Shaojun Pan

The paper uses long-read metagenomics to analyze pet dog gut microbiomes, generating high-quality MAGs and identifying antimicrobial resistance elements in a Shanghai cohort.

AEMB improves metagenomic binning efficiency by reducing computational demands while maintaining binning accuracy.

SemiBin2 improves metagenomic binning by using self-supervised learning, outperforming previous methods in both short- and long-read sequencing.

metaMIC identifies and corrects misassemblies in metagenomic assemblies, improving downstream scaffolding and binning results.

SemiBin improves metagenomic binning by integrating reference genomes with semi-supervised deep learning, producing higher-quality bins with greater taxonomic diversity in simulated and real datasets.

MACREL identifies high-quality antimicrobial peptide candidates from genomes and metagenomes using a novel set of peptide features and classifiers.