Structural proteomics defines a sequential priming mechanism for the progesterone receptor

Abstract

The progesterone receptor (PR) is a steroid-responsive nuclear receptor with two isoforms: PR-A and PR-B. Disruption of PR-A:PR-B signaling is associated with breast cancer through interactions with oncogenic co-regulatory proteins (CoRs). However, molecular details of isoform-specific PR-CoR interactions remain poorly understood. Using structural mass spectrometry, we investigate the sequential binding mechanism of purified full-length PR and intact CoRs, steroid receptor coactivator 3 (SRC3) and p300, as complexes on target DNA. Our findings reveal selective CoR NR-box binding by PR and unique interaction surfaces between PR and CoRs during complex assembly, providing a structural basis for CoR sequential binding on PR. Antagonist-bound PR showed persistent CoR interactions, challenging the classical model of nuclear receptor activation and repression. Collectively, we offer a peptide-level perspective on the organization of the PR transcriptional complex and infer the mechanisms behind the interactions of these proteins, both in active and inactive conformations.

Keywords: Progesterone receptor; crosslinking; hydrogen-deuterium exchange; mass spectrometry; nuclear receptors; protein-protein interactions; transcriptional co-regulatory proteins.

Extended Data Fig. 1. HDX overlays on best HDXer models of PR-B:SRC3 complexes.

HDX-MS overlays on best selected model of PR-B:SRC3 complex in both non-DNA-bound (top) and DNA-bound (bottom) states. Warmer colors (yellow, orange, red), indicate increased deuterium exchange, and cooler colors (green, blue) indicate decreased deuterium exchange. Black indicates the peptide was not found by HDX and gray indicates exchange within ±5%. Models selected by HDXer RMSE values, and visualizations made using ChimeraX 1.8.

Extended Data Fig. 2. PR and SRC3 deuterium exchange differences align with crosslinking results.

A. XiView images of differential XL-MS data for PR-A vs. PR-A:SRC3 experiments with crosslinks enriched in apo samples (top) and pre-bound samples (bottom) represented. HDX overlays are indicative of their comparable differential HDX-MS experiments. Top: SRC3 exchange - SRC3 vs. PR-A:SRC3 (non-DNA bound), PR exchange – PR-A vs. PR-A:SRC3. Bottom: SRC3 exchange – SRC3 vs. PR-A:SRC3:PRE, PR exchange – PR-A:SRC3 vs. PR-A:SRC3:PRE. B. XiView images of differential XL-MS data for PR-B vs. PR-B:SRC3 experiments with the same HDX overlays as shown in A. Intraprotein crosslinks are represented in purple, interprotein crosslinks are represented as green. Differential HDX-MS scale shows the % change in deuterium incorporation, where cooler colors represent reduced deuterium exchange, while warmer colors (yellow, orange, red) represent increased deuterium exchange. Black represents peptides not detected in HDX-MS experiments, and PR isoforms have numbering normalized to the B isoform.

Extended Data Fig. 3. Crosslinking shows NR-Box 3 is exclusively used by p300.

A. Top: All validated crosslinks from differential PR-A:SRC3:p300±PRE experiments. Bottom: Zoomed in view of SRC3 to show NR-Box crosslinks specific to the PR-A-containing complex. B. Top: All validated crosslinks from differential PR-B:SRC3:p300±PRE experiments. Bottom: Zoomed in view of SRC3 to show NR-Box crosslinks specific to the PR-B-containing complex. Defined domains are as follows: PR - DBD (purple) and LBD (green); SRC3 – NR-boxes (purple) and histone acetyltransferase domain (yellow); p300 - bromodomain (pink), zinc finger domain (green), and NCOA2-interaction domain (yellow).

Extended Data Fig. 4. Mutation of NR-box 2 or multiple NR-boxes to LXXAA in SRC3 reduces PR activity.

