Spatial single-cell biology is the next frontier in biomedical sciences. Over the last couple of years, academic researchers have pushed the boundaries of highly-multiplexed spatial technologies to finally reach true single-cell resolution. We can now unravel the cellular architecture of tissues, and precisely localise each individual cell, determine its cellular neighbourhood and profile its activation state. However, if applied on tissue samples from large patient cohorts and on large pre-clinical animal studies, this approach generates enormous amounts of data that cannot realistically be analysed manually. For the spatial revolution to reach the industry, we therefore require deep-learning-assisted computational pipelines to automate the analysis of such large-scale data. In this project, we combine the liver biology expertise from the Guilliams lab with the machine learning expertise from the Saeys lab to build such an Automated Spatial Analysis Pipeline (ASAP). The aim of ASAP is to (i) automatically model tissue architecture, (ii) assess spatial distributions of cells of interest with respect to the tissue architecture and (iii) map transcriptomic information onto these spatial distributions at single-cell resolution. Finally, we will provide a proof-of-concept study in which we will develop an ASAP-approach automatically analyse spatial patterns during liver regeneration.