METADOCK: A parallel metaheuristic schema for virtual screening methods

2017 ◽  
Vol 32 (6) ◽  
pp. 789-803 ◽  
Author(s):  
Baldomero Imbernón ◽  
José M Cecilia ◽  
Horacio Pérez-Sánchez ◽  
Domingo Giménez
Keyword(s):  
Molecular Docking ◽  
Virtual Screening ◽  
High Performance ◽  
Optimization Technique ◽  
Screening Methods ◽  
Scoring Functions ◽  
Dynamic Assignment ◽  
Parallel Metaheuristics ◽  
Heterogeneous Architectures ◽  
Metaheuristic Methods

Virtual screening through molecular docking can be translated into an optimization problem, which can be tackled with metaheuristic methods. The interaction between two chemical compounds (typically a protein, enzyme or receptor, and a small molecule, or ligand) is calculated by using highly computationally demanding scoring functions that are computed at several binding spots located throughout the protein surface. This paper introduces METADOCK, a novel molecular docking methodology based on parameterized and parallel metaheuristics and designed to leverage heterogeneous computers based on heterogeneous architectures. The application decides the optimization technique at running time by setting a configuration schema. Our proposed solution finds a good workload balance via dynamic assignment of jobs to heterogeneous resources which perform independent metaheuristic executions when computing different molecular interactions required by the scoring functions in use. A cooperative scheduling of jobs optimizes the quality of the solution and the overall performance of the simulation, so opening a new path for further developments of virtual screening methods on high-performance contemporary heterogeneous platforms.

scholarly journals Metaheuristics Based Optimization Technique for Protein-Ligand Docking

2019 ◽  
Vol 8 (3) ◽  
pp. 4617-4622
Keyword(s):  
Molecular Docking ◽  
Virtual Screening ◽  
Heterogeneous Computing ◽  
Optimization Technique ◽  
Ligand Docking ◽  
Screening Methods ◽  
Scoring Functions ◽  
Parallel Metaheuristics ◽  
Novel Approach ◽  
Computationally Intensive

Virtual screening using molecular docking requires optimization, which can be solved by using metaheuristics methods. Typically the interaction between two compounds is calculated using computationally intensive Scoring Functions (SF) which is computed in several spots which are called as binding surfaces. In this paper we present a novel approach for molecular docking which is based on parameterized and parallel metaheuristics which is useful in leveraging heterogeneous computing based on heterogeneous architectures. The approach decides on the optimization technique at running time by setting up a new configuration schema that allows parallel offloading of the data intensive sections of the docking. Hence the docking process is carried out in parallel efficiently while performing the metaheuristics execution. The approach carries out docking and computations of molecular interactions required for SF in parallel so that the time efficiency is improved. This opens a new path for further developments in virtual screening methods in heterogeneous platform.

Parallelization of Molecular Docking: A Review

2018 ◽  
Vol 18 (12) ◽  
pp. 1015-1028 ◽  
Author(s):  
Dong Dong ◽  
Zhijian Xu ◽  
Wu Zhong ◽  
Shaoliang Peng
Keyword(s):  
Big Data ◽  
Molecular Docking ◽  
Computational Complexity ◽  
Virtual Screening ◽  
High Performance ◽  
Screening Methods ◽  
Small Molecule Ligands ◽  
Target Binding ◽  
Performance Computing ◽  
Target Binding Site

Molecular docking, as one of the widely used virtual screening methods, aims to predict the binding-conformations of small molecule ligands to the appropriate target binding site. Because of the computational complexity and the arrival of the big data era, molecular docking requests High- Performance Computing (HPC) to improve its performance and accuracy. We discuss, in detail, the advances in accelerating molecular docking software in parallel, based on the different common HPC platforms, respectively. Not only the existing suitable programs have been optimized and ported to HPC platforms, but also many novel parallel algorithms have been designed and implemented. This review focuses on the techniques and methods adopted in parallelizing docking software. Where appropriate, we refer readers to exemplary case studies.

scholarly journals Virtual Screening of DPP-4 Inhibitors Using QSAR-Based Artificial Intelligence and Molecular Docking of Hit Compounds to DPP-8 and DPP-9 Enzymes

2020 ◽  
Author(s):  
Oky Hermansyah ◽  
Alhadi Bustamam ◽  
Arry Yanuar
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Molecular Docking ◽  
Side Effects ◽  
Virtual Screening ◽  
Learning Algorithms ◽  
Qsar Model ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Screening Methods

