Advanced Microarray Data Analysis

The course section on experimental design will contain material about factorial and fractional factorial designs.
The section on preprocessing and filtering will contain material on noise removal, transformations and normalization methods.
The data analysis section will contain material about classical statistics (hypothesis testing, multiple comparisons), finding differentially expressed genes, unsupervised classification (hierarchical cluster analysis, principal component analysis, k means clustering Kohonen networks), supervised classification (disciminant partial least squares regression) and regression (multiple linear regression, partial least squares regression) and use of external information (gene ontology/annotation, metabolic networks)

The student should be able to understand and apply the most common methods for experimental design, preprocessing/filtering and data analysis of microarrays. The student should also be able to perform critical assessment of the statistical results and make effective use of biological information.

Lectures, exercises, and self study.
20 hours exercises.
15 lectures.
The course is lectured in a concentrated period of time (1 week). The examination (2 hours) will be given in connection with the course week. Multiple choice examination.
Oral examination if few students.
English teaching by request.