This MOOC introduces students to the use of artificial intelligence for mass spectrometry (MS) data analysis. The course explores the main theoretical approaches and machine learning algorithms applicable to MS data analysis, such as classification, clustering, regression, and dimensionality reduction. Participants will acquire skills to understand, design, and implement intelligent analytical pipelines, with a focus on concrete examples. The MOOC provides practical tools for developing effective computational solutions and critically interpreting results. Each module combines theory and applied case studies.
The course is organised into seven modules that introduce the main machine learning techniques applicable to mass spectrometry data and illustrate their use in various application contexts, including multi-omics and forensics. The modules combine theory, practical exercises and case studies to support active learning and the development of analytical skills in digital environments.
Module 1 - Introduction to mass spectrometry and role of deep learning
Module 2 - Case study: Machine Learning for Multi-Omics Thyroid Disease Classification
Module 3 - Case study: Neural Networks for Structural Alert Detection in Environmental Contaminants
Module 4 - Case study: Deep learning in proteomics: from DIA to de novo sequencing
Module 5 - Case study: AI-based rapid detection of illicit drugs
Module 6 - Case study: Transformers and large language models in metabolomics: the future of automated metabolite annotation
Module 7 - Synthesis: advantages, challenges and future perspective
At the end of the course, students will be able to:
Knowledge and understanding:
- Know the main machine learning models applied to mass spectrometry data analysis.
- Know the omics sciences investigated with mass spectrometry.
- Know the limitations of machine learning models for mass spectrometry.
Apply knowledge and understanding:
- Apply machine learning models in the clinical field.
- Apply machine learning models in the forensic field.
- Apply machine learning models in the environmental field.
Critical thinking
- Analyse an example of the application of machine learning models appropriate to the field of analysis.
- Discuss and evaluate the implications of using artificial intelligence for data analysis in mass spectrometry.
Communication skills
- Communicate the workflow sequence for data analysis and the choice of machine learning model to be applied.
- Discuss the strengths and weaknesses of using AI for data analysis in mass spectrometry.
Learning skills
- Develop autonomy when selecting machine learning models suitable for the analyses being conducted.
Quiz.
Each module contains several lessons, consisting of videos, written texts, infographics, quizzes with automatic assessment, and interactive activities.
None
Federica Dal Bello
For any queries or technical issues relating to the course and the platform, please contact:
edvancedeh@unito.it
Contact details of the MOOC lecturer: