Deep-learning-enabled protein–protein interaction analysis for prediction of SARS-CoV-2 infectivity and variant evolution - Nature Medicine

  • 📰 NatureMedicine
  • ⏱ Reading Time:
  • 7 sec. here
  • 2 min. at publisher
  • 📊 Quality Score:
  • News: 6%
  • Publisher: 53%

Health Health Headlines News

Health Health Latest News,Health Health Headlines

Based on a deep learning model predicting the binding affinities of protein-protein interactions, the effects of SARS-CoV-2 spike protein variants on binding to ACE2 and neutralizing antibodies was used to predict immune escape and viral evolution

, Validation of immune escape prediction on the Omicron sublineage. Yellow dots indicate log transformed fifty-percent inhibitory dilutions of pseudovirus neutralization assay , curated from Gruell et al. Blue dots indicated log transformed escape scores of four variants against by monoclonal antibodies. Columns shows mean of the data. Error bar shows standard deviation. Differences between variants were tested by two-tailed Student’s t-test.

Extended Data Table 1 Comparison of various methods on prediction performance in the SKEMPI 2.0 set with mutation-level validation

 

Thank you for your comment. Your comment will be published after being reviewed.
Please try again later.
We have summarized this news so that you can read it quickly. If you are interested in the news, you can read the full text here. Read more:

 /  🏆 451. in HEALTH

Health Health Latest News, Health Health Headlines