ABSTRACT
One of the emerging subjects to combat the SARS-CoV-2 virus is to design accurate and efficient drug such as inhibitors against the viral protease to stop the viral spread. In addition to laboratory investigation of the viral protease, which is fundamental, the in silico research of viral protease such as the protease cleavage site prediction is critically important and urgent. However, this problem has yet to be addressed. This article has, for the first time, investigated this problem using the pattern recognition approaches. The article has shown that the pattern recognition approaches incorporating a specially tailored kernel function for dealing with amino acids has the outstanding performance in the accuracy of cleavage site prediction and the discovery of the prototype cleavage peptides.
Subject(s)
COVID-19/virology , Coronavirus 3C Proteases/metabolism , Peptides/metabolism , SARS-CoV-2/metabolism , Algorithms , Amino Acid Sequence , Coronavirus 3C Proteases/chemistry , Humans , Machine Learning , Peptides/chemistry , Proteolysis , SARS-CoV-2/chemistryABSTRACT
Recently, the recurrence of positive SARS-CoV-2 viral RNA in recovered COVID-19 patients is receiving more attention. Herein we report a cohort study on the follow-up of 182 recovered patients under medical isolation observation. Twenty (10.99%) patients out of the 182 were detected to be SARS-CoV-2 RNA positive (re-positives), although none showed any clinical symptomatic recurrence, indicating that COVID-19 responds well to treatment. Patients aged under 18 years had higher re-positive rates than average, and none of the severely ill patients re-tested positive. There were no significant differences in sex between re-positives and non-re-positives. Notably, most of the re-positives turned negative in the following tests, and all of them carried antibodies against SARS-CoV-2. This indicates that they might not be infectious, although it is still important to perform regular SARS-CoV-2 RNA testing and follow-up for assessment of infectivity. The findings of this study provide information for improving the management of recovered patients, and for differentiating the follow-up of recovered patients with different risk levels.