I am a PhD candidate working on computational immunology, TCR-pMHC recognition, and AI-driven immune receptor design.

My research focuses on developing machine learning and generative AI methods to understand, predict, and design antigen-specific immune receptors. I am particularly interested in TCR-pMHC interaction modeling, antigen-specific TCR generation, and single-cell immune repertoire analysis. I wish that these computational efforts will facilitate the development of immunotherapy in the future.

• TCR-pMHC binding specificity prediction
• Antigen-specific T-cell receptor design
• Structure-aware modeling of immune recognition
• Single-cell transcriptomics and immune repertoire analysis
• AI for precision immunotherapy

• TCRDiff: Generative design of antigen-specific T-cell receptor sequences with a conditional diffusion model.
• UniAIR: Generalizable mutation-effect prediction across adaptive immune recognition via unified multimodal framework.
• ImmuScope: Self-iterative multiple-instance learning enables the prediction of CD4+ T cell immunogenic epitopes.
• EPACT: Epitope-anchored contrastive transfer learning for paired CD8+ T cell receptor–antigen recognition.
• DeepSecE: A Deep-learning-based framework for multiclass prediction of secreted proteins in Gram-negative bacteria.

• GitHub: https://github.com/zhangyumeng1sjtu
• LinkedIn: https://www.linkedin.com/in/yumeng-zhang-b6114732b/
• X: https://x.com/yumengzhang99
• Personal website: https://zhangyumeng1sjtu.github.io/