lnc-Helf is increased in mouse and human hepatic fibrosis

We previously identified differentially expressed lncRNAs between mouse normal and fibrotic livers [14]. From that study, we noted that lncRNA ENSMUST00000147617 (lnc-Helf) was increased in fibrotic liver (Additional file 1: Fig. S1A). To confirm this result by qRT–PCR, the RNA level of lnc-Helf was detected in fibrotic livers of mice treated with BDL or CCl4 for various time periods, and the data revealed that the level of lnc-Helf was markedly increased with persistent injury (Fig. 1A, B). Subsequently, 5′- and 3′-RACE assay in mouse liver demonstrated that lnc-Helf was a 680 nt transcript, consistent with the ensemble database (Fig. 1C; Additional file 1: Fig. S1B). Moreover, sequence homology searches identified a clear lnc-HELF homologous transcript in the human genome with 70% sequence similarity (Additional file 1: Fig. S1C, D). Cell fractionation followed by qRT–PCR and fluorescence in situ hybridization (FISH) assays revealed that lnc-Helf was located both in the nucleus and cytoplasm of primary HSCs and single-cell suspensions from the liver (Fig. 1D; Additional file 1: Fig. S1E, F). As expected, the coding potential calculator 2 (CPC2) and coding potential assessment tool (CPAT) demonstrated that lnc-Helf had no protein coding potential. To assess the expression of lnc-Helf in various cell types of healthy and fibrotic livers, we have isolated HSCs, HCs, HMs, and liver sinusoidal endothelial cells (LSECs) from livers treated with or without CCl4 and found that lnc-Helf was mainly expressed in primary HSCs, followed by HMs, rather than HCs and LSECs (Fig. 1E). Notably, lnc-Helf was upregulated in HSCs and HMs of fibrotic livers compared to normal livers (Fig. 1E). However, lnc-Helf was minimally expressed in AML12 cells, LX-2 cells, RAW264.7 cells, human umbilical vein endothelial cells (HUVECs), and mouse BMMs (Additional file 1: Fig. S1G). Moreover, the expression of lnc-Helf was also significantly upregulated at day 7 and day 14 in activated HSCs, compared with day 3 HSCs (Fig. 1F). However, recombinant TGFβ did not regulate the expression of lnc-Helf in primary HSCs (Additional file 1: Fig. S1H). To correlate these findings with data from patients, we tested the RNA level of human lnc-HELF in 6 healthy livers and 28 fibrotic livers, and the data revealed that lnc-HELF was markedly increased in the livers of subjects with fibrosis than it was in individuals with normal livers (Fig. 1G). However, no correlation was found with the level of ACTA2, COL1α1, ALT, and AST (Additional file 1: Fig. S1I–L). Altogether, these data demonstrate that lnc-Helf is increased in mouse and human fibrotic livers, with activated HSCs and HMs.

Fig. 1

lnc-Helf is increased in mouse and human hepatic fibrosis. A, B The expression of lnc-Helf and Acta2 (α-SMA) were analyzed by qRT–PCR in livers from mice that underwent CCl4 treatment or mice that underwent BDL for different timepoints. C The PCR products from the 5'-RACE procedure and 3'-RACE procedure underwent agarose gel electrophoresis. D The nuclei or cytoplasm of single-cell suspensions from the normal liver were isolated, and qRT–PCR analysis detected the expression of lnc-Helf, Neat1, and Gapdh. E qRT–PCR was used to assess the expression of lnc-Helf in HCs, HSCs, HMs, and LSECs that were isolated from livers of mice with or without CCl4 treatment for 6 weeks. F qRT–PCR was used to assess the expression of lnc-Helf and Acta2 in the HSCs after culture-induced activation for indicated times. G qRT–PCR was used to assess the expression of lnc-HELF in liver samples from fibrotic patients (n = 28) and healthy people (n = 6). Data are presented as mean ± SEM. *p < 0.05, unpaired Student’s t test (A, B, and E–G)

