Predicting Compound Selectivity by Self‐Organizing Maps: Cross‐Activities of Metabotropic Glutamate Receptor Antagonists

Abstract

The self-organizing map (SOM) principle was introduced by Kohonen in 1982, [1] and has been applied to a variety of tasks in chemistry and chemical biology ever since. [2,3] In this study, we used the SOM algorithm for mapping known ligands according to a topological pharmacophore descriptor (CATS) [4] and predicting potential cross-activities. Our aim was to see whether 1) the descriptor is able to discriminate antagonists of metabotropic glutamate receptors (mGluR) 1 and 5, and 2) the SOM could be used for predicting potential additional binding behaviors of the ligands.First, an mGluR reference collection containing 338 compounds was compiled including published and Merz in-house structures of noncompetitive group I mGluR antagonists. The collection comprises two subsets: allosteric mGlu1 receptor antagonists (213 compounds), and allosteric mGlu5 receptor antagonists (125 compounds).[5] These molecules cover a broad range of binding activities (K i values between 1 nm and % 10 mm) and represent different chemical classes. This mGluR reference library was complemented by the molecules from the COBRA database (v. 3.12; 5376 molecules) containing a broad set of known drugs, leads, and lead candidates affecting a large number of different drug targets. [6] Subsequently, the molecules were converted to a vector representation giving the scaled occurrence frequencies of topological potential pharmacophore point pairs (CATS2D method). [4,7] In this study, intramolecular distances from zero to nine bonds were considered, resulting in a 150-dimensional vector representation of each molecular compound.The complete COBRA database was subjected to clustering and mapping onto a two-dimensional grid by the SOM approach. The SOM provides a nonlinear two-dimensional projection of the 150-dimensional data space ("chemical space"), where local neighborhood is conserved. This means, that molecules that are located close to each other on the map are also close in the original high-dimensional space. For SOM training we applied a slightly modified version of the Kohonen algorithm as described previously. [6,8] As a result, all molecules from COBRA were distributed into 225 (15 15) clusters A C H T U N G T R E N N U N G ("neurons"or "receptive fields"). The distribution of these compounds is shown in Figure 1 a. It is evident that the SOM is devoid of large patches of empty clusters (< 3 %) and pronounced densities, which indicates successful mapping and also reflects the diversity of the COBRA entries. After SOM training we projected the mGluR data onto this map and analyzed the resulting distribution patterns. The two mGluR ligand classes form separate localized distributions, where the distribution of the mGluR5 antagonists (Figure 1 c) appears to be slightly more focused than the mGluR1 data (Figure 1 b). Notably, only 6 % of the two ligand classes were clustered together. The SOM was Figure 1. a) SOM projection of the complete COBRA data, b) the mGluR1 antagonists, and c) mGluR5 antagonists. The distribution of the compounds...

Translational Bioinformatics Approaches to Drug Development

“…Noeske et al 34 used this conceptual approach to identify new treatment targets for a group of known metabotropic glutamate (mGlu) receptor agonists by preparing pharmacophore descriptors for the antagonists as well as a range of additional known compounds, and used self-organizing maps to create a compound map. They reported subclusters containing mGlu antagonists, with proximity to additional compounds known to bind to dopamine and histamine receptors.…”

Case Study 3: Fragment Hopping to Design Highly Potent and Selective Neuronal Nitric Oxide Synthase Inhibitors

“…If the structure of the receptor is unknown, the pharmacophoric sites can be identified by the structure-activity analysis of ligands and ligand-based pharmacophore mapping using Catalyst, DISCO, and GASP [39]. Self-organizing maps (SOM) can be used as a ligand-based tool to predict compound selectivity [40].…”

Application of Self-Organizing Maps in Chemistry. The Case of Phenyl Cations

“…Closer to the topic of the present study, the SOM methods has been applied for recognizing the chemical properties of molecules, e.g. for assigning a degree of aromaticity (Alonso & Herradin, 2008), or more generally for predicting the chemical reactivity and its selectivity (Chen & Gasteiger, 1997;Noeske et al, 2006). As a matter of fact, phenyl cations had been all by unknown to chemists up to a decade ago, when it was discovered that electron-donating substituted phenyl halides, sulfonates and phosphates smoothly undergo heterolytic cleavage forming such intermediates in the triplet state, and that in this multiplicity these react efficiently with π , not with n, nucleophiles (Fagnoni & Albini, 2005).…”