mRNA expression signatures of human skeletal muscle atrophy identify a natural compound that increases muscle mass

Abstract

Skeletal muscle atrophy is a common and debilitating condition that lacks a pharmacologic therapy. To develop a potential therapy, we identified 63 mRNAs that were regulated by fasting in both human and mouse muscle, and 29 mRNAs that were regulated by both fasting and spinal cord injury in human muscle. We used these two unbiased mRNA expression signatures of muscle atrophy to query the Connectivity Map, which singled out ursolic acid as a compound whose signature was opposite to those of atrophy-inducing stresses. A natural compound enriched in apples, ursolic acid reduced muscle atrophy and stimulated muscle hypertrophy in mice. It did so by enhancing skeletal muscle insulin/IGF-I signaling and inhibiting atrophy-associated skeletal muscle mRNA expression. Importantly, ursolic acid's effects on muscle were accompanied by reