PROBER identifies proteins associated with programmable sequence-specific DNA in living cells

Abstract

DNA-protein interactions mediate physiologic gene regulation and may be altered by DNA variants linked to polygenic disease. To enhance the speed and signal-to-noise ratio (SNR) in the identification and quantification of proteins associated with specific DNA sequences in living cells, we developed proximal biotinylation by episomal recruitment (PROBER). PROBER uses high-copy episomes to amplify SNR, and proximity proteomics (BioID) to identify the transcription factors and additional gene regulators associated with short DNA sequences of interest. PROBER quantified both constitutive and inducible association of transcription factors and corresponding chromatin regulators to target DNA sequences and binding quantitative trait loci due to single-nucleotide variants. PROBER identified alterations in regulator associations due to cancer hotspot mutations in the hTERT promoter, indicating that these mutations increase promoter association with specific gene activators. PROBER provides an approach to rapidly identify proteins associated with specific DNA sequences and their variants in living cells.

Extended Data Fig. 1. PROBER specificity and optimization of motif concatemers, insert size and bait copy

a, PROBER-WB of canonical YY1, NF-κB, STAT1 DNA motifs and their nucleotide composition-matched scrambled controls + /− TNF-α or IFN-γ probed together with YY1, RelA, or STAT1 antibodies. b, Heatmap of a representing fold enrichment of signals, n = 1 biological replicate. c, PROBER-WB showing effect of single-copy, duplicate, triplicate, quadruplicate and quintuplicate YY1 motifs on fold enrichment, d, quantification of c representing mean enrichment, n = 2 biologically independent replicates. e, Trimeric NF-κB motif and matched scrambled sequences were cloned in pBait with different lengths of flanks at both ends to obtain inserts of varying sizes. The NF-κB motifs are shown as “N”, position of UAS elements are also shown. f, PROBER-WB showing the effect of insert size on RelA enrichment, and g, quantification of f representing mean enrichment, n = 2 biologically independent replicates. Note that increasing distance between NF-κB motifs and UAS beyond 25-nt stuffer flanks results in loss of enrichment because it puts the TFs outside BASU labeling radius. h, Nuclear plasmid copies after transfection of HEK293T cells with varying amounts of bait plasmid and 3 μg pSprayer; an SV40 Ori-less derivative of pBait with trimeric YY1 motif was used eliminate copy number increase by endogenous large T antigen, and i, resulting YY1 PROBER fold enrichment in response to bait copy number in h. n = 1 biological replicate.

Extended Data Fig. 2. Validation of YY1 interactors.

a, PROBER-WB of YY1 motif showing co-enrichment of ZHX1, ZHX2 and ZHX3, and b, quantification of enrichment normalized to BASU-Gal4DBD, n = 1 biological replicate. c, WB of normal and anti-YY1 siRNA treated HEK293T cells. Bar plot indicates YY1 levels normalized to β-actin, n = 2 biologically independent replicates. d, logFC (between control vs. YY1-knockdown condition) vs. average FC (over scramble controls) plot representing effect of YY1 knockdown on YY1 PROBER. Color codes are as indicated in Fig. 2a. e, Euler diagram and UpSet plot of overlapping ENCODE ChIP-seq peaks in HepG2 cells. f, Euler diagram and UpSet plot of overlapping ENCODE ChIP-seq peaks in K562 cells. In both UpSet plots, bottom panels indicate the combination of peak sets, and the number of peaks in each set. The middle panel indicates the size of the overlapping sets. The top panel indicates the relative enrichment of each combination.

Extended Data Fig. 3. Detection and validation of RelA and STAT1 interactors

a, logFC (between + TNF-α vs. -TNF-α condition) vs. average FC (over scramble controls) plot representing effect of TNF-α stimulation on NF-κB PROBER. Color codes are as indicated in Fig. 2a. b, WB of normal and anti-RelA siRNA treated HEK293T cells in presence of TNF-α. Bar plot indicates RelA levels normalized to β-actin, n = 2 biologically independent replicates. c, logFC (between control vs. RelA-knockdown condition) vs. average FC (over scramble controls) plot representing effect of RelA knockdown on NF-κB PROBER. Color codes are as indicated before. d, Differential analysis of proteins enriched in STAT1 PROBER-MS in –IFN-γ vs. +IFN-γ conditions. Red and cyan dots are as indicated before, pink dots indicate select DNA/chromatin binders with FDR above 0.25. e, logFC (between + IFN-γ vs. -IFN-γ condition) vs. average FC (over scramble controls) plot representing effect of IFN-γ stimulation on STAT1 PROBER, color codes as indicated in d. f, PWM of ETS and STAT1 motifs (Source: http://jaspar.genereg.net). Sequence of STAT1 motif used in PROBER is shown at the bottom.

