Guanxiang Liang

Highly accurate prophage island detection with PIDE

PIDE detects prophages in bacterial genomes and metagenomes with high accuracy using a protein language model and gene density clustering.

FEDKEA: Enzyme function prediction with a large pretrained protein language model and distance-weighted k-nearest neighbor

FEDKEA improves enzyme function prediction by combining a pretrained protein language model with distance-weighted k-nearest neighbor, outperforming existing tools.

iVirP: An integrative, efficient, and user-friendly pipeline to annotate viral contigs from raw reads of metagenome or VLP sequencing

iVirP is a pipeline for annotating viral contigs from metagenome or VLP sequencing data, improving accuracy and efficiency in virome analysis.

ESM-PVP: Identification and classification of phage virion proteins with a large pretrained protein language model and an MLP neural network

ESM-PVP uses a pretrained protein language model and an MLP to identify and classify phage virion proteins, outperforming previous methods on a new benchmark dataset.

The MOV10 RNA helicase is a dosage-dependent host restriction factor for LINE1 retrotransposition in mice

This study shows MOV10 restricts LINE1 retrotransposition in mice in a dosage-dependent manner, affecting reproductive fitness and transcriptome regulation.