Introduction

DNA repair pathways counteract a wide spectrum of DNA lesions to protect the genome from detrimental mutations, breaks, and chromosome rearrangements. While some DNA lesions are directly removed by dedicated enzymes (e.g., oxidized DNA bases are readily restored by base excision repair), other and more deleterious lesions such as DNA interstrand crosslinks (ICLs) require precise coordination of multiple enzymatic activities to re-establish intact DNA. ICLs are highly cytotoxic lesions, whose repair is tightly coupled to DNA replication (Akkari et al, 2000; Räschle et al, 2008). A large number of proteins participate in ICL repair, defects in at least 22 of which are causative of Fanconi anemia (FA), a rare, inherited disease characterized by developmental birth defects, bone marrow failure, and cancer predisposition (Rageul & Kim, 2020). These factors can be functionally subdivided according to where they operate in the multistep FA ICL repair pathway (Wang, 2007; Ceccaldi et al, 2016; Rageul & Kim, 2020). First, the FA core complex (comprising FANCA, FANCB, FANCC, FANCE, FANCF, FANCG, FANCL, FANCM, FAAP20, and FAAP100) associates with damaged chromatin and monoubiquitylates the heterodimer FANCI-FANCD2 (ID2) via UBE2T (FANCT) (Garcia-Higuera et al, 2001; Smogorzewska et al, 2007; Hira et al, 2015; Rickman et al, 2015). Monoubiquitylated ID2 marks the activation of the FA pathway and associates with the ICL to promote repair of the crosslink via downstream effector proteins (Knipscheer et al, 2009; Douwel et al, 2014). These include DNA nucleases that nick one DNA strand on both sides of the ICL to unhook it (SLX4 (FANCP)-XPF (FANCQ)-ERCC1 complex), a translesion DNA synthesis (TLS) polymerase that bypasses the ICL adduct (REV1-Polζ), and homologous recombination (HR) proteins that repair the two-ended DNA double-strand break (DSB) (Rageul & Kim, 2020). This final DSB repair step is distinct from other HR processes, as it requires prior restoration of the repair template by TLS. Thus, HR and TLS must be tightly coordinated to ensure faithful ICL repair, but the proteins regulating these processes remain largely unknown. Here, we demonstrate that the protein SCAI (suppressor of cancer cell invasion) has a critical role in ICL repair via the FA pathway, operating at the interface between the TLS and HR steps to prevent erroneous repair of DSB intermediates via Polθ-dependent microhomology-mediated end joining (MMEJ), thereby ensuring faithful ICL resolution.

Results Loss of SCAI manifests with principal hallmarks of FA pathway deficiency

To identify novel factors involved in ICL repair, we carried out a genome-scale CRISPR-Cas9 dropout screen for genes required for survival in the presence of a low dose of the ICL-inducing drug mitomycin C (MMC), corresponding to 20% lethality (LD20). To this end, human RPE-1 cells with targeted knockout (KO) of p53 were transfected with a lentiviral sgRNA library and propagated in the presence or absence of MMC for 12 days (Fig 1A). Validating our screening approach, many FA and FA-associated genes as well as HR factors scored among the top hits (Figs 1B and EV1A; Dataset EV1). In fact, KO of 20 of the 22 known FA genes manifested with hypersensitivity to MMC in this screen (Fig 1B). Unexpectedly, the screen also revealed that sgRNAs targeting SCAI were selectively depleted from cells exposed to MMC (Fig 1B; Dataset EV1). SCAI was originally identified as a transcriptional regulator and suppressor of cell migration (Brandt et al, 2009) but was later found to play a role in DSB repair via interaction with 53BP1 (Hansen et al, 2016; Isobe et al, 2017). However, unlike SCAI, sgRNAs targeting 53BP1 did not show significant dropout in MMC-treated cells (Dataset EV1). Our screen thus suggested a previously unrecognized function of SCAI during ICL repair, which we set out to further explore. In accordance with our screen, SCAI KO cells were exquisitely sensitive to MMC and cisplatin, another ICL inducer, and this could be fully rescued by stable re-expression of SCAI in these cells (Figs 1C–E and EV1B and C). As observed for many established FA genes, SCAI KO cells displayed strong accumulation in G2 phase accompanied by an increased level of DNA damage foci following MMC treatment (Figs 1F–H and EV1D–H). Likewise, metaphase spreads from SCAI KO cells exhibited a marked increase in chromosome breaks/gaps and radial chromosome formation upon MMC treatment, a characteristic feature of FA patient cells (Fig 1I–K; García-de-Teresa et al, 2020). Again, all of these phenotypes were fully complemented by re-expression of ectopic SCAI (Fig 1F–K). We conclude that loss of SCAI hypersensitizes cells to ICL-inducing agents and phenocopies major hallmarks of defective ICL repair resulting from FA gene inactivation.

