Superfamily-wide portrait of serine hydrolase inhibition achieved by library-versus-library screening

Abstract

Serine hydrolases (SHs) are one of the largest and most diverse enzyme classes in mammals. They play fundamental roles in virtually all physiological processes and are targeted by drugs to treat diseases such as diabetes, obesity, and neurodegenerative disorders. Despite this, we lack biological understanding for most of the 110+ predicted mammalian metabolic SHs, in large part because of a dearth of assays to assess their biochemical activities and a lack of selective inhibitors to probe their function in living systems. We show here that the vast majority (> 80%) of mammalian metabolic SHs can be labeled in proteomes by a single, active site-directed fluorophosphonate probe. We exploit this universal activity-based assay in a library-versus-library format to screen 70+ SHs against 140+ structurally diverse carbamates. Lead inhibitors were discovered for ∼40% of the screened enzymes, including many poorly characterized SHs. Global profiles identified carbamate inhibitors that discriminate among highly sequence-related SHs and, conversely, enzymes that share inhibitor sensitivity profiles despite lacking sequence homology. These findings indicate that sequence relatedness is not a strong predictor of shared pharmacology within the SH superfamily. Finally, we show that lead carbamate inhibitors can be optimized into pharmacological probes that inactivate individual SHs with high specificity in vivo.

Fig. 1.

Determining the full complement of mammalian metabolic SHs targeted by FP activity-based probes. (A) A panel of mouse tissue proteomes (1 mg of protein per mL) was labeled with FP-rhodamine (2 μM, 45 min) and proteomes analyzed by 1D-SDS-PAGE and in-gel fluorescence scanning. Representative fluorescent gel of FP-rhodamine-labeling events shown in gray scale. (B) Hierarchical cluster analysis of SH activity signals identified in mouse tissues by ABPP-MudPIT. Data are presented as the average spectral counts from three independent experiments normalized for each SH to the tissue containing the most spectral counts for that enzyme. (C) A dendrogram showing all 128 members of the mouse metabolic SH family with branch length depicting sequence relatedness. This analysis includes two additional human SHs, FAAH2 and PNPLA4, that lack mouse orthologues. SHs that were labeled by FP activity-based probes are shown in red (105 enzymes or 82% of the metabolic SH family). cm, conditioned media; LPS, cells treated with 10 μg/mL lipopolysaccharide for 24 h; RAW, RAW264.7 mouse macrophage cell line.

Fig. 2.

A library-versus-library format for competitive ABPP. (A) SHs were expressed individually and assayed for activity in crude cell lysates by treatment with FP-Rh and analysis by gel-based ABPP. Gel-resolvable SHs were combined and screened for inhibition by the carbamate library; a representative example is shown for the carbamate URB597, which is a known inhibitor of FAAH (33). (B) General structure of a carbamate library and mechanism of SH inactivation by carbamates. (C) Representative example of the primary competitive ABPP screening data for the enzyme FAAH2 expressed by transient transfection in 293T cells. A mock-transfected proteome and FP-rhodamine signals from an endogenously expressed SH are shown for comparison. Unless otherwise indicated, each number on the horizontal axis refers to a carbamate (lacking the WWL prefix to conserve space). From this analysis, several hits were identified, including WWL44, which selectively inhibited FAAH2 relative to other SHs with an IC₅₀ value of 1.7 μM (Table 1). See SI Appendix, Fig. S4 for a complete set primary competitive ABPP data from our library-versus-library screen.

Fig. 3.

Identification and characterization of lead inhibitors for SHs (A) Hierarchical cluster analysis of carbamate inhibition profiles for a representative subset of SHs. From this analysis, compounds that inactivate several SHs (e.g., WWL98 and WWL202) can be readily discriminated from those that show high selectivity for individual SHs (listed in Table 1 and B–D). (B–D) Concentration-dependent inhibition profiles for carbamates that show high selectivity for one member of a pair of sequence-related enzymes. (B) FAAH-1 versus FAAH-2, (C) AADAC versus AADACL1, and (D) PLA2G7 versus PAFAH2. See SI Appendix, Fig. S5 for more expanded concentration-dependent inhibition curves used to generate the reported IC₅₀ values.

Fig. 4.

Development of a selective and in vivo-active inhibitor of ABHD11. (A) Competitive ABPP signals for WWL151 and structural analogues (5 μM) against ABHD11 and the common off-targets for this compound scaffold—FAAH, MGLL, ABHD6, and PNPLA8. (B) Cluster analysis of the competitive ABPP data shown in A, designating WWL222 as a potent and selective ABHD11 inhibitor. (C) Concentration-dependent inhibition curve for WWL222 against ABHD11. From this curve, an IC₅₀ value of 170 nM was calculated. Data are presented as means ± standard error of the mean (SEM); n = 3/group. (D) ABPP-MudPIT analysis of SHs from the brain proteomes of mice treated with vehicle or WWL222 (10 mg kg^-1, i.p., 4 h); Among the ∼50 SHs detected in this analysis, only ABHD11 was inhibited by WWL222 (*p < 0.02). Data are presented as means ± SEM; n = 3/group.