Research Interests

deep learning, bioinformatics

Publications

    Adversarial regularized autoencoder graph neural network for microbe-disease associations prediction

    Limuxuan He, Quan Zou, Qi Dai, Shuang Cheng*, Yansu Wang*

    Briefings in Bioinformatics, 2024, CCF-B, IF2024=6.8, Q2.

    • We propose an adversarial regularized autoencoder graph neural network algorithm, named Stacked Adversarial Regularization for Microbe-Disease Associations Prediction (SARMDA), for predicting associations between microbes and diseases.

    metaTP: a meta-transcriptome data analysis pipeline with integrated automated workflows

    Limuxuan He, Quan Zou, Yansu Wang*

    BMC Bioinformatics, 2025, CCF-C, IF2025=3.3, Q3.

    • We developed metaTP, a pipeline that integrates bioinformatics tools for analyzing meta-transcriptomic data comprehensively. The pipeline includes quality control, non-coding RNA removal, transcript expression quantification, differential gene expression analysis, functional annotation, and co-expression network analysis.

    MCT-ARG: Identification and classification of antibiotic resistance genes based on a multi-channel Transformer model

    Limuxuan He, Huan Li, Ren Qi, Quan Zou, Yansu Wang*

    Science of The Total Environment, 2025

    • We propose MCT-ARG, a multi-channel Transformer framework that integrates protein primary sequences, predicted secondary structure, and relative solvent accessibility (RSA) to construct comprehensive multimodal representations for ARG prediction and mechanistic insight. Additionally, a dual-constraint regularization strategy-combining entropy minimization and local continuity enforcement-improves attention focus on functionally relevant residues.