Back

Utility of cellular imaging modality in subcellular spatial transcriptomic profiling of tumor tissues

Song, X.; Yu, X.; Moran-Segura, C.; Grass, G. D.; Li, R.; Wang, X.

2024-07-26 bioinformatics
10.1101/2024.07.25.605221 bioRxiv
Show abstract

Spatial transcriptomics (ST) technologies, like GeoMx Digital Spatial Profiler, are increasingly utilized to reveal the role of diverse tumor microenvironment components, particularly in relation to cancer progression, treatment response, and therapeutic resistance. However, in many ST studies, the spatial information obtained from immunofluorescence imaging is primarily used for identifying regions of interest, rather than as an integral part of downstream transcriptomic data interpretation. We developed ROICellTrack, a deep learning-based framework, to better integrate cellular imaging with spatial transcriptomic profiling. By examining 56 ROIs from urothelial carcinoma of the bladder (UCB) and upper tract urothelial carcinoma (UTUC), ROICellTrack accurately identified cancer-immune mixtures and associated cellular morphological features. This approach also revealed different sets of spatial clustering patterns and receptor-ligand interactions. Our findings underscore the importance of combining imaging and transcriptomics for comprehensive spatial omics analysis, offering potential new insights into within-sample heterogeneity and implications for targeted therapies and personalized medicine.

Matching journals

The top 11 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.