SpaRx: Elucidate Single-cell Spatial Heterogeneity of Drug Responses for Personalized Treatment
Overview
Affiliations
Spatial cellular authors heterogeneity contributes to differential drug responses in a tumor lesion and potential therapeutic resistance. Recent emerging spatial technologies such as CosMx, MERSCOPE and Xenium delineate the spatial gene expression patterns at the single cell resolution. This provides unprecedented opportunities to identify spatially localized cellular resistance and to optimize the treatment for individual patients. In this work, we present a graph-based domain adaptation model, SpaRx, to reveal the heterogeneity of spatial cellular response to drugs. SpaRx transfers the knowledge from pharmacogenomics profiles to single-cell spatial transcriptomics data, through hybrid learning with dynamic adversarial adaption. Comprehensive benchmarking demonstrates the superior and robust performance of SpaRx at different dropout rates, noise levels and transcriptomics coverage. Further application of SpaRx to the state-of-the-art single-cell spatial transcriptomics data reveals that tumor cells in different locations of a tumor lesion present heterogenous sensitivity or resistance to drugs. Moreover, resistant tumor cells interact with themselves or the surrounding constituents to form an ecosystem for drug resistance. Collectively, SpaRx characterizes the spatial therapeutic variability, unveils the molecular mechanisms underpinning drug resistance and identifies personalized drug targets and effective drug combinations.
The Impact of Klotho in Cancer: From Development and Progression to Therapeutic Potential.
Ortega M, Boaru D, De Leon-Oliva D, De Castro-Martinez P, Minaya-Bravo A, Casanova-Martin C Genes (Basel). 2025; 16(2).
PMID: 40004457 PMC: 11854833. DOI: 10.3390/genes16020128.
Eastburn D, White K, Jayne N, Camiolo S, Montis G, Ha S Sci Rep. 2024; 14(1):31285.
PMID: 39732835 PMC: 11682069. DOI: 10.1038/s41598-024-82736-6.
Single cell spatial profiling of FFPE splenic tissue from a humanized mouse model of HIV infection.
Wu G, Keller S, Sardo L, Magliaro B, Zuck P, Balibar C Biomark Res. 2024; 12(1):116.
PMID: 39380117 PMC: 11462831. DOI: 10.1186/s40364-024-00658-x.
AntiFormer: graph enhanced large language model for binding affinity prediction.
Wang Q, Feng Y, Wang Y, Li B, Wen J, Zhou X Brief Bioinform. 2024; 25(5).
PMID: 39162312 PMC: 11333967. DOI: 10.1093/bib/bbae403.
Advances in spatial transcriptomics and its applications in cancer research.
Jin Y, Zuo Y, Li G, Liu W, Pan Y, Fan T Mol Cancer. 2024; 23(1):129.
PMID: 38902727 PMC: 11188176. DOI: 10.1186/s12943-024-02040-9.