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

Table 6 Prediction performance of 25 scoring functions evaluated on PDBbind v2007 core set (N = 195) in terms of Pearson correlation coefficient Rp, Spearman correlation coefficient Rs and standard deviation SD in linear correlation on the test set

Scoring function	Rp	Rs	SD
RF::CyscoreVinaElem	0.803	0.798	1.42
RF-Score::Elem-v2	0.803	0.797	1.54
SFCscoreRF	0.779	0.788	1.56
RF-Score	0.774	0.762	1.59
ID-Score	0.753	0.779	1.63
RF::CyscoreVina	0.749	0.759	1.58
SVR-Score	0.726	0.739	1.70
RF::Cyscore	0.687	0.694	1.73
Cyscore	0.660	0.687	1.79
X-Score::HMScore	0.644	0.705	1.83
DrugScoreCSD	0.569	0.627	1.96
SYBYL::ChemScore	0.555	0.585	1.98
DS::PLP1	0.545	0.588	2.00
GOLD::ASP	0.534	0.577	2.02
SYBYL::G-Score	0.492	0.536	2.08
DS::LUDI3	0.487	0.478	2.09
DS::LigScore2	0.464	0.507	2.12
GlideScore-XP	0.457	0.435	2.14
DS::PMF	0.445	0.448	2.14
GOLD::ChemScore	0.441	0.452	2.15
SYBYL::D-Score	0.392	0.447	2.19
DS::Jain	0.316	0.346	2.24
GOLD::GoldScore	0.295	0.322	2.29
SYBYL::PMF-Score	0.268	0.273	2.29
SYBYL::F-Score	0.216	0.243	2.35

The scoring functions are sorted in the descending order of Rp. RF::CyscoreVinaElem and Cyscore rank 1st and 9th respectively in terms of Rp. The statistics for the other 21 scoring functions are collected from [8, 22, 31].

ISSN: 1471-2105