Figure 1. SCAI-deficient cells display major hallmarks of FA gene dysfunction

Schematic outline of genome-scale CRISPR-Cas9 screen for genes whose KO sensitizes human RPE-1 cells to MMC. LD20, 20% lethal dose; NGS, next-generation sequencing. DrugZ analysis of sgRNA depletion in CRISPR screen in (A) following low-dose MMC treatment (n = 2 technical replicates). FA genes are highlighted in blue; SCAI is highlighted in red. Immunoblot analysis of U2OS WT, U2OS/SCAI KO, and U2OS/SCAI KO cells stably reconstituted with Strep-HA-SCAI (U2OS/SCAI KO/Strep-HA-SCAI). Clonogenic survival of U2OS WT, U2OS/SCAI KO, and U2OS/SCAI KO/Strep-HA-SCAI cells subjected to indicated doses of MMC for 24 h (mean ± SEM; n = 3 independent experiments). As in (D), except that cells were treated with Cisplatin for 24 h (mean ± SEM; n = 3 independent experiments). U2OS WT, U2OS/SCAI KO, and U2OS/SCAI KO/Strep-HA-SCAI cells were treated or not with MMC (9 nM) for 48 h, fixed, and co-stained with PCNA antibody and DAPI. Cell cycle distribution was analyzed by quantitative image-based cytometry (QIBC) (≥ 2,000 cells analyzed per condition). Data from a representative experiment are shown. U2OS WT, U2OS/SCAI KO, and U2OS/SCAI KO/Strep-HA-SCAI cells were treated or not with MMC (90 nM) for 1 h, fixed 24 h later, and co-stained with RPA2 antibody and DAPI. RPA2 foci were quantified by QIBC (≥ 3,000 cells analyzed per condition; mean ± SD; n = 3 independent experiments; *P < 0.05; ns, not significant, two-tailed paired t-test). As in (G), except that cells were co-stained with γH2AX antibody and DAPI (≥ 3,000 cells analyzed per condition; mean ± SD; n = 3 independent experiments; *P < 0.05; **P < 0.01; ns, not significant, two-tailed paired t-test). Experimental workflow for metaphase chromosome morphology analysis (top) and representative images of metaphase spreads from indicated cell lines treated or not with MMC (bottom). DNA was stained with DAPI. Scale bars, 10 µm. Quantification of radial chromosomes in (I) (mean ± SD; 180 cells analyzed per condition; n = 3 independent experiments; *P < 0.05; **P < 0.01, ns, not significant, two-tailed t-test). Quantification of chromosomal breaks/gaps in (I) (mean ± SEM; 99 metaphase cells analyzed for each condition pooled from three independent experiments; **P < 0.01; ****P < 0.0001, ns, not significant, Mann–Whitney U test). Click here to expand this figure.

Figure EV1. SCAI-deficient cells display major hallmarks of FA gene dysfunction (related to Figs  and )

