A novel, multitargeted endogenous metabolic modulator composition impacts metabolism, inflammation, and fibrosis in nonalcoholic steatohepatitis-relevant primary human cell models

Abstract

Nonalcoholic steatohepatitis (NASH) is a complex metabolic disease of heterogeneous and multifactorial pathogenesis that may benefit from coordinated multitargeted interventions. Endogenous metabolic modulators (EMMs) encompass a broad set of molecular families, including amino acids and related metabolites and precursors. EMMs often serve as master regulators and signaling agents for metabolic pathways throughout the body and hold the potential to impact a complex metabolic disease like NASH by targeting a multitude of pathologically relevant biologies. Here, we describe a study of a novel EMM composition comprising five amino acids and an amino acid derivative (Leucine, Isoleucine, Valine, Arginine, Glutamine, and N-acetylcysteine [LIVRQNac]) and its systematic evaluation across multiple NASH-relevant primary human cell model systems, including hepatocytes, macrophages, and stellate cells. In these model systems, LIVRQNac consistently and simultaneously impacted biology associated with all three core pathophysiological features of NASH-metabolic, inflammatory, and fibrotic. Importantly, it was observed that while the individual constituent amino acids in LIVRQNac can impact specific NASH-related phenotypes in select cell systems, the complete combination was necessary to impact the range of disease-associated drivers examined. These findings highlight the potential of specific and potent multitargeted amino acid combinations for the treatment of NASH.

Figure 1

LIVRQNac improves dysregulated metabolism in a NASH-relevant primary human hepatocyte model of lipotoxicity. (a) Representative images of PHHs exposed to lipotoxic insult (FFA group) for 72 h in the presence (right) or absence (left) of LIVRQNac (30x relative to human plasma concentration for LIVRQ and 7.5 mM Nac; applied 24 h before lipotoxic insult) and stained with high-content screening LipidTOX red neutral lipid stain (red) to reveal lipid droplets and with Hoechst (blue) to show nuclei. Scale bars 74 µm. Insets have been magnified to provide greater clarity of the lipid phenotype. (b) Intracellular triglyceride levels measured in PHHs treated with vehicle (without lipotoxic insult) or exposed to lipotoxic insult (FFA group) and treated with LIVRQNac (30x relative to human plasma concentration for LIVRQ and 7.5 mM Nac, applied 24 h before lipotoxic insult) for 72 h post insult. Data are normalized to protein concentration assessed by BCA assay and shown as a mean percentage change relative to the FFA group. Data represent at least two technical replicates from at least three independent donors. Error bars represent ± SEM. *p < 0.05 versus FFA group, ***p < 0.001 versus FFA group. (c) ApoB, (d) urea, (e) MCP-1, (f) ALT levels measured in PHH supernatant exposed to lipotoxic insult (FFA group) and treated with either phosphate-buffered saline (0x) or LIVRQNac (10x–30x relative to human plasma concentration for LIVRQ and 2.5–7.5 mM Nac; applied 24 h before lipotoxic insult) for 72 h (ApoB and Urea, ALT) or 24 h (MCP-1) post insult. 0x corresponds to FFA-stimulated PHHs without additional LIVRQNac. Data are displayed as percent change relative to vehicle-treated PHHs exposed to lipotoxic insult (0x) and represent the mean of three technical replicates from four individual donors. Error bars represent ± SEM. **p < 0.01, ***p < 0.001, **** p < 0.0001 versus FFA (0x) group for all four donors combined. Analysis was performed using GraphPad Prism version 9.0.1 for Windows, GraphPad Software, San Diego, California USA, www.graphpad.com. The graphs were assembled using Adobe Illustrator CC 2019, www.adobe.com. ApoB apolipoprotein B, ALT alanine aminotransferase, BCA bicinchoninic acid, FFA lipotoxic insult (0.25 mM saturated free fatty acid [2:1 oleate: palmitate] + 1 ng/mL TNF-α), MCP-1 monocyte chemoattractant protein 1, Nac N-acetylcysteine, PHH primary human hepatocyte, SEM standard error of mean, TNF-α tumor necrosis factor-alpha, x fold concentration.

