Project Leads: This email address is being protected from spambots. You need JavaScript enabled to view it. , This email address is being protected from spambots. You need JavaScript enabled to view it.
Spatial omics technologies now generate data at a scale and diversity that far outstrips our ability to evaluate the methods analysing them. OpenProblems.Bio x SpaceHack 5.0 brings together two established community efforts to address this: the OpenProblems benchmarking platform and the SpaceHack spatial transcriptomics hackathon series.
Over five days we will port existing spatial benchmarks onto the OpenProblems platform and build new ones, working across parallel subprojects that include:
1. multimodal niche detection
2. spatial trajectory inference
3. spatial cell-cell communication,
4. spatial and single-cell integration
5. spatial proteomics preprocessing
6. foundation model evaluation
7. cell segmentation evaluation
8. spatial segmentation simulation
9. porting existing benchmark to OpenProblems
10. develop loaders for the BioImage Archive and other FAIR spatial data resources (e.g. LaminLabs SpatialDB), making community datasets directly usable for continuous, reproducible benchmarking
We welcome method developers, tool maintainers, data infrastructure engineers and tissue biologists. Contributions range from implementing a metric or a dataset loader through to defining what a task should measure in the first place. All outputs are open source and land in a platform that keeps evaluating methods long after the hackathon ends.