- ExperimentHub: current state of art, notable examples
- Are any innovations needed?
- Seurat compatibility
- Internal interoperability assurances
- Different concepts of representing analysis progression - successively stick results into the 'same' object vs have separate objects for primary and derived results
- Create an S4 dimensionality reduction object to store PCA results.
- rhdf5 can be used with socket-level parallelism, how about forking?
- HDF5 local and remote
- Spark and other distributed data architectures
- Parquet, Arrow
- accommodating the HCA schema/terminology beyond files to features, cells, donors
- Does SingleCellExperiment need additional infrastructure to increase precision of provenance
- Integrating elasticsearch functionality for R users
- CWL/WDL