Yufeng Jane Tseng
Professor
Graduate Institute of Biomedical Electronics,
Bioinformatics, Department of Computer Science and Information Engineering School of Pharmacy
National Taiwan University
yjtseng@csie.ntu.edu.tw
Dept. and Web
Project Description
Research team has developed a 3D mass spectrometry imaging (3D MSI) model using schizophrenia mouse brains to map molecular distributions and concentrations, with a focus on understanding their roles in the disease.
The key stages of this 3D MSI analysis include:
- preparing tissue samples via cryosectioning and conducting DESI-MSI experiments, with Nissl staining for histological context,
- preprocessing MSI data to extract significant peaks and applying normalization to reduce inter-spectra variability,
- summarizing high-dimensional MSI data for easier visualization,
- reconstructing a 3D model by aligning tissue slices using histological images for precision
- conducting statistical analysis on the 3D model to identify biomarkers and investigate potential disease mechanisms.
This 3D MSI approach offers new insights into the molecular underpinnings of schizophrenia, supporting the discovery of biomarkers and disease pathways.
Requirement
- Machine learning (ML) and AI: Strong understanding of machine learning algorithms and neural network architectures.
- Programming: Proficiency in programming languages such as Python, and familiarity with libraries for data analysis (eg. NumPy, pandas, scikit-learn) and ML frameworks (eg. TensorFlow, PyTorch).
- Cheminformatics: Experience with handling molecular structures, visualizing compounds (e.g., using RDKit), and calculating molecular descriptors (e.g., using PaDEL or similar tools).
- Molecular Docking: Familiarity with docking software such as AutoDock Vina or similar platforms.
- PET tracer design: Foundational knowledge of the principles behind PET tracer design, including radiochemistry, radiolabeling, and pharmacokinetics.