Liqing Zhang

ARGfore forecasts antibiotic resistance gene abundances from time-series metagenomic data, outperforming standard methods with lower error and better efficiency.

NicheAgent identifies spatial niches in transcriptomics data without training, using LLMs to refine assignments based on gene expression and spatial context.

This study evaluates lightweight LLM agents for improving spatial transcriptomics annotation using rule-based heuristics and multirole reasoning across multiple datasets.

CancerSubminer improves cancer subtyping by combining supervised and unsupervised learning on DNA methylation data, identifying prognostic subtypes across multiple cancers.

ProtAlign-ARG improves antibiotic resistance gene detection by combining protein language models with alignment-based scoring, achieving higher recall than existing methods.

The paper identifies and characterizes phage-plasmid hybrids across diverse environments, revealing their niche-specific functional traits and ecological roles.

MetaMLP is a machine learning classifier for metagenomic functional profiling that uses word embeddings and a neural network to achieve high accuracy and speed.

NanoARG identifies antimicrobial resistance elements from nanopore-derived environmental metagenomes, enabling analysis of ARGs, MRGs, MGEs, and pathogens.