Entry requirements

120 credits inclusive Discrete Computational Biology or equivalent, Basic Statistics

Learning outcomes

To teach advanced concepts of Artificial Intelligence (AI) applicable to selected life science problems such as, for example, but not restricted to, gene function prediction from transcriptome data, modelling protein properties, modelling ligand-protein interactions, drug target discovery, using structured data repositories (ontologies) for reasoning about biological entities and processes, and extracting information from free text (scientific publications). To teach the design and implementation of computer programs that apply AI methods and techniques with a special attention to all-ome-wide approaches.

Upon completing the course, the student should:

• Have good knowledge of computational methods and techniques based on heuristic search, knowledge representation, reasoning and machine learning, and the ability to apply them to life science problems.
• Be experienced in extracting data from biological data bases and data repositories and in using the data in AI programs.

Content

Search and heuristic search, introduction to logic and automatic reasoning techniques, knowledge representation. Ontologies. Grammars and natural language processing. Constraint satisfaction. Machine learning: clustering, rough sets and decision trees, Monte Carlo-based feature selection, statistical validity and significance of models. Advanced network models. All topics applied to life science problems.

Instruction

Lectures, lab-based computer exercises, and a project.

Assessment

Written exam at the end of the course - 3 credits. Successful (pass/fail) completion of 66% of the problem sets - 1 credit, successful (pass/fail) completion of the project 1 credit.