Visualization of multi-property landscapes for compound selection and optimization

Abstract

Compound optimization generally requires considering multiple properties in concert and reaching a balance between them. Computationally, this process can be supported by multi-objective optimization methods that produce numerical solutions to an optimization task. Since a variety of comparable multi-property solutions are usually obtained further prioritization is required. However, the underlying multi-dimensional property spaces are typically complex and difficult to rationalize. Herein, an approach is introduced to visualize multi-property landscapes by adapting the concepts of star and parallel coordinates from computer graphics. The visualization method is designed to complement multi-objective compound optimization. We show that visualization makes it possible to further distinguish between numerically equivalent optimization solutions and helps to select drug-like compounds from multi-dimensional property spaces. The methodology is intuitive, applicable to a wide range of chemical optimization problems, and made freely available to the scientific community.

Recent developments in SAR visualization

“…For example, the ligand-target differentiation map 42 and various extensions of SAS maps 12 are prototypes of relatively simple multi-target AL designs, indicating that rather different types of graphs might be considered. Moreover, first attempts have been made to visualize multi-property compound optimization spaces without the need for dimensionality reduction, for example, using star coordinates, 43 a 2D visualization technique for multi-dimensional data from computer science. Such developments are equally relevant for chemical informatics and medicinal chemistry.…”