GFscore

A general nonlinear consensus scoring function for high-throughput docking

Stéphane Betzi, Karsten Suhre, Bernard Chétrit, Françoise Guerlesquin, Xavier Morelli

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

Most of the recent published works in the field of docking and scoring protein/ligand complexes have focused on ranking true positives resulting from a Virtual Library Screening (VLS) through the use of a specified or consensus linear scoring function. In this work, we present a methodology to speed up the High Throughput Screening (HTS) process, by allowing focused screens or for hitlist triaging when a prohibitively large number of hits is identified in the primary screen, where we have extended the principle of consensus scoring in a nonlinear neural network manner. This led us to introduce a nonlinear Generalist scoring Function, GFscore, which was trained to discriminate true positives from false positives in a data set of diverse chemical compounds. This original Generalist scoring Function is a combination of the five scoring functions found in the CScore package from Tripos Inc. GFscore 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 where the remaining 25% of molecules would be sent to in vitro screening experiments. GFscore is therefore a powerful tool for the biologist, saving both time and money.

Original languageEnglish
Pages (from-to)1704-1712
Number of pages9
JournalJournal of Chemical Information and Modeling
Volume46
Issue number4
DOIs
Publication statusPublished - Jul 2006
Externally publishedYes

Fingerprint

Throughput
Screening
Molecules
Chemical compounds
neural network
ranking
money
campaign
confidence
Ligands
Neural networks
Proteins
experiment
methodology
Experiments

ASJC Scopus subject areas

  • Chemistry(all)
  • Chemical Engineering(all)
  • Computer Science Applications
  • Library and Information Sciences

Cite this

GFscore : A general nonlinear consensus scoring function for high-throughput docking. / Betzi, Stéphane; Suhre, Karsten; Chétrit, Bernard; Guerlesquin, Françoise; Morelli, Xavier.

In: Journal of Chemical Information and Modeling, Vol. 46, No. 4, 07.2006, p. 1704-1712.

Research output: Contribution to journalArticle

Betzi, Stéphane ; Suhre, Karsten ; Chétrit, Bernard ; Guerlesquin, Françoise ; Morelli, Xavier. / GFscore : A general nonlinear consensus scoring function for high-throughput docking. In: Journal of Chemical Information and Modeling. 2006 ; Vol. 46, No. 4. pp. 1704-1712.
@article{391fc7a767344befbe5867142723372e,
title = "GFscore: A general nonlinear consensus scoring function for high-throughput docking",
abstract = "Most of the recent published works in the field of docking and scoring protein/ligand complexes have focused on ranking true positives resulting from a Virtual Library Screening (VLS) through the use of a specified or consensus linear scoring function. In this work, we present a methodology to speed up the High Throughput Screening (HTS) process, by allowing focused screens or for hitlist triaging when a prohibitively large number of hits is identified in the primary screen, where we have extended the principle of consensus scoring in a nonlinear neural network manner. This led us to introduce a nonlinear Generalist scoring Function, GFscore, which was trained to discriminate true positives from false positives in a data set of diverse chemical compounds. This original Generalist scoring Function is a combination of the five scoring functions found in the CScore package from Tripos Inc. GFscore 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 where the remaining 25{\%} of molecules would be sent to in vitro screening experiments. GFscore is therefore a powerful tool for the biologist, saving both time and money.",
author = "St{\'e}phane Betzi and Karsten Suhre and Bernard Ch{\'e}trit and Fran{\cc}oise Guerlesquin and Xavier Morelli",
year = "2006",
month = "7",
doi = "10.1021/ci0600758",
language = "English",
volume = "46",
pages = "1704--1712",
journal = "Journal of Chemical Information and Modeling",
issn = "1549-9596",
publisher = "American Chemical Society",
number = "4",

}

TY - JOUR

T1 - GFscore

T2 - A general nonlinear consensus scoring function for high-throughput docking

AU - Betzi, Stéphane

AU - Suhre, Karsten

AU - Chétrit, Bernard

AU - Guerlesquin, Françoise

AU - Morelli, Xavier

PY - 2006/7

Y1 - 2006/7

N2 - Most of the recent published works in the field of docking and scoring protein/ligand complexes have focused on ranking true positives resulting from a Virtual Library Screening (VLS) through the use of a specified or consensus linear scoring function. In this work, we present a methodology to speed up the High Throughput Screening (HTS) process, by allowing focused screens or for hitlist triaging when a prohibitively large number of hits is identified in the primary screen, where we have extended the principle of consensus scoring in a nonlinear neural network manner. This led us to introduce a nonlinear Generalist scoring Function, GFscore, which was trained to discriminate true positives from false positives in a data set of diverse chemical compounds. This original Generalist scoring Function is a combination of the five scoring functions found in the CScore package from Tripos Inc. GFscore 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 where the remaining 25% of molecules would be sent to in vitro screening experiments. GFscore is therefore a powerful tool for the biologist, saving both time and money.

AB - Most of the recent published works in the field of docking and scoring protein/ligand complexes have focused on ranking true positives resulting from a Virtual Library Screening (VLS) through the use of a specified or consensus linear scoring function. In this work, we present a methodology to speed up the High Throughput Screening (HTS) process, by allowing focused screens or for hitlist triaging when a prohibitively large number of hits is identified in the primary screen, where we have extended the principle of consensus scoring in a nonlinear neural network manner. This led us to introduce a nonlinear Generalist scoring Function, GFscore, which was trained to discriminate true positives from false positives in a data set of diverse chemical compounds. This original Generalist scoring Function is a combination of the five scoring functions found in the CScore package from Tripos Inc. GFscore 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 where the remaining 25% of molecules would be sent to in vitro screening experiments. GFscore is therefore a powerful tool for the biologist, saving both time and money.

UR - http://www.scopus.com/inward/record.url?scp=33746867935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746867935&partnerID=8YFLogxK

U2 - 10.1021/ci0600758

DO - 10.1021/ci0600758

M3 - Article

VL - 46

SP - 1704

EP - 1712

JO - Journal of Chemical Information and Modeling

JF - Journal of Chemical Information and Modeling

SN - 1549-9596

IS - 4

ER -