Supervised Learning Models for the Preliminary Detection of COVID-19 in Patients Using Demographic and Epidemiological Parameters

The World Health Organization labelled the new COVID-19 breakout a public health crisis of worldwide concern on 30 January 2020, and it was named the new global pandemic in March 2020. It has had catastrophic consequences on the world economy and well-being of people and has put a tremendous strain on already-scarce healthcare systems globally, particularly in underdeveloped countries. Over 11 billion vaccine doses have already been administered worldwide, and the benefits of these vaccinations will take some time to appear. Today, the only practical approach to diagnosing COVID-19 is through the RT-PCR and RAT tests, which have sometimes been known to give unreliable results. Timely diagnosis and implementation of precautionary measures will likely improve the survival outcome and decrease the fatality rates. In this study, we propose an innovative way to predict COVID-19 with the help of alternative non-clinical methods such as supervised machine learning models to identify the patients at risk based on their characteristic parameters and underlying comorbidities. Medical records of patients from Mexico admitted between 23 January 2020 and 26 March 2022, were chosen for this purpose. Among several supervised machine learning approaches tested, the XGBoost model achieved the best results with an accuracy of 92%. It is an easy, non-invasive, inexpensive, instant and accurate way of forecasting those at risk of contracting the virus. However, it is pretty early to deduce that this method can be used as an alternative in the clinical diagnosis of coronavirus cases.

Phage therapeutics: from promises to practices and prospectives.

The rise in multi-drug resistant bacteria and the inability to develop novel antibacterial agents limits our arsenal against infectious diseases. Antibiotic resistance is a global issue requiring an immediate solution, including the development of new antibiotic molecules and other alternative modes of therapy. This article highlights the mechanism of bacteriophage treatment that makes it a real solution for multidrug-resistant infectious diseases. Several case reports identified phage therapy as a potential solution to the emerging challenge of multi-drug resistance. Bacteriophages, unlike antibiotics, have special features, such as host specificity and do not impact other commensals. A new outlook has also arisen with recent advancements in the understanding of phage immunobiology, where phages are repurposed against both bacterial and viral infections. Thus, the potential possibility of phages in COVID-19 patients with secondary bacterial infections has been briefly elucidated. However, significant obstacles that need to be addressed are to design better clinical studies that may contribute to the widespread use of bacteriophage therapy against multi-drug resistant pathogens. In conclusion, antibacterial agents can be used with bacteriophages, i.e. bacteriophage-antibiotic combination therapy, or they can be administered alone in cases when antibiotics are ineffective.Key points• AMR, a consequence of antibiotic generated menace globally, has led to the resurgence of phage therapy as an effective and sustainable solution without any side effects and high specificity against refractory MDR bacterial infections.• Bacteriophages have fewer adverse reactions and can thus be used as monotherapy as well as in conjunction with antibiotics.• In the context of the COVID-19 pandemic, phage therapy may be a viable option.

Vitality of Proteinase K in rRTPCR Detection of SARS-CoV2 Bypassing RNA Extraction.

This study aimed to detect the SARS-COV2 viral component directly from inoculated VTM without RNA extraction. Inoculated VTMs of already tested 50 positive and 50 negative samples were divided into three groups. Group I was treated with Proteinase K (PK) followed by 3-step-heat treatment at different temperatures (25°C, 60°C, and 98°C) and stored at 4°C. Group II was directly subjected to 3-step-heat treatment without PK exposure and stored at 4°C. And group III was set-up as standard group; it was processed using Qiagen's column based QIAamp Nucleic Acid kit and the obtained nucleic acids were stored at 4°C. These stored samples were used as a template to execute real-time polymerase chain reaction, and results were noted. Group I demonstrated 96% and 88% sensitivity for N and ORF1ab genes respectively, whereas group II demonstrated 78% and 60% when compared to the results of standard group III. Overall group I showed better results than group II when compared to group III. Thus, in situations where gold-standard reagents are not available, PK exposure and heat treatment can be employed to carry out molecular detection of SARS-CoV2 viral component.

Assessment of Successful qRT-PCR of SARS-CoV-2 Assay in Pool Screening Using Isopropyl Alcohol Purification Step in RNA Extraction.

The study is aimed at establishing the optimal parameters for RNA purification of pooled specimens, in SARS-CoV-2 assay. This research work evaluates the difference of extracted RNA purity of pooled samples with and without treatment with isopropyl alcohol and its effect on real-time RT-PCR. As per the protocol of the Indian Council of Medical Research (ICMR), 5 sample pools were analysed using qRT-PCR. A total of 100 pooled samples were selected for the study by mixing 50 µL of one COVID-19 positive nasopharyngeal/oropharyngeal (NP/OP) specimen and 50 µL each of 4 known negative specimens. Pool RNA was extracted using the column-based method, and 1 set of pooled extracted RNA was tested as such, while RNA of the second set was treated additionally with chilled isopropyl alcohol (modified protocol). Further, the purity of extracted RNA in both the groups was checked using Microvolume Spectrophotometers (Nanodrop) followed by RT-PCR targeting E-gene and RNaseP target. The results showed that the purity index of extracted RNA of untreated pooled specimens was inferior to isopropyl alcohol-treated templates, which was observed to be 85% sensitivity and 100% specificity. The average Cq (E gene) in the unpurified and purified pool RNA group was 34.66 and 31.48, respectively. The nanodrop data suggested that purified RNA concentration was significantly increased with an average value of 24.73 ± 1.49 ng/uL, which might be the reason for high sensitivity and specificity. Thus, this group testing of SARS-CoV-2 cases using pools of 5 individual samples would be the best alternative for saving molecular reagents, personnel time, and can increase the overall testing capacity. However, purity of RNA is one of the important determinants to procure unfailing results, thus, this additional purification step must be included in the protocol after RNA has been extracted using commercially available kit before performing qRT-PCR.

Reprofiling of approved drugs against SARS-CoV-2 main protease: an in-silico study.

Given the COVID-19 pandemic, currently, there are many drugs in clinical trials against this virus. Among the excellent drug targets of SARS-CoV-2 are its proteases (Nsp3 and Nsp5) that plays vital role in polyprotein processing giving rise to functional nonstructural proteins, essential for viral replication and survival. Nsp5 (also known as Mpro) hydrolyzes replicase polyprotein (1ab) at eleven different sites. For targeting Mpro, we have employed drug repurposing approach to identify potential inhibitors of SARS-CoV-2 in a shorter time span. Screening of approved drugs through docking reveals Hyaluronic acid and Acarbose among the top hits which are showing strong interactions with catalytic site residues of Mpro. We have also performed docking of drugs Lopinavir, Ribavirin, and Azithromycin on SARS-CoV-2 Mpro. Further, binding of these compounds (Hyaluronic acid, Acarbose, and Lopinavir) is validated by extensive molecular dynamics simulation of 500 ns where these drugs show stable binding with Mpro. We believe that the high-affinity binding of these compounds will help in designing novel strategies for structure-based drug discovery against SARS-CoV-2.Communicated by Ramaswamy H. Sarma.