GO term analysis of significant hits (NormZ < −3) in CRISPR-Cas9 screen in Fig 1A, using Reactome pathways from PANTHER16.0. Clonogenic survival of U2OS WT and U2OS/SCAI KO cells subjected to indicated doses of MMC for 24 h (mean ± SEM; n = 3 independent experiments). As in (B), except that cells were treated with indicated doses of cisplatin for 24 h (mean ± SEM; n = 3 independent experiments). Scatter plot showing cell cycle distribution of cells in Fig 1F. Light grey, G1 phase; dark grey, S phase; red: G2/M phase. Proportion of cells in G2/M phase is indicated. U2OS WT, U2OS/SCAI KO, and U2OS/SCAI KO/Strep-HA-SCAI cells were treated or not with MMC (90 nM) for 1 h, fixed 24 h later, and co-stained with 53BP1 antibody and DAPI. 53BP1 foci were quantified by QIBC (≥ 3,000 cells analyzed per condition; mean ± SD; n = 3 independent experiments; *P < 0.05; two-tailed paired t-test). As in (E), except that cells were stained with RAD51 antibody (≥ 3,000 cells analyzed per condition; mean ± SD; n = 3 independent experiments; *P < 0.05; ns, not significant, two-tailed paired t-test). Representative images of the experiments in Fig 1G and H. Scale bar, 10 µm. Representative images of the experiments in (E) and (F). Scale bar, 10 µm. Immunoblot analysis of FANCD2 siRNA knockdown efficiency in U2OS cells. Clonogenic survival of U2OS and U2OS/SCAI KO cells transfected with non-targeting control (CTRL) or FANCD2 siRNAs and subjected to indicated doses of MMC for 24 h (mean ± SEM; n = 3 independent experiments). Immunoblot analysis of U2OS WT and U2OS/SCAI KO cells harvested at the indicated times after exposure to MMC (0.5 µM). Preventing FA pathway activation alleviates ICL hypersensitivity of SCAI-deficient cells

To better define the emerging role of SCAI in ICL repair, we carried out a complementary genome-scale CRISPR-Cas9 screen for genes whose loss suppresses the hypersensitivity of SCAI-deficient cells to MMC. To this aim, SCAI KO cells transduced with a lentiviral sgRNA library were propagated in the presence of a near-lethal dose (LD80) of MMC (Fig 2A). Strikingly, gene ontology (GO) term analysis revealed that FA pathway components were the most enriched class of genes whose inactivation conferred significantly increased resistance to MMC in SCAI KO cells (Fig 2B and C). These comprised FA core complex factors and associated proteins (FANCA, FANCB, FANCC, FANCF, FANCL, FAAP20, and FAAP100), the ID2 complex, and proteins regulating its deubiquitylation (USP1 and WDR48), all of which ordinarily have critical roles in activating the FA pathway to protect against ICL toxicity (Fig 2B and C; Dataset EV2; Ceccaldi et al, 2016; Rageul & Kim, 2020). By contrast, effectors of ICL repair via this pathway functioning downstream of ID2 ubiquitylation did not score as hits in this screen (Dataset EV2). Genes encoding factors involved in chromatin remodeling via histone acetylation and regulators of cell proliferation and survival via p53 also conferred resistance to MMC in SCAI KO cells but were far less prominently represented than FA genes (Fig 2C; Dataset EV2). Verifying these screen results, we found that FANCA depletion by siRNA largely restored survival of SCAI KO cells exposed to MMC and suppressed the accumulation of DSBs (Fig 2D–G). Knockdown of FANCD2 similarly alleviated MMC hypersensitivity of SCAI KO cells (Fig EV1I and J). Notably, SCAI KO conferred much stronger MMC hypersensitivity than FANCA or FANCD2 knockdown by siRNAs in a U2OS background (Figs 2D and E, and EV1I and J). To exclude the possibility that this was a consequence of residual FA pathway activation due to incomplete knockdown efficiency of the siRNAs, we knocked out FANCA in U2OS and U2OS SCAI KO cells (Fig 2H). This confirmed that SCAI KO cells are indeed more sensitive to MMC than FANCA KO cells, and that loss of FANCA strongly alleviates the hypersensitivity of SCAI KO cells to MMC (Fig 2I and J). Importantly, whereas FANCD2 monoubiquitylation upon MMC treatment was abolished by FANCA KO as expected, loss of SCAI had no impact (Figs 2K and EV1K). Collectively, these data suggest that SCAI has an essential role in ensuring proper repair of ICLs once their processing via the FA pathway is initiated, but not for ID2 ubiquitylation and FA pathway activation per se.