Figure 2

LIVRQNac reduces secreted levels of pro-inflammatory cytokines while inducing anti-inflammatory cytokine production in stimulated M1 and M2 primary human macrophages. (a) IL-6 and (b) TNF-α levels were measured in granulocyte–macrophage colony-stimulating factor derived M1 PHM supernatant following LPS (0.15 ng/mL) stimulation with or without the addition of LIVRQNac (10x–30x). Data are expressed in percentages relative to LPS-stimulated M1 (0x) and represent the mean of at least three technical replicates from five individual donors. **p < 0.01; ***p < 0.001 versus LPS (0x). (c) CCL17 and (d) CCL18 levels were measured in macrophage colony-stimulating factor-derived M2 PHM supernatants following IL-4 (1 ng/mL) stimulation with or without the addition of LIVRQNac (10x–30x). Data expressed in percentages relative to IL-4-stimulated M2 (0x) and represent the mean of at least three technical replicates from four individual donors. ***p < 0.001 versus IL-4 (0x). Note: 0x corresponds to LPS- or IL-4-stimulated M1 and M2 PHMs, respectively, treated with 1×HMDB media supplemented with an equivalent PBS vehicle volume. Error bars represent ± SEM. For (a–d): LIVRQNac was used at a range of concentrations (10x–30x of the human plasma concentration for LIVRQ and 2.5–7.5 mM Nac, respectively). Analysis was performed using GraphPad Prism version 9.0.1 for Windows, GraphPad Software, San Diego, California USA, www.graphpad.com. The graphs were assembled using Adobe Illustrator CC 2019, www.adobe.com. CCL C–C motif chemokine ligand, HMDB Human Metabolome Database, IL interleukin, LPS lipopolysaccharide, Nac N-acetylcysteine, PBS phosphate-buffered saline, PHM primary human macrophage, SEM standard error of the mean, TNF-α tumor necrosis factor-alpha, x fold concentration.

Figure 3

LIVRQNac reduces the induction of fibrogenic markers in TGF-β-treated human hepatic stellate cells. (a) α-SMA immunostaining and (b) labeled EdU positive intensity quantification from fixed and stained HSCs stimulated with TGF-β1 (3 ng/mL) and treated with either LIVRQNac (10x–20x) or with PBS vehicle (0x) for 24 h. Data is normalized to nuclei count and represented as a mean percentage change relative to TGF-β1-stimulated HSCs (0x) of at least three technical replicates from three independent donors. ***p < 0.001 versus TGF-β1 (0x) for all three donors combined. (c) Procollagen 1 and (d) procollagen 3 secreted levels measured in HSCs supernatant stimulated with TGF-β1 (3 ng/mL) and treated with either LIVRQNac or with PBS vehicle (0x) for 24 h. Data displayed as percent change relative to TGF-β1-stimulated HSCs (0x) represents the mean of at least three technical replicates from three independent donors. ***p < 0.001 versus TGF-β1 (0x) for all three donors combined. (e) HSP47 gene expression measured by qRT-PCR on RNA extracted from HSCs cells stimulated with TGF-β1 (3 ng/mL) and treated with either LIVRQNac (10x–20x) or with PBS vehicle (0x) for 24 h. GAPDH-normalized expression of HSP47 is represented as the mean of relative fold change to TGF-β1-stimulated HSCs (0x) of at least three technical replicates from three independent donors. ***p < 0.001 versus TGF-β1 (0x) for all three donors combined. Note: 0x corresponds to TGF-β1-stimulated HSCs without additional LIVRQNac. Error bars represent ± SEM. LIVRQNac was used at a range of concentrations (10x–20x relative to human plasma concentration for LIVRQ and 2.5 mM and 5 mM Nac; applied 24 h before TGF-β1 stimulation). Analysis was performed using GraphPad Prism version 9.0.1 for Windows, GraphPad Software, San Diego, California USA, www.graphpad.com. The graphs were assembled using Adobe Illustrator CC 2019, www.adobe.com. α-SMA alpha-smooth muscle actin, EdU 5-ethynyl-2′-deoxyuridine, GAPDH glyceraldehyde 3-phosphate dehydrogenase, HSC primary human stellate cell, HSP47 heat shock protein 47, Nac N-acetylcysteine, PBS phosphate-buffered saline, qRT-PCR quantitative reverse transcription-polymerase chain reaction, RNA ribonucleic acid, SEM standard error of mean, TGF-β1 transforming growth factor beta-1, x fold concentration.

Figure 4

LIVRQNac treatment impacts markers of inflammation and fibrosis associated with NASH in a primary human multicellular system. (a) Cartoon scheme of liver multicellular in vitro system of primary human cells coculture in a transwell set up consisting of hepatocytes (top of the transwell: tw) and NPCs macrophages and HSCs (bottom of the tw; w). Adapted with permission from Ref. no. 31, American Society for Clinical Investigation using a CC BY license. (b) Secreted inflammatory markers (MCP-1, IL-6) and fibrosis marker (procollagen 1) were measured in the coculture supernatant collected from either the transwell (tw; PHHs) or the well (w; M1-PHMs + HSCs) side after 24 h treatment with either vehicle (without FFA) or with FFA, with or without additional LIVRQNac (30x of the human plasma concentration for LIVRQ and 7.5 mM Nac, applied 24 h before insult; FFA + LIVRQNac). Data expressed in percentage relative to FFA-treated cells represents the mean of two to three technical replicates from two individual donors. Error bars represent ± SEM. ***p < 0.001; **p < 0.01; *p < 0.05 versus FFA. Analysis was performed using GraphPad Prism version 9.0.1 for Windows, GraphPad Software, San Diego, California USA, www.graphpad.com. The graphs were assembled using Adobe Illustrator CC 2019, www.adobe.com. FFA lipotoxic insult (0.25 mM saturated free fatty acids [2:1 oleate: palmitate] + 1 ng/mL TNF-α), IL interleukin, MCP-1 monocyte chemoattractant protein-1, Nac N-acetylcysteine, NPC nonparenchymal cell, PHH primary human hepatocyte, SEM standard error of the mean, TNF-α tumor necrosis factor-alpha, tw top of transwell, w bottom of transwell.

