Liqing Zhang

Predicting Unseen Gene Perturbation Response Using Graph Neural Networks with Biological Priors

This paper introduces PerturbGraph, a graph neural network framework that predicts transcriptional responses to unseen gene perturbations by integrating biological priors, outperforming existing methods on benchmark datasets.

Leveraging AI for facioscapulohumeral muscular dystrophy prediction and omics biomarker identification

This study uses machine learning to predict FSHD using multi-omics data and identifies key biomarkers, showing improved accuracy with limited samples.

ARGContextProfiler: Extracting and Scoring the Genomic Contexts of Antibiotic Resistance Genes using Assembly Graphs

ARGContextProfiler improves accuracy in identifying antibiotic resistance gene contexts in metagenomic data using assembly graphs and read mapping.

Fast-Part: Fast and Accurate Data Partitioning for Biological Sequence Analysis

Fast-Part partitions biological sequence data efficiently while maintaining homology separation and stratification ratios.

MetaCompare 2.0: Differential ranking of ecological and human health resistome risks

MetaCompare 2.0 differentiates human health and ecological resistome risks using metagenomic data, showing higher risk scores for human-contaminated environments.

CIWARS: a web server for waterborne antibiotic resistance surveillance using longitudinal metagenomic data

CIWARS is a web server for analyzing longitudinal metagenomic data to detect antibiotic resistance genes and assess AR risks in environmental samples.

PathoLM: Identifying pathogenicity from the DNA sequence through the Genome Foundation Model

PathoLM is a pathogen language model that improves pathogenicity identification in bacterial and viral sequences by leveraging pre-trained DNA models and minimal data, outperforming existing methods.

DeepMRG: a multi-label deep learning classifier forpredicting bacterial metal resistance genes

DeepMRG predicts bacterial metal resistance genes using a multi-label deep learning classifier, achieving high accuracy and reducing false negatives.

Kairos infers in situ horizontal gene transfer in longitudinally sampled microbiomes through microdiversity-aware sequence analysis

Kairos detects in situ horizontal gene transfer in microbiomes using time-series metagenomic data and competitive read alignment, improving detection of antibiotic resistance genes compared to MAG-based methods.

DeepGeni: Deep generalized interpretable autoencoder elucidates gut microbiota for better cancer immunotherapy

This paper introduces DeepGeni, an interpretable autoencoder for microbiome analysis, showing improved prediction of melanoma immunotherapy response and identifying key microbial taxa.

mobileOG-db: a manually curated database of protein families mediating the life cycle of bacterial mobile genetic elements

The paper introduces mobileOG-db, a manually curated database of protein families involved in bacterial mobile genetic element life cycles, enabling improved MGE annotation and analysis.

DeepMicro: deep representation learning for disease prediction based on microbiome data

DeepMicro uses deep representation learning to predict diseases from microbiome data, outperforming existing methods and achieving faster training.

Uncovering missed indels by leveraging unmapped reads

This paper identifies novel indels from unmapped reads in breast cancer data, revealing previously missed genetic variations linked to oncogenes and tumor suppressor genes.

BisPin and BFAST-Gap: Mapping Bisulfite-Treated Reads

BisPin and BFAST-Gap are read mappers for bisulfite-treated DNA data, showing improved mapping accuracy on real and simulated data compared to existing tools.

DeepARG: A deep learning approach for predicting antibiotic resistance genes from metagenomic data

This paper introduces deepARG, a deep learning method for predicting antibiotic resistance genes from metagenomic data, achieving high precision and recall over traditional methods.

UPS-indel: A Universal Positioning System For Indels

UPS-indel identifies and resolves redundant indels in genomic databases, improving data consistency and comparison across variant calling tools.

InfoTrim: A DNA Read Quality Trimmer Using Entropy

InfoTrim is a DNA read trimmer that uses entropy to improve alignment quality, performing reasonably well on bisulfite-treated data compared to other trimmers.