Introduction to machine learning for oncology
The course covers the basics of classical machine learning algorithms and their application to oncology. It is intended for a biomedical audience with a small background in statistics. Slides are available here. The course is highly based on the reference "An introduction to statistical learning with applications in R" by Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani.Introduction to mathematical oncology
You can find material on a graduate course for introduction to mathematical and computational oncology.- The data file (.xlsx)
- Some basic data exploration and the correction (jupyter notebooks here and here, pdf files here and here)
- Investigations of basic tumor growth law through model fitting and the correction (jupyter notebooks here and here, pdf files here and here)
Introduction to modeling, simulation and data science in oncology
Hands-on sessions are jupyter notebooks in python.- Nonlinear regression. Slides. Hands-on: html or jupyter notebook.
- Population modeling. Slides. Hands-on (Monolix).
- Statistical learning. Slides. Hands-on: html or jupyter notebook.
Population pharmacokinetics modeling using Monolix
You can find here the text of a practical hands-on session on parameter estimation using the excellent software Monolix. It deals with the modeling analysis (within the mixed-effects statistical framework) of pharmacokinetics data of warfarin. See also the warfarin case study video by the Lixoft team, which inspired part of this material. (NB: a Monolix license is required. Monolix is free for academic researchers/students).Mathematical tools for pharmacometrics
- Slides
- Hands-on in R (jupyter notebook).
- Hands-on simulx