Chen Liao

The paper develops a genomic language model framework to predict essential genes in fungi by integrating sequence embeddings with biological features, showing consistent performance across species.

The paper shows gut microbiota regulates the intestinal kynurenine pathway through vitamin E absorption, using mouse models and computational analysis of microbiota associations.

This study identifies TDCA, a microbiota-derived bile acid, as a mediator that restores immune checkpoint therapy efficacy after antibiotic-induced hyporesponsiveness by enhancing CD8+ T cell antitumor immunity.

MuSHIN improves genome-scale metabolic models by predicting missing reactions using a deep hypergraph learning method, enhancing their predictive accuracy and phenotypic predictions.

The paper uses machine learning to identify valeric acid as a bacterial metabolite that inhibits Candida parapsilosis growth through intracellular acidification, reducing fungal colonization in mice.

The paper investigates the evolution and regulation of rhamnolipid biosynthesis in Pseudomonas aeruginosa, linking it to oxidative stress and explaining its inconsistent distribution across lineages.

The paper introduces CHESHIRE, a deep learning method to predict missing reactions in metabolic networks using topology, outperforming existing methods and improving phenotypic predictions.

The paper compiles shotgun metagenomic data from stool samples of hospitalized hematopoietic cell transplant patients to enhance microbiome analysis beyond taxonomic composition.