Xiaoqing Jiang

Tripleknock: predicting lethal effect of three-gene knockout in bacteria by deep learning

Tripleknock predicts lethal effects of three-gene knockouts in bacteria using deep learning, achieving faster predictions than FBA with high cross-species accuracy.

KuafuPrimer: Machine learning empowers the design of 16S amplicon sequencing primers toward minimal bias for bacterial communities

KuafuPrimer uses machine learning to design 16S rRNA gene primers with minimal bias, improving taxonomic accuracy and detecting rare taxa missed by universal primers.

eBiota: Designing microbial communities from large seed pools with desired function using rapid optimization and deep learning

eBiota designs microbial communities from large strain pools to generate target products using optimization and deep learning, showing accurate predictions and experimental validation.

Developing Foundation Models for Predicting Viral Animal Host Range in Intelligent Surveillance

This paper introduces VirHRanger, a foundation model for predicting viral host range using genomic and protein data, achieving high accuracy across diverse viruses and host categories.

IPEV: Identification of Prokaryotic and Eukaryotic Virus-derived sequences in virome using deep learning

IPEV identifies and classifies prokaryotic and eukaryotic virus-derived sequences in viromes using deep learning, achieving higher precision and efficiency than existing methods.

Distinguish virulent and temperate phage-derived sequences in metavirome data with a deep learning approach

DeePhage is a deep learning tool that classifies virulent and temperate phage-derived sequences in metavirome data with high accuracy and speed.

Identify phage hosts from metaviromic short reads based on deep learning and Markov chain model

HoPhage identifies phage hosts from metavirome short reads using deep learning and a Markov chain model, achieving good performance on short fragments across a wide host range.