Data Science Center #DSC
DSC will develop a scientific framework to efficiently extract information from large sets of heterogeneous data (both structured and unstructured, possibly noisy), with the aim of generating structured knowledge. Correlation patterns hidden deep in datasets are the key to transforming data into intelligence so it can be used to make predictions about the system in question.
A virtual landscape of the system is thus generated, which serves as an efficient toolkit for decision makers and policy makers seeking to intervene. Within the HT project, this strategy and methodology will seek to address the profound questions posed by Precision Medicine.
The Data Science Center will follow five main research lines:
- Basic Issues in Data Science #RL1
- Data-driven Genomics #RL2
- Data-driven Neuroscience #RL3
- Digital Epidemiology #RL4
- Ethical Issues in Data Science #RL5
The research lines RL2 to RL4 closely connect DSC to all other HT centers in a mutual exchange of data and information. In particular, DSC will work closely with OGC, NGC, and AFNGC to analyze genomic and patient data. DSC will rely on CLSC for all aspects connected to algorithm implementation, software optimization, and high-performance computing, and it will rely on CADS for analyzing and interpreting social impact data. RL5 is transversal with respect to all centers.
The DSC will be headquarters within HT, with several laboratories inside and outside. DSC will work closely with all HT’s centers. Collaborative agreements will involve the ISI Foundation, the University of Milan, the University of Milan-Bicocca and the Politecnico of Milan.