The abstract is read at the publisher; the summary is JClub's.
SpaceMACE, an extension of MACE for spatial transcriptomics, retains MACE’s high precision while improving the spatial coherence of tumour-cell annotations across multiple platforms and cancers.
- Why it matters: Tumour versus non-tumour discrimination is critical for interpreting spatial transcriptomics and finding spatially resolved therapeutic targets, yet existing methods largely ignore spatial cell organization.
- What they did: SpaceMACE combines reference-based cell-type classification with copy-number-variation-based tumour classification, then refines consensus labels using spatial proximity and gene-expression similarity across Stereo-seq, Visium HD, CosMx, and Xenium.
- The result: Across colorectal, hepatocellular, and ovarian cancer datasets, SpaceMACE improves spatial coherence without sacrificing precision, enabling scalable, platform-independent tumour-cell annotation and spatial study of tumour-specific molecular targets.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.