Skip to main content

Table 5 The performance of classification models for the manually curated TMC test set

From: Profiling and analysis of chemical compounds using pointwise mutual information

Model AUC Acc SN SP
SYBA 0.903 0.871 0.902 0.840
SAScore 0.865 0.859 0.799 0.919
ZRFT 0.871 0.831 0.827 0.836
RF 0.875 0.842 0.855 0.828
  1. Quality measures AUC, Acc, SN and SP are reported as their average values over 30 TMC instances. Results for SYBA, SAScore and RF classification are taken from SYBA publication [37]
Back to article page

Journal of Cheminformatics

ISSN: 1758-2946

Contact us