Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

A Deep-Learning Approach toward Rational Molecular Docking Protocol Selection.

ABSTRACT: While a plethora of different protein-ligand docking protocols have been developed over the past twenty years, their performances greatly depend on the provided input protein-ligand pair. In this study, we developed a machine-learning model that uses a combination of convolutional and fully connected neural networks for the task of predicting the performance of several popular docking protocols given a protein structure and a small compound. We also rigorously evaluated the performance of our model using a widely available database of protein-ligand complexes and different types of data splits. We further open-source all code related to this study so that potential users can make informed selections on which protocol is best suited for their particular protein-ligand pair.

SUBMITTER: Jimenez-Luna J

PROVIDER: S-EPMC7321124 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

A Deep-Learning Approach toward Rational Molecular Docking Protocol Selection.

Jiménez-Luna José J Cuzzolin Alberto A Bolcato Giovanni G Sturlese Mattia M Moro Stefano S

Molecules (Basel, Switzerland) 20200527 11

While a plethora of different protein-ligand docking protocols have been developed over the past twenty years, their performances greatly depend on the provided input protein-ligand pair. In this study, we developed a machine-learning model that uses a combination of convolutional and fully connected neural networks for the task of predicting the performance of several popular docking protocols given a protein structure and a small compound. We also rigorously evaluated the performance of our mo ...[more]

PMID: 32471211

Similar Datasets

Rational approach toward COVID-19 main protease inhibitors via molecular docking, molecular dynamics simulation and free energy calculation.

Project description:In the rapidly evolving coronavirus disease (COVID-19) pandemic, repurposing existing drugs and evaluating commercially available inhibitors against druggable targets of the virus could be an effective strategy to accelerate the drug discovery process. The 3C-Like proteinase (3CLpro) of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been identified as an important drug target due to its role in viral replication. The lack of a potent 3CLpro inhibitor and the availability of the X-ray crystal structure of 3CLpro (PDB-ID 6LU7) motivated us to perform computational studies to identify commercially available potential inhibitors. A combination of modeling studies was performed to identify potential 3CLpro inhibitors from the protease inhibitor database MEROPS ( https://www.ebi.ac.uk/merops/index.shtml ). Binding energy evaluation identified key residues for inhibitor design. We found 15 potential 3CLpro inhibitors with higher binding affinity than that of an α-ketoamide inhibitor determined via X-ray structure. Among them, saquinavir and three other investigational drugs aclarubicin, TMC-310911, and faldaprevir could be suggested as potential 3CLpro inhibitors. We recommend further experimental investigation of these compounds.

| S-EPMC7572583 | biostudies-literature

GNINA 1.0: molecular docking with deep learning.

Project description:Molecular docking computationally predicts the conformation of a small molecule when binding to a receptor. Scoring functions are a vital piece of any molecular docking pipeline as they determine the fitness of sampled poses. Here we describe and evaluate the 1.0 release of the Gnina docking software, which utilizes an ensemble of convolutional neural networks (CNNs) as a scoring function. We also explore an array of parameter values for Gnina 1.0 to optimize docking performance and computational cost. Docking performance, as evaluated by the percentage of targets where the top pose is better than 2Å root mean square deviation (Top1), is compared to AutoDock Vina scoring when utilizing explicitly defined binding pockets or whole protein docking. GNINA, utilizing a CNN scoring function to rescore the output poses, outperforms AutoDock Vina scoring on redocking and cross-docking tasks when the binding pocket is defined (Top1 increases from 58% to 73% and from 27% to 37%, respectively) and when the whole protein defines the binding pocket (Top1 increases from 31% to 38% and from 12% to 16%, respectively). The derived ensemble of CNNs generalizes to unseen proteins and ligands and produces scores that correlate well with the root mean square deviation to the known binding pose. We provide the 1.0 version of GNINA under an open source license for use as a molecular docking tool at https://github.com/gnina/gnina .

| S-EPMC8191141 | biostudies-literature

Machine learning and molecular descriptors enable rational solvent selection in asymmetric catalysis.

Project description:Rational solvent selection remains a significant challenge in process development. Here we describe a hybrid mechanistic-machine learning approach, geared towards automated process development workflow. A library of 459 solvents was used, for which 12 conventional molecular descriptors, two reaction-specific descriptors, and additional descriptors based on screening charge density, were calculated. Gaussian process surrogate models were trained on experimental data from a Rh(CO)2(acac)/Josiphos catalysed asymmetric hydrogenation of a chiral ?-? unsaturated ?-lactam. With two simultaneous objectives - high conversion and high diastereomeric excess - the multi-objective algorithm, trained on the initial dataset of 25 solvents, has identified solvents leading to better reaction outcomes. In addition to being a powerful design of experiments (DoE) methodology, the resulting Gaussian process surrogate model for conversion is, in statistical terms, predictive, with a cross-validation correlation coefficient of 0.84. After identifying promising solvents, the composition of solvent mixtures and optimal reaction temperature were found using a black-box Bayesian optimisation. We then demonstrated the application of a new genetic programming approach to select an appropriate machine learning model for a specific physical system, which should allow the transition of the overall process development workflow into the future robotic laboratories.

| S-EPMC6625492 | biostudies-literature

QSAR and molecular docking for the search of AOX inhibitors: a rational drug discovery approach.

