66576 - Systems and In Silico Biology

Learning outcomes

At the end of the course, the student acquires advanced machine learning based approaches (Support Vector Machine, Conditional Random Fields, Hybrid methods) to complement previous expertise. Problems of Systems Biology will be introduced with focusing on network theory and dynamic modeling to approach complexity at the cell level. In particular, the student will be able to: - understand and modeling biological complexity; - modeling time evolution of a biological system; - predicting protein-protein interaction and DNA/RNA protein interaction.

Course contents

MACHINE LEARNING TOOLS FOR BIOINFORMATICS
Neural Networks
Support Vector Machines
Kernel methods
Deep learning methods
Decision trees and Random Forests

Applications to protein structure and function prediction

INTRODUCTION TO SYSTEMS BIOLOGY
Biological Systems
Experimental Techniques
Genomics, Proteomics, Interactomics, Transcriptomics, Metabolomics, Metagenomics, Epigenomics

Basics on Model
Mathematical Methods: Networks
Mathematical Methods: Differential equations

Kinetics of biochemical reactions and simple metabolic pathways

Transcription networks in Prokariotes.
Analysis of simple motifs (self-regulation, Feed-forward loops)

Readings/Bibliography

Slides of the lecture, scientific literature and on-line materials. All materials will be made available on Virtuale

Suggested books for a deeper study are following. They are not necessary to pass the exam.

Bishop C (2006) Pattern recognition and Machine Learning. Springer [ISBN 0-38-731073-8]

Goodfellow I, Bengio Y, Courville A. Deep Learning (2016) MIT Press [ISBN: 9780262035613]

Ingalls BP (2013) Mathematical Modeling in Systems Biology. MIT press [ISBN: 9780262018883]

Aron U. (2006) An Introduction to Systems Biology: Design Principles of Biological Circuits. Chapman & Hall/CRC Mathematical and Computational Biology (Vol. 10) [ISBN-13: 9781584886426]

Teaching methods

Lectures
The frequency requires to have passed the e-learning modules: Moduli 1 e 2 di formazione sulla sicurezza nei luoghi di studio, [https://elearning-sicurezza.unibo.it/].

Assessment methods

The final exam consists of a written test followed by an oral discussion.
The written test consist of a set of 4-6 exercises aiming at assessing the ablity of the student to apply the concepts learned during the course to simple problems. The exercises should be solved in 120 minutes.

During the oral session, the results of the written exam will be discussed and the theoretical knowledge of the student will be assessed.

The topics of the exam are:

- the knowledge of the theory and applications of machine learning tools for Bioinformatics

- the knowledge of the theory of complex networks and their application to the description of biological systems;

- the analysis and integration of omics data

- the knowledge of the basic theory of ordinary differential equations and their application to the description of biological systems.

Teaching tools

Office hours

See the website of Pier Luigi Martelli