Artificial intelligence for genomics
The never-ending quest about the “hidden heritability” in Human phenotypes highlights the limitations of existing methods to discover all genomics determinants of complex traits. We use the power of deep learning in representing non-linear relationships, to help uncover genomics patterns underlying the biological complexity. Additionally, we invest in explainable artificial intelligence, to boost the discovery potential of deep learning and provide new insights into the molecular mechanisms underlying Human diseases.
Inflammation as key predictor
Inflammation is one of the most basic as well as pervasive biological mechanisms, and plays a key role in a wide range of physiological phenomena, including behaviour, and pathological conditions, from cancer to neurodegeneration and psychiatric disorders. A progressive chronic inflammatory status characterises human ageing, and can be targeted with pharmacological, nutritional and life-style changes. It is therefore an actionable key indicator of the health-disease transition. We aim at combining our work in computational genomics with deep learning methods trained on inflammatory parameters, to model and predict the evolution of different phenotypes.
Open Science and Responsible Research
Our core values: transparency and reproducibility of methods, accessibility of code (open source) and results (open data), responsible research (RRI). For this reason, all our code will always be available on Github; our methods are executed through Nextflow to ensure reproducibility and portability of our pipelines.
We participate in the nf-core community, because we believe in the value of collaboration and community standards.
We challenge ourselves by contributing to responsible research and innovation initiatives, because our work should ultimately benefit and therefore respond to societal needs.