A General Non-Linear Consensus Scoring Function for High-Throughput
Bernard Chétrit**, Françoise
Guerlesquin** and Xavier Morelli**
of the recent work published in the field of Docking and Scoring
Protein/Ligand complexes have focused in ranking true positives
resulting from a Virtual Library Screening (VLS) through
the use of a specified or consensus linear scoring function.
GFscore is a methodology to accelerate the process
of High Throughput Screening (HTS). We have extended the principle
of consensus scoring in a Non-Linear Neural
Network manner. This original global scoring function is
a combination of the five scoring functions found in the Cscore
package from Tripos Inc.
GFscore learned to discriminate true negatives from false
negatives in a dataset of diverse chemical compounds
and eliminates up to 75% of molecules with a confidence
rate of 90%. The final result is a Hit Enrichment
in the list of molecules to investigate during a research campaign
for biological active compounds. The resulting 25% of molecules
to be tested by in vitro screening make of GFscore a powerful
tool for the biologist, saving his time and money.
Betzi, S.**, Suhre, K.***, Chetrit, B.**, Guerlesquin, F.**, Morelli, X**.
GFscore: A General Non-Linear Consensus Scoring Function for High-Throughput Docking
Journal of Chemical Information and Modeling. 2006 Jul-Aug;46(4):1704-12
|This work was
partially supported by :
French National AIDS Research Agency (ANRS) AC14.3
Génopole and the French National Genomic Network (RNG).
KS thanks Prof. J-M Claverie (head of the IGS) for laboratory
space and support.
et Ingénierie des Protéines (BIP), CNRS UPR9036
Institute for Structural Biology and Microbiology (IBSM),
31 Chemin Joseph Aiguier 13402 Marseille Cedex 20, France