Scaffold Fusion and SAR Transfer with a Chemical Language Model Generates Novel Liver X Receptor Modulators

Liver X receptors (LXRs) are promising targets for metabolic disorders including atherosclerosis and metabolic dysfunction-associated steatotic liver disease (MASLD). In this study, we employed a chemical language model (CLM) for LXR modulator design in an explorative fashion and observed that structural features from different LXR modulator templates were merged, and structure–activity relationship (SAR) knowledge was transferred. The generated computational designs demonstrated LXR modulation with diverse activity profiles and selective modulator properties, including a promising lipolytic activity of an inverse LXR agonist in an in vitro MASLD model that warrants its further development to improve ADME properties.