Extended Data Fig. 4. PROBER-MS reflects endogenous DNA–protein interactions

a-c, SAINT score vs. fold-change (FC) scatter plots of endogenous BS1, BS2 and BS3 PROBER-MS, n = 3 biologically independent replicates. The 26-nt chromosomal sequences that were cloned in triplicate are shown on top of each plot, the central YY1 motifs are indicated in red. The ETS motif overlapping YY1 motif in BS3 is underlined. Proteins that were enriched (SAINT scores ≥ 0.9) are indicated in red (known DNA or chromatin binder) or cyan (not known to be a DNA or chromatin binder); known YY1 interactors are highlighted in red. d-f, NFRKB, GABPA and ELK1 ChIP-seq signal p-values at BS1, BS2 and BS3 from publicly available datasets, Integrated Genome Viewer (IGV) (https://software.broadinstitute.org/software/igv/) screenshots of approximately 1 kb region surrounding BS1, BS2 and BS3 are shown.

Extended Data Fig. 5. PROBER-WB in multiple cell lines and primary cells

a, PROBER-WB of YY1 motif in U2OS (Bone osteosarcoma), A549 (lung carcinoma), ReNcell^® CX (immortalized human neural progenitor), primary keratinocytes (NHEK), and primary dermal fibroblasts. Bar plots represent mean YY1-fold enrichment, n = 3 (for U2OS and ReNCell CX) and 2 (for A549, NHEK and fibroblasts) biologically independent replicates. b, SAINT score vs. fold-change (FC) scatter plots of triplicate YY1 motif (used in Fig. 1b), and c, triplicate 26-nt endogenous BS1 loci (used in Extended Data Fig. 4a) from U2OS cells, n = 3 biologically independent PROBER-MS replicates. Color codes are as described in Fig. 2a. d, Venn diagrams showing proteins enriched at triplicate YY1 motif and endogenous BS1 construct in U2OS cells and e, endogenous BS1 construct in HEK293T and U2OS cells. f, Differential analysis of proteins enriched at BS1 from HEK293T and U2OS PROBER-MS, color codes as indicated before. Dotted line represents FDR 0.25. g, Comparison of biotinylation (green smear) in HEK293T and U2OS cells in cell lysate and after enrichment by streptavidin pull-down. Note that BASU-GAL4 is minimally expressed in both cell types and visible in WB only after pull-down.

Extended Data Fig. 6. DNA affinity pull-down using an NF-κB.

a, SAINT score vs. fold-change (FC) scatter plots of DNA affinity pull-down with triplicate NF-κB motif from nuclear lysates of TNF-α stimulated and b, unstimulated HEK293T cells, n = 2 biologically independent replicates, color codes are as indicated in Fig. 2a. NF-κB family proteins are indicated in red text. c, Scatter plot comparing fold-change (FC) of proteins enriched (SAINT ≥ 0.9) by pull-down in TNF-α stimulated vs. unstimulated conditions. Blue dots indicate proteins enriched with TNF-α, green dots indicate proteins enriched in unstimulated condition, and red dots indicate proteins enriched under both conditions. d, Differential analysis of proteins enriched in NF-κB DNA affinity pull-down +TNF-α vs. -TNF-α, color codes are as indicated in a. Horizontal dotted line indicates FDR 0.25. e, PROBER vs. DNA pull-down (–TNF-α) fold-change scatter plot; blue dots indicate proteins enriched (SAINT ≥ 0.9) by PROBER, green dots indicate proteins enriched by DNA pull-down, and red dots indicate proteins enriched by both methods.

Extended Data Fig. 7. RelA BioID using BASU-RelA fusion.