Bar graph showing the ratio of Firefly to Renilla luciferase normalized over the vehicle (ethanol) signal for both R5020 PR agonist and RU486 PR antagonist. Mock is indicative of base vector in the place of PR or SRC3 plasmid. ‘Mut’ in the legend indicates an LXXLL NR-Box mutated to LXXAA, validated by whole plasmid next-generation sequencing (Azenta). Similarly, ‘BOX’ denoted in the PR-A experiments indicates the mutated NR-Box(es). Points indicative of 4 replicates with SEM error bars. Two-way ANOVA was performed with Tukey correction for multiple comparisons, and asterisks indicate p<0.001 (***) and p<0.0001 (****).

Extended Data Fig. 5. SEC-MALS of purified PR-A and PR-B bound to the progestin antagonist RU486 with and without DNA.

DNA induces assembly of PR dimers A-B. SEC-MALS chromatograms of antagonist (RU486)- bound PR-A (A) and PR-B (B) with and without DNA. The molar mass of DNA and PR-A alone matches the monomeric molar mass (black line/dots across the peaks). DNA induces assembly of both PR-A and PR-B into a complex with 2:1 (protein:DNA) stoichiometry. The presence of DNA in the complexes were confirmed by deconvolution of the protein and DNA fractions in the peak (red and blue lines, respectively).

Figure 1.. DNA induces assembly of PR-A and PR-B.

A-B. SEC-MALS chromatograms of agonist (R5020)-bound PR-A (A) and PR-B (B) with and without DNA. The molar mass of DNA and PR-A alone matches the monomeric molar mass (black line/dots across the peaks). DNA induces assembly of both PR-A and PR-B into a complex with 2:1 (protein:DNA) stoichiometry. The presence of DNA in the complexes were confirmed by deconvolution of the protein and DNA fractions in the peak (red and blue lines, respectively).

Figure 2.. Structural proteomics reveals isoform differences upon response element binding.

A. Consolidated HDX-MS data, run in triplicate, showing the differential analysis between unbound PR vs. PRE-bound where the top is PR-B, and the bottom is PR-A. Domains are labeled as the following: N-terminal Domain (NTD), DNA-binding domain (DBD), Hinge region (Hinge), and Ligand binding domain (LBD). B. Trimmed AlphaFold 3.0 model (residues 375–769) of PR-A homodimer with unbound PR-A vs. PR-A:PRE HDX overlays. Highlighted regions are the PR dimerization domain (top) and the DBD C-terminal extension (bottom). Cooler colors indicate stronger HDX protection. C. XlinkX images of differential PR-A ± PRE experiments, where crosslinks from the unbound (top) and PRE-bound (bottom) states are shown. Crosslinks mapped onto PR-B numbering with the gray region representing the 164 amino acids not expressed in PR-A. Results representative of triplicate experiments, with validation in Skyline. D. XlinkX view of differential PR-B ± PRE experiments, where crosslinks from unbound (top) and PRE-bound (bottom) states are shown. Domains – Gray: Not expressed; Purple: DBD; Green: LBD.

Figure 3.. SRC3 induces LBD changes to PR upon PRE addition.

A. Left HDX overlay (PR-A vs. PR-A:SRC3) mapped onto AlphaFold3.0 model of the PR-A:SRC3 ternary complex with the PR homodimer highlighted. Zoomed-in sections of PR corresponding to the dimerization domains (Amino acids: 720–769 and 438–454) and N-terminal domain (PR-A amino acids 1–476) highlighted with matching HDX overlays. Right. Differential HDX overlay of SRC3 vs. PR-A:SRC3 onto the best scoring PR:SRC3 apo complex with SRC3 highlighted. NR-Boxes 1 and 2 (amino acids 685–689 and 738–742, respectively) blown up to show differential exchange. B. Left HDX overlay (PR-A:PRE vs. PR-A:SRC3:PRE) mapped onto AlphFold3.0 model of PR-A:SRC3:PRE ternary complex with the PR homodimer highlighted. One PR-A monomer is shown as a zoomed-in section. Right. Differential HDX overlay of SRC3 vs. PR-A:SRC3:PRE onto the best scoring PR:SRC3 apo complex with SRC3 highlighted. NR-Boxes 1 and 2 and the p300 interaction site (amino acids 1023–1093) are highlighted to show differential exchange. Black peptide regions correspond to peptides not identified by HDX-MS. Each color represents the percent change in deuterium incorporation (Δ%D), following the scale shown at the bottom.