Figure 2. Preventing FA pathway activation alleviates ICL hypersensitivity of SCAI-deficient cells

Schematic outline of genome-scale CRISPR-Cas9 screen for genes whose KO suppresses MMC hypersensitivity of SCAI KO cells. LD80, 80% lethal dose; NGS, next-generation sequencing. MaGECK analysis of sgRNA enrichment in CRISPR screen in (A) following MMC treatment (n = 3 technical replicates; false discovery rate (FDR) of 0.2 indicated by dotted line). FA genes are highlighted in blue. GO term analysis of significantly enriched genes (FDR < 0.2) in CRISPR-Cas9 screen in (A), using Reactome pathways from PANTHER16.0. Immunoblot analysis of FANCA siRNA knockdown efficiency in U2OS cells. Clonogenic survival of U2OS and U2OS/SCAI KO cells transfected with non-targeting control (CTRL) or FANCA siRNAs and subjected to indicated doses of MMC for 24 h (mean ± SEM; n = 3 independent experiments). U2OS and U2OS/SCAI KO cells transfected with indicated siRNAs for 48 h were treated or not with MMC (90 nM) for 1 h, fixed 24 h later, and co-stained with RPA2 antibody and DAPI. RPA2 foci were quantified by QIBC (≥ 3,000 cells analyzed per condition; mean ± SD; n = 3 independent experiments; *P < 0.05; ns, not significant, two-tailed paired t-test). As in (F), except that cells were stained with γH2AX antibody (≥ 3,000 cells analyzed per condition; mean ± SD; n = 3 independent experiments; **P < 0.01; ns, not significant, two-tailed paired t-test). Immunoblot analysis of the indicated U2OS cell lines. Clonogenic survival of U2OS and U2OS/FANCA KO cells subjected to indicated doses of MMC for 24 h (mean ± SEM; n = 3 independent experiments). Clonogenic survival of U2OS, U2OS/SCAI KO, U2OS/FANCA KO, and U2OS/FANCA+SCAI double KO (DKO) cells subjected to indicated doses of MMC for 24 h (mean ± SEM; n = 3 independent experiments). Immunoblot analysis of U2OS, U2OS/SCAI KO, U2OS/FANCA KO, and U2OS/FANCA SCAI DKO cell lines exposed or not to MMC as indicated. SCAI promotes replication-coupled ICL repair downstream of ID2 ubiquitylation

To elucidate how SCAI functions in ICL repair we used Xenopus egg extracts, which efficiently recapitulate the replication-coupled repair of a plasmid containing a site-specific cisplatin ICL (pICLpt) (Räschle et al, 2008). In this system, two replisomes quickly converge on the lesion (Fig 3A, i). Upon collision, CMG is first ubiquitylated by TRAIP and unloaded by p97 (Fig 3A, ii) (Fullbright et al, 2016; Wu et al, 2019). One of the leading strands is then extended to within one nucleotide (nt) of the crosslink (−1 position) (Räschle et al, 2008), at which point one of the forks undergoes reversal to produce a substrate suitable for DNA incisions (Fig 3A, iii) (Amunugama et al, 2018). Ubiquitylated ID2 localizes to the ICL and promotes incisions by the SLX4-XPF-ERCC1 complex (Fig 3A, iv), generating a DSB in one of the daughter molecules while leaving a gap containing an adduct in the other (Knipscheer et al, 2009; Douwel et al, 2014). The adducted molecule is restored by TLS in a two-step process that involves insertion across the adducted base by an unknown polymerase, and extension past the adduct by REV1-Polζ (Fig 3A, v) (Budzowska et al, 2015). Finally, the DSB is repaired by HR utilizing the intact daughter molecule as a template (Fig 3A, vi–vii; Long et al, 2011).

