Designing Libraries with CNS Activity

Library design is an important and difficult task. In this paper we describe one possible solution to designing a CNS-active library. CNS-actives and -inactives were selected from the CMC and the MDDR databases based on whether they were described as having some kind of CNS activity in the databases...

Full description

Saved in:
Bibliographic Details
Published in:Journal of medicinal chemistry 1999-12, Vol.42 (24), p.4942-4951
Main Authors: Ajay, Bemis, Guy W, Murcko, Mark A
Format: Article
Language:English
Subjects:
Animals
Biological and medical sciences
Blood-Brain Barrier
Central Nervous System - drug effects
Central Nervous System Agents - chemistry
Central Nervous System Agents - classification
Central Nervous System Agents - pharmacology
Chemical Phenomena
Chemistry, Physical
Combinatorial Chemistry Techniques
Databases, Factual
Hydrogen Bonding
Medical sciences
Miscellaneous
Molecular Structure
Molecular Weight
Neuropharmacology
Nitrogen - chemistry
Pharmacology. Drug treatments
Structure-Activity Relationship
User-Computer Interface
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Library design is an important and difficult task. In this paper we describe one possible solution to designing a CNS-active library. CNS-actives and -inactives were selected from the CMC and the MDDR databases based on whether they were described as having some kind of CNS activity in the databases. This classification scheme results in over 15 000 actives and over 50 000 inactives. Each molecule is described by 7 1D descriptors (molecular weight, number of donors, number of acceptors, etc.) and 166 2D descriptors (presence/absence of functional groups such as NH2). A neural network trained using Bayesian methods can correctly predict about 75% of the actives and 65% of the inactives using the 7 1D descriptors. The performance improves to a prediction accuracy on the active set of 83% and 79% on the inactives on adding the 2D descriptors. On a database with 275 compounds where the CNS activity is known (from the literature) for each compound, we achieve 92% and 71% accuracy on the actives and inactives, respectively. The models we construct can therefore be used as a “filter” to examine any set of proposed molecules in a chemical library. As an example of the utility of our method, we describe the generation of a small library of potentially CNS-active molecules that would be amenable to combinatorial chemistry. This was done by building and analyzing a large database of a million compounds constructed from frameworks and side chains frequently found in drug molecules.
ISSN:0022-2623
1520-4804
DOI:10.1021/jm990017w