Figure 4.. p300 differentially alters the conformational dynamics of PR-A and PR-B within the PR:SRC3:p300 complex.

Top. Consolidated HDX plots of PR-B showing the differential HDX-MS comparisons within the plot to the left. Changes in deuterium uptake are represented by the rainbow plot shown at the bottom. Common PR domains are highlighted at the top: N-terminal domain (NTD, orange), DNA-binding domain (DBD, purple), Hinge (yellow), and ligand-binding domain (LBD, teal). Bottom. AlphaFold3.0 models of PR from the AF1 to LBD (amino acids 456–933 using PR-B numbering). HDX-MS overlays represent the same experiments as the consolidated views on the top. Each color represents the percent change in deuterium incorporation (Δ%D), following the scale shown at the bottom. Gray overlays indicate no significant changes and black indicates peptides not detected in the HDX-MS experiment.

Figure 5.. PR-A and PR-B differentially interact with SRC3 and are stabilized by p300 addition.

Top. Consolidated differential HDX-MS results for SRC3, comparing the changes induced by PR-A and p300 binding in the presence and absence of PRE DNA. Middle. Consolidated HDX-MS plot of SRC3 exchange, with PR-B comparisons in the same order as PR-A. The motifs highlighted are the following: bHLH (orange), PAS (purple), LXXLL motifs (yellow), CREBBP Interaction domain (teal), and acetyltransferase domain (dark blue). Each color represents the percent change in deuterium incorporation (Δ%D), following the scale shown at the bottom.Gray overlays indicate no significant changes and black indicates peptides not detected in the HDX-MS experiment. Bottom. Selected deuterium uptake plots for peptides that contain LXXLL motifs 1, 2, and 3. The %D uptake indicates the percent deuterium uptake over time for the PR-A:SRC3 ± DNA and PR-A:SRC3:p300 ± DNA HDX experiments.

Figure 6.. XL-MS shows p300 directly interacts with PR.

A. Crosslinking results from PR-B:p300±PRE experiments. Purple: intraprotein crosslinks, green: interprotein crosslinks. PR highlighted domains: DBD (purple) and LBD (green). p300 highlighted domains: bromodomain (pink), zinc finger domain (green), and NCOA2-interaction domain (yellow).

Figure 7.. RU486 antagonism rearranges PR-SRC3-p300 interactions.

Top. Plotted differential crosslinks in PR:SRC3 experiments, comparing R5020-specific (agonist, red) and RU-486-specific (antagonist, blue) crosslinks. Crosslinks represented by circles with corresponding XlinkX scores as point size. Top. Red. XlinkX view of R5020-specific crosslinks in differential PR:SRC3 experiments. Top. Blue. XlinkX view of RU486-specific crosslinks in differential PR:SRC3 experiments. B. All validated R5020-bound (left) and RU486-bound (right) crosslinks for differential PR-B:SRC3:p300 ± PRE experiments. The x-axis represents the Log2 transformed fold change values from Skyline, while the y-axis represents the −log10 transformation of the Skyline p-value output. The lines are indicative of a Log2 fold change of 1 (two-fold increase) and −log10 p-value of 1.3, corresponding to p<0.05. Crosslinks highlighted in red show notable differences in PR:SRC3:p300 interactions between PR ligands. Defined domains are as follows: PR - DBD (purple) and LBD (green); SRC3 – NR-boxes (purple) and histone acetyltransferase domain (yellow); p300 - bromodomain (pink), zinc finger domain (green), and NCOA2-interaction domain (yellow).

Figure 8.. RU486-bound PR has reduced deuterium exchange upon CoR binding.

A. PR models of AF1 to C-terminus (amino acids 456–933) with PR-A HDX overlays, corresponding to the comparisons shown beneath them. B. PR models of the AF1 to C-terminus with corresponding PR-B HDX overlays labeled beneath. Each color represents the percent change in deuterium incorporation (Δ%D), following the scale shown at the bottom. Gray overlays indicate no significant changes and black indicates peptides not detected in the HDX-MS experiment.