Cluster-based text mining for extracting drug candidates for the prevention of COVID-19 from the biomedical literature.

Objective: The coronavirus disease 2019 (COVID-19) health crisis that began at the end of 2019 made researchers around the world quickly race to find effective solutions. Related literature exploded and it was inevitable that an automated approach was needed to find useful information, namely text mining, to overcome COVID-19, especially in terms of drug candidate discovery. While text mining methods for finding drug candidates mostly try to extract bioentity associations from PubMed, very few of them mine with a clustering approach. The purpose of this study was to demonstrate the effectiveness of our approach to identify drugs for the prevention of COVID-19 through literature review, cluster analysis, drug docking calculations, and clinical trial data. Methods: This research was conducted in four main stages. First, the text mining stage was carried out by involving Bidirectional Encoder Representations from Transformers for Biomedical to obtain vector representation of each word in the sentence from texts. The next stage generated the disease-drug associations, which were obtained from the correlation between disease and drug. Next, the clustering stage grouped the rules through the similarity of diseases by utilizing Term Frequency-Inverse Document Frequency as its feature. Finally, the drug candidate extraction stage was processed through leveraging PubChem and DrugBank databases. We further used the drug docking package AUTODOCK VINA in PyRx software to verify the results. Results: Comparative analyses showed that the percentage of findings using mining with clustering outperformed mining without clustering in all experimental settings. In addition, we suggest that the top three drugs/phytochemicals by drug docking analysis may be effective in preventing COVID-19. Conclusions: The proposed method for text mining utilizing the clustering method is quite promising in the discovery of drug candidates for the prevention of COVID-19 through the biomedical literature.

The Predicted Structure For The Anti-Sense Sirna Of The Rna Polymerase Enzyme (Rdrp) Gene Of The Sars-Cov-2

The SARS-CoV-2 or COVID-19 pandemic has reached a new height with an unprecedented infection rate and mortality post-world war II history. However, there is no particular designed drug for COVID-19 up to this point. Thus, there exist three strategies for COVID-19 drug design;drug repurposing option, herbal medicine development, and transcriptomics-based drug lead. As the most underutilized option, transcriptomics-based drug lead could be leveraged to deal with SARS-CoV-2 infection. One of the main methods to block the SARS-CoV-2 infection is to inhibit the RNA polymerase enzyme that is responsible to the viral replication. In this regard, the objective of the strategy is to design the anti-sense siRNA drug and lead to inhibit the mRNA of the RNA Polymerase Enzyme (RdRp) gene that encodes the viral RNA Polymerase of the SARS-CoV-2. The Computer-Aided Drug Design (CADD)-based method was leveraged with sequence retrieval of 24 RdRp gene sequences, multiple sequence alignment, phylogenetic tree reconstruction, 2D/3D RNA structure predictions, and RNA-RNA docking. Both the RNAalifold conserved structure from the RdRp genes and the RNAfold structure of the siRNA for blocking the conserved structure are negative or less than 0 kcal/mol. The predicted RNA docking occurred with the best RMSD score of 22.53 �, which is beyond the accepted threshold of 10-20 �. Based on the findings, the 2D/3D structures of both the siRNA and mRNA could be elucidated, and the docking between them is feasible. However, this finding should be elucidated in the wet laboratory setting for the final lead validation.�

In silico investigation of potential inhibitors to main protease and spike protein of SARS-CoV-2 in propolis.

Docking analysis of propolis's natural compound was successfully performed against SARS-CoV-2 main protease (Mpro) and spike protein subunit 2 (S2). Initially, the propolis's protein was screened using chromatography analysis and successfully identified 22 compounds in the propolis. Four compounds were further investigated, i.e., neoblavaisoflavone, methylophiopogonone A, 3'-Methoxydaidzin, and genistin. The binding affinity of 3'-Methoxydaidzin was -7.7 kcal/mol, which is similar to nelfinavir (control), while the others were -7.6 kcal/mol. However, we found the key residue of Glu A:166 in the methylophiopogonone A and genistin, even though the predicted binding energy slightly higher than nelfinavir. In contrast, the predicted binding affinity of neoblavaisoflavone, methylophiopogonone A, 3'-Methoxydaidzin, and genistin against S2 were -8.1, -8.2, -8.3, and -8.3 kcal/mol, respectively, which is far below of the control (pravastatin, -7.3 kcal/mol). Instead of conventional hydrogen bonding, the π bonding influenced the binding affinity against S2. The results reveal that this is the first report about methylophiopogonone A, 3'-Methoxydaidzin, and genistin as candidates for anti-viral agents. Those compounds can then be further explored and used as a parent backbone molecule to develop a new supplementation for preventing SARS-CoV-2 infections during COVID-19 outbreaks.