Filippo Castiglione

Research Director
Institute for Applied Computing (IAC)
National Research Council of Italy

Areas of Expertise:
Computational Biology
Machine Learning


Filippo Castiglione is Research Director at the Institute for Applied Computing (IAC) of the National Research Council of Italy. He has a degree in Computer Science from the University of Milan (Italy) and a Ph.D. in Scientific Computing of the University of Cologne (Germany).

He has been postdoc / visiting researcher at the IBM T.J. Watson Research Center, the Department of Molecular Biology of Princeton University, the Harvard Medical School in Boston, the Institute for Medical Bio-Mathematics in Tel Aviv and the Institute for Advanced Studies of the University of Amsterdam. He has served as Program Committee member of many international conferences and is Editorial Board Member of few journals in the field of Computer Science and System Biology.

FC has coauthored one book, edited another and coauthored more than 120 peer-reviewed research papers among journals, books and conference proceedings.

He has received funds from the European Commission for coordinating or participating in scientific projects in the area of IC-for-Health.

Since 2015 FC has been Adjunct Professor at the Department of Mathematics and Physics of the University of Roma Tre, teaching Machine Learning and Computational Biology. His research interests range from the study of complex systems in general to the modeling of biological systems with particular interest in the immune system and related pathologies. He is also interested in Machine Learning applied to Medicine and Biology


Biotech data processing
Modern biology research is generally rooted in a wide range of experiments that produce large quantities of information, such as genetic sequences, protein interaction, medical records, and more. This complexity and vastness in data must be adequately interpreted to gain value. Data analytics provides tools to derive useful information from this wealth of very heterogenous and complex data.

This course aims to provide a basic understanding of what type of data we are dealing with and some basic methodologies coming from machine learning and data science that can be used to derive meaningful distilled information from such large amount data.

Broadly speaking the lectures will consist in the following topics: introduction to big data in biomedicine and the concept of systems biology; basic knowledge to understand the souce of biomedical data; text mining and information retrieval; the problem of storage and where to find the data; search tools for big data; network biology and concepts from graph theory; the need for predictive analytics; statistical inference; machine learning basic concepts; techniques for dimensionality reduction, regression and clustering; recommender systems and decision trees; methods to estimate the goodness of a prediction.