20884 - BIO-INFORMATICS
Department of Computing Sciences
Course taught in English
Go to class group/s: 31
Course Director:
FRANCESCA BUFFA
FRANCESCA BUFFA
Suggested background knowledge
For a fruitful and effective learning experience, it is recommended a good knowledge of statistics, machine learning and deep learning. Knowledge of information theory and optimization algorithms would help but the necessary material will be provided during the course.
Mission & Content Summary
MISSION
Bioinformatics, computer science applied to biology, has revolutionized our understanding of life and its complexities. It has enabled us to study biology, such as exploring the human genome, and also to build useful models that empower medics to deliver better treatments. Without powerful computer methods, interpreting data such as DNA sequencing, or tracking the spread or the evolution of disease would be impossible. Computers play a pivotal role in drug development, agricultural advancements, and environmental conservation efforts. Simultaneously, biology has inspired groundbreaking innovations in computer science, from modeling neurons to leveraging evolution for optimization algorithms.
This course aims to provide students with a solid understanding of the core principles and applications of Artificial Intelligence (AI) in the life and health sciences. While AI has been applied to medicine for over 50 years, the current era presents unprecedented challenges and opportunities due to the sheer quantity, complexity, and resolution of biological data.
Students will gain extensive knowledge of how current AI methods address fundamental questions in biology and medicine. Additionally, the course will explore how biological systems, including evolutionary principles, inspire the development of innovative AI algorithms.
By mastering these tools and techniques, students will be equipped to contribute to transformative advancements in science and medicine.
CONTENT SUMMARY
1. Basic concepts in Life Sciences: building blocks and recent fundamental discoveries.
2. Evolution: from modelling evolution to the application of evolution to computer sciences: genetic algorithms, genetic programming and their applications:
a. DNA/genetics/evolution
b. Evolution in computing
3. The new Big Data science: technological developments. Introduction to current biological data and biological databases, with emphasis on large genetics databases and omics databases (i.e., genomics, transcriptomics, epigenetics, proteomics), including very new data such as single-cell sequencing and spatial transcriptomics
a. Introduction to biological databases
b. Genes/DNAseq/mapping
c. Bulk data and single-cell data
d. Current methods and Hands-on bulk RNA-Seq
e. Current methods and Hands-on scRNA-Seq
f. Current methods and Hands-on scATAC-Seq
g. Introduction to spatial transcriptomics
4. Systems biology and perturbation biology, including algorithms for reconstructing Gene Networks, signalling, and simulations: from ordinary differential equations to stochastic simulations and multi-agent modelling
a. Interaction-, logic-, and mechanism modelling
b. Deterministic simulation + hands-on
c. Stochastic simulation + hands-on
d. Reconstructing Gene Networks
e. Multi-agent modelling
5. The application of the latest generative models, to life sciences: from answering fundamental biological questions to generating new biology for understanding human diseases
6. Machine Learning and other AI techniques in Health and Medicine: the use of AI to inform drug development, imaging and pathology, integration of biological and clinical data, and construction of clinical classifiers
Intended Learning Outcomes (ILO)
KNOWLEDGE AND UNDERSTANDING
At the end of the course student will be able to...
- Understand a broad spectrum of basic concepts in modern biology, including evolution theories and applications to computer sciences.
- Understand the algorithms used in systems biology and perturbation biology.
- Know how to analyze a broad range of modern biological and medical data.
- Understand the application of current AI methods to decode and model them, including the latest generative models.
APPLYING KNOWLEDGE AND UNDERSTANDING
At the end of the course student will be able to...
- Reason on a broad spectrum of basic concepts in modern biology, including evolution theories and applications to computer sciences.
- Master the analysis of a broad range of modern biological and medical data.
- Be able to apply current AI methods to decode and model them, including the latest generative models.
Teaching methods
- Lectures
- Guest speaker's talks (in class or in distance)
- Practical Exercises
- Collaborative Works / Assignments
DETAILS
Assessment methods
| Continuous assessment | Partial exams | General exam | |
|---|---|---|---|
|
x | ||
|
x |
ATTENDING STUDENTS
The evaluation for this course will consist of two components:
A) Written Assessment
The written assessment will take place at the end of the course and will account for 50% of the final grade. It will include a mix of open-ended and multiple-choice questions to evaluate students' understanding of key concepts and practical applications.
B) Group Project
Students will work collaboratively on a group project, which will also contribute 50% to the final grade. The assessment will be based on three components:
- A written report detailing the project findings,
- The quality and functionality of the code developed, and
- A presentation delivered to the class.
The individual contribution of each group member will be evaluated separately to ensure fair and accurate grading.
NOT ATTENDING STUDENTS
The evaluation for this course will consist of two components:
A) Written Assessment
The written assessment will take place at the end of the course and will account for 50% of the final grade. It will include a mix of open-ended and multiple-choice questions to evaluate students' understanding of key concepts and practical applications.
B) Group Project
Students will work collaboratively on a group project, which will also contribute 50% to the final grade. The assessment will be based on three components:
- A written report detailing the project findings,
- The quality and functionality of the code developed, and
- A presentation delivered to the class (for authorized non-attending students this could be organized remotely)
The individual contribution of each group member will be evaluated separately to ensure fair and accurate grading.
Teaching materials
ATTENDING STUDENTS
NOT ATTENDING STUDENTS
All material will be distributed during the course, both during the (remote) lessons and on-line
Last change 09/01/2025 10:36