PSnpBind-ML: predicting the effect of binding site mutations on protein-ligand binding affinity

Table 3 Nested cross-validation results of four machine learning models on six data splits to predict protein-ligand binding affinity (Model 1)

Dataset	Random forest	Decision tree	Lasso regression	Ridge regression
BASR	0.85	0.75	0.62	0.76
BSS	0.87	0.77	0.65	0.77
PS	0.86	0.74	0.64	0.76
LS	0.87	0.75	0.62	0.76
LWSR	0.85	0.72	0.62	0.76
LVSR	0.85	0.71	0.62	0.76

The models are: Random Forest, Decision Tree, Lasso Regression and Ridge Regression. The models performance metric reported is correlation coefficient R²
Data splits acronyms: BASR binding affinity-stratified random split, PS protein similarity-based split, BSS binding site similarity-based split, LS ligand similarity-based split, LWSR ligand weight-stratified random split, and LVSR ligand volume-stratified random split

ISSN: 1758-2946