Labelling a new blood single-cell study: annotation methods and thresholds
Labelling cells in a new single-cell study often means training a method on cells that already carry labels. A recorded benchmark, not peer reviewed, trained six methods on one reference, ran two released models, and tested them on four blood studies kept out of training (32 donors). The benchmark could not establish a clear difference among four learned methods in agreement with author labels. At the threshold chosen on other studies to label 90% of cells, no method labelled 90% of the pooled test cells.
