Statistical Inference for Bioinformatics

5 credits

Syllabus, Master's level, 1MB459

A revised version of the syllabus is available.
Code
1MB459
Education cycle
Second cycle
Main field(s) of study and in-depth level
Bioinformatics A1N, Technology A1N
Grading system
Pass with distinction (5), Pass with credit (4), Pass (3), Fail (U)
Finalised by
The Faculty Board of Science and Technology, 7 March 2017
Responsible department
Biology Education Centre

Entry requirements

Alt. 1) 120 credits in the engineering programme in molecular biotechnology including Multivariate data analysis and experimental design. Alt. 2) 120 credits. Bioinformatics - starting course (can be read in parallel).

Learning outcomes

After passing the course the student should be able to

  • account for and apply classical statistical inference based on Bayesian and frequentist methods, traditional computer-based methods, as well as computer-intensive methods, for analysis one variable alone and several variables at the same time
  • choose and apply the appropriate among above-mentioned methods and technologies for statistical inference for a given set of biological and biomedical molecular data and their associated biomedical questions.

Content

Classical inference: Frequentist and Bayesian inference, maximum likelihood estimation. Traditional computer-based methods: Empirical Bayes, ridge regression, generalized linear models, regression trees, survival analysis and the EM-algorithm. Computer-intensive methods as resampling, resampling based confidence intervals, cross validation, large-scale hypothesis testing, sparse regression models, random forests, and boosting. Bioinformatic application examples.

Instruction

Lectures, calculation exercises and computer exercises.

Assessment

Written examination (3 credits), computer exercises (2 credits).

FOLLOW UPPSALA UNIVERSITY ON

facebook
instagram
twitter
youtube
linkedin