Abstract

ClustSIGNAL is cell-type spatial clustering method for high-resolution spatial transcriptomics data. It uses both the gene expression and spatial locations of cells to group them into clusters. ClustSIGNAL aims to: (i) overcome data sparsity using an adaptive smoothing approach that uses cell-specific weights based on the heterogeneity level (entropy) of a cell’s neighbourhood and (ii) embed spatial context information into the gene expression generating a transformed, adaptively smoothed expression matrix that is used for clustering. In this workshop, we will discuss how ClustSIGNAL works as a spatial clustering method, and how it can be run on R. We will also cover various parameters for ClustSIGNAL, assess cluster relevance through accuracy metrics and marker genes, and explore entropy and neighbourhood data generated by ClustSIGNAL.

Organiser(s)

• Dr Pratibha Panwar, School of Mathematics and Statistics, University of Sydney (contact person)
• Dr Shila Ghazanfar, School of Mathematics and Statistics, University of Sydney

Schedule

• Date: Thursday, 27 November 2025

• Time: 3:30 PM - 5:00 PM (AEDT)

Registration Details