a, Expression of BASU-RelA fusion protein compared to endogenous RelA, n = 1 biological replicate. b, SAINT score vs. FC scatter plots of RelA BioID in presence and absence of TNF-α, n = 3 biologically independent replicates. Color codes are as indicated in Fig. 2a, NF-κB family proteins are indicated in red text. c, PROBER vs. BioID (–TNF-α) fold-change scatter plot; blue dots indicate proteins enriched (SAINT ≥ 0.9) by PROBER, green dots indicate proteins enriched by DNA pull-down, and red dots indicate proteins enriched by both methods. d, Proximity Ligation Assay (PLA) of RelA and PHF21A in presence or absence of TNF-α. Nuclei are visualized with DAPI (blue), orange dots indicate PLA signal. The boxplot represents nuclear PLA signal obtained by counting orange dots in 8 representative transfected cells, the center is the median, lower and upper limits depict the first and third quartile, and the whiskers show minimum and maximum dot counts. ***P < 0.001, 4.03 × 10⁻⁴ (obtained by two-tailed Student’s t-test from 8 transfected cells, n = 1 biological replicate). e, Scatter plot comparing fold-change (FC) of proteins enriched (SAINT ≥ 0.9) by BioID in TNF-α stimulated vs. unstimulated conditions. Blue dots indicate proteins enriched with TNF-α, green dots indicate proteins enriched in unstimulated condition, and red dots indicate proteins enriched under both conditions. f, Differential analysis of proteins enriched in RelA BioID +TNF-α vs. -TNF-α, color codes as indicated in b. Horizontal dotted line indicates FDR 0.25. NF-κB family proteins and common RelA interactors that were not differentially enriched are indicated in red text.

Extended Data Fig. 8. C-BERST WB of chromosomal YY1 binding

a, C-BERST WB of centromeric α-satellite repeats as positive control showing enrichment of CENP-B and corresponding streptavidin blot, n = 2 biologically independent replicates. b, anti-FLAG ChIP-qPCR of BS1, BS2, BS3 loci and a gene desert negative control locus showing specific recruitment of dCas9-APEX2-mCherry fusion protein using sgBS1, sgBS2, and sgBS3. Tukey’s multiple comparison test performed, ns= not significant, ***P < 0.001, n = 2 biologically independent replicates. c, C-BERST WB of BS1, BS2, and BS3 showing no YY1 enrichment over sgNS control. Bar plots represent mean enrichment of 2 independent replicates.

Extended Data Fig. 9. Detection of differential TF recruitment at SNPs.

a, Sequence surrounding SNP rs2349075 showing both A- and G-alleles, and expression of CASP8 associated with rs2349075 G allele in sun exposed lower leg skin (Source- http://www.gtexportal.org/home/). The c-Jun motif overlapping rs2349075 is underlined. b, Luciferase assay of SNP rs2349075 A-and G-alleles showing higher reporter activity associated with G allele with phorbol ester treatment. Bar plots represent mean normalized expressions, n = 2 biologically independent replicates. Two-tailed Student’s t-test, *P < 0.05, 1.91 × 10⁻². c, PROBER-WB of SNPs rs2349075 A-and G- alleles in presence of PMA. Bar plots represent mean enrichment, n = 3 biologically independent replicates. Two-tailed Student’s t-test performed; *P < 0.05, 1.54 × 10⁻². d, Sequence surrounding SNP rs7132503 showing both A- and G-alleles, and expression of linked pseudogene RP1–102E24.10 in pancreas tissue (http://www.gtexportal.org/home/). The overlapping NF-κB motif is underlined. e, PROBER-WB of SNPs rs7132503 both A-and G- alleles in presence of TNF-α, bar plot represents mean enrichment, n = 2 biologically independent replicates. Two-tailed Student’s t-test performed, *P < 0.05, 4.86 × 10⁻². f, Episomal ChIP-qPCRs performed on plasmids encoding approximately 1 kb native chromosomal region surrounding G-or A-alleles of rs7132503 in presence of TNF-α. Bar plots represent mean enrichment, n = 4 biologically independent replicates. Two-tailed Student’s t-test performed, ***P < 0.001, 3.47 × 10⁻⁶. g, PROBER-WB on c-Jun binding SNP variants identified by SNP-SELEX. Normalized PROBER enrichment scores and area under the curve (AUC) values derived by SNP-SELEX experiment are indicated below.

Extended Data Fig. 10. PROBER with WT hTERT promoter and high-throughput compatibility.

a, Presence of ZNF148 and partial ZNF282 motifs in hTERT promoter, PWMs were downloaded from http://jaspar.genereg.net. b, PROBER-MS with chr5:1,295,260–1,295,218 region (single-copy native fragment) of hTERT promoter, color coding as indicated in Fig. 2a. c, PROBER-MS predicted interactors of chr5:1,295,260–1,295,218 region, DNA/chromatin binders are indicated in blue. d, siRNA-mediated knockdown of HDAC2, RBBP4, ZNF148 and ZNF281 in HEK293T cells. Bar plots represent mean relative expression, n = 3 biologically independent replicates, error bars represent SEM. e, TERT expression from WT hTERT loci in HEK293T after siRNA-mediated knockdown of HDAC2, RBBP4, ZNF148 and ZNF281. Bar plots represent mean relative expression, n = 3 biologically independent replicates, error bars represent SEM. Two-tailed t-test performed with Welch’s correction; *P < 0.05, 2.13 × 10⁻² (RBBP4) and 1.10 × 10⁻² (HDAC2); **P < 0.01, 8.76 × 10⁻³ (ZNF148) and 3.59 × 10⁻³ (ZNF281). f, SAINT score vs. fold-change (FC) scatter plot resulting from PROBER-MS of triplicate YY1 motif (used in Fig. 1b) in HEK293T cells, where MS samples were prepared by high-throughput compatible on-bead sample processing (gel-free purification). Color codes are as described in b. g, Venn-diagram showing proteins enriched at triplicate YY1 motif in PROBER-MS samples prepared by gel-based or on-bead processing.