Knockdown of lnc-Helf alleviates hepatic fibrosis induced by CCl4 and BDL

To investigate the role of lnc-Helf during liver fibrogenesis in vivo, AAV8-lnc-Helf-shRNA1#, AAV8-lnc-Helf-shRNA2#, or AAV8-NC was injected 2 weeks after the first injection of CCl4 via the tail vein. Mice were then treated with CCl4 or oil twice per week for an additional 6 weeks. qRT–PCR analysis confirmed that lnc-Helf was knocked down in liver tissues (Fig. 2A). Moreover, we performed RNA-seq to explore the influence of lnc-Helf deficiency on CCl4-induced hepatic fibrosis. A total of 556 mRNAs were dysregulated in CCl4-treated lnc-Helf-shRNA1# mice, and 1423 mRNAs were dysregulated in CCl4-treated lnc-Helf-shRNA2# mice, compared with the CCl4-treated AAV8-NC mice (Fig. 2B). Among these, 303 (100 mRNAs were upregulated and 203 mRNAs were downregulated) genes were also dysregulated in the CCl4-treated lnc-Helf-shRNAs mice (Fig. 2C; Additional file 1: Fig. S2A, B), and the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway and Gene Ontology (GO) analyses showed that knockdown of lnc-Helf affected a series of genes related with drug metabolism, arachidonic acid metabolism, retinol metabolism, PI3K-AKT pathway, and ECM–receptor interaction (Fig. 2D, E; Additional file 1: Fig. S2C, D), suggesting that lnc-Helf deficiency regulates CCl4-induced liver metabolic dysfunction and fibrosis. To confirm this, we performed hematoxylin and eosin (H&E) staining, Masson staining, Sirius red staining, and immunohistochemistry (IHC) for α-SMA, COL1α1, and TGFβ, and the data revealed that lnc-Helf silencing alleviated hepatic fibrosis induced by CCl4 (Fig. 2F and Additional file 1: Fig. S3A). Western blotting demonstrated that lnc-Helf silencing decreased the upregulation of MMP2, α-SMA, and TIMP1 induced by CCl4 (Fig. 2G). Consistently, qRT–PCR analysis showed that lnc-Helf deficiency noticeably alleviated CCl4-induced upregulation of profibrotic genes (Acta2, Col1α1, Mmp2, Timp1, and Tgfβ1) (Additional file 1: Fig. S3B). The serum level of AST and hepatic hydroxyproline content in CCl4-treated lnc-Helf-shRNAs mice were also markedly downregulated compared with CCl4-treated AAV8-NC mice (Fig. 2H; Additional file 1: Fig. S3C, D). In addition, CCl4-treated lnc-Helf-shRNAs mice exhibited reduced inflammatory response and compensated proliferation compared with CCl4-treated AAV8-NC mice, as evidenced by IHC and western blot for CD11b, F4/80, LY6C, TNF-α, IL-1β, MCP1, and PCNA, together with the mRNA level of genes related with inflammation (Tnf-α, Mcp1, Il-6, and Il-1β) and proliferation (Pcna, Ki67 and Cyclin D1) in the livers (Additional file 1: Fig. S4A–D).

Fig. 2

Knockdown of lnc-Helf alleviates hepatic fibrosis induced by CCl4. Mice were divided into six groups: AAV8-NC, NC + CCl4, lnc-Helf-sh1#, lnc-Helf-sh1# + CCl4, lnc-Helf-sh2#, and lnc-Helf-sh2# + CCl4. Mice were injected with AAV8-lnc-Helf-shRNAs, or AAV8-NC virus 2 weeks after the first injection of CCl4 via tail vein. After CCl4 treatment for 8 weeks. A qRT–PCR was used to assess the expression of lnc-Helf in livers of each group (n = 3). B The significantly differentially expressed mRNAs were displayed by hierarchical cluster analysis: bright red, upregulation; bright blue, downregulation (n = 3). C–E The Venn diagram, KEGG, and GO analyses of differentially expressed mRNAs in lnc-Helf-sh1# + CCl4 mice and lnc-Helf-sh2# + CCl4 mice, compared with NC + CCl4 mice. F The degree of liver fibrosis was evaluated by morphological detection: H&E staining, Masson staining, Sirius red staining, and IHC for α-SMA; five images of each liver and five livers from different mice were quantified for each group; scale bar is 100 μm for 40× and 400 μm for 10× magnifications . G Western blot was used to determine the protein level of MMP2, α-SMA, and TIMP1. GAPDH was used as an internal control. H The content of hepatic hydroxyproline was quantified in livers of each group (n = 5). The data were displayed as hydroxyproline (μg)/liver wet weight. Data are presented as mean ± SEM. */#p < 0.05. *p < 0.05 for AAV8-NC. #p < 0.05 for NC + CCl4, one-way ANOVA (A, F, H)

