Jiayu Shang

This paper organizes a community challenge to develop automated virus taxonomy classification tools and evaluates their performance on a combined dataset of expert-curated and metagenomic sequences.

VirProtRAG improves viral protein function annotation by integrating literature retrieval and evidence-based generation, introducing 32.53% new annotations and supporting sequence-inferred functions.

PlasRAG characterizes and retrieves plasmids using sequence-text alignment, showing that plasmids with broader host ranges and ARGs spread more extensively.

ViraLM is a viral language model that improves virus detection in metagenomic data, particularly for short contigs, by leveraging a genome foundation model and a curated dataset.

PlasGO predicts GO terms for plasmid-encoded proteins using a hierarchical model, achieving high precision in function annotation.

GDmicro improves disease status classification using gut microbiome data by combining semi-supervised learning and domain adaptation, achieving higher accuracy than existing methods.

CHEER improves taxonomic classification of viral metagenomic data by using a hierarchical deep learning model, achieving higher accuracy than existing methods.

The paper introduces VirBin, a tool for clustering viral contigs into haplotypes, showing improved sensitivity and precision over existing methods.