Figure 1
Performance of all tools on eight projections. The top and bottom names on the x axis represent the reference and test data sets, respectively. The pairs of data sets labeled with ‘*’ mean that test data sets contain novel cell types not included in the reference data set. (A) Accuracies of all tools across eight tests. (B) AUC of macro ROC curves of all tools except scmapc2c, scmapc2clus, CellFishing and AltAnalyze on eight pairs of data sets. These four tools do not output a probability or score value for each class and cannot be evaluated through ROC curves.

Performance of all tools on eight projections. The top and bottom names on the x axis represent the reference and test data sets, respectively. The pairs of data sets labeled with ‘*’ mean that test data sets contain novel cell types not included in the reference data set. (A) Accuracies of all tools across eight tests. (B) AUC of macro ROC curves of all tools except scmapc2c, scmapc2clus, CellFishing and AltAnalyze on eight pairs of data sets. These four tools do not output a probability or score value for each class and cannot be evaluated through ROC curves.

Close
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close

This PDF is available to Subscribers Only

View Article Abstract & Purchase Options

For full access to this pdf, sign in to an existing account, or purchase an annual subscription.

Close