Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 4 de 4
SN Comput Sci ; 4(1): 91, 2023.
Article in English | MEDLINE | ID: covidwho-2158268


In the paper, the authors investigated and predicted the future environmental circumstances of a COVID-19 to minimize its effects using artificial intelligence techniques. The experimental investigation of COVID-19 instances has been performed in ten countries, including India, the United States, Russia, Argentina, Brazil, Colombia, Italy, Turkey, Germany, and France using machine learning, deep learning, and time series models. The confirmed, deceased, and recovered datasets from January 22, 2020, to May 29, 2021, of Novel COVID-19 cases were considered from the Kaggle COVID dataset repository. The country-wise Exploratory Data Analysis visually represents the active, recovered, closed, and death cases from March 2020 to May 2021. The data are pre-processed and scaled using a MinMax scaler to extract and normalize the features to obtain an accurate prediction rate. The proposed methodology employs Random Forest Regressor, Decision Tree Regressor, K Nearest Regressor, Lasso Regression, Linear Regression, Bayesian Regression, Theilsen Regression, Kernel Ridge Regressor, RANSAC Regressor, XG Boost, Elastic Net Regressor, Facebook Prophet Model, Holt Model, Stacked Long Short-Term Memory, and Stacked Gated Recurrent Units to predict active COVID-19 confirmed, death, and recovered cases. Out of different machine learning, deep learning, and time series models, Random Forest Regressor, Facebook Prophet, and Stacked LSTM outperformed to predict the best results for COVID-19 instances with the lowest root-mean-square and highest R 2 score values.

Journal of Ambient Intelligence and Humanized Computing ; : 1-12, 2022.
Article in English | EuropePMC | ID: covidwho-2033981
Int J Mol Sci ; 23(14)2022 Jul 11.
Article in English | MEDLINE | ID: covidwho-1964002


Chikungunya virus (CHIKV) has repeatedly spread via the bite of an infected mosquito and affected more than 100 countries. The disease poses threats to public health and the economy in the infected locations. Many efforts have been devoted to identifying compounds that could inhibit CHIKV. Unfortunately, successful clinical candidates have not been found yet. Computations through the simulating recognition process were performed on complexation of the nsP3 protein of CHIKV with the structures of triply conjugated drug lead candidates. The outcomes provided the aid on rational design of functionalized quinazoline-(α-substituted coumarin)-arylsulfonate compounds to inhibit CHIKV in Vero cells. The molecular docking studies showed a void space around the ß carbon atom of coumarin when a substituent was attached at the α position. The formed vacancy offered a good chance for a Michael addition to take place owing to steric and electronic effects. The best conjugate containing a quinazolinone moiety exhibited potency with EC50 = 6.46 µM, low toxicity with CC50 = 59.7 µM, and the selective index (SI) = 9.24. Furthermore, the corresponding 4-anilinoquinazoline derivative improved the anti-CHIKV potency to EC50 = 3.84 µM, CC50 = 72.3 µM, and SI = 18.8. The conjugate with 4-anilinoquinazoline exhibited stronger binding affinity towards the macro domain than that with quinazolinone via hydrophobic and hydrogen bond interactions.

Chikungunya virus , Animals , Antiviral Agents/chemistry , Arylsulfonates/metabolism , Arylsulfonates/pharmacology , Chlorocebus aethiops , Computer-Aided Design , Coumarins/pharmacology , Molecular Docking Simulation , Quinazolines/metabolism , Quinazolines/pharmacology , Quinazolinones/pharmacology , Vero Cells , Virus Replication
Biotechnol J ; 15(6): e2000214, 2020 06.
Article in English | MEDLINE | ID: covidwho-617418