Evaluating the Diversity and Target Addressability of DELs using Scaffold Analysis and Machine Learning

DELs enable efficient experimental screening of vast combinatorial libraries, offering a powerful platform for drug discovery. Apart from ensuring the druglike physicochemical properties, other key parameters to maximize the success rate of DEL designs include the scaffold diversity and target addressability. While several tools exist to assess chemical diversity, a dedicated computational approach combining both parameters is currently lacking. Here, we present a cheminformatics tool leveraging scaffold analysis and machine learning to evaluate both scaffold diversity and target-orientedness. Using two in-house libraries as a case study, we demonstrate the workflow's ability to distinguish between generalist and focused libraries. This capability can guide medicinal chemists in selecting libraries tailored for specific objectives, such as hit-finding or hit-optimization. To facilitate utilization, this tool is freely available both as a web application and as a Python script at https://github.com/novalixofficial/NovaWebApp.