Abstract Background: Dipeptidyl Peptidase-4 (DPP-4) inhibitors are becoming an essential drug in the treatment of type 2 diabetes mellitus, but some classes of these drugs have side effects such as joint pain that can become severe to pancreatitis. It is thought that these side effects appear related to their inhibition against enzymes DPP-8 and DPP-9. Objective: This study aims to find DPP-4 inhibitor hit compounds that are selective against the DPP-8 and DPP-9 enzymes. By building a virtual screening workflow using the Quantitative Structure-Activity Relationship (QSAR) method based on artificial intelligence (AI), millions of molecules from the database can be screened for the DPP-4 enzyme target with a faster time compared to other screening methods. Result: Five regression machine learning algorithms and four classification machine learning algorithms were used to build virtual screening workflows. The algorithm that qualifies for the regression QSAR model was Support Vector regression with R 2 pred 0.78, while the classification QSAR model was Random Forest with 92.21% accuracy. The virtual screening results of more than 10 million molecules from the database, obtained 2,716 hit compounds with pIC50 above 7.5. Molecular docking results of several potential hit compounds to the DPP-4, DPP-8 and DPP-9 enzymes, obtained CH0002 hit compound that has a high inhibitory potential against the DPP-4 enzyme and low inhibition of the DPP-8 and DPP-9 enzymes. Conclusion: This research was able to produce DPP-4 inhibitor hit compounds that are potential to DPP-4 and selective to DPP-8 and DPP-9 enzymes so that they can be further developed in the DPP-4 inhibitors discovery. The resulting virtual screening workflow can be applied to the discovery of hit compounds on other targets. Keywords: Artificial Intelligence; DPP-4; KNIME; Machine Learning; QSAR; Virtual Screening

scholarly journals A Review on Parallel Virtual Screening Softwares for High-Performance Computers

2022 ◽  
Vol 15 (1) ◽  
pp. 63
Author(s):  
Natarajan Arul Murugan ◽  
Artur Podobas ◽  
Davide Gadioli ◽  
Emanuele Vitali ◽  
Gianluca Palermo ◽  
...  
Keyword(s):  
Drug Discovery ◽  
Virtual Screening ◽  
High Throughput Screening ◽  
High Performance ◽  
Parallel Implementation ◽  
Scoring Function ◽  
Scoring Functions ◽  
Screening Programs ◽  
Lead Compounds ◽  
High Performance Computers

Drug discovery is the most expensive, time-demanding, and challenging project in biopharmaceutical companies which aims at the identification and optimization of lead compounds from large-sized chemical libraries. The lead compounds should have high-affinity binding and specificity for a target associated with a disease, and, in addition, they should have favorable pharmacodynamic and pharmacokinetic properties (grouped as ADMET properties). Overall, drug discovery is a multivariable optimization and can be carried out in supercomputers using a reliable scoring function which is a measure of binding affinity or inhibition potential of the drug-like compound. The major problem is that the number of compounds in the chemical spaces is huge, making the computational drug discovery very demanding. However, it is cheaper and less time-consuming when compared to experimental high-throughput screening. As the problem is to find the most stable (global) minima for numerous protein–ligand complexes (on the order of 106 to 1012), the parallel implementation of in silico virtual screening can be exploited to ensure drug discovery in affordable time. In this review, we discuss such implementations of parallelization algorithms in virtual screening programs. The nature of different scoring functions and search algorithms are discussed, together with a performance analysis of several docking softwares ported on high-performance computing architectures.

scholarly journals Virtual Screening of DPP-4 Inhibitors Using QSAR-Based Artificial Intelligence and Molecular Docking of Hit Compounds to DPP-8 and DPP-9 Enzymes

2020 ◽  
Author(s):  
Oky Hermansyah ◽  
Alhadi Bustamam ◽  
Arry Yanuar
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Molecular Docking ◽  
Side Effects ◽  
Virtual Screening ◽  
Learning Algorithms ◽  
Qsar Model ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Screening Methods

