FINDSITE-COMB

THIS WEBSERVICE IS TEMPORARILY UNAVAILABLE FOR MAINTENANCE

FINDSITECOMB: Drug Discovery Tool



In recent work, the performance of FINDSITECOMB was compared to several commercially and freely available docking programs against the DUD set - A Directory of Useful Decoys. We demonstrated that FINDSITECOMB has virtual screening accuracy better than the best docking method under the challenging condition that no templates > 30% sequence ID to the target are present in the ligand binding databases. We find an average area under the ROC curve, AUC, of 0.77 using crystal target structures and 0.74 using modeled structures with average TM-score ~ 0.75. The individual results for each DUD target can be viewed here. If we set the sequence identity cutoff to 95%, FINDSITECOMB will give the unprecedented mean AUC=0.90 using modeled structures. Thus, FINDSITECOMB does not require experimental structure to give the best performance. For a ~ 300 AA protein, FINDSITECOMB can screen ten million compounds within 2 days on a single computer node.


NOTE:
  • This web service is freely available to all academic users and not-for-profit institutions.
  • Commercial users wishing an evaluation copy should contact skolnick@gatech.edu .
  • Commercial users may license the FINDSITECOMB software after completing the license agreement and sending it to skolnick@gatech.edu . Download the license agreement license agreement.


If you find this service useful, please cite the following paper:

H. Zhou and J. Skolnick. FINDSITECOMB: A threading/structure-based, proteomic-scale virtual ligand screening approach. Journal of Chemical Information and Modeling, in press. PDF


Submit your target protein below



Sequence name:
Email - address for returning results:*
INPUT sequence (only one single letter FASTA formatted sequence):

Or upload PDB ( single chain only ! )
Select compound library:
67871 ZINC8 (TC<0.7) + 6507 DrugBank drugs, ranks for all molecules will be returned
12 million drug-like ZINC12 + 6507 DrugBank drugs, ranks for top 1% of ZINC12 molecules and all drugs will be returned
NCI Open ( ~ 240 k compounds )
GLIDA + ZINC8
Kegg Compound
Kegg Drug
BindingDB
Upload your own compounds (only MDL SDF/MOL format, check examples here , should be less than 100 molecules due to file size limit. Uploaded compounds will be added to the above database and be named sequencially: MOL1, MOL2, ......, MOLn) :





Field marked with (*) are essential


Output format


Download DrugBank target modeled structures
Download ChEMBL target modeled structures

This site is maintained by Dr. H.Zhou: hzhou3@gatech.edu