Data Science: Machine Learning and its Application in Cancer Genomics

Development and application of machine learning methods in cancer genomics allows to develop new strategies in cancer risk evaluation, early intervention and treatment stratification, diagnosis/prognosis biomarker identification, and medical image processing. Cancer immunology and immunotherapy, prediction and cancer immunotherapy biomarker discovery are also included.The program of this intensive intensive school is structured into three main parts.
The first aims at teaching statistical aspects of machine learning since it is important to understand how machine learning can be seen as a perspective of statistics, having its own set of strengths, limitations and goals. In particular, thinking in terms of machine learning methods provides a fresh way of performing predictive modeling, data reduction and causal inference. The second is focused on Phyton, an interpreted high-level general-purpose programming language that, over the years, have grown massively in popularity among data scientist, to the point of becoming one of the default choices for anyone approaching the field. Python is known for being easy to learn and read, flexible, powerful and for having a huge and active community. It also possesses some of the best libraries around for data manipulation, Machine Learning and data visualization. The third part focuses on statistical inference for genomic studies and practical applications of machine learning and Python in cancer genomics. The course lasts 9 half time days ( 14.00 am – 17.00 pm CEST ) and it is structured in lectures and practical sessions.
The course will be given ONLINE in vivo and simultaneously RECORDED.
The recordings will be made available to the registered students.