Abstract Background: Dipeptidyl Peptidase-4 (DPP-4) inhibitors are becoming an essential drug in the treatment of type 2 diabetes mellitus, but some classes of these drugs have side effects such as joint pain that can become severe to pancreatitis. It is thought that these side effects appear related to their inhibition against enzymes DPP-8 and DPP-9. Objective: This study aims to find DPP-4 inhibitor hit compounds that are selective against the DPP-8 and DPP-9 enzymes. By building a virtual screening workflow using the Quantitative Structure-Activity Relationship (QSAR) method based on artificial intelligence (AI), millions of molecules from the database can be screened for the DPP-4 enzyme target with a faster time compared to other screening methods. Result: Five regression machine learning algorithms and four classification machine learning algorithms were used to build virtual screening workflows. The algorithm that qualifies for the regression QSAR model was Support Vector regression with R 2 pred 0.78, while the classification QSAR model was Random Forest with 92.21% accuracy. The virtual screening results of more than 10 million molecules from the database, obtained 2,716 hit compounds with pIC50 above 7.5. Molecular docking results of several potential hit compounds to the DPP-4, DPP-8 and DPP-9 enzymes, obtained CH0002 hit compound that has a high inhibitory potential against the DPP-4 enzyme and low inhibition of the DPP-8 and DPP-9 enzymes. Conclusion: This research was able to produce DPP-4 inhibitor hit compounds that are potential to DPP-4 and selective to DPP-8 and DPP-9 enzymes so that they can be further developed in the DPP-4 inhibitors discovery. The resulting virtual screening workflow can be applied to the discovery of hit compounds on other targets.

Methods for Docking and Drug Designing

2016 ◽  
pp. 39-53
Author(s):  
Ahmad Abu Turab Naqvi ◽  
Md. Imtaiyaz Hassan
Keyword(s):  
Molecular Docking ◽  
Drug Discovery ◽  
Virtual Screening ◽  
Force Field ◽  
De Novo ◽  
Scoring Functions ◽  
Receptor Molecule ◽  
Knowledge Based ◽  
Ligand Screening ◽  
Novel Drug

Molecular docking is the prediction of conformational complementarity between ligand and receptor molecule. The process of docking integrates two schematic approaches namely sampling of ligand conformations and ranking of selected conformations based on scoring functions. The authors have discussed established methodologies for molecular docking and well-known tools implementing these methods. A brief account of different classes of scoring functions such as force field based, empirical, knowledge based, and descriptor based scoring functions is given along with the exemplary implementations of these scoring functions. By replacing test and trial based ligand screening with structure based virtual screening, molecular docking has helped in shortening the duration of novel drug discovery up to some extent. However, the developments made in the field of drug discovery are assisted by the advances in the techniques of molecular docking, but there is strong need of enrichment in the techniques, especially in scoring functions, to tackle the inbound problems of de novo drug discovery.

scholarly journals BEAR, a Novel Virtual Screening Methodology for Drug Discovery

2010 ◽  
Vol 16 (1) ◽  
pp. 129-133 ◽  
Author(s):  
Gianluca Degliesposti ◽  
Corinne Portioli ◽  
Marco Daniele Parenti ◽  
Giulio Rastelli
Keyword(s):  
Molecular Dynamics ◽  
Drug Discovery ◽  
Virtual Screening ◽  
Screening Methods ◽  
Scoring Functions ◽  
Free Energies ◽  
Reliable Tool ◽  
Biological Target ◽  
Binding Free Energies ◽  
Screening Technology

BEAR (binding estimation after refinement) is a new virtual screening technology based on the conformational refinement of docking poses through molecular dynamics and prediction of binding free energies using accurate scoring functions. Here, the authors report the results of an extensive benchmark of the BEAR performance in identifying a smaller subset of known inhibitors seeded in a large (1.5 million) database of compounds. BEAR performance proved strikingly better if compared with standard docking screening methods. The validations performed so far showed that BEAR is a reliable tool for drug discovery. It is fast, modular, and automated, and it can be applied to virtual screenings against any biological target with known structure and any database of compounds.

scholarly journals An Epithelial Sodium Channel (ENaC)-Specific Aptamer Determined through Structure-Based Virtual Screening for the Development of Hypertension Early Detection System

2020 ◽  
Vol 27 (1) ◽  
pp. 67-75
Author(s):  
Dina Ratna Komala ◽  
Ari Hardianto ◽  
Shabarni Gaffar ◽  
Yeni Wahyuni Hartati
Keyword(s):  
Molecular Docking ◽  
Virtual Screening ◽  
Early Detection ◽  
Sodium Channel ◽  
Transmembrane Protein ◽  
Epithelial Sodium Channel ◽  
Screening Methods ◽  
Crystallographic Structure ◽  
Potential Biomarker ◽  
Epithelial Sodium Channel Enac

