Back

ANNAVP, using neural networks to predict neutralization efficiency of antibodies against viral strains and to cluster strains by protein sequence

Cristian, G. I.

2020-09-22 bioinformatics
10.1101/2020.09.21.307074 bioRxiv
Show abstract

Studying viral antibody neutralization data is a complex task and knowledge relating to the effectiveness of a particular antibody to particular strains of viruses cannot easily be extrapolated to other new, related strains. We have developed ANNAVP, a software that uses neural networks to model viral protein data. ANNAVP uses supervised or unsupervised learning and viral protein sequence data to form correlations between different strains and to predict the effectiveness of neutralizing agents against them.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

50% of probability mass above

"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.