A Distance Function for Retrieval of Active Molecules from Complex Chemical Space Representations
- 28 March 2006
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 46 (3) , 1094-1097
- https://doi.org/10.1021/ci050510i
Abstract
The concept of chemical space is of fundamental importance for chemoinformatics research. It is generally thought that high-dimensional space representations are too complex for the successful application of many compound classification or virtual screening methods. Here, we show that a simple “activity-centered” distance function is capable of accurately detecting molecular similarity relationships in “raw” chemical spaces of high dimensionality.Keywords
This publication has 8 references indexed in Scilit:
- Hit-Directed Nearest-Neighbor SearchingJournal of Medicinal Chemistry, 2004
- Molecular Similarity Analysis and Virtual Screening by Mapping of Consensus Positions in Binary-Transformed Chemical Descriptor Spaces with Variable DimensionalityJournal of Chemical Information and Computer Sciences, 2003
- Active Learning with Support Vector Machines in the Drug Discovery ProcessJournal of Chemical Information and Computer Sciences, 2003
- Recursive Median Partitioning for Virtual Screening of Large DatabasesJournal of Chemical Information and Computer Sciences, 2003
- Integration of virtual and high-throughput screeningNature Reviews Drug Discovery, 2002
- Combinatorial informatics in the post-genomics eraNature Reviews Drug Discovery, 2002
- Metric Validation and the Receptor-Relevant Subspace ConceptJournal of Chemical Information and Computer Sciences, 1999
- Chemical Similarity SearchingJournal of Chemical Information and Computer Sciences, 1998