Machine Learning for the Life Sciences

Period of duration of course
‌‌
Course info
Number of course hours
20
Number of hours of lecturers of reference
20
Number of hours of supplementary teaching
0
CFU 3
‌‌

Type of exam

Oral exam

Lecturer

View lecturer details

Prerequisites

Students with no background in python are recommended to attend the course "Scientific Programming I: Data Processing and Software Prototyping" by Prof. Bloino

Programme

Application of Machine Learning algorithms in Bioinformatics and Life Sciences  (Dr. Raimondi)

1)      protein structure/function prediction using machine learning

2)      protein structure prediction using deep learning and co-evolution

3)      protein language models

4)      application of graph neural network for the prediction of biomolecular properties and interaction networks

5)      deep learning applications to genomics :DNA motif discovery

6)      deep learning applications to genomics: variant intepretation

7)      deep learning applications to genomics: single cell RNAseq analysis and interpretation

8)      practicals: a) functional predictions with protein language models;b) deep learning for genomics (Transcription factor binding prediction); c) multiomics data integration (python)

Educational aims

Aim of the course is to provide students with basic knowledge of both theoretical foundations and practical aspects of machine learning, with a particular focus on applications to bioinformatics and biology.

Bibliographical references

Introduction to Machine Learning, Lecture notes. MIT, 2019. https://phillipi.github.io/6.882/2020/notes/6.036_notes.pdf

Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning. MIT Press, 2016. https://www.deeplearningbook.org/

Bharath Ramsundar, Peter Eastman, Patrick Walters, Vijay Pande, Deep Learning for the Life Sciences, 2019, https://www.oreilly.com/library/view/deep-learning-for/9781492039822/

Ad hoc selected scientific papers