Pre-binning correction of chimeric contigs reduces reference-discordant gene annotations in near-complete metagenome-assembled genomes
Yi Ding, Jin Xiao, bohao ZOU, Chao Yang, Zhenfeng Wu, Aiping Lyu, Lu Zhang
The paper introduces DeepMM, a deep learning method to correct chimeric contigs in MAGs, improving gene annotation accuracy and reducing reference-discordant genes and virulence-factor calls.
bioRxiv · Oct 15, 2026 · PreprintBioinformatics