Get access

Neighborhood-Preserving Visualization of Adaptive Structure–Activity Landscapes: Application to Drug Discovery


  • This research was supported in parts by the Deutsche Forschungsgemeinschaft (DFG, FOR1406, TP4), the Swiss National Science Foundation (grant no. 205321_134783), and the OPO-Foundation Zurich.


original image

Staying fit: A computational approach that generates an intuitive visual fitness landscape (see picture; blue: possible hits, red: nonproductive hits) of chemical space that serves as a roadmap for chemical optimization of drug candidates is presented. Potential compound liabilities can be avoided, multiple properties can be considered at a time, and the information contained in both active and inactive compounds is optimally exploited.

Get access to the full text of this article