Skip to main content
. 2022 Jun 7;14:32. doi: 10.1186/s13321-022-00611-w

Fig. 10.

Fig. 10

Performance of imputation models according to test compound label availability. AD show the MCC scores obtained in 20 independent runs (same hyperparameters, different random seeds) of the models on the different bins of the test set for TA100, TA100_S9, TA98 and TA98_S9. The number (n = x) written next to each bin indicates the number of compounds placed in the bin. E shows the median MCC scores and interquartile ranges across the different runs after computing the mean across the assays for a single run.