- Docente: Pier Luigi Martelli
- Credits: 3
- SSD: BIO/10
- Language: English
- Teaching Mode: Traditional lectures
- Campus: Bologna
- Corso: Second cycle degree programme (LM) in Bioinformatics (cod. 8020)
Learning outcomes
"Course aims: The course intends to investigate the use of tool out of machine learning theory for solving problems related to the prediction of structural and functional features of biological sequences. At the end of the course will be able to: - discuss the theoretical basics of machine learning tools (Neural Networks, Hidden Markov Models, Support Vector Machines) - describe and apply the basic algorithms for training machine learning tools and for making prediction - understand differences among the different methods and to discuss their suitability for solving real world problems - use available predictors - design a prototype of predictor for solving real world application related to the prediction of structural and functional features of proteins starting from their amino acid sequence "
Course contents
Statistical models for significance assessment: z-test, t-test,
ANOVA, chi-square-test
Methods for qualitative data analysis: Principal component
analysis, Correspondence analysis
Clustering methods
Support Vector Machines
Kernel methods
Readings/Bibliography
Durbin R, Eddy S, Krogh A, Mitchison G (1998) Biological Sequence
Analysis:
Probabilistic Models of Proteins and Nucleic Acids. Cambridge
University Press [ISBN 0-521-62971-3]
Bishop C (2006) Pattern recognition and Machine Learning. Srpinger
[ISBN 0-38-731073-8]
Teaching methods
Lectures
Assessment methods
Written and oral exams
Teaching tools
Office hours
See the website of Pier Luigi Martelli