790384 Machine learning and pattern recognition for bioinformatics

Type
Lecture and exercise
Semester hours
3
Lecturer (assistant)
Organisation
Offered in
Sommersemester 2024
Languages of instruction
Englisch
Content

Introduction to machine learning and pattern recognition for data analysis in bioinformatics.
1) Theory:
1.1) Brief introduction to Python 3, numpy und pandas.
1.2) Classification of problems and optimal choice of analysis methods.
1.3) Supervised learning for modeling of continuous and discrete observations. Derivation of relations between machine learning methods and statistical models.
1.4) Unsupervised learning and exploratory data analysis.
1.5) Methods used in machine learning for model diagnosis and model selection.
1.6) Discussion of selected machine learning and pattern recognition algorithms from the scikit.learn library in bioinformatics use cases.

2) Practical part:
Application of the theoretical skills to biological data analysis problems using the publicly available Python 3 libraries numpy, pandas and scikit.learn.
Previous knowledge expected

Skills in Mathematics and Statistics which are provided in the compulsory courses in the Biotechnology bachelor and master curricula.
Objective (expected results of study and acquired competences)

Successful completion of this course enables students to independently analyze bio(techno)logical data sets with machine learning methods. Course participants will after a successful completion understand the mathematical and statistical background of machine learning algorithms. Successful students will know ho to apply important scikit.learn algorithms and be able to script solutions for bioinformatics data analysis problems in Python 3. Students will furthermore have acquired skills which allow them to assess machine learning derived analysis results quantitatively. The theoretical skills which students acquire during this course allow them to critically assess published methods and to select optimally suited strategies for their future bioinformatics data analysis challenges.
You can find more details like the schedule or information about exams on the course-page in BOKUonline.