The results were further confirmed in BDL-induced hepatic fibrosis model. As shown in Fig. 3 and Additional file 1: Fig. S5, the BDL group mice developed serious hepatic fibrosis, while lnc-Helf silencing alleviated BDL-induced hepatic fibrosis and inflammation as demonstrated by H&E staining, Masson staining, Sirius red staining, serum ALT, AST level, liver hydroxyproline content, western blot, and qRT–PCR (Fig. 3A–E; Additional file 1: Fig. S5A–D). Altogether, these data prove that knockdown of lnc-Helf obviously alleviates hepatic inflammation and fibrosis induced by CCl4 and BDL.

Fig. 3

Knockdown of lnc-Helf alleviates hepatic fibrosis induced by BDL. Mice were divided into six groups: AAV8-NC, NC + BDL, lnc-Helf-sh1#, lnc-Helf-sh1# + BDL, lnc-Helf-sh2#, and lnc-Helf-sh2# + BDL. Mice were injected with AAV8-lnc-Helf-shRNAs or AAV8-NC virus 2 days before sham operation or bile duct ligation operation via tail vein. After 21 days of operation. A The degree of liver fibrosis was evaluated by morphological detection: H&E staining, Masson staining, and Sirius red staining. Five images of each liver and five livers from different mice were quantified for each group; Scale bar is 400 μm for 10× magnification. B Western blot was used to determine the protein level of MMP2, α-SMA, TIMP1, CD11b, TNF-α, IL-1β, and MCP1. GAPDH was used as an internal control. C, D qRT–PCR was used to assess the expression of profibrogenic genes (Acta2, Col1α1, Mmp2, Timp1, and Tgfβ1) and proinflammatory genes (Tnf-α, Mcp1, Il-6, and Il-1β) in livers of each group (n = 3). E The content of hepatic hydroxyproline was quantified in livers of each group (n = 5). The data were displayed as hydroxyproline (μg)/liver wet weight. Data are presented as mean ± SEM. */#p < 0.05. *p < 0.05 for AAV8-NC. #p < 0.05 for NC + BDL, one-way ANOVA (A and C–E)

lnc-Helf promotes HSCs activation and proliferation

Activated HSCs are the central ECM-producing cells in the liver [3]. To investigate the effect of lnc-Helf on the activation and proliferation of HSCs, lnc-Helf was knocked down by lentivirus vector of lnc-Helf-shRNA at day 2 primary HSCs. Cells were treated with recombinant TGFβ for 24 h, and qRT–PCR analysis detected the expression of fibrosis-associated (Acta2, Col1α1, Col1α2, Timp1, and Tgf-β1) and proliferation-associated genes (Pcna, Ki67, and Cyclin E1). We found that knockdown of lnc-Helf significantly reduced the level of lnc-Helf, profibrotic, and proproliferation genes in the presence or absence of TGFβ (Fig. 4A). Consistently, western blot showed that lnc-Helf silencing downregulated the protein level of α-SMA, MMP2, CYCLIN B1, and PCNA in the presence or absence of TGFβ (Fig. 4B; Additional file 1: Fig. S6A). Similar results were also obtained by confocal microscopy (Fig. 4C; Additional file 1: Fig. S6B). On the other hand, forced expression of lnc-Helf increased the level of the profibrotic and proproliferation genes evaluated by western blot, qRT–PCR, and confocal microscopy (Fig. 4D–F and Additional file 1: Fig. S6C, D). To further confirm the results in LX-2 cells, lnc-HELF was overexpressed in the cells by lentivirus vector of lnc-HELF (LV-lnc-HELF), as the level of lnc-HELF in LX-2 cells was quite low. qRT–PCR and western blot analysis revealed that overexpression of lnc-HELF enhanced the level of the profibrotic and proproliferation genes (Additional file 1: Fig. S6E, F). In addition, CCK8 assays demonstrated that overexpression of lnc-HELF promoted LX-2 cells and primary HSCs proliferation (Additional file 1: Fig. S6G, H). Altogether, these data suggest that lnc-Helf accelerates HSCs activation and proliferation.