Project description:The alternative oxidase (AOX) is a monotopic diiron carboxylate protein that catalyses the oxidation of ubiquinol and the reduction of oxygen to water. Although a number of AOX inhibitors have been discovered, little is still known about the ligand-protein interaction and essential chemical characteristics of compounds required for a potent inhibition. Furthermore, owing to the rapidly growing resistance to existing inhibitors, new compounds with improved potency and pharmacokinetic properties are urgently required. In this study we used two computational approaches, ligand-protein docking and Quantitative Structure-Activity Relationships (QSAR) to investigate binding of AOX inhibitors to the enzyme and the molecular characteristics required for inhibition. Docking studies followed by protein-ligand interaction fingerprint (PLIF) analysis using the AOX enzyme and the mutated analogues revealed the importance of the residues Leu 122, Arg 118 and Thr 219 within the hydrophobic cavity. QSAR analysis, using stepwise regression analysis with experimentally obtained IC50 values as the response variable, resulted in a multiple regression model with a good prediction accuracy. The model highlighted the importance of the presence of hydrogen bonding acceptor groups on specific positions of the aromatic ring of ascofuranone derivatives, acidity of the compounds, and a large linker group on the compounds on the inhibitory effect of AOX.

| S-EPMC7904559 | biostudies-literature

A Deep Learning Approach For Programmable RNA Switches

Project description:Engineered RNA elements are programmable tools capable of detecting small molecules, proteins, and nucleic acids. Predicting the behavior of these tools remains a challenge, a situation that could be addressed through enhanced pattern recognition from deep learning. Thus, we investigate Deep Neural Networks (DNN) to predict toehold switch function as a canonical riboswitch model in synthetic biology. To facilitate DNN training, we synthesized and characterized in vivo a dataset of 91,534 toehold switches spanning 23 viral genomes and 906 human transcription factors. DNNs trained on nucleotide sequences outperformed (R2=0.43-0.70) previous state-of-the-art thermodynamic and kinetic models (R2=0.04-0.15) and allowed for human-understandable attention-visualizations (VIS4Map) to identify success and failure modes. This deep learning approach constitutes a major step forward in engineering and understanding of RNA synthetic biology.

2020-08-12 | GSE149225 | GEO

Combined deep learning and molecular docking simulations approach identifies potentially effective FDA approved drugs for repurposing against SARS-CoV-2.

Project description:The ongoing pandemic of Coronavirus Disease 2019 (COVID-19) has posed a serious threat to global public health. Drug repurposing is a time-efficient approach to finding effective drugs against SARS-CoV-2 in this emergency. Here, we present a robust experimental design combining deep learning with molecular docking experiments to identify the most promising candidates from the list of FDA-approved drugs that can be repurposed to treat COVID-19. We have employed a deep learning-based Drug Target Interaction (DTI) model, called DeepDTA, with few improvements to predict drug-protein binding affinities, represented as KIBA scores, for 2440 FDA-approved and 8168 investigational drugs against 24 SARS-CoV-2 viral proteins. FDA-approved drugs with the highest KIBA scores were selected for molecular docking simulations. We ran around 50,000 docking simulations for 168 selected drugs against 285 total predicted and/or experimentally proven active sites of all 24 SARS-CoV-2 viral proteins. A list of 49 most promising FDA-approved drugs with the best consensus KIBA scores and binding affinity values against selected SARS-CoV-2 viral proteins was generated. Most importantly, 16 drugs including anidulafungin, velpatasvir, glecaprevir, rifapentine, flavin adenine dinucleotide (FAD), terlipressin, and selinexor demonstrated the highest predicted inhibitory potential against key SARS-CoV-2 viral proteins. We further measured the inhibitory activity of 5 compounds (rifapentine, velpatasvir, glecaprevir, anidulafungin, and FAD disodium) on SARS-CoV-2 PLpro using Ubiquitin-Rhodamine 110 Gly fluorescent intensity assay. The highest inhibition of PLpro activity was seen with rifapentine (IC50: 15.18 μM) and FAD disodium (IC50: 12.39 μM), the drugs with high predicted KIBA scores and binding affinities.

| S-EPMC8604796 | biostudies-literature

A pharmacophore-guided deep learning approach for bioactive molecular generation.

