Application of 3D Zernike Descriptors to Shape Based Ligand Similarity Searching
This page provides the datasets used for evaluating the performance of 3D Zernike descriptors for shape based ligand similarity searching. The first dataset includes 47 odour compounds which have been grouped into 7 categories: Amber, Bitter Almond, Camphor, Jasmine, Muguet and Musk. The second dataset originally downloaded from http://ligand.info contains 39256 structures divdided into 330 actives, 38022 inactives and 904 moderately actives.
Implementation details are available from the paper: Application of 3D Zernike Descriptors to Shape Based Ligand Similarity Searching, Vishwesh Venkatraman, Padmasini Chakravarthy, and Daisuke Kihara Submitted
Datasets
The datasets are available as a tar.gz file
Anti HIV datasetA list of actives, inactives and moderately actives is also provided. The first column indicates the #ID of the structure while Column II lists the activity status.
Activity ListInformation on the query and results shown in Figures 4,5 and 8 in the paper can be obtained from the following files.
Contact Information
If you have any questions or suggestions, please feel free to contact us (dkihara@purdue.edu).