Fig. 1:. PROBER detects sequence-specific DNA binding factors.

a, Schematic diagram of PROBER. b, PROBER-WB with quantification for the YY1 DNA motif and two nucleotide composition-matched scrambled controls (two-tailed Student’s t-test, **P < 0.01: 8.41 × 10⁻³ and 8.42 × 10⁻³, n = 3 biologically independent replicates). c, PROBER-WB with quantification for the NF-κB DNA motif ±TNF-α (two-tailed Student’s t-test, **P < 0.01: 1.59 × 10⁻³ and 1.61 × 10⁻³, n = 3 biologically independent replicates). d, PROBER-WB with quantification for the STAT1 DNA motif ±IFN-γ (two-tailed Student’s t-test, ***P < 0.001: 5.13 × 10⁻⁴ and 5.35 × 10⁻⁴, n = 3 biologically independent replicates. Bar graphs in b–d represent mean enrichment and the error bars represent s.e.m. CO, transcription coregulator; CR, chromatin regulator; HM, histone modifier; LC-MS/MS, liquid chromatography–tandem mass spectrometry; ori, origin of replication; TF, transcription factor.

Fig. 2:. PROBER-MS enriches transcription complexes.

a, SAINT score versus fold-change (FC) scatter plot of YY1 PROBER-MS (n = 2 biologically independent replicates). Proteins that were enriched (SAINT ≥ 0.9) are indicated in red (transcriptional regulator or known DNA or chromatin binder) or cyan (not known to be a DNA or chromatin binder); known YY1 interactors are highlighted in red. b, SAINT score versus FC scatter plot of YY1 PROBER-MS from anti-YY1 short interfering RNA-treated HEK293T cells (n = 2 biologically independent replicates). c, Differential analysis of proteins enriched in control versus YY1-knockdown conditions, highlighting proteins that are most affected by YY1 knockdown. d,e, SAINT score versus FC scatter plots of NF-κB PROBER-MS ±TNF-α (n = 2 biologically independent replicates). f, Differential analysis of proteins enriched in presence versus absence of TNF-α; the horizontal dotted line indicates a false discovery rate (FDR) of 0.25. g, SAINT score versus FC scatter plot of NF-κB PROBER-MS from anti-RelA short hairpin RNA-treated HEK293T cells in the presence of TNF-α (n = 2 biologically independent replicates). h, Differential analysis of proteins enriched in control versus RelA-knockdown conditions, highlighting proteins that are most affected by RelA knockdown (FDR < 0.25). i,j, SAINT score versus FC scatter plot of STAT1 PROBER-MS ±IFN-γ (n = 2 biologically independent replicates). k, The top enriched proteins for the YY1 motif (Y), NF-κB motif (N) (in the presence of TNF-α) and STAT1 motif (S) (in the presence of IFN-γ).

Fig. 3:. PROBER recapitulates endogenous chromatin–protein

a, PROBER-MS-enriched proteins (SAINT ≥ 0.9) at endogenous BS1, BS2 and BS3 loci from three biologically independent replicates; the edges in the network are experimentally determined interactions from STRING-db (https://string-db.org/). Proteins for which the binding was verified by ChIP-qPCR are indicated in red. The inset plot shows the empirical cumulative frequency distribution of experimentally determined interaction scores (from STRING-db) of all protein pairs sharing a binding site (red, blue, green) and the protein pairs that share no site (gray; BD, background distribution). b, ChIP-qPCR of BRD2, ZNF644, ZHX2, GABPA and a gene desert negative control (CTRL). The bar plots represent mean enrichment of n = 2 biologically independent replicates. *P < 0.05, **P < 0.01, ***P < 0.001 (two-tailed Student’s t-test).

