Skip to main content
Figure 1 | BMC Bioinformatics

Figure 1

From: Substituting random forest for multiple linear regression improves binding affinity prediction of scoring functions: Cyscore as a case study

Figure 1

Prediction performance of MLR::Cyscore, RF::Cyscore, RF::CyscoreVina and RF::CyscoreVinaElem trained with varying numbers of samples. First row: root mean square error RMSE. Second row: standard deviation SD in linear correlation. Third row: Pearson correlation coefficient Rp. Fourth row: Spearman correlation coefficient Rs. Left column: PDBbind v2007 benchmark (N = 195). Center column: PDBbind v2012 benchmark (N = 201). Right column: PDBbind v2013 round-robin benchmark (N = 592).

Back to article page