Fig. 4

lnc-Helf promotes HSCs activation and proliferation. A–C Primary HSCs were isolated and infected with lnc-Helf-shRNA or lenti-control at day 2 for 48 h, following the treatment with 10 ng/ml TGF-β1 for 24 h. qRT-PCR was used to assess the RNA level of lnc-Helf, Acta2, Col1α1, Col1α2, Timp1, Tgf-β1, Pcna, Ki67, and Cyclin E1 (A); western blot was used to determine the expression of α-SMA, MMP2, CYCLIN D1, CYCLIN B1, and PCNA (B). GAPDH was used as an internal control; the expression and location of α-SMA was assessed by confocal microscopy (C). Scale bar is 20 μm. D–F Primary HSCs were isolated and infected with lenti-lnc-Helf or lenti-control at day 2 for 48 h, following the treatment with 10 ng/ml TGF-β1 for 24 h. The expression and location of α-SMA was assessed by confocal microscopy (D). Scale bar is 20 μm. qRT–PCR was used to detect the RNA level of lnc-Helf, Acta2, Col1α1, Col1α2, Timp1, Tgf-β1, Pcna, Ki67, and Cyclin E1 (E); western blot was used to determine the expression of α-SMA, MMP2, CYCLIN D1, CYCLIN B1, and PCNA (F). GAPDH was used as an internal control. Data are presented as mean ± SEM. */#p < 0.05. *p < 0.05 for LV-control. #p < 0.05 for LV-control + TGF-β1, one-way ANOVA (A, E)

lnc-Helf induces HMs M1 polarization and proliferation

Given the evidences that lnc-Helf was upregulated in HMs from the fibrotic livers and lnc-Helf silencing ameliorated CCl4- and BDL- induced hepatic inflammation in vivo, we investigated the role of lnc-Helf on the polarization and proliferation of macrophage in vitro. Mouse HMs were transfected with lnc-Helf siRNA following a treatment with 20 ng/ml IFN-γ. qRT–PCR analysis showed that lnc-Helf silencing decreased the expression of lnc-Helf, proinflammatory genes including Ly6c, Tnf-α, Il-6, Mcp-1, and Il-1β, as well as proproliferation genes including Pcna, Cyclin D1, and Cyclin E1 in the absence or presence of IFN-γ (Fig. 5A). Moreover, mature IL-1β level in the supernatant was also assessed by enzyme-linked immunosorbent assay (ELISA), and the data indicated that IL-1β level was downregulated in the supernatant of lnc-Helf-silenced HMs compared with the control (Fig. 5B). Similarly, confocal microscopy revealed that lnc-Helf silencing decreased the expression of TNF-α (Fig. 5C). On the other hand, qRT–PCR analysis revealed that lnc-Helf silencing promoted, while forced expression of lnc-Helf decreased the expression of anti-inflammatory genes including Mrc1, Cd163, and Il10 (Additional file 1: Fig. S7A, B). In addition, forced expression of lnc-Helf increased the level of proinflammatory and proproliferation genes evaluated by qRT–PCR, ELISA, and confocal microscopy (Fig. 5D–F). Consistently, similar results were also obtained in RAW264.7 cells (Additional file 1: Fig. S7C, D). In addition, CCK8 assay demonstrated that overexpression of lnc-Helf markedly promoted RAW264.7 cells proliferation (Fig. 5G). Altogether, these data demonstrate that lnc-Helf induces the M1 polarization and proliferation of macrophages.

