K-CLIER: A clinical application of single-cell RNA sequencing data

In collaboration with Dr. Med. Pietro CippĂ , Dr. Anna Rinaldi and Lorenzo Ruinelli (EOC)

Main image

Single-cell transcriptomics is an extremely rich source of data, which has been of primary importance in refining our understanding of the cellular composition of tissues and organs. Nevertheless, unlike bulk transcriptomics, the use of such technology in clinical routine is not viable, due to major challenges related to tissue processing and data analysis.

With K-CLIER, using state-of-the-art transfer learning methods, we learned a transformation able to produce a low-dimensional representation of bulk gene expression that can be easily interpreted from a single-cell point of view.

We applied the transformation to several different datasets containing patients affected by renal pathologies. Using the transformed datasets, we developed machine learning models to predict clinical outcome and response to therapy in oncological patients, and we studied rejection in transplanted patients.