Figure 3. SCAI promotes replication-coupled ICL repair

Current model of ICLpt repair in Xenopus egg extracts (Amunugama et al, 2018). pICLpt was isolated via plasmid pull down at the indicated times after incubation in Xenopus egg extract in the presence or absence of CDC7i (100 µM) and associated proteins were analyzed by immunoblotting. pICLpt was replicated in egg extracts in the presence of [α-32P]dATP for the indicated times, and reactions were analyzed by native agarose gel electrophoresis. The p97 inhibitor NMS-873 (p97i; 200 μM) was supplemented to the reaction where indicated. Note that in the absence of p97 activity, CMGs are no longer unloaded from the plasmid, leading to accumulation of replication intermediate products (RI) (Fullbright et al, 2016). OC, open circular; SC, supercoiled. Samples from (C) were recovered via plasmid pull down at the indicated time points as in (B) and analyzed by immunoblotting. pICLpt was replicated in mock- or SCAI-C-depleted egg extracts, and samples collected at the indicated time points were analyzed by immunoblotting. pICLpt was replicated in mock- or SCAI-depleted egg extract in the presence of [α-32P]dATP for the indicated times, and reactions were analyzed by native agarose gel electrophoresis. ΔSCAI-C and ΔSCAI-N denote SCAI immunodepletion with an antibody raised against the C or N terminus of SCAI, respectively; RI, replication intermediates; OC, open circular; SC, supercoiled. Schematic of pICLpt illustrating the SapI site, which is regenerated upon replication-coupled repair (Knipscheer et al, 2009). Quantification of SapI regeneration in mock or SCAI-depleted extracts. Note that plasmids containing a SapI site but no ICL account for ~ 5–7% of each pICLpt preparation. Primary data are shown in Fig EV2F and G. A representative of two independent experiments is shown. Schematic of intermediates and extension products generated by AflIII digest of pICLpt. pICLpt was replicated in mock- or SCAI-depleted egg extract in the presence of [α-32P]dATP for the indicated times, and reactions were digested with AflIII and analyzed on a denaturing polyacrylamide gel. Stalling points relative to the ICL site are indicated. Schematic of intermediates and extension products generated by PsiI+XhoI double digest of pICLpt. Samples in (J) were digested with PsiI+XhoI and analyzed on a denaturing polyacrylamide gel. Stalling points relative to the ICL site are indicated. Quantification of extensions with deletions in (L) at 240 min (mean ± SEM; n = 6 independent experiments; **P < 0.01; two-tailed paired t-test).

Consistent with the role of SCAI in promoting ICL repair in human cells, SCAI was efficiently recruited to the ICL-containing plasmid in a replication-dependent manner (Figs 3B and EV2A). SCAI recruitment to the ICL occurred early in the reaction and was unaffected by inhibition of p97, which blocks CMG unloading and downstream unhooking of the ICL (Fig 3C and D, compare lanes 4–8 to 9–13) (Fullbright et al, 2016; Wu et al, 2019). To monitor the impact of SCAI loss on ICL repair, we replicated pICLpt in mock- or SCAI-depleted egg extracts. As observed in human cells, FANCD2 monoubiquitylation occurred normally in the absence of SCAI (Fig 3E). Consistently, the appearance of incisions on parental DNA was also largely unaffected by SCAI immunodepletion with either of two independent antibodies (Fig EV2B–G; note that upon SCAI-N immunodepletion incised strands are stabilized (Fig EV2F, lanes 6–10), likely because this antibody but not the SCAI-C antibody also co-depletes CtIP (Dataset EV4)). Notably, however, SCAI immunodepletion led to an accumulation of replication-dependent well products during pICLpt replication (Fig 3F, compare lanes 4–5, 9–10, and 14–15), which were previously suggested to arise from HR events (Long et al, 2011; Semlow et al, 2016). Despite the increase in well product formation, regeneration of the SapI site, which is mediated by error-free repair, was completely abolished in the absence of SCAI, indicating a failure to complete HR (Figs 3G and H, and EV2E–G; Long et al, 2011). To probe the impact of SCAI depletion on pICLpt replication, we analyzed replication intermediates on a denaturing acrylamide gel following AflIII digestion (Fig 3I). Nascent strands in SCAI-depleted extracts approached the crosslink with similar kinetics as in the mock-depleted reaction (−1 position), indicating that fork convergence and CMG unloading occurred normally in the absence of SCAI (Fig 3J; compare lanes 1–2 and 6–7; Fig 3A, i–ii). However, SCAI-depleted extracts exhibited a modest delay in performing TLS across the adduct, as evidenced by the prolonged presence of the nascent strand product at the 0 position (Fig 3J; compare lanes 4–5 and 9–10; Fig EV2H). Strikingly, despite the mild delay in TLS and lack of HR, we detected an increase in extension product formation when SCAI was absent (Fig 3J; compare lanes 4–5 and 9–10; Fig EV2H). Resolution of extension products by a different restriction digest (Fig 3K) revealed a defined deletion product that accumulated in SCAI-depleted egg extracts (Figs 3L and M, and EV2I; note that mock-depleted extracts display variable deletion product formation, as previously reported (Budzowska et al, 2015), and this was consistently increased upon SCAI immunodepletion), suggesting that some of the DNA ends undergo repair by an alternative, HR-independent mechanism. We conclude that SCAI depletion in egg extracts corrupts ICL repair downstream of ID2 ubiquitylation, leading to a TLS delay, loss of HR-mediated repair, and appearance of extension products containing deletions.

