scholarly journals Virtual Screening of Drug Proteins Based on Imbalance Data Mining

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Peng Li ◽  
Lili Yin ◽  
Bo Zhao ◽  
Yuezhongyi Sun
Keyword(s):  
Data Mining ◽  
Molecular Docking ◽  
Virtual Screening ◽  
Test Data ◽  
Imbalanced Data ◽  
Screening Process ◽  
Active Compounds ◽  
Data Imbalance ◽  
Imbalance Problem ◽  
Data Problem

To address the imbalanced data problem in molecular docking-based virtual screening methods, this paper proposes a virtual screening method for drug proteins based on imbalanced data mining, which introduces machine learning technology into the virtual screening technology for drug proteins to deal with the imbalanced data problem in the virtual screening process and improve the accuracy of the virtual screening. First, to address the data imbalance problem caused by the large difference between the number of active compounds and the number of inactive compounds in the docking conformation generated by the actual virtual screening process, this paper proposes a way to improve the data imbalance problem using SMOTE combined with genetic algorithm to synthesize new active compounds artificially by upsampling active compounds. Then, in order to improve the accuracy in the virtual screening process of drug proteins, the idea of integrated learning is introduced, and the random forest (RF) extended from Bagging integrated learning technique is combined with the support vector machine (SVM) technique, and the virtual screening of molecular docking conformations using RF-SVM technique is proposed to improve the prediction accuracy of active compounds in docking conformations. To verify the effectiveness of the proposed technique, first, HIV-1 protease and SRC kinase were used as test data for the experiments, and then, CA II was used to validate the model of the test data. The virtual screening of drug proteins using the proposed method in this paper showed an improvement in both enrichment factor (EF) and AUC compared with the use of the traditional virtual screening, for the test dataset. Therefore, it can be shown that the proposed method can effectively improve the accuracy of drug virtual screening.

Improving Classification Accuracy on Imbalanced Data by Ensembling Technique

2017 ◽  
Vol 19 (1) ◽  
pp. 42-49
Author(s):  
Divya Agrawal ◽  
Padma Bonde
Keyword(s):  
Classification Accuracy ◽  
Area Under The Curve ◽  
Imbalanced Data ◽  
Data Handling ◽  
Imbalanced Dataset ◽  
Classification Techniques ◽  
Data Imbalance ◽  
Logistics Regression ◽  
Good Evaluation ◽  
Imbalance Problem

Prediction using classification techniques is one of the fundamental feature widely applied in various fields. Classification accuracy is still a great challenge due to data imbalance problem. The increased volume of data is also posing a challenge for data handling and prediction, particularly when technology is used as the interface between customers and the company. As the data imbalance increases it directly affects the classification accuracy of the entire system. AUC (area under the curve) and lift proved to be good evaluation metrics. Classification techniques help to improve classification accuracy, but in case of imbalanced dataset classification accuracy does not predict well and other techniques, such as oversampling needs to be resorted. Paper presented Voting based ensembling technique to improve classification accuracy in case of imbalanced data. The voting based ensemble is based on taking the votes on the best class obtained by the three classification techniques, namely, Logistics Regression, Classification Trees and Discriminant Analysis. The observed result revealed improvement in classification accuracy by using voting ensembling technique.

Mitigating Data Imbalance Issues in Medical Image Analysis

2021 ◽  
pp. 66-89
Author(s):  
Debapriya Banik ◽  
Debotosh Bhattacharjee
Keyword(s):  
Learning Community ◽  
Medical Diagnosis ◽  
Medical Image ◽  
Learning Algorithm ◽  
Medical Image Analysis ◽  
Imbalanced Data ◽  
Disease Classification ◽  
Data Imbalance ◽  
Imbalance Problem ◽  
Optimal Procedures

Medical images mostly suffer from data imbalance problems, which make the disease classification task very difficult. The imbalanced distribution of the data in medical datasets happens when a proportion of a specific type of disease in a dataset appears in a small section of the entire dataset. So analyzing medical datasets with imbalanced data is a significant challenge for the machine learning and deep learning community. A standard classification learning algorithm might be biased towards the majority class and ignore the importance of the minority class (class of interest), which generally leads to the wrong diagnosis of the patients. So, the data imbalance problem in the medical image dataset is of utmost importance for the early prediction of disease, specifically cancer. This chapter attempts to explore different problems concerning data imbalance in medical diagnosis. The authors have discussed different rebalancing strategies that offer guidelines for choosing appropriate optimal procedures to train the samples by a classifier for an efficient medical diagnosis.

Exploring the Active Compounds of Traditional Mongolian Medicine Agsirga in Intervention of Novel Coronavirus (2019-nCoV) Based on HPLC-Q-Exactive-MS/MS and Molecular Docking Method

2020 ◽  
Author(s):  
Jie Cheng ◽  
Yuchen Tang ◽  
Baoquan Bao ◽  
Ping Zhang
Keyword(s):  
Mass Spectrometry ◽  
Molecular Docking ◽  
High Resolution ◽  
Mass Spectra ◽  
High Resolution Mass Spectrometry ◽  
Structural Formula ◽  
Active Compounds ◽  
High Resolution Mass ◽  
Q Exactive ◽  
Resolution Mass

<p><a></a><a></a><a></a><a><b>Objective</b></a>: To screen all compounds of Agsirga based on the HPLC-Q-Exactive high-resolution mass spectrometry and find potential inhibitors that can respond to 2019-nCoV from active compounds of Agsirga by molecular docking technology.</p> <p><b>Methods</b>: HPLC-Q-Exactive high-resolution mass spectrometry was adopted to identify the complex components of Mongolian medicine Agsirga, and separated by the high-resolution mass spectrometry Q-Exactive detector. Then the Orbitrap detector was used in tandem high-resolution mass spectrometry, and the related molecular and structural formula were found by using the chemsipider database and related literature, combined with precise molecular formulas (errors ≤ 5 × 10<sup>−6</sup>) , retention time, primary mass spectra, and secondary mass spectra information, The fragmentation regularities of mass spectra of these compounds were deduced. Taking ACE2 as the receptor and deduced compounds as the ligand, all of them were pretreated by discover studio, autodock and Chem3D. The molecular docking between the active ingredients and the target protein was studied by using AutoDock molecular docking software. The interaction between ligand and receptor is applied to provide a choice for screening anti-2019-nCoV drugs.</p> <p><b>Result</b>: Based on the fragmentation patterns of the reference compounds and consulting literature, a total of 96 major alkaloids and stilbenes were screened and identified in Agsirga by the HPLC-Q-Exactive-MS/MS method. Combining with molecular docking, a conclusion was got that there are potential active substances in Mongolian medicine Agsirga which can block the binding of ACE2 and 2019-nCoV at the molecular level.</p>

Dose COVID-19 Uncovered a New Feature of Metronidazole Drug?

2020 ◽  
Author(s):  
Mohammad Seyedhamzeh ◽  
Bahareh Farasati Far ◽  
Mehdi Shafiee Ardestani ◽  
Shahrzad Javanshir ◽  
Fatemeh Aliabadi ◽  
...  
Keyword(s):  
Molecular Docking ◽  
Drug Discovery ◽  
Virtual Screening ◽  
Active Sites ◽  
Initial Plasma ◽  
New Feature ◽  
Metronidazole Benzoate ◽  
Global Health Problem ◽  
A Current ◽  
Pro Inflammatory Cytokines

Studies of coronavirus disease 2019 (COVID-19) as a current global health problem shown the initial plasma levels of most pro-inflammatory cytokines increased during the infection, which leads to patient countless complications. Previous studies also demonstrated that the metronidazole (MTZ) administration reduced related cytokines and improved treatment in patients. However, the effect of this drug on cytokines has not been determined. In the present study, the interaction of MTZ with cytokines was investigated using molecular docking as one of the principal methods in drug discovery and design. According to the obtained results, the IL12-metronidazole complex is more stable than other cytokines, and an increase in the surface and volume leads to prevent to bind to receptors. Moreover, ligand-based virtual screening of several libraries showed metronidazole phosphate, metronidazole benzoate, 1-[1-(2-Hydroxyethyl)-5- nitroimidazol-2-yl]-N-methylmethanimine oxide, acyclovir, and tetrahydrobiopterin (THB or BH4) like MTZ by changing the surface and volume prevents binding IL-12 to the receptor. Finally, the inhibition of the active sites of IL-12 occurred by modifying the position of the methyl and hydroxyl functional groups in MTZ. <br>

Promising Anti-stroke Signature of Voglibose: Investigation through In- Silico Molecular Docking and Virtual Screening in In-Vivo Animal Studies

2020 ◽  
Vol 20 (3) ◽  
pp. 223-235
Author(s):  
Pooja Shah ◽  
Vishal Chavda ◽  
Snehal Patel ◽  
Shraddha Bhadada ◽  
Ghulam Md. Ashraf
Keyword(s):  
Molecular Docking ◽  
Virtual Screening ◽  
In Silico ◽  
Reductase Activity ◽  
Infarct Volume ◽  
Docking Studies ◽  
Serum Glucose ◽  
In Vivo Studies ◽  
In Silico Molecular Docking

Background: Postprandial hyperglycemia considered to be a major risk factor for cerebrovascular complications. Objective: The current study was designed to elucidate the beneficial role of voglibose via in-silico in vitro to in-vivo studies in improving the postprandial glycaemic state by protection against strokeprone type 2 diabetes. Material and Methods: In-Silico molecular docking and virtual screening were carried out with the help of iGEMDOCK+ Pymol+docking software and Protein Drug Bank database (PDB). Based on the results of docking studies, in-vivo investigation was carried out for possible neuroprotective action. T2DM was induced by a single injection of streptozotocin (90mg/kg, i.v.) to neonates. Six weeks after induction, voglibose was administered at the dose of 10mg/kg p.o. for two weeks. After eight weeks, diabetic rats were subjected to middle cerebral artery occlusion, and after 72 hours of surgery, neurological deficits were determined. The blood was collected for the determination of serum glucose, CK-MB, LDH and lipid levels. Brains were excised for determination of brain infarct volume, brain hemisphere weight difference, Na+-K+ ATPase activity, ROS parameters, NO levels, and aldose reductase activity. Results: In-silico docking studies showed good docking binding score for stroke associated proteins, which possibly hypotheses neuroprotective action of voglibose in stroke. In the present in-vivo study, pre-treatment with voglibose showed a significant decrease (p<0.05) in serum glucose and lipid levels. Voglibose has shown significant (p<0.05) reduction in neurological score, brain infarct volume, the difference in brain hemisphere weight. On biochemical evaluation, treatment with voglibose produced significant (p<0.05) decrease in CK-MB, LDH, and NO levels in blood and reduction in Na+-K+ ATPase, oxidative stress, and aldose reductase activity in brain homogenate. Conclusion: In-silico molecular docking and virtual screening studies and in-vivo studies in MCAo induced stroke, animal model outcomes support the strong anti-stroke signature for possible neuroprotective therapeutics.

Sign in / Sign up

Export Citation Format

Share Document