Cancer Data Science
BDSI.2024.CDS@umich.edu
Instructor: Veera Baladandayuthapani (veerab@umich.edu)
Jian Kang (jiankang@umich.edu)
Co-mentor: Junsouk Choi (junsouk@umich.edu)
Grant Carr (grantcar@umich.edu)
The Cancer Data Science group will delve into statistical, computational, and mathematical questions that arise in cancer research. The research project will involve an application to advancing cancer prevention and care. Examples include developing predictive models to assess recurrence risk based on clinical, genomic, or pathological data; investigating spatial and temporal dynamics of tumor evolution using genomic and medical imaging data; leveraging clinical data to identify biomarkers associated with tumor initiation and progression, and much more. Student teams will initiate novel research questions using the provided data sources and conduct in-depth analysis to explore these questions. This immersive experience will teach students valuable skills in data manipulation, statistical computing, and data visualization. Within this research group, students will have a chance to engage with members of the UM Cancer Data Science group Links to an external site. and learn to apply advanced statistical methods, such as survival analysis, machine learning, and spatial data analysis.
|
Monday |
Tuesday |
Wednesday |
Thursday |
|
|
Week 1: |
Orientation |
Introduction to data |
Julia Wrobel guest speaker |
Introductions to data |
|
Week 2: |
First order analysis: analysis of cell prevalences |
|||
|
Week 3: |
Second order analysis: spatial analysis of cell interactions |
July 4th: No research meeting |
||
|
Week 4: |
Model building: prediction of and association with outcomes |
|||
|
Week 5: |
Continue and/or finalize work for poster and presentation |
|||
|
Week 6: |
Continue work |
Presentation rehearsals |
Poster printing and rehearsals |
Symposium |
Pre-Class Readings
Here are some reading materials to familiarize yourself with the technology, scientific questions, structure and type of data and relevant quantitative methods.
Note: you don't need to get ALL the details – just a basic understanding – and we’ll fill in the details once you are here at U-M.
- This review paper Download review paper has a condensed section on MI data. You just need to focus on Section 4 to get a high-level overview.
- This tutorial, Links to an external site. given by Dr. Julia Wrobel also has a nice introduction to MI data that you take a look at (just look at the first deck of slides Links to an external site.). Dr. Wrobel will be giving an overview and introduction in the first week of BDSI (June 19th) as well.
- This is another review paper Download another review paper by Dr. Wrobel and colleagues that you can skim through.
- Finally, here is a recent paper Download here is a recent paper on analyses of such data that might be useful to look at.
R Code
We will be working with mIF data for lung cancer Download lung cancer and ovarian cancer Download ovarian cancer. If you are curious how these objects are constructed, you may look at this script Download this script. However, you may simply use readRDS() to read these objects into the R environment.
Additionally, we provide the R package MItools Links to an external site. for second-order spatial analysis of multiplex imaging data, which gathers essential R functions needed to perform this analysis on multiplex imaging data.
- Code Download Code for tasks 1 and 2 on exploratory/descriptive analyses
- Code Download Code for task 3 on first order non-spatial analysis
- Additional code Download code for first order analysis
- Code Download Code for task 4 on second order spatial analysis
Week 1
Please look through this document Download this document and complete tasks 1 and 2 by the end of Week 1. This will get you acquainted with the data sets that you will be working with throughout the program. You may use this code Download this code to help guide you.
Below, you can find the recording of Dr. Julia Wrobel's talk along with the materials Links to an external site. for her presentation.
Spatial Analysis of Multiplex Imaging Data
Survival Analysis