Optimization and visualization of the edge weights in optimal assignment methods for virtual screening.

Lars Rosenbaum,Andreas Jahn,Andreas Zell,Alexander Dörr

doi:10.1186/1756-0381-6-7

Lars Rosenbaum, Andreas Jahn + Show 2 more

Open Access

https://doi.org/10.1186/1756-0381-6-7

Copy DOI

Abstract

BackgroundLigand‐based virtual screening plays a fundamental part in the early drug discovery stage. In a virtual screening, a chemical library is searched for molecules with similar properties to a query molecule by means of a similarity function. The optimal assignment of chemical graphs has proven to be a valuable similarity function for many cheminformatic tasks, such as virtual screening. The optimal assignment assumes all atoms of a query molecule to be equally important, which is not realistic depending on the binding mode of a ligand. The importance of a query molecule’s atoms can be integrated in the optimal assignment by weighting the assignment edges. We optimized the edge weights with respect to the virtual screening performance by means of evolutionary algorithms. Furthermore, we propose a visualization approach for the interpretation of the edge weights.ResultsWe evaluated two different evolutionary algorithms, differential evolution and particle swarm optimization, for their suitability for optimizing the assignment edge weights. The results showed that both optimization methods are suited to optimize the edge weights. Furthermore, we compared our approach to the optimal assignment with equal edge weights and two literature similarity functions on a subset of the Directory of Useful Decoys using sophisticated virtual screening performance metrics. Our approach achieved a considerably better overall and early enrichment performance. The visualization of the edge weights enables the identification of substructures that are important for a good retrieval of ligands and for the binding to the protein target.ConclusionsThe optimization of the edge weights in optimal assignment methods is a valuable approach for ligand‐based virtual screening experiments. The approach can be applied to any similarity function that employs the optimal assignment method, which includes a variety of similarity measures that have proven to be valuable in various cheminformatic tasks. The proposed visualization helps to get a better understanding of the binding mode of the analyzed query molecule.

Highlights

Ligand-based virtual screening plays a fundamental part in the early drug discovery stage
The optimization of the edge weights in optimal assignment methods is a valuable approach for ligand-based virtual screening experiments
The approach can be applied to any similarity function that employs the optimal assignment method, which includes a variety of similarity measures that have proven to be valuable in various cheminformatic tasks

Summary

Introduction

Ligand-based virtual screening plays a fundamental part in the early drug discovery stage. A chemical library is searched for molecules with similar properties to a query molecule by means of a similarity function. The optimal assignment assumes all atoms of a query molecule to be important, which is not realistic depending on the binding mode of a ligand. High-throughput screenings of a chemical library for ligands against a certain protein target play a fundamental part in the early stages of the drug discovery pipeline. The searching of a chemical library in-silico, called virtual screening (VS), is the complementary computational approach to high-throughput screening [1]. Ligandbased VS methods rank a chemical library operating only on a small set of known ligands that serve as query structures. Ligand-based methods can still be applied if protein structures are not available [4]

Methods

Results

Conclusion