Clusters consisting only of virus types with two mutations in the helicase found by Autoencoder analysis in Washington State, USA
Miyake, J.; Yoshino, M.; Sato, T.; Niioka, H.; Sakata, Y.; Nakazawa, Y.
Show abstract
Using an autoencoder-based analysis to classify genomes of SARS-CoV-2 coronaviruses, we found a cluster consisting only of a specific genotype with two mutations in the helicase. This virus genotype, called C-type SARS-CoV-2, was almost exclusively prevalent in the United States from March to July 2020. This type of virus, characterized by a pair of the C17747T (P504L) and A17858G (Y541C) mutations on the nsp13 gene, had never been highly prevalent at any other time or in any other part of the world. In the U.S., Washington State was the center of the epidemic, and the C-type viruses, along with the viruses with wild-type helicase, seemed to have aroused the pandemic. In Washington State, USA, the CoViD-19 epidemic during the first two months of the year, starting at the end of February 2020, was mainly caused by the type-C virus. During this period, the infection spread rapidly; from May onwards, the number of viruses with wild-type helicases became higher than that of type-C viruses, and no type-C viruses have been collected since early July. The involvement of the helicase in this COVID-19 disease was discussed.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Molecular features similarities between SARS-CoV-2, SARS, MERS and key human genes could favour the viral infections and trigger collateral effects 95%
- Host and infectivity prediction of Wuhan 2019 novel coronavirus using deep learning algorithm 93%
- Sequence analysis of SARS-CoV-2 genome reveals features important for vaccine design 93%
Similar papers in this journal
- Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study 96%
- Structural impact of synonymous mutations in six SARS-CoV-2 Variants of Concern 94%
- Short k-mer Abundance Profiles Yield Robust Machine Learning Features and Accurate Classifiers for RNA Viruses 93%
Similar papers in this journal
- Translation-associated mutational U-pressure in the first ORF of SARS-CoV-2 and other coronaviruses 94%
- Positive selection of ORF3a and ORF8 genes drives the evolution of SARS-CoV-2 during the 2020 COVID-19 pandemic 94%
- The discovery of a recombinant SARS2-like CoV strain provides insights into SARS and COVID-2019 pandemics 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.