ABSTRACT
DCAF1 is a substrate receptor of two distinct E3 ligases (CRL4DCAF1 and EDVP), plays a critical physiological role in protein degradation, and is considered a drug target for various cancers. Antagonists of DCAF1 could be used toward the development of therapeutics for cancers and viral treatments. We used the WDR domain of DCAF1 to screen a 114-billion-compound DNA encoded library (DEL) and identified candidate compounds using similarity search and machine learning. This led to the discovery of a compound (Z1391232269) with an SPR KD of 11 µM. Structure-guided hit optimization led to the discovery of OICR-8268 (26e) with an SPR KD of 38 nM and cellular target engagement with EC50 of 10 µM as measured by cellular thermal shift assay (CETSA). OICR-8268 is an excellent tool compound to enable the development of next-generation DCAF1 ligands toward cancer therapeutics, further investigation of DCAF1 functions in cells, and the development of DCAF1-based PROTACs.
Subject(s)
Neoplasms , Ubiquitin-Protein Ligases , Humans , Ligands , Ubiquitin-Protein Ligases/metabolism , Carrier Proteins/chemistryABSTRACT
DNA-encoded small molecule libraries (DELs) have enabled discovery of novel inhibitors for many distinct protein targets of therapeutic value. We demonstrate a new approach applying machine learning to DEL selection data by identifying active molecules from large libraries of commercial and easily synthesizable compounds. We train models using only DEL selection data and apply automated or automatable filters to the predictions. We perform a large prospective study (â¼2000 compounds) across three diverse protein targets: sEH (a hydrolase), ERα (a nuclear receptor), and c-KIT (a kinase). The approach is effective, with an overall hit rate of â¼30% at 30 µM and discovery of potent compounds (IC50 < 10 nM) for every target. The system makes useful predictions even for molecules dissimilar to the original DEL, and the compounds identified are diverse, predominantly drug-like, and different from known ligands. This work demonstrates a powerful new approach to hit-finding.