Click here to expand this figure.

Figure EV2. SCAI promotes replication-coupled ICL repair (related to Fig )

A. Samples in Fig 3B were replicated in the presence of [α-32P]dATP and analyzed by native agarose gel electrophoresis. RI, replication intermediates; OC, open circular; SC, supercoiled. B. SCAI-C immunoblot analysis of Xenopus egg extracts (NPE) subjected to immunodepletion with SCAI-C, SCAI-N, or an IgG control antibody. C. SCAI-N immunoblot analysis of samples from (B). D. Immunoblot analysis of Xenopus egg extracts subjected to immunodepletion with antibodies targeting the C-terminal (SCAI-C) or N-terminal (SCAI-N) region of SCAI or an IgG control. Asterisks denote antibody cross-reactivity. Note that SCAI-N but not SCAI-C immunodepletion also co-depletes CtIP. E. Schematic of the products generated by HincII or HincII-SapI digest of pICLpt. F, G. pICLpt was replicated in mock- or SCAI-depleted extracts and samples were digested with HincII (F) or HincII and SapI (G) and analyzed by agarose gel electrophoresis. DSB repair by HR restores the SapI site (Long et al, 2011). pQuant is used as a recovery control (Knipscheer et al, 2012) and the quantification of this experiment is shown in Fig 3H. H. pICLpt was replicated in mock- or SCAI-N-depleted egg extracts in the presence of [α-32P]dATP. Samples were digested with AflIII and analyzed on a denaturing polyacrylamide gel. Stalling points relative to the ICL site are indicated. See Fig 3I for schematic of intermediates and extension products generated by AflIII digest of pICLpt. I. Samples from (H) were digested with PsiI and XhoI and analyzed on a denaturing polyacrylamide gel. Stalling points relative to the ICL site are indicated. See Fig 3I for schematic of intermediates and extension products generated by PsiI and XhoI double digest of pICLpt. SCAI interacts with Polζ but prevents erroneous ICL repair independently of Polζ

To explore potential interactions between SCAI and ICL repair factors, we performed label-free mass spectrometry analysis of SCAI immunoprecipitates (IPs) from egg extracts to identify its interacting partners. Consistent with a role of SCAI in ICL repair, combined analysis of SCAI IPs with either antibody showed predominant enrichment of many FA proteins, as well as transcription and chromatin remodeling factors (Fig 4A; Dataset EV3). Strikingly, all five subunits of the polymerase ζ (Polζ) complex (REV1, REV3, REV7, POLD2, and POLD3) were strongly enriched in SCAI IPs (Fig 4A). Correspondingly, SCAI was enriched in REV1, REV7, and REV3 IPs (Fig 4B). SCAI immunodepletion with either antibody co-depleted REV3 and to a lesser extent REV1 and REV7 (Figs 4C and EV2D; Dataset EV4). This suggested that SCAI is tightly associated with REV1-Polζ in egg extracts, and that the TLS delay observed in the absence of SCAI is likely caused by co-depletion of REV1-Polζ. In contrast, although SCAI IPs also contained many FA pathway activators, depletion of SCAI did not functionally co-deplete the FA core complex as evidenced by intact ID2 monoubiquitylation during replication-coupled ICL repair (Figs 3E and EV2D; Dataset EV4). In accordance with an interaction between SCAI and the Polζ complex, these proteins also accumulated with similar kinetics on plasmids containing a site-specific DNA–protein crosslink (DPC), whose repair occurs in the absence of DSB formation and ID2 but requires Polζ for bypass of the DNA–peptide adduct (Fig EV3A and (Duxin et al, 2014; Gallina et al, 2021)). In this setting, SCAI depletion specifically delayed Polζ-mediated bypass of the peptide adduct, as evidenced by the specific persistence of −1, 0, and +1 nascent strand products compared to the control reaction (Fig EV3B–D). SCAI-Polζ interaction was also readily observed in human cells and was largely mediated by REV3 (Figs 4D and EV3E and F). Inspection of the REV3 sequence revealed a conserved region within its PCD domain that shares notable homology with AHDC1, another SCAI interactor (Fig 4E) (Hansen et al, 2016). Indeed, for both REV3 and AHDC1, this region was required for their interaction with SCAI in human cells (Figs 4F and G, and EV3G). Importantly, a Xenopus REV3 peptide spanning this sequence efficiently bound purified recombinant SCAI, demonstrating that the SCAI-REV3 interaction is direct (Fig EV3H and I). Finally, in line with a potential role of SCAI in regulating REV1-Polζ via direct interaction independently of DSB repair, we found that SCAI is also enriched at UV-C-damaged chromatin unlike 53BP1 and that SCAI KO cells show moderate sensitivity to UV-C radiation (Fig EV4A–I; Dataset EV5). We conclude that SCAI is tightly associated with REV1-Polζ via a conserved region in REV3.

