A De Novo Substructure Generation Algorithm For Identifying The Privileged Chemical Fragments Of Liver X Receptor Beta Agonists

Liver X receptor beta (LXR beta) is a promising therapeutic target for lipid disorders, atherosclerosis, chronic inflammation, autoimmunity, cancer and neurodegenerative diseases. Druggable LXR beta agonists have been explored over the past decades. However, the pocket of LXR beta ligand-binding domain (LBD) is too large to predict LXR beta agonists with novel scaffolds based on either receptor or agonist structures. In this paper, we report a de novo algorithm which drives privileged LXR beta agonist fragments by starting with individual chemical bonds (de novo) from every molecule in a LXR beta agonist library, growing the bonds into substructures based on the agonist structures with isomorphic and homomorphic restrictions, and electing the privileged fragments from the substructures with a popularity threshold and background chemical and biological knowledge. Using these privileged fragments as queries, we were able to figure out the rules to reconstruct LXR beta agonist molecules from the fragments. The privileged fragments were validated by building regularized logistic regression (RLR) and supporting vector machine (SVM) models as descriptors to predict a LXR beta agonist activities.