eHiTS_Score, the next stage in scoring function evolution: a new statistically derived empirical scoring function
Zsolt Zsoldos1, Aniko Simon1,
Darryl Reid1, A. Peter Johnson2
(1) SimBioSys
Inc., 135 Queen's Plate Drive, Unit 520, Toronto, ON, M9W 6V1 Canada
(2) Institute for Computer Applications in Molecular Sciences (ICAMS),
School of Chemistry, University of Leeds, Leeds, UK LS2 9JT
Abstract:
eHiTS_Score is the next stage in scoring function evolution. By combining the energy prediction of empirical scoring functions with interaction information obtainable with statistical methods, eHiTS_Score is a unique approach to scoring. The new method takes advantage of the temperature factors in PDB files during the statistics collection phase of the scoring function generation to better capture the interaction geometries between ligands and receptors. Parameters of an "empirical" function are then fitted to the data collected to represent the statistical distribution of the interactions with continuous, easy/fast to evaluate formula. The weights of each interaction term are derived by training using known binding affinity information to generate the full eHiTS_Score scoring function. Family based training futher improves the accuracy of the scoring function. eHiTS uses an automated receptor clustering algorithm to identify receptor families and tunes the scoring function to suit families. Results will be analysed and discussed in details.
For more information, see the company's web site: http://www.simbiosys.com/
|