Background: Epithelial sodium channel (ENaC) is a transmembrane protein involved in maintaining sodium levels in blood plasma. It is also a potential biomarker for the early detection of hypertension since the amount of ENaC is related to the familial history of hypertension. ENaC can be detected by an aptamer, a single-stranded DNA (ssDNA) or RNA which offers advantages over an antibody. This study aimed to obtain an ssDNA aptamer specific to ENaC through virtual screening. Methods: Forty-one aptamers were retrieved from the Protein Data Bank (PDB) and the RNA was converted to ssDNA aptamers. The X-ray crystallographic structure of ENaC protein was remodelled using Modeller 9.20 to resolve missing residues. Molecular docking of aptamers against ENaC was performed using Patchdock and Firedock, then the selected aptamer was subjected to molecular docking against other ion channel proteins to assess its selectivity to ENaC. A molecular dynamics (MD) simulation was also conducted using Amber16 to acquire an in-depth understanding of the interaction within the aptamer-ENaC complex. Results: The virtual screening suggested that the ssDNA of iSpinach aptamer (PDB: 5OB3) displayed the strongest binding to ENaC (-49.46 kcal/mol) and was selective for ENaC over the other ion protein channels. An MMGBSA calculation on the complex of aptamer-ENaC revealed binding energy of -42,12 kcal/mol. Conclusion: The iSpinach-based aptamer is a potential probe for detecting ENaC or iDE and may be useful for the development of hypertension early detection systems.

scholarly journals Machine learning classification can reduce false positives in structure-based virtual screening

2020 ◽  
Author(s):  
Yusuf Adeshina ◽  
Eric Deeds ◽  
John Karanicolas
Keyword(s):  
Virtual Screening ◽  
Acetylcholinesterase Inhibitors ◽  
General Purpose ◽  
Training Dataset ◽  
Screening Methods ◽  
Scoring Functions ◽  
Machine Learning Classification ◽  
Biochemical Assays ◽  
New Strategy ◽  
Boosted Decision Trees

AbstractWith the recent explosion in the size of libraries available for screening, virtual screening is positioned to assume a more prominent role in early drug discovery’s search for active chemical matter. Modern virtual screening methods are still, however, plagued with high false positive rates: typically, only about 12% of the top-scoring compounds actually show activity when tested in biochemical assays. We argue that most scoring functions used for this task have been developed with insufficient thoughtfulness into the datasets on which they are trained and tested, leading to overly simplistic models and/or overtraining. These problems are compounded in the literature because none of the studies reporting new scoring methods have validated their model prospectively within the same study. Here, we report a new strategy for building a training dataset (D-COID) that aims to generate highly-compelling decoy complexes that are individually matched to available active complexes. Using this dataset, we train a general-purpose classifier for virtual screening (vScreenML) that is built on the XGBoost framework of gradient-boosted decision trees. In retrospective benchmarks, our new classifier shows outstanding performance relative to other scoring functions. We additionally evaluate the classifier in a prospective context, by screening for new acetylcholinesterase inhibitors. Remarkably, we find that nearly all compounds selected by vScreenML show detectable activity at 50 µM, with 10 of 23 providing greater than 50% inhibition at this concentration. Without any medicinal chemistry optimization, the most potent hit from this initial screen has an IC50 of 280 nM, corresponding to a Ki value of 173 nM. These results support using the D-COID strategy for training classifiers in other computational biology tasks, and for vScreenML in virtual screening campaigns against other protein targets. Both D-COID and vScreenML are freely distributed to facilitate such efforts.

Convolutional Neural Network Based Virtual Screening

2020 ◽  
Vol 27 ◽  
Author(s):  
Wenying Shan ◽  
Xuanyi Li ◽  
Hequan Yao ◽  
Kejiang Lin
Keyword(s):  
Neural Networks ◽  
Virtual Screening ◽  
Scoring Function ◽  
Learning Ability ◽  
Screening Methods ◽  
Scoring Functions ◽  
Lead Compound ◽  
Chemical Screening ◽  
Powerful Learning ◽  
Important Means

: Virtual screening is an important means for lead compound discovery. The scoring function is the key to selecting hit compounds. Many scoring functions are currently available; however, there are no all-purpose scoring functions because different scoring functions tend to have conflicting results. Recently, neural networks, especially convolutional neural networks, have been constantly penetrating drug design and most CNN-based virtual screening methods are superior to traditional docking methods, such as Dock and AutoDock. CNN-based virtual screening is expected to improve the previous model of overreliance on computational chemical screening. Utilizing the powerful learning ability of neural networks provides us with a new method for evaluating compounds. We review the latest progress of CNN-based virtual screening and propose prospects.

Sign in / Sign up

Export Citation Format

Share Document