Fig. 5

lnc-Helf promotes HMs M1 polarization and proliferation. A–C Mouse primary HMs transfected with siRNA for 24 h, following treatment with 20 ng/ml IFN-γ for 24 h. qRT–PCR analysis was used to detect the RNA level of lnc-Helf, Ly6c, Tnf-α, Mcp-1, Il-1β, Il-6, Pcna, Cyclin D1, and Cyclin E1 (A); mature supernatant IL-1β level was detected by ELISA (B); the expression and location of TNF-α was assessed by confocal microscopy (C). Scale bar is 20 μm. D HMs were transfected with pcDNA3.1-lnc-Helf or pcDNA3.1 for 48 h; qRT–PCR was used to assess the expression of lnc-Helf, Ly6c, Tnf-α, Mcp-1, Il-1β, Il-6, Pcna, Cyclin D1, and Cyclin E1. E, F HMs were transfected with pcDNA3.1-lnc-Helf or pcDNA3.1 for 48 h, following treatment with 20 ng/ml IFN-γ for 24 h. Mature supernatant IL-1β level was detected by ELISA (E); the expression and location of TNF-α was assessed by confocal microscopy (F). Scale bar is 20 μm. G RAW264.7 cells were transfected with pcDNA3.1-lnc-Helf or pcDNA3.1 for the indicated times, cell proliferation was detected by CCK8. Data are presented as mean ± SEM. */#p < 0.05. *p < 0.05 for si-NC or pcDNA3.1. #p < 0.05 for si-NC + IFN-γ or pcDNA3.1 + IFN-γ, one-way ANOVA (A, B, E) and unpaired Student’s t test (D, G)

lnc-Helf promotes hepatic inflammation and fibrosis through activating AKT pathway

Since the KEGG pathway and GO analyses indicated that knockdown of lnc-Helf affected a serial of genes related with the PI3K-AKT pathway (Fig. 2D), we measured the level of phos-AKT (Thr308), phos-c-Raf1 (Ser259), phos-GSK-3β (Ser9), and AKT in liver tissues from lnc-Helf-silenced or control mice treated with or without CCl4/BDL. Western blot analysis revealed that knockdown of lnc-Helf suppressed CCl4- and BDL-induced phosphorylation of AKT and GSK-3β (Fig. 6A and Additional file 1: Fig. S8A). Moreover, knockdown of lnc-Helf reduced, while overexpression of lnc-Helf promoted, the phosphorylation of AKT in HSCs and LX-2 cells (Fig. 6B, C; and Additional file 1: Fig. S8B), suggesting that lnc-Helf silencing alleviated hepatic inflammation and fibrosis through the AKT pathway. Subsequently, MK2206, the specific inhibitor of AKT, was applied in lnc-Helf-upregulated HSCs and RAW264.7 cells. qRT–PCR analysis showed that MK2206 abrogated lnc-Helf overexpression and increased the expression of profibrotic, proinflammatory, and proproliferation genes (Fig. 6D; Additional file 1: Fig. S8C). Consistently, ELISA and CCK8 assays demonstrated that the increased supernatant IL-1β levels and cell proliferation by lnc-Helf overexpression was abrogated by MK2206 (Fig. 6E, F). Altogether, these data indicate that lnc-Helf promotes hepatic inflammation and fibrosis through activating AKT pathway.

Fig. 6

lnc-Helf promotes hepatic inflammation and fibrosis through activating AKT pathway. A Mice were divided into six groups: AAV8-NC, NC + CCl4, lnc-Helf-sh1#, lnc-Helf-sh1# + CCl4, lnc-Helf-sh2#, and lnc-Helf-sh2# + CCl4. Western blot was used to determine the protein level of phos-AKT (Thr308), phos-c-Raf1 (Ser259), phos-GSK-3β (Ser9), and AKT in liver tissues of each group. B, C Primary HSCs at day 2 were infected with lenti-control, lnc-Helf-shRNA, or lenti-lnc-Helf for 48 h, following treatment with 10 ng/ml TGF-β1 for 24 h. Western blot was used to determine the protein level of phos-AKT (Thr308) and AKT. GAPDH was used as an internal control. D Primary HSCs treated with or without the AKT inhibitor MK2206 at day 2 were infected with lenti-control or lenti-lnc-Helf for 72 h. qRT–PCR was used to detect the RNA level of lnc-Helf, Acta2, Col1α2, Timp1, Pcna, and Cyclin E1. E, F RAW264.7 cells treated with or without the AKT inhibitor MK2206 were transfected with pcDNA3.1-lnc-Helf or pcDNA3.1 for 72 h. Mature supernatant IL-1β level was detected by ELISA (E); cell proliferation was detected by CCK8 (F). Data are presented as mean ± SEM. */#p < 0.05. *p < 0.05 for LV-control + DMSO or pcDNA3.1 + DMSO. #p < 0.05 for LV-lnc-Helf + DMSO or pcDNA3.1-lnc-Helf + DMSO, one-way ANOVA (D–F)

