Back

Lineage Detector: Efficient Tool for Detecting New SARS-Cov-2 Lineages

Zou, X.

2024-11-04 bioinformatics
10.1101/2024.11.01.621557 bioRxiv
Show abstract

Since the novel virus of SARS-Cov-2s emergence, it continues to mutate at significant speed. The mutation speed and diversity of the virus has reached a level that is hard to be analysed purely via human tracing even with the help of UShER trees. We create an open-sourced tool of Lineage Detector, an automated tool that helps highlight the most important lineages of interest on Usher trees. Lineage Detector can highlight the most interesting SARS-CoV-2 branches for manual investigation and reduce the work of volunteer variant hunters to 8 [~] 10%, greatly improve their efficiency. Since its release, it has helped the identification, proposal and designation process of more than 100 SARS-CoV-2 variants.

Matching journals

The top 5 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.