Figure 5

Treatment with LIVRQNac is necessary to achieve the desired impact on NASH-relevant metabolic, inflammatory, and fibrotic phenotypes across multiple primary human cell systems. (a) Schema to describe the global ranking approach to assess the effectiveness of LIVRQNac versus the individual amino acids of the composition. The figure was designed using Adobe Illustrator CC 2019, www.adobe.com. (b) Heatmap shows phenotype effects in four different cell types (Hepatocytes, M1 and M2 macrophages, and Hepatic stellate cells) after being treated with the adequate stimuli for each of the cell types (e.g., sFFA [0.25 mM] + TNF-α [1 ng/mL]) for hepatocytes; LPS (0.15 ng/mL) for M1; IL4 (1 ng/mL) for M2 and TGF-β (3 ng/mL) for Hepatic stellate cells) with or without additional LIVRQNac, L, I, V, R, Q, Nac, and LIV at 20x concentration relative to the normal plasma levels for LIVRQ, L, I, V, R and Q and 5 mM for Nac. For each phenotype, a rank was assigned to each treatment according to their desired effect, 1 being the best treatment for that phenotype, and 8 being the worst. For each cell type, a META-rank was calculated, which is the mean of the ranks for the phenotypes measured in the cell type. Treatments with low meta-ranks are most beneficial across all the considered phenotypes for the cell type. For all cell types, an all-META-rank was calculated, which is the mean meta-rank of all cell types. (c) Examples of Nac and R effects compared to LIVRQNac on selected NASH-related endpoints implicated in metabolism, inflammation, and fibrosis. Error bars represent ± SEM. ***p < 0.001; **p < 0.01; *p < 0.05. Analysis was performed using GraphPad Prism version 9.0.1 for Windows, GraphPad Software, San Diego, California USA, www.graphpad.com. The graphs were assembled using Adobe Illustrator CC 2019, www.adobe.com. α-SMA α-smooth muscle actin, CCL C–C motif chemokine ligand, EdU 5-ethynyl-2′-deoxyuridine, I isoleucine, IL-4 interleukin-4, IL-6 interleukin-6, L leucine, LPS lipopolysaccharide, MCP-1 monocyte chemoattractant protein 1, Nac N-acetylcysteine, Q glutamine, R arginine, sFFA saturated free fatty acid, TGF-β tumor growth factor-beta, TNF-α tumor necrosis factor-alpha, V valine.

Figure 5

Treatment with LIVRQNac is necessary to achieve the desired impact on NASH-relevant metabolic, inflammatory, and fibrotic phenotypes across multiple primary human cell systems. (a) Schema to describe the global ranking approach to assess the effectiveness of LIVRQNac versus the individual amino acids of the composition. The figure was designed using Adobe Illustrator CC 2019, www.adobe.com. (b) Heatmap shows phenotype effects in four different cell types (Hepatocytes, M1 and M2 macrophages, and Hepatic stellate cells) after being treated with the adequate stimuli for each of the cell types (e.g., sFFA [0.25 mM] + TNF-α [1 ng/mL]) for hepatocytes; LPS (0.15 ng/mL) for M1; IL4 (1 ng/mL) for M2 and TGF-β (3 ng/mL) for Hepatic stellate cells) with or without additional LIVRQNac, L, I, V, R, Q, Nac, and LIV at 20x concentration relative to the normal plasma levels for LIVRQ, L, I, V, R and Q and 5 mM for Nac. For each phenotype, a rank was assigned to each treatment according to their desired effect, 1 being the best treatment for that phenotype, and 8 being the worst. For each cell type, a META-rank was calculated, which is the mean of the ranks for the phenotypes measured in the cell type. Treatments with low meta-ranks are most beneficial across all the considered phenotypes for the cell type. For all cell types, an all-META-rank was calculated, which is the mean meta-rank of all cell types. (c) Examples of Nac and R effects compared to LIVRQNac on selected NASH-related endpoints implicated in metabolism, inflammation, and fibrosis. Error bars represent ± SEM. ***p < 0.001; **p < 0.01; *p < 0.05. Analysis was performed using GraphPad Prism version 9.0.1 for Windows, GraphPad Software, San Diego, California USA, www.graphpad.com. The graphs were assembled using Adobe Illustrator CC 2019, www.adobe.com. α-SMA α-smooth muscle actin, CCL C–C motif chemokine ligand, EdU 5-ethynyl-2′-deoxyuridine, I isoleucine, IL-4 interleukin-4, IL-6 interleukin-6, L leucine, LPS lipopolysaccharide, MCP-1 monocyte chemoattractant protein 1, Nac N-acetylcysteine, Q glutamine, R arginine, sFFA saturated free fatty acid, TGF-β tumor growth factor-beta, TNF-α tumor necrosis factor-alpha, V valine.