Laura CANTINI

This is a crucial moment for the study and clinical management of complex diseases. Single-cell sequencing introduced a paradigm shift in healthcare, from precision medicine to cell-based interceptive medicine. Indeed single-cell multi-modal data ( i.e. large-scale quantitative measurements such as transcriptome, epigenome, spatial positioning at the resolution of single cells) provide us the potential (i) to track the molecular trajectories performed by human cells during disease onset or therapy resistance; (ii) to provide a mechanistic understanding of the complex networks that drive the different phases of the transformation and (iii) to delineate the contribution of neighboring cells in such transformation. However, to make these biological objectives a reality we need to develop powerful methods able to co-analyze multi-modal single-cell data and extract actionable biological knowledge.

My research activity lies at the interphase of machine learning and genomics. I design machine learning methods able to co-analyze and translate the enormous amount of available single-cell multi-modal data into actionable biological knowledge. I then apply the developed methods in collaboration with wet-lab biologists to derive concrete biological hypothesis and ultimately contribute to improve the understanding and clinical management of complex diseases.