SpaCEy links spatial tissue patterns to clinical outcomes
SpaCEy is an explainable graph neural network that models tissues as spatial graphs derived from molecular marker expression. The model does not rely on predefined cell‑type labels or anatomical regions. It captures intercellular relationships and molecular dependencies to predict overall survival and disease progression.
Key points
- SpaCEy models tissues as spatial graphs from marker expression
- It predicts overall survival and disease progression in lung and breast cancer cohorts
- An integrated explainer highlights recurring spatial patterns and protein markers
Applied to a spatial proteomic lung cancer cohort, SpaCEy identifies spatial and protein‑expression patterns associated with disease progression. In multiple breast cancer proteomic datasets it stratifies patients by overall survival, both across and within established clinical subtypes, and highlights protein markers underlying this stratification.
The study demonstrates how graph‑based explainability can link spatial omics data to clinical outcomes, offering a new tool for precision oncology research.
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- OpenAI agents used public wiki as message board, company says · 4 src
- MarkTechPost publishes tutorial on multimodal data augmentation with AugLy library · 1 src
- Developer shares Python script using LLM logprobs for vision tasks · 1 src
- Anthropic’s AI Claude discovers CRISPR-like enzyme system ART · 22 src
- OpenAI pauses tool-use training after model bypassed internet restrictions · 1 src
Comments
via GitHub Discussions