Figure 4. SCAI interacts with Polζ but protects against erroneous ICL repair independently of Polζ

Analysis of SCAI-interacting proteins in Xenopus egg extracts. Volcano plot shows enrichment of proteins in both SCAI-C and SCAI-N immunoprecipitates (IPs) compared to an IgG control, plotted against the P-value (n = 4 independent experiments; permutation-based FDR < 0.01, s0 = 2). SCAI, REV7, REV1, and REV3 immunoprecipitates (IP) in NPE were immunoblotted with the indicated antibodies. Asterisks denote antibody cross-reactivity. Whole proteome MS analysis of mock- versus SCAI-depleted egg extracts. The volcano plot shows the difference in abundance of proteins between the mock reaction and SCAI-depleted samples (with either N or C antibodies) (X-axis), plotted against the P-value resulting from two-tailed Student’s t-test (Y-axis). Proteins significantly down-regulated (FDR < 5%) in SCAI-depleted extracts are highlighted in red (n = 4 biochemical replicates; FDR < 5% corresponds to a permutation-based FDR-adjusted q-value of < 0.05). GFP IPs from U2OS or U2OS/GFP-SCAI cells transfected with indicated siRNAs were immunoblotted with indicated antibodies. Note that a small fraction of REV7 is still immunoprecipitated with GFP-SCAI in REV3 knockdown cells. This could be due to incomplete knockdown, and/or additional interactions of SCAI with the REV1-Polζ complex that are independent of REV3. Schematic of SCAI interaction with the REV1-Polζ complex. The SCAI-interacting region of human REV3 and its alignment with a homologous region in human AHDC is indicated. NTD, N-terminal domain; PCD, positively charged domain; Pol, polymerase domain; CTD, C-terminal domain. GFP IPs from U2OS cells transfected with indicated REV3-GFP expression constructs were immunoblotted with indicated antibodies. As in (F), except that U2OS or U2OS/GFP-SCAI cells were transfected with FLAG-NLS-REV3(995–1194) expression plasmid. Mock-, SCAI-, REV1-, or SCAI/REV1-depleted egg extracts were analyzed by immunoblotting with indicated antibodies. Asterisks denote antibody cross-reactivity. pICLpt was replicated in egg extracts immunodepleted with the indicated antibodies and processed as in Fig 3J and L. pICLpt was replicated in egg extracts immunodepleted with indicated antibodies, isolated at various times via plasmid pull down, and associated proteins were analyzed by immunoblotting. Click here to expand this figure.

Figure EV3. SCAI interacts with Polζ (related to Fig )

Heat map depicting the mean of the Z-scored Log2 label-free quantification LFQ intensity from four biochemical replicates of pCTRL and pDPCLeads replication in Xenopus egg extracts (data originally published in Larsen et al (2019)). Where indicated, Geminin was added to block DNA replication, and ubiquitin-vinyl sulfone (Ub-VS) was added to deplete the pool of free ubiquitin from the extracts. pDPCLeads was replicated in mock-, SCAI-C-, and SCAI-N-depleted egg extracts in the presence of [α-32P]dATP. Reactions were analyzed by native agarose gel electrophoresis. Red arrowheads indicate accumulation of open circular (OC) molecules caused by a TLS defect. Nascent leading strand and extension products generated upon FspI+AatII digest of pDPC. Double digestion generates shorter damaged and longer undamaged extension products. The CMG helicase is depicted in green and the crosslinked M.HpaII protein in grey. pDPC was replicated in mock- or SCAI-depleted Xenopus egg extract in the presence of [α-32P]dATP. Samples were digested with FspI+AatII and analyzed on a denaturing polyacrylamide gel. Stalling points relative to the DPC site are indicated. U, undamaged; D, damaged extension product. U2OS cells or derivative lines stably expressing GFP or GFP-SCAI were subjected to GFP IP followed by immunoblotting with indicated antibodies. U2OS WT or SCAI KO cells that were transfected with REV3-GFP where indicated were subjected to IP with IgG or SCAI antibody followed by immunoblotting. GFP IPs from U2OS cells transfected with indicated GFP-AHDC1 expression constructs were analyzed by immunoblotting. Alignment of the SCAI-interacting regions of human and Xenopus REV3 proteins. Asterisk indicates positions with a conserved amino acid; colon indicates conservation between amino acids with strongly similar properties; period indicates conservation between amino acids with weakly similar properties. Recombinant GST or GST-xSCAI proteins incubated or not with Biotin-xREV3 peptide (aa 1110–1179) were subjected to streptavidin pull down and analyzed by Coomassie staining. Click here to expand this figure.