lnc-Helf promotes hepatic inflammation and fibrosis by interacting with PTBP1 to facilitate PIK3R5 mRNA stabilization

To further explore the molecular mechanism of lnc-Helf during hepatic fibrogenesis, we performed RNA pulldown–mass spectrometry (MS) assay to identify the proteins binding with lnc-Helf (Fig. 7A; Additional file 1: Table S2). Among the lnc-Helf-bound proteins, PTBP1, which is an RNA-binding protein and regulates pre-mRNA splicing and mRNA stability, caught our attention. Western blot further confirmed that lnc-Helf interacted with PTBP1 (Fig. 7B). Moreover, lnc-Helf was detected in the immunoprecipitates of PTBP1 by RIP assay (Fig. 7C, D), further demonstrating the binding of lnc-Helf to PTBP1. Subsequently, specific siRNAs targeting PTBP1 were transfected into lnc-Helf-overexpressed RAW264.7 cells, and the data of the qRT–PCR, ELISA and CCK8 demonstrated that PTBP1 silencing blocked lnc-Helf overexpression-induced inflammation response and proliferation (Fig. 7E–G). Consistently, these data were also confirmed in HSCs (Fig. 7H; Additional file 1: Fig. S9). All these data suggest that lnc-Helf aggravates hepatic inflammation and fibrosis via binding with PTBP1.

Fig. 7

lnc-Helf promotes hepatic inflammation and fibrosis by interacting with PTBP1. A In vitro RNA pulldown–mass spectrometry assay in single liver cell lysates. B The specific interaction of sense lnc-Helf RNA with PTBP1 protein was determined by western blot. C, D RIP–qRT–PCR assay in single-cell suspensions from the liver (C) and RAW264.7 cells (D). E qRT–PCR was used to detect the expression of lnc-Helf, Ptbp1, Tnf-α, Mcp-1, Il-1β, Il-6, Pcna, Cyclin D1, and Cyclin E1 in lnc-Helf-overexpressed RAW264.7 cells simultaneously transfected with siPTBP1. F Mature supernatant IL-1β levels in lnc-Helf-overexpressed RAW264.7 cells simultaneously transfected with siPTBP1 was detected by ELISA. G Cell proliferation of lnc-Helf-overexpressed RAW264.7 cells simultaneously transfected with siPTBP1 was detected by CCK8. H The expression of lnc-Helf, Ptbp1, Acta2, Col1α2, Timp1, Pcna, and Cyclin E in lnc-Helf-upregulated primary HSCs, simultaneously transfected with siPTBP1, was detected by qRT–PCR. Data are presented as mean ± SEM. */#p < 0.05. *p < 0.05 for IgG RIP or pcDNA3.1 + si-NC or LV-control + si-NC. #p < 0.05 for pcDNA3.1-lnc-Helf + si-NC or LV-lnc-Helf + si-NC, unpaired Student’s t test (C, D) and one-way ANOVA (E–H)

