VOPROSY MEDITSINSKOI KHIMII (ISSN 0042-8809)

Prediction of binding affinities for protein-ligand complexes by using non-linear models

   
Krepets V.V.1, Belkina N. V.1, Skvortsov V.S.1, Ivanov A. S.1

1. Orekhovich Institute of biomedical chemistry RAMS
PubMed Id: 11204627
Year: 2000  Volume: 46  Issue: 5  Pages: 462-473
A network model for prediction of the free energy changes in protein-ligand complexes has been developed. The 150 complexes of different nature were used as a training set. The computational physics-chemical parameters of these complexes were used as independent variables. Both classical models of multiple linear regression and several network models with one hidden layer were created and the best was chosen. Significant improvement was shown for network model prediction quality in comparison with classical model of multiple linear regression (R2 on training - 0,81 and 0,54; R2 on «leave-one-out» procedure - 0,74 and 0,52 respectively).
Download PDF:
Keywords: protein-Iigand complex, dissociation constant, neural network
Citation:

Krepets, V. V., Belkina, N. , V., Skvortsov, V. S., Ivanov, A. , S. (2000). Prediction of binding affinities for protein-ligand complexes by using non-linear models. Voprosy meditsinskoi khimii, 46(5), 462-473.
References  
 2002 (vol 48)
 2001 (vol 47)
 2000 (vol 46)
 1999 (vol 45)
 1998 (vol 44)
 1997 (vol 43)
 1996 (vol 42)
 1995 (vol 41)
 1994 (vol 40)
 1993 (vol 39)
 1992 (vol 38)
 1991 (vol 37)
 1990 (vol 36)
 1989 (vol 35)
 1988 (vol 34)
 1987 (vol 33)
 1986 (vol 32)
 1985 (vol 31)