Fig. 4:. PROBER provides a DNA-centric view of the interactome compared with DNA pull-down and BioID.

a, PROBER versus DNA pull-down fold-change scatter plot in the presence of TNF-α. Enrichment is defined as SAINT score ≥ 0.9. b, GO molecular function analysis of NF-κB PROBER- and DNA affinity pull-down-enriched proteins from TNF-α-stimulated HEK293T cells (only the top 10 enriched molecular functions are shown). c, PROBER versus BioID fold-change scatter plot in the presence of TNF-α. d, GO molecular function analysis of RelA BioID-enriched proteins from TNF-α-stimulated HEK293T cells (only the top 10 enriched molecular functions are shown). e, Venn diagrams showing the proteins enriched (SAINT ≥ 0.9) by NF-κB PROBER, DNA affinity pull-down and RelA BioID in the presence and absence of TNF-α.

Fig. 5:. PROBER differentially detects transcription factors and regulators as a function of SNVs.

a, The SNP eQTL rs7296179, both minor (C allele) and major (G allele), are shown the overlapping NF-κB motif. The violin plot indicates the expression of SLC5A8 from thyroid tissue (source: https://www.gtexportal.org), white line = median, black bar = interquartile range. Numbers on the x-axis indicate number of individuals. b, PROBER-WB of the rs7296179 C and G alleles. The bar plots represent the mean enrichment of n = 3 biologically independent replicates and the error bars represent the s.e.m. **P < 0.01, that is, 1.32 × 10⁻³ (two-tailed Student’s t-test). c, Scatter plots of SAINT score versus fold change of the rs7296179 C allele and G allele for n = 2 biologically independent replicates. Proteins that were enriched (SAINT ≥ 0.9) are indicated in red (transcriptional regulator or known DNA or chromatin binder) or cyan (not known to be a DNA or chromatin binder); known RelA and/or c-Rel interactors are indicated with red text and arrows. d, Differential analysis of proteins enriched in the C allele versus the G allele (color coding as in c). e, Episomal ChIP-qPCRs performed on plasmids encoding an approximately 1 kb native chromosomal region surrounding the C or G alleles of rs7296179 in the presence of TNF-α. Bar plots represent the mean enrichment of n = 4 biologically independent replicates and the error bars represent the s.e.m. ***P < 0.001, that is, 9.50 × 10⁻⁵ (RelA), 1.36 × 10⁻⁵ (p300) and 6.74 × 10⁻⁴ (SMARCC1) (two-tailed Student’s t-test).

Fig. 6:. Differential detection of transcription factors and regulators at cancer-associated hotspot munitions

a, Schematic diagram of the hTERT promoter showing the position of recurrent non-coding mutations C250T, C228T and A161C (not drawn to scale). Mutated bases are highlighted in red and the position of the ETS motifs is indicated. b, SAINT score versus fold-change scatter plots of the wild type, 250WT (chr5: 1295260–1295240 region), and the mutation, 250MT (chr5: 1295260–1295240 with the C250T mutation at the center) for n = 2 biologically independent replicates. Proteins that were enriched (SAINT score ≥ 0.9) are indicated in red (transcriptional regulator or known DNA or chromatin binder) or cyan (not known to be a DNA or chromatin binder), and known 250MT interactors are indicated with red text. c, PROBER-predicted 250MT interaction network representing all enriched proteins (SAINT score ≥ 0.9) at 250MT. The dotted lines indicate the proteins predicted by PROBER and the solid lines indicate known protein–protein interactions (BioGrid > 2 reported interactions). DNA or chromatin binders are shown in blue and ETS factors previously reported to bind C250T are highlighted in red. d, Differential analysis of proteins enriched in 250WT versus 250MT; the horizontal dotted line represents FDR = 0.25. Known C250T binders are highlighted in red text. e, SAINT score versus fold-change scatter plots of 228WT (chr5: 1295238–1295218 region) and 228MT (chr5: 1295238–1295218 region with the C228T mutation at the center) for n = 2 biologically independent replicates. f, PROBER-predicted 228MT interaction network representing all enriched proteins (SAINT score ≥ 0.9). g, Differential analysis of proteins enriched in 228WT versus 228MT; *P value of ZNF148 = 4.0 × 10⁻⁷. h, SAINT score versus fold-change scatter plots of 161WT (chr5: 1295171–1295151 region) and 161MT (chr5: 1295171–1295151 region with the A161C mutation at the center) for n = 2 biologically independent replicates. i, PROBER-predicted 228MT interaction network representing all enriched proteins (SAINT score ≥ 0.9). j, Differential analysis of proteins enriched in 161WT versus 161MT; *P value of HCFC1 = 7.2 × 10⁻⁶.