Triple SILAC to determine stimulus specific interactions in the Wnt pathway

Abstract

Many important regulatory functions are performed by dynamic multiprotein complexes that adapt their composition and activity in response to different stimuli. Here we employ quantitative affinity purification coupled with mass spectrometry to efficiently separate background from specific interactors but add an additional quantitative dimension to explicitly characterize stimulus-dependent interactions. This is accomplished by SILAC in a triple-labeling format, in which pull-downs with bait, with bait and stimulus, and without bait are quantified against each other. As baits, we use full-length proteins fused to the green fluorescent protein and expressed under endogenous control. We applied this technology to Wnt signaling, which is important in development, tissue homeostasis, and cancer, and investigated interactions of the key components APC, Axin-1, DVL2, and CtBP2 with differential pathway activation. Our screens identify many known Wnt signaling complex components and link novel candidates to Wnt signaling, including FAM83B and Girdin, which we found as interactors to multiple Wnt pathway players. Girdin binds to DVL2 independent of stimulation with the ligand Wnt3a but to Axin-1 and APC in a stimulus-dependent manner. The core destruction complex itself, which regulates beta-catenin stability as the key step in canonical Wnt signaling, remained essentially unchanged.

Figure 1

Analysis of interaction dynamics by QUBIC triple SILAC based quantitative mass spectrometry. (A) Experimental workflow for triple SILAC pull-downs to determine Wnt3a-dependent interaction dynamics. The cell line expressing the GFP-tagged protein of interest is light and medium SILAC labeled, the untransfected wild-type control cell line is heavy SILAC labeled. Cells are lysed after two hour treatment with Wnt3a (200 ng/mL) or vehicle solution respectively. GFP-pull-downs are performed separately for each SILAC state. Eluates are combined, separated on a one-dimensional gel into eight slices and in-gel digested. Resulting peptide mixtures are analyzed by high resolution LC-MS/MS on an LTQ-Orbitrap Velos. SILAC ratios are automatically quantified by MaxQuant. (B) SILAC peptide triplets representing peak profiles characteristic of background, constitutive and dynamic binders. (C) Data analysis plot of the ratio representing interaction specificity versus the ratio representing stimulus specificity of the interaction. Filled dots represent significant interactors and of these, constitutive interactors are depicted in blue. Dynamic interactors with enhanced binding to the bait protein are shown in red and those with reduced binding to the bait protein in green.

Figure 1

Analysis of interaction dynamics by QUBIC triple SILAC based quantitative mass spectrometry. (A) Experimental workflow for triple SILAC pull-downs to determine Wnt3a-dependent interaction dynamics. The cell line expressing the GFP-tagged protein of interest is light and medium SILAC labeled, the untransfected wild-type control cell line is heavy SILAC labeled. Cells are lysed after two hour treatment with Wnt3a (200 ng/mL) or vehicle solution respectively. GFP-pull-downs are performed separately for each SILAC state. Eluates are combined, separated on a one-dimensional gel into eight slices and in-gel digested. Resulting peptide mixtures are analyzed by high resolution LC-MS/MS on an LTQ-Orbitrap Velos. SILAC ratios are automatically quantified by MaxQuant. (B) SILAC peptide triplets representing peak profiles characteristic of background, constitutive and dynamic binders. (C) Data analysis plot of the ratio representing interaction specificity versus the ratio representing stimulus specificity of the interaction. Filled dots represent significant interactors and of these, constitutive interactors are depicted in blue. Dynamic interactors with enhanced binding to the bait protein are shown in red and those with reduced binding to the bait protein in green.

Figure 2

Dynamic APC interactome. (A) Results from a triple SILAC pull-down as described in Figure 1 using Wnt3a as the stimulus and GFP-APC as bait protein, plotted as explained in Figure 1C. Annotated filled circles represent specific interactors determined by box plot statistics of the fold-change distribution of unstimulated pull-down against control. Specific dynamic interactors with enhanced binding to APC upon Wnt stimulation are depicted in green; the ones with decreased binding are depicted in red. Significance thresholds for dynamic changes were obtained from a box plot of fold-change distribution of stimulated pull-down against unstimulated pull-down. Constitutive, specific interactors are shown in blue. (B) Same experiment as in (A) but with the fold-change distribution of stimulated pull-down against control on the x-axis. In this plot dynamic interactors move to the upper right-hand quadrant as can be seen for the proteins shown in bold.

Figure 3

Volcano plot to determine reproducible APC interactors. (A) Log2 ratios of the median of four pull-downs of GFP-APC against control (x-axis) are plotted versus −log10 of the p-values derived from a t-test. Proteins with a minimum 4-fold change combined with a p-value smaller than 0.1 are considered significant (red lines). (B) Same as (A) but for simulated pull-downs against controls.

Figure 4

Dynamic APC interactome visualized by a heat map and one-way hierarchical clustering. The three ratios of the triple SILAC pull-down (median of four experiments) are used to cluster the reproducible APC interactors (determined in Figure 3) by one-way hierarchical clustering. A green color value signifies specific binding to APC without Wnt stimulation (first column) or with Wnt stimulation (second column) in the heat map. The third column depicts the SILAC ratio of stimulated against unstimulated bait pull-down. In this column, a green color value represents enhanced binding to APC upon Wnt activation and a red color represents reduced binding. Constitutive interactors have no significant ratio and therefore appear in black. All ratio intensities are shown in log scale. Note that only those parts of the cluster that contain significant binders are depicted. Refer to Suppl. Figure 6 for the complete clustering (Supporting Information). Additionally, t-test results for the ratio reproducibility (Figure 3) were visualized in the right panel after the clustering process. Proteins with reproducible ratios (p-value < 0.1) are in blue and those above the threshold in yellow. KIFC3 does not meet the significance criteria for specific and reproducible APC binding (minimum ratio of 4 and p-value < 0.1) both without and with stimulus and is therefore greyed out in the figure.

Figure 5

(A) Dynamic Axin-1, (B) CtBP2 and (C) DVL2 interactomes. Heat map and one-way hierarchical clustering of SILAC ratios from biological duplicates of triple SILAC experiments performed with label swap (FWD and REV experiment). Only those parts of the cluster with significant ratio intensities are depicted. Proteins that do not fulfilling the significance criteria of reproducible detection with a minimum ratio of 4 in the forward and reverse pull-down for at least one stimulus state were greyed out. For color coding of the heat map see Figure 4. All ratio intensities are shown in log scale.

Figure 6

Overlap of APC and Axin-1 interactomes. Protein-protein interactions were drawn in Cytoscape, after importing the pull-down data from Figures 4 and 5A. Baits are depicted in yellow, shared APC and Axin-1 interactors in blue and unique interactors for APC and Axin-1 in purple and pink, respectively. Lines represent detected interactions. Green lines indicate enhanced interaction upon Wnt3a activation while red lines indicate reduced interactions upon Wnt3a activation. Line width reflects the SILAC ratio intensity for the dynamic interactors.