Project description:The rational design of novel molecules with the desired bioactivity is a critical but challenging task in drug discovery, especially when treating a novel target family or understudied targets. We propose a Pharmacophore-Guided deep learning approach for bioactive Molecule Generation (PGMG). Through the guidance of pharmacophore, PGMG provides a flexible strategy for generating bioactive molecules. PGMG uses a graph neural network to encode spatially distributed chemical features and a transformer decoder to generate molecules. A latent variable is introduced to solve the many-to-many mapping between pharmacophores and molecules to improve the diversity of the generated molecules. Compared to existing methods, PGMG generates molecules with strong docking affinities and high scores of validity, uniqueness, and novelty. In the case studies, we use PGMG in a ligand-based and structure-based drug de novo design. Overall, the flexibility and effectiveness make PGMG a useful tool to accelerate the drug discovery process.

| S-EPMC10558534 | biostudies-literature

Wireless Link Selection Methods for Maritime Communication Access Networks-A Deep Learning Approach.

Project description:In recent years, we have been witnessing a growing interest in the subject of communication at sea. One of the promising solutions to enable widespread access to data transmission capabilities in coastal waters is the possibility of employing an on-shore wireless access infrastructure. However, such an infrastructure is a heterogeneous one, managed by many independent operators and utilizing a number of different communication technologies. If a moving sea vessel is to maintain a reliable communication within such a system, it needs to employ a set of network mechanisms dedicated for this purpose. In this paper, we provide a short overview of such requirements and overall characteristics of maritime communication, but our main focus is on the link selection procedure-an element of critical importance for the process of changing the device/system which the mobile vessel uses to retain communication with on-shore networks. The paper presents the concept of employing deep neural networks for the purpose of link selection. The proposed methods have been verified using propagation models dedicated to realistically represent the environment of maritime communications and compared to a number of currently popular solutions. The results of evaluation indicate a significant gain in both accuracy of predictions and reduction of the amount of test traffic which needs to be generated for measurements.

| S-EPMC9824693 | biostudies-literature

Toward a Rational Approach to Design Split G-Quadruplex Probes.

Project description:Hybridization probes have become an indispensable tool for nucleic acid analysis. Systematic efforts in probe optimization resulted in their improved binding affinity, turn-on ratios, and ability to discriminate single nucleotide substitutions (SNSs). The use of split (or multicomponent) probes is a promising strategy to improve probe selectivity and enable an analysis of folded analytes. Here, we developed criteria for the rational design of a split G-quadruplex (G4) peroxidase-like deoxyribozyme (sPDz) probe that provides a visual output signal. The sPDz probe consists of two DNA strands that hybridize to the abutting positions of a DNA/RNA target and form a G4 structure catalyzing, in the presence of a hemin cofactor, H2O2-mediated oxidation of organic compounds into their colored oxidation products. We have demonstrated that probe design becomes complicated in the case of target sequences containing clusters (two or more) of cytosine residues and developed strategies to overcome the challenges to achieving high signal-to-noise and excellent SNS discrimination. Specifically, to improve selectivity, a conformational constraint that stabilizes the probe's dissociated state is beneficial. If the signal intensity is compromised, introduction of flexible non-nucleotide linkers between the G4-forming and target-recognizing elements of the probe helps to decrease the steric hindrance for G4 PDz formation observed as a signal increase. Varying the modes of G4 core splitting is another instrument for the optimal sPDz design. The suggested algorithm was successfully utilized for the design of the sPDz probe interrogating a fragment of the Influenza A virus genome (subtype H1N1), which can be of practical use for flu diagnostics and surveillance.

| S-EPMC7179085 | biostudies-literature

A deep learning-based approach toward differentiating scalp psoriasis and seborrheic dermatitis from dermoscopic images.

Project description:ObjectivesThis study aims to develop a new diagnostic method for discriminating scalp psoriasis and seborrheic dermatitis based on a deep learning (DL) model, which uses the dermatoscopic image as input and achieved higher accuracy than dermatologists trained with dermoscopy.MethodsA total of 1,358 pictures (obtained from 617 patients) with pathological and diagnostic confirmed skin diseases (508 psoriases, 850 seborrheic dermatitides) were randomly allocated into the training, validation, and testing datasets (1,088/134/136) in this study. A DL model concerning dermatoscopic images was established using the transfer learning technique and trained for diagnosing two diseases.ResultsThe developed DL model exhibits good sensitivity, specificity, and Area Under Curve (AUC) (96.1, 88.2, and 0.922%, respectively), it outperformed all dermatologists in the diagnosis of scalp psoriasis and seborrheic dermatitis when compared to five dermatologists with various levels of experience. Furthermore, non-proficient doctors with the assistance of the DL model can achieve comparable diagnostic performance to dermatologists proficient in dermoscopy. One dermatology graduate student and two general practitioners significantly improved their diagnostic performance, where their AUC values increased from 0.600, 0.537, and 0.575 to 0.849, 0.778, and 0.788, respectively, and their diagnosis consistency was also improved as the kappa values went from 0.191, 0.071, and 0.143 to 0.679, 0.550, and 0.568, respectively. DL enjoys favorable computational efficiency and requires few computational resources, making it easy to deploy in hospitals.ConclusionsThe developed DL model has favorable performance in discriminating two skin diseases and can improve the diagnosis, clinical decision-making, and treatment of dermatologists in primary hospitals.

| S-EPMC9669613 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data