Training aims
The objective of this tutorial is to introduce the fundamental concepts behind projection-based approaches and illustrate their application on some exemplar studies using the R package mixOmics. In this tutorial, we will focus on the application of these approaches to medium and high throughput biological data (transcriptomics, metabolomics, proteomics data) using PCA, CCA, PLS, PLS-DA and the variants that the mixOmics team and collaborators have developed.
Training program*
- Key methodologies in mixOmics and their variants
- Principal Component Analysis: PCA, sparse PCA, NIPALS
- Canonical Correlation Analysis: CCA, regularized CCA
- Partial Least Squares regression: PLS, sparse PLS
- Partial Least Squares Discriminant Analysis: PLS-DA, sparse PLS-DA
- Recent developments in mixOmics, including multilevel PLS for repeated measurements and introduction to the integration of multiple data sets
- Review on the graphical outputs implemented in mixOmics
- Sample plots
- Correlation circles
- Integrating two data sets: relevance networks and clustered image map
- Case studies and applications
- Example with PCA: Nutrimouse
- Example with CCA: Multidrug
- Example with PLS: Liver toxicity
- Example with PLS-DA: SRBCT study
* The methodologies will be presented throughout the two days training session. Each methodology will be illustrated on a case study (we will alternate theory and application).
Course material will be available in a hard printed copy and online.
Other information
Details for registration are provided here.
The session will take place in the formation room of the INRA center of Toulouse-Auzeville.