PTBP1 belongs to a family of RNA-binding proteins famous for its function in regulating mRNA stability [20, 21]. Therefore, we assumed that the interaction between lnc-Helf and PTBP1 may regulate the effect of PTBP1 on its target mRNAs, thus activating the AKT pathway. The online bioinformatics analysis tools (RPIseq, RBPmap) were used to predict the target RNAs binding with PTBP1 (Additional file 1: Fig. S10A, B). PIK3R5, which was significantly decreased in CCl4-treated lnc-Helf-shRNAs mice compared with CCl4-treated AAV8-NC mice (Fig. 2B, C; Additional file 1: Fig. S2A, B), was predicted to comprise several PTBP1 binding sites. We first measured the expression of PIK3R5 and PTBP1 in 6 healthy liver tissues and 28 fibrotic liver tissues, and the results revealed that PIK3R5 rather than PTBP1 was increased in fibrotic livers (Fig. 8A; Additional file 1: Fig. S10C). Moreover, lnc-HELF was found to be positively correlated with PIK3R5 and PTBP1 (Fig. 8B; Additional file 1: Fig. S10D). A correlation of PTBP1 with PIK3R5 was also observed (Additional file 1: Fig. S10E). Furthermore, the expression of Pik3r5 but not Ptbp1 was upregulated in mouse fibrotic livers, induced by CCl4 and BDL, and deficiency of lnc-Helf abrogated this upregulation (Additional file 1: Fig. S10F–I). In addition, knockdown of lnc-Helf reduced the level of Pik3r5, while forced expression of lnc-Helf promoted the level of Pik3r5, in primary HSCs, LX-2 cells, primary HMs ,and RAW264.7 cells (Additional file 1: Fig. S11A–F). Next, RIP assay demonstrated that Pik3r5 mRNA was enriched by PTBP1 in single-cell suspensions from the liver (Fig. 8C) and RAW264.7 cells, and this enrichment was markedly augmented by lnc-Helf upregulation (Fig. 8D), suggesting that interaction of lnc-Helf and PTBP1 accelerated PTBP1 binding to Pik3r5 mRNA. Interestingly, confocal microscopy demonstrated that forced expression of lnc-Helf promoted PTBP1 to translocate into the cytoplasm (Fig. 8E). Indeed, qRT–PCR analysis demonstrated that knockdown of PTBP1 blocked lnc-Helf overexpression-induced upregulation of Pik3r5 in HSCs and RAW264.7 cells (Fig. 8F; Additional file 1: Fig. S11G). Then we analyzed how PTBP1 regulates Pik3r5 expression. Actinomycin D, which blocks de novo transcription, was used in RAW264.7 cells transfected with PTBP1-siRNA or pcDNA3.1-lnc-Helf, alone or in combination. The results demonstrated that overexpression of lnc-Helf decreased Pik3r5 mRNA degradation via PTBP1 (Fig. 8G). Altogether, the data reveal that lnc-Helf aggravates hepatic inflammation and fibrosis by interacting with PTBP1 to facilitate PIK3R5 mRNA stabilization.

Fig. 8

lnc-Helf promotes hepatic inflammation and fibrosis by interacting with PTBP1 to facilitate PIK3R5 mRNA stabilization. A The RNA level of PIK3R5 was detected in liver samples of fibrotic patients (n = 28) and healthy people (n = 6) by qRT–PCR analysis. B The correlation of lnc-HELF and PIK3R5 was assessed by Pearson correlation analysis, n = 34. C, D RIP–qRT–PCR assay in single-cell suspensions from the liver (C) and RAW264.7 cells transfected with pcDNA3.1-lnc-Helf or pcDNA3.1 (D). E The expression and location of PTBP1 in primary HSCs infected with lenti-control or lenti-lnc-Helf was assessed by confocal microscopy. Scale bar is 20 μm. The fluorescence intensity of nuclear and cytoplasm was quantified on the right. F qRT–PCR was used to detect the RNA level of Pik3r5 in lnc-Helf-overexpressed primary HSCs simultaneously transfected with siPTBP1. G RAW264.7 cells transfected with pcDNA3.1 or pcDNA3.1-lnc-Helf with or without si-PTBP1 were treated with 5 μg/ml actinomycin D. RNA of each group was extracted at indicated time points (0, 2, 4 h) and the expression of Pik3r5 mRNA was analyzed by qRT–PCR and normalized to Gapdh. Data are presented as mean ± SEM. */#p < 0.05. *p < 0.05 for IgG RIP or LV-control + si-NC or pcDNA3.1 + si-NC. #p < 0.05 for LV-lnc-Helf + si-NC or pcDNA3.1-lnc-Helf + si-NC, unpaired Student’s t test (A, C, E) and one-way ANOVA (D, F, G)