| Home | GFscore Run | Explanations | Databases | Example | Links |

GFscore: A General Non-Linear Consensus Scoring Function for High-Throughput Docking
Stéphane Betzi, Karsten Suhre, Bernard Chétrit, Françoise Guerlesquin and Xavier Morelli

We propose in this work, an original methodology to eliminate as many molecules as possible from proprietary in house database after a Virtual Library Screening (VLS) using TRIPOS FlexX for docking and the TRIPOS Cscore module for scoring.

GFscore is a ranked-based consensus scoring function based on the five scoring functions : FlexX Score, G_Score, D_Score, ChemScore, and PMF Score available in TRIPOS Cscore module.

We have selected a “diverse” database (1420 compounds of the NCI Diversity database) and a set of “diverse” protein-ligand complexes to train a neural network. Among the FlexX 200 protein-ligand dataset complexes, FlexX was able to generate 78 complexes with an accurate RMSD (<2 Å). We have then hidden each of these 78 ligands into the Diversity database and High Throughput docked each of them for each of the 78 targets.

We trained a neural network on the scoring results to combine the 5 scoring functions and generate our Generalist Function score GFscore.

What do you need to launch a GFscore calculation ?
  1. You need first to run you FlexX/Cscore docking experiment on the Diversity database used to train the GFscore neural network :
    The Diversity filtered database available here
  2. Then you must export your results using the export command from the MSS Sybyl menu. Export your table in a ASCII file using the comma separator (more details below). Download an example of a small virtual screening experiment here : (use it to try the GFscore server).
  3. Compute your virtual screening experiment on your "in house" database and export the results the same way (ASCII file).
  4. Upload your two files on our GFscore calculation web page and obtain your list of potential hits.
Input file format

You can export your data in a .txt or .csv file. BE CAREFULL : the first line must contain the labels for each column.
Make sure you have the correct column order. To help you, check the format below an compare it with the beginning of your results :


Other columns are not taken into account.

Here is a typical GFscore result
Contact | 2006 |

    intern search