Dong‐Qing Wei

RNASTOP predicts and optimizes mRNA chemical stability using deep learning, improving accuracy by 13% and reducing free energy in a vaccine sequence.

EnzOracle predicts enzyme environmental adaptation traits from sequence using a mixture-of-experts framework, showing strong accuracy and mechanism-aware validation.

This study uses single-cell RNA-seq data to identify disease-related gene programs and pathways in Alzheimer's disease, offering potential targets for personalized therapies.

This paper develops a mathematical model of adaptive immunity that integrates humoral and cellular responses, explaining immune memory, original antigenic sin, and cancer-immune interactions.

ProStab predicts protein stability changes upon mutations using a deep learning framework combining sequence and structure information, showing strong performance and experimental validation.

GRATCR generates epitope-specific TCR sequences with fewer training data than state-of-the-art models, showing higher specificity and biological functionality.

This study uses mathematical modeling to show that viral infections reshape the antibody repertoire through the proliferation of high-affinity antibody pools and contraction of low-affinity pools, with self-antigens maintaining antibody persistence.

This paper introduces Hot2Mol, a deep learning framework for designing drug-like PPI inhibitors by generating molecules that mimic hot-spot residues, showing improved performance over baselines.

This paper uses mathematical modeling to show that ADCC targeting Th cells hinders HIV vaccine development by damaging immune responses and reducing vaccine effectiveness.

This paper introduces MultiPPIMI, a deep learning framework that predicts PPI-modulator interactions without requiring target structure or reference modulators, achieving high AUROC scores in benchmark tests.

This paper develops an AI-based simulation method to predict future high-risk SARS-CoV-2 variants by simulating RBD mutations and screening potential variants efficiently.

scCobra is a deep learning tool that integrates and harmonizes single-cell data by mitigating batch effects and enabling online label transfer.

The paper introduces a self-attention graph convolutional network to identify key DNA methylation sites for multi-tumor early diagnostics, achieving improved sensitivity in blood-based detection.

This study introduces T4SE-XGB, an XGBoost-based model for predicting type IV secreted effectors from protein sequences, achieving high accuracy and interpretability.

This study introduces DTI-MLCD, a multi-label learning method with community detection for predicting drug-target interactions, showing improved performance over existing methods.

This study investigates how SrtA inhibitors' activity depends on the closed lid conformation of SrtA from Bacillus anthracis through molecular dynamics and docking analyses.

DTI-CDF improves drug-target interaction prediction by integrating hybrid features into a cascade deep forest model, achieving higher performance than existing methods.

The paper introduces an anti-cancer peptide prediction tool, ACS, achieving 95% accuracy, outperforming existing methods.