Closed jimmymathews closed 1 year ago
We should also have a default response that responds like "This study's specimens are too small to train a cg-gnn instance on." and "This study lacks strata to train a cg-gnn instance on." depending on which study we're looking at. This could be handled solely at the GUI level or, preferably, in the SPT API.
Now that cggnn importance scores can be made available as
quantitative_feature_value
records, as discussed previously we should make a new API endpoint inapiserver/app/main.py
that returns, for each specimen, the fraction of important cells expressing a given cell phenotype.The call signature could be: