Document Detail


Reoptimization of MDL keys for use in drug discovery.
MedLine Citation:
PMID:  12444722     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
For a number of years MDL products have exposed both 166 bit and 960 bit keysets based on 2D descriptors. These keysets were originally constructed and optimized for substructure searching. We report on improvements in the performance of MDL keysets which are reoptimized for use in molecular similarity. Classification performance for a test data set of 957 compounds was increased from 0.65 for the 166 bit keyset and 0.67 for the 960 bit keyset to 0.71 for a surprisal S/N pruned keyset containing 208 bits and 0.71 for a genetic algorithm optimized keyset containing 548 bits. We present an overview of the underlying technology supporting the definition of descriptors and the encoding of these descriptors into keysets. This technology allows definition of descriptors as combinations of atom properties, bond properties, and atomic neighborhoods at various topological separations as well as supporting a number of custom descriptors. These descriptors can then be used to set one or more bits in a keyset. We constructed various keysets and optimized their performance in clustering bioactive substances. Performance was measured using methodology developed by Briem and Lessel. "Directed pruning" was carried out by eliminating bits from the keysets on the basis of random selection, values of the surprisal of the bit, or values of the surprisal S/N ratio of the bit. The random pruning experiment highlighted the insensitivity of keyset performance for keyset lengths of more than 1000 bits. Contrary to initial expectations, pruning on the basis of the surprisal values of the various bits resulted in keysets which underperformed those resulting from random pruning. In contrast, pruning on the basis of the surprisal S/N ratio was found to yield keysets which performed better than those resulting from random pruning. We also explored the use of genetic algorithms in the selection of optimal keysets. Once more the performance was only a weak function of keyset size, and the optimizations failed to identify a single globally optimal keyset. Instead multiple, equally optimal keysets could be produced which had relatively low overlap of the descriptors they encoded.
Authors:
Joseph L Durant; Burton A Leland; Douglas R Henry; James G Nourse
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Journal of chemical information and computer sciences     Volume:  42     ISSN:  0095-2338     ISO Abbreviation:  J Chem Inf Comput Sci     Publication Date:    2002 Nov-Dec
Date Detail:
Created Date:  2002-11-26     Completed Date:  2003-02-05     Revised Date:  2004-11-17    
Medline Journal Info:
Nlm Unique ID:  7505012     Medline TA:  J Chem Inf Comput Sci     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1273-80     Citation Subset:  IM    
Affiliation:
MDL Information Systems, 14600 Catalina Street, San Leandro, California 94577, USA. jdurant@mdi.com
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Computational Biology / methods*
Databases, Factual
Drug Evaluation, Preclinical / methods*
Genetics
Pattern Recognition, Automated
Software
Structure-Activity Relationship

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Structure and absolute configuration of new diterpenes from Lavandula multifida.
Next Document:  Data mining for seeking an accurate quantitative relationship between molecular structure and GC ret...