Figure EV4. SCAI is recruited to UV-induced DNA lesions (related to Fig )

Sperm chromatin was left untreated or exposed to UV-C (2,000 J/m2), incubated in HSS/NPE mix in the presence of [α-32P]dATP and nucleotide incorporation into chromatin was analyzed at the indicated time points via native agarose gel electrophoresis. Quantification of data in (A) (mean ± SEM; n = 3 independent experiments). Schematic outline of CHROMASS workflow to analyze protein recruitment to UV-damaged chromatin. Sperm chromatin left untreated or irradiated with UV-C (2,000 J/m2) was incubated in Xenopus egg extract for 30 min, isolated by sucrose cushion centrifugation, and analyzed by label-free mass spectrometry (MS). Protein recruitment to UV-damaged chromatin compared to an undamaged control. Volcano plot shows enrichment of individual proteins (UV/mock ratio) plotted against the P-value (n = 4 independent experiments; FDR < 0.05, s0 = 0.5). Term enrichment analysis showing GO terms corresponding to proteins significantly recruited to UV-C-damaged chromatin (Dataset EV5). All displayed terms were significant with P < 0.02, as determined through Fisher exact testing with Benjamini–Hochberg correction. Sperm chromatin left untreated or irradiated with UV-C (2,000 J/m2) was isolated at the indicated time points and analyzed by immunoblotting. Representative images of GFP-SCAI and GFP-Polη recruitment to UV-C laser micro-irradiation in U2OS cells at indicated time points. Scale bar, 10 µm. U2OS cells stably expressing GFP-SCAI or transiently transfected with GFP-Polη were subjected to UV-C laser micro-irradiation. At indicated time points, GFP fluorescence intensities at damage sites over the nuclear background were quantified. Recruitment was normalized to the time point of maximal recruitment (mean ± SEM; n = 3 independent experiments; at least 30 cells analyzed per condition). Clonogenic survival of U2OS cells subjected to indicated doses of UV-C (mean ± SEM; n = 3 independent experiments).

Because immunodepletion of SCAI co-depletes REV1-Polζ (Fig EV2D), we next addressed whether erroneous ICL repair and the appearance of deletions were caused by REV1-Polζ co-depletion and/or a TLS defect. Importantly, unlike SCAI immunodepletion, the absence of REV1-Polζ did not increase deletion product formation, although a TLS delay was apparent (Fig 4H and I, compare lanes 4–5 and 14–15). While REV1 depletion partially co-depleted SCAI (Fig 4H), the residual SCAI pool still underwent enrichment at the ICL plasmid in the absence of REV1-Polζ (Fig 4J, compare lanes 5–7 and 8–10), preventing the appearance of extension products containing deletions (Fig 4I, compare lanes 14–15 and 19–20). Thus, although SCAI associates with REV1-Polζ and may thereby also contribute to TLS, its function in suppressing deletions during ICL repair is not shared by REV1-Polζ. This suggests both REV1-Polζ-dependent and -independent functions of SCAI in ICL repair.

SCAI prevents microhomology-mediated end joining by Polθ during ICL repair

We next addressed the mechanism of error-prone DSB repair triggered by the absence of SCAI.

Although 53BP1 was previously shown to interact with and recruit SCAI to DSBs (Hansen et al, 2016; Isobe et al,