Bioinformatics
A.Y. 2023/2024
Learning objectives
- Provide the student with the fundamental knowledge for the analysis of complex biological and medical data with Machine Learning methods.
- Introduce the student to the state-of-the-art computational methodologies to extract biological and medical knowledge from even massive collections of data or observations, even in presence of uncertain information, and to create predictive models for fundamental bio-medical applications.
- Provide the fundamental methodological tools to undertake scientific research according to international standards in the area of Bioinformatics and Computational Biology.
- Introduce the student to the state-of-the-art computational methodologies to extract biological and medical knowledge from even massive collections of data or observations, even in presence of uncertain information, and to create predictive models for fundamental bio-medical applications.
- Provide the fundamental methodological tools to undertake scientific research according to international standards in the area of Bioinformatics and Computational Biology.
Expected learning outcomes
- Ability of applying the main Machine Learning methodologies for the analysis of bio-molecular data aimed at both knowledge extraction and the construction of predictive models in Molecular Biology and Personalized Medicine.
- Understanding of issues related to large-scale biological and medical data processing.
- Ability to apply and adapt Machine Learning models developed in different application areas in the context of Bioinformatics and Computational Biology
- Ability to think critically and to question design and implementation choices.
These abilities will be evaluated through the combination of a software project and an oral discussion on the topics of the course.
- Understanding of issues related to large-scale biological and medical data processing.
- Ability to apply and adapt Machine Learning models developed in different application areas in the context of Bioinformatics and Computational Biology
- Ability to think critically and to question design and implementation choices.
These abilities will be evaluated through the combination of a software project and an oral discussion on the topics of the course.
Lesson period: First semester
Assessment methods: Esame
Assessment result: voto verbalizzato in trentesimi
Single course
This course cannot be attended as a single course. Please check our list of single courses to find the ones available for enrolment.
Course syllabus and organization
Single session
Responsible
Lesson period
First semester
Course syllabus
The course provides methodological tools to deal with relevant problems in Molecular Biology and Medicine, using Machine Learning algorithms and techniques.
The course is divided into two main parts: a) Introduction to Machine Learning methods: b) Machine Learning methods for Computational Biology.
In the first part (Introduction to Machine Learning methods) the following topics are introduced:
a) the fundamental concepts of supervised, semi-supervised and unsupervised learning with examples of Machine Learning methods for each type of learning;
b) the experimental techniques for estimating the generalization error of the Machine Learning systems;
In the second part (Machine Learning Methods for Computational Biology) a general picture of the applications of Machine Learning methods in Computational Biology is provided, and in particular the following problems are treated, with a particular focus on the methodologies used:
a) The problem of supervised prediction of protein function;
b) Computational Biology and Network Medicine problems based on graph analysis through Artificial Intelligence methods;
c) Supervised and unsupervised learning problems for Medical Genomics.
For each considered Computational Biology problem, the biological knowledge necessary to model each bio-medical problem as a Machine Learning problem is provided.
The course is divided into two main parts: a) Introduction to Machine Learning methods: b) Machine Learning methods for Computational Biology.
In the first part (Introduction to Machine Learning methods) the following topics are introduced:
a) the fundamental concepts of supervised, semi-supervised and unsupervised learning with examples of Machine Learning methods for each type of learning;
b) the experimental techniques for estimating the generalization error of the Machine Learning systems;
In the second part (Machine Learning Methods for Computational Biology) a general picture of the applications of Machine Learning methods in Computational Biology is provided, and in particular the following problems are treated, with a particular focus on the methodologies used:
a) The problem of supervised prediction of protein function;
b) Computational Biology and Network Medicine problems based on graph analysis through Artificial Intelligence methods;
c) Supervised and unsupervised learning problems for Medical Genomics.
For each considered Computational Biology problem, the biological knowledge necessary to model each bio-medical problem as a Machine Learning problem is provided.
Prerequisites for admission
Notions of mathematics and statistics, learned in the three-year courses of Computer Science (or in equivalent courses in Continuous Mathematics and Discrete Mathematics for students coming from other three-year degrees).
Recommended courses (but not compulsory): Statistical Methods for Machine Learning and Artificial Intelligence (degree course in Computer Science)
Recommended courses (but not compulsory): Statistical Methods for Machine Learning and Artificial Intelligence (degree course in Computer Science)
Teaching methods
The lessons are held frontally or in the form of a discussion with the students regardingpreviously indicated teaching material and scientific articles. Group work is also planned for the development of software projects relating to course topics.
Teaching Resources
Bibliography and teaching material related to the course (slides, scientific articles and books) are available from the Ariel course web site:
https://gvalentinib.ariel.ctu.unimi.it/
https://gvalentinib.ariel.ctu.unimi.it/
Assessment methods and Criteria
The exam is divided into two parts:
I. Development of a software project or oral discussion of scientific literature, related to a topic of the course. The software project requires, in addition to writing the code for the analysis of genomic data, the preparation of a report describing the problem faced, the Machine Learning methods used, the experimental set-up, the results obtained and a critical discussion on the results, outlining the advantages and limitations of the proposed approach. The oral discussion of the scientific literature aims to verify that the student has understood the scientific content and that he is able to highlight the problematic and critical aspects of the work studied.
II. Oral discussion on the topics covered during the course.
At the end of the oral test, the overall evaluation, expressed in thirtieths, takes into account the following factors: degree of knowledge of the topics, ability to apply the knowledge acquired during the course to the resolution of concrete problems, ability of critical reasoning, clarity of presentation and language appropriateness .
I. Development of a software project or oral discussion of scientific literature, related to a topic of the course. The software project requires, in addition to writing the code for the analysis of genomic data, the preparation of a report describing the problem faced, the Machine Learning methods used, the experimental set-up, the results obtained and a critical discussion on the results, outlining the advantages and limitations of the proposed approach. The oral discussion of the scientific literature aims to verify that the student has understood the scientific content and that he is able to highlight the problematic and critical aspects of the work studied.
II. Oral discussion on the topics covered during the course.
At the end of the oral test, the overall evaluation, expressed in thirtieths, takes into account the following factors: degree of knowledge of the topics, ability to apply the knowledge acquired during the course to the resolution of concrete problems, ability of critical reasoning, clarity of presentation and language appropriateness .
Educational website(s)
Professor(s)
Reception:
Appointments by e-mail
Dept. of Computer Science, via Celoria 18, room 3011