hilal Tayara ◽  
Kil To Chong
Keyword(s):  
Protein Structure ◽  
Ligand Binding ◽  
Binding Sites ◽  
Protein Structures ◽  
Structural Similarity ◽  
Vital Role ◽  
Biological Functions ◽  
True Nature ◽  
Ligand Binding Sites ◽  
Deep Learning Model

Abstract Background Predicting protein-ligand binding sites is a fundamental step in understanding the functional characteristics of proteins, which plays a vital role in elucidating different biological functions and is a crucial step in drug discovery. A protein exhibits its true nature after binding to its interacting molecule known as a ligand that binds only in the favorable binding site of the protein structure. Different computational methods exploiting the features of proteins have been developed to identify the binding sites in the protein structure, but none seems to provide promising results, and therefore, further investigation is required. Results In this study, we present a deep learning model PUResNet and a novel data cleaning process based on structural similarity for predicting protein-ligand binding sites. From the whole scPDB (an annotated database of druggable binding sites extracted from the Protein DataBank) database, 5020 protein structures were selected to address this problem, which were used to train PUResNet. With this, we achieved better and justifiable performance than the existing methods while evaluating two independent sets using distance, volume and proportion metrics.

scholarly journals FTSite: high accuracy detection of ligand binding sites on unbound protein structures

2011 ◽  
Vol 28 (2) ◽  
pp. 286-287 ◽  
Author(s):  
Chi-Ho Ngan ◽  
David R. Hall ◽  
Brandon Zerbe ◽  
Laurie E. Grove ◽  
Dima Kozakov ◽  
...  
Keyword(s):  
Ligand Binding ◽  
Binding Sites ◽  
Protein Structures ◽  
High Accuracy ◽  
Ligand Binding Sites

scholarly journals BionoiNet: ligand-binding site classification with off-the-shelf deep neural network

2020 ◽  
Vol 36 (10) ◽  
pp. 3077-3083
Author(s):  
Wentao Shi ◽  
Jeffrey M Lemoine ◽  
Abd-El-Monsif A Shawky ◽  
Manali Singha ◽  
Limeng Pu ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Ligand Binding ◽  
Binding Sites ◽  
Protein Structures ◽  
Supplementary Information ◽  
Heme Binding ◽  
Unseen Data ◽  
Ligand Binding Sites ◽  
Binding Pockets

Abstract Motivation Fast and accurate classification of ligand-binding sites in proteins with respect to the class of binding molecules is invaluable not only to the automatic functional annotation of large datasets of protein structures but also to projects in protein evolution, protein engineering and drug development. Deep learning techniques, which have already been successfully applied to address challenging problems across various fields, are inherently suitable to classify ligand-binding pockets. Our goal is to demonstrate that off-the-shelf deep learning models can be employed with minimum development effort to recognize nucleotide- and heme-binding sites with a comparable accuracy to highly specialized, voxel-based methods. Results We developed BionoiNet, a new deep learning-based framework implementing a popular ResNet model for image classification. BionoiNet first transforms the molecular structures of ligand-binding sites to 2D Voronoi diagrams, which are then used as the input to a pretrained convolutional neural network classifier. The ResNet model generalizes well to unseen data achieving the accuracy of 85.6% for nucleotide- and 91.3% for heme-binding pockets. BionoiNet also computes significance scores of pocket atoms, called BionoiScores, to provide meaningful insights into their interactions with ligand molecules. BionoiNet is a lightweight alternative to computationally expensive 3D architectures. Availability and implementation BionoiNet is implemented in Python with the source code freely available at: https://github.com/CSBG-LSU/BionoiNet. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals webPDBinder: a server for the identification of ligand binding sites on protein structures

2013 ◽  
Vol 41 (W1) ◽  
pp. W308-W313 ◽  
Author(s):  
Valerio Bianchi ◽  
Iolanda Mangone ◽  
Fabrizio Ferrè ◽  
Manuela Helmer-Citterich ◽  
Gabriele Ausiello
Keyword(s):  
Ligand Binding ◽  
Binding Sites ◽  
Protein Structures ◽  
Ligand Binding Sites

scholarly journals Systematic domain-based aggregation of protein structures highlights DNA-, RNA- and other ligand-binding positions

2018 ◽  
Vol 47 (2) ◽  
pp. 582-593 ◽  
Author(s):  
Shilpa Nadimpalli Kobren ◽  
Mona Singh
Keyword(s):  
Ligand Binding ◽  
Small Molecules ◽  
Binding Sites ◽  
Protein Structures ◽  
Complex Structures ◽  
Disease Etiology ◽  
Systematic Assessment ◽  
Protein Ligand Interactions ◽  
Ligand Binding Sites ◽  
Ligand Interactions

Abstract Domains are fundamental subunits of proteins, and while they play major roles in facilitating protein–DNA, protein–RNA and other protein–ligand interactions, a systematic assessment of their various interaction modes is still lacking. A comprehensive resource identifying positions within domains that tend to interact with nucleic acids, small molecules and other ligands would expand our knowledge of domain functionality as well as aid in detecting ligand-binding sites within structurally uncharacterized proteins. Here, we introduce an approach to identify per-domain-position interaction ‘frequencies’ by aggregating protein co-complex structures by domain and ascertaining how often residues mapping to each domain position interact with ligands. We perform this domain-based analysis on ∼91000 co-complex structures, and infer positions involved in binding DNA, RNA, peptides, ions or small molecules across 4128 domains, which we refer to collectively as the InteracDome. Cross-validation testing reveals that ligand-binding positions for 2152 domains are highly consistent and can be used to identify residues facilitating interactions in ∼63–69% of human genes. Our resource of domain-inferred ligand-binding sites should be a great aid in understanding disease etiology: whereas these sites are enriched in Mendelian-associated and cancer somatic mutations, they are depleted in polymorphisms observed across healthy populations. The InteracDome is available at http://interacdome.princeton.edu.

scholarly journals Physical chemistry and membrane properties of two phosphatidylinositol bisphosphate isomers

2015 ◽  
Vol 17 (19) ◽  
pp. 12608-12615 ◽  
Author(s):  
David R. Slochower ◽  
Yu-Hsiu Wang ◽  
Ravi Radhakrishnan ◽  
Paul A. Janmey
Keyword(s):  
Physical Chemistry ◽  
Ligand Binding ◽  
Signaling Pathways ◽  
Binding Sites ◽  
Specific Protein ◽  
Membrane Properties ◽  
Biological Functions ◽  
Phosphatidylinositol Bisphosphate ◽  
Cell Matrix ◽  
Ligand Binding Sites

The most highly charged phospholipids, polyphosphoinositides, are often involved in signaling pathways that originate at cell–cell and cell–matrix contacts, and different isomers of polyphosphoinositides have distinct biological functions that cannot be explained by separate highly specific protein ligand binding sites [Lemmon, Nat. Rev. Mol. Cell Biol., 2008, 9, 99–111].

scholarly journals Bioinformatics Analysis Unveils Certain Mutations Implicated in Spike Structure Damage and Ligand-Binding Site of Severe Acute Respiratory Syndrome Coronavirus 2

2021 ◽  
Vol 15 ◽  
pp. 117793222110182
Author(s):  
Emre Aktas
Keyword(s):  
Protein Structure ◽  
North America ◽  
Severe Acute Respiratory Syndrome ◽  
South Korea ◽  
Ligand Binding ◽  
Binding Sites ◽  
Spike Protein ◽  
Structure Damage ◽  
Ligand Binding Sites ◽  
New Mutations

There are certain mutations related to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). In addition to these known mutations, other new mutations have been found across regions in this study. Based on the results, in which 4,326 SARS-CoV-2 whole sequences were used, some mutations are found to be peculiar with certain regions, while some other mutations are found in all regions. In Asia, mutations (3 different mutations in QLA46612 isolated from South Korea) were found in the same sequence. Although huge number of mutations are detected (more than 70 in Asia) by regions, according to bioinformatics tools, some of them which are G75V (isolated from North America), T95I (isolated from South Korea), G143V (isolated from North America), M177I (isolated from Asia), L293M (isolated from Asia), P295H (isolated from Asia), T393P (isolated from Europe), P507S (isolated from Asia), and D614G (isolated from all regions) (These color used only make correct) predicted a damage to spike’ protein structure. Furthermore, this study also aimed to reveal how binding sites of ligands change if the spike protein structure is damaged, and whether more than one mutation affects ligand binding. Mutations that were predicted to damage the structure did not affect the ligand-binding sites, whereas ligands’ binding sites were affected in those with multiple mutations. It is thought that this study will give a different perspective to both the vaccine SARS-CoV studies and the change in the structure of the spike protein belonging to this virus against mutations.

scholarly journals Bioinformatic Analysis Reveals That Some Mutations May Affect On Both Spike Structure Damage and Ligand Binding Site

2020 ◽  
Author(s):  
Emre Aktas
Keyword(s):  
Protein Structure ◽  
North America ◽  
South Korea ◽  
Ligand Binding ◽  
Binding Sites ◽  
Bioinformatic Analysis ◽  
Spike Protein ◽  
Huge Number ◽  
Structure Damage ◽  
Ligand Binding Sites

AbstractThere are some mutations are known related to SARS-CoV-2. Together with these mutations known, I tried to show other newly mutations regionally. According to my results which 4326 whole sequences are used, I found that some mutations occur only in a certain region, while some other mutations are found in each regions. Especially in Asia, more than one mutation(three different mutations are found in QLA46612 isolated from South Korea) was seen in the same sequence. Although I detected a huge number of mutations (more than seventy in Asia) by regions, some of them were predicted that damage spike’s protein structure by using bioinformatic tools.The predicted results are G75V(isolated from North America), T95I(isolated from South Korea), G143V(isolated from North America), M177I(isolated Asia), L293M(isolated from Asia), P295H(isolated from Asia), T393P(isolated from Europe), P507S(isolated from Asia), D614G(isolated from all regions) respectively. Also, in this study, I tried to show how possible binding sites of ligands change if the spike protein structure is damaged and whether more than one mutation affects ligand binding was estimated using bioinformatics tools. Interestingly, mutations that predicted to damage the structure do not affect ligand binding sites, whereas ligands’ binding sites were affected in those with multiple mutations.Focusing on mutations may opens up the window to exploit new future therapeutic targets.

Sign in / Sign up

Export Citation Format

Share Document