Drug Discovery Maps, a Machine Learning Model That Visualizes and Predicts Kinome-Inhibitor Interaction Landscapes.

The interpretation of high-dimensional structure-activity data sets in drug discovery to predict ligand-protein interaction landscapes is a challenging task. Here we present Drug Discovery Maps (DDM), a machine learning model that maps the activity profile of compounds across an entire protein family, as illustrated here for the kinase family. DDM is based on the t-distributed stochastic neighbor embedding (t-SNE) algorithm to generate a visualization of molecular and biological similarity. DDM maps chemical and target space and predicts the activities of novel kinase inhibitors across the kinome. The model was validated using independent data sets and in a prospective experimental setting, where DDM predicted new inhibitors for FMS-like tyrosine kinase 3 (FLT3), a therapeutic target for the treatment of acute myeloid leukemia. Compounds were resynthesized, yielding highly potent, cellularly active FLT3 inhibitors. Biochemical assays confirmed most of the predicted off-targets. DDM is further unique in that it is completely open-source and available as a ready-to-use executable to facilitate broad and easy adoption.

Comprehensive structure-activity-relationship of azaindoles as highly potent FLT3 inhibitors.

Acute myeloid leukemia (AML) is characterized by fast progression and low survival rates, in which Fms-like tyrosine kinase 3 (FLT3) receptor mutations have been identified as a driver mutation in cancer progression in a subgroup of AML patients. Clinical trials have shown emergence of drug resistant mutants, emphasizing the ongoing need for new chemical matter to enable the treatment of this disease. Here, we present the discovery and topological structure-activity relationship (SAR) study of analogs of isoquinolinesulfonamide H-89, a well-known PKA inhibitor, as FLT3 inhibitors. Surprisingly, we found that the SAR was not consistent with the observed binding mode of H-89 in PKA. Matched molecular pair analysis resulted in the identification of highly active sub-nanomolar azaindoles as novel FLT3-inhibitors. Structure based modelling using the FLT3 crystal structure suggested an alternative, flipped binding orientation of the new inhibitors.

Activity-Based Protein Profiling Identifies α-Ketoamides as Inhibitors for Phospholipase A2 Group XVI.

Phospholipase A2, group XVI (PLA2G16) is a thiol hydrolase from the HRASLS family that regulates lipolysis in adipose tissue and has been identified as a host factor enabling the cellular entry of picornaviruses. Chemical tools are essential to visualize and control PLA2G16 activity, but they have not been reported to date. Here, we show that MB064, which is a fluorescent lipase probe, also labels recombinant and endogenously expressed PLA2G16. Competitive activity-based protein profiling (ABPP) using MB064 enabled the discovery of α-ketoamides as the first selective PLA2G16 inhibitors. LEI110 was identified as a potent PLA2G16 inhibitor ( Ki = 20 nM) that reduces cellular arachidonic acid levels and oleic acid-induced lipolysis in human HepG2 cells. Gel-based ABPP and chemical proteomics showed that LEI110 is a selective pan-inhibitor of the HRASLS family of thiol hydrolases (i.e., PLA2G16, HRASLS2, RARRES3 and iNAT). Molecular dynamic simulations of LEI110 in the reported crystal structure of PLA2G16 provided insight in the potential ligand-protein interactions to explain its binding mode. In conclusion, we have developed the first selective inhibitor that can be used to study the cellular role of PLA2G16.

Development of a Multiplexed Activity-Based Protein Profiling Assay to Evaluate Activity of Endocannabinoid Hydrolase Inhibitors.

Endocannabinoids, an important class of signaling lipids involved in health and disease, are predominantly synthesized and metabolized by enzymes of the serine hydrolase superfamily. Activity-based protein profiling (ABPP) using fluorescent probes, such as fluorophosphonate (FP)-TAMRA and ß-lactone-based MB064, enables drug discovery activities for serine hydrolases. FP-TAMRA and MB064 have distinct, albeit partially overlapping, target profiles but cannot be used in conjunction due to overlapping excitation/emission spectra. We therefore synthesized a novel FP-probe with a green BODIPY as a fluorescent tag and studied its labeling profile in mouse proteomes. Surprisingly, we found that the reporter tag plays an important role in the binding potency and selectivity of the probe. A multiplexed ABPP assay was developed in which a probe cocktail of FP-BODIPY and MB064 visualized most endocannabinoid serine hydrolases in mouse brain proteomes in a single experiment. The multiplexed ABPP assay was employed to profile endocannabinoid hydrolase inhibitor activity and selectivity in the mouse brain.