About
About Bin Xu 许膑
Bin obtained his Master of Medicine degree from Southern Medical University in 2022 and shortly thereafter joined the Shidang Team at South China University of Technology. His research focuses on the development and application of integrated diagnosis and treatment biomaterials in tumor targeting and immune therapy drug delivery. Currently, he is committed to applying artificial intelligence to early tumor diagnosis, designing and developing drug delivery carriers, and enhancing precise prediction of drug efficacy.
Research questions
Questions I care about
How can carrier design variables be connected to tumor targeting and immune-therapy delivery goals?
I am interested in making the relationship between a biomaterial design decision and its intended biomedical function more explicit and testable.
What evidence is needed for AI-guided nanoparticle design to support precision cancer drug delivery?
The challenge is to connect model outputs with experimentally meaningful carrier properties and clinically relevant questions.
How can clinical knowledge and experimental data support more reliable prediction of therapeutic efficacy?
I am exploring how biomedical context can guide the choice of data, targets, and evaluation criteria used in predictive studies.
Current work
What I am working on
Research direction
AI-guided nanoparticle and carrier design
Studying how data-driven models can connect carrier composition and design variables with delivery goals in precision cancer therapy.
My role: Integrating clinical, biomaterials, and data-driven perspectives when defining questions and interpreting evidence.
Research direction
Tumor-targeted and immune-therapy delivery
Investigating biomaterial strategies for tumor targeting and delivery systems intended to support immune-therapy applications.
My role: Connecting carrier-design questions with disease and treatment context.
Contribution profile
What I bring to a project
Methods
- Clinical and biomedical question formulation
- Biomaterial and drug-delivery design reasoning
- Machine-learning-assisted prediction
Scientific domains
- Tumor targeting
- Immunotherapy delivery
- Early cancer diagnosis
I can contribute
- Translating biomedical needs into testable design questions
- Connecting clinical, experimental, and computational perspectives
- Interpreting model predictions in a carrier-design context
Selected work
Selected research outputs
2025
ACS Nano, 19(36), 32674-32692 (2025)
2025
Adv. Sci., 12(30), e03138 (2025)
Open to conversation
Where we might work together
I welcome discussions that connect clinically meaningful cancer questions with biomaterial design, drug-delivery evidence, and machine-learning methods.
I can contribute
- Clinical and disease-context framing
- Biomaterial and carrier-design questions
- Interpretation across biomedical and computational evidence
I am looking for
- Experimental characterization of carrier–disease interactions
- Learning methods suited to heterogeneous biomedical evidence
- Clinical or translational perspectives on evaluation
Possible formats
- Joint computational–experimental studies
- Data and model benchmarking
- Exploratory research conversations
