Abstract
Deep learning-based variant callers are becoming the standard and have achieved superior SNP calling performance using long reads. In this paper, we present Clair3, which leveraged the best of two major method categories: pile-up calling handles most variant candidates with speed, and full-alignment tackles complicated candidates to maximize precision and recall. Clair3 ran faster than any of the other state-of-the-art variant callers and performed the best, especially at lower coverage.
Competing Interest Statement
R. L. receives research funding from ONT. The remaining authors declare no competing interests.
Footnotes
Updated with Guppy5 data results. Revised descriptions in the methods.
Copyright
The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY 4.0 International license.