About
About Meitang Peng 彭美堂
MT is a PhD student in Biomedical Engineering at the Xu Group, having joined as a master’s student in 2023 and transferred to the PhD programme in 2025. His research focuses on the integration of machine learning and quantum computing for the discovery of biomaterials, drug discovery, and controlled carrier delivery. MT has a keen interest in automated experimental technologies, dedicating his efforts to optimizing bioengineering processes and material properties through innovative computational approaches.
Research questions
Questions I care about
How can physical and chemical calculations provide learning signals that remain useful beyond a single dataset?
I am interested in connecting simulation-derived information with models that can be evaluated across molecular and materials questions.
How can molecular simulation and machine learning be combined so that predictions are easier to interrogate scientifically?
The goal is not only predictive performance, but a clearer account of which interactions and assumptions drive a result.
Where can automation shorten the path from a candidate idea to usable evidence?
This includes more reproducible calculations, model comparisons, and handoffs between computational and experimental work.
Current work
What I am working on
Active direction
Simulation-informed molecular and material discovery
Combining molecular simulation, first-principles calculations, and learning-based models for biomaterial and drug-discovery questions.
My role: Computational modelling, analysis design, and comparison of candidate representations.
Exploratory
AI-assisted carrier and molecular design
Exploring computational approaches for reasoning about candidate materials, molecular properties, and controlled-delivery systems.
My role: Linking physical calculations with machine-learning workflows and interpretable comparisons.
Contribution profile
What I bring to a project
Methods
- Molecular dynamics simulation
- First-principles calculation
- Machine-learning model development
Scientific domains
- Biomaterials
- Drug discovery
- Controlled carrier delivery
I can contribute
- Designing simulation-informed computational studies
- Developing learning-space and representation strategies for scientific discovery
- Connecting computational evidence with experimental observations for mechanistic interpretation
Working philosophy
Principles I work by
Trust the Process
Accept uncertainty and unexpected turns, and try to make the best of what each stage brings.
Make Things Simple
Reduce complexity to its essential structure before adding unnecessary sophistication.
格物致知 · Learn Through Inquiry
Seek understanding by examining things carefully, questioning assumptions, and grounding conclusions in evidence.
Selected work
Selected research outputs
2026
Nat. Commun., 17(1), 7424 (2026)
2025
ChemRxiv, preprint (2025)
2025
J. Am. Chem. Soc., 147(20), 17330-17341 (2025)
Open to conversation
Where we might work together
I welcome conversations that connect molecular simulation or first-principles calculations with machine-learning methods for biomolecular and materials discovery.
I can contribute
- Designing simulation-informed computational studies
- Developing learning-space and representation strategies for scientific discovery
- Connecting computational evidence with experimental observations for mechanistic interpretation
I am looking for
- Experimental perspectives that can test computational hypotheses
- Complementary methods for molecular representation and scientific learning
Possible formats
- Joint computational–experimental studies
- Method benchmarking and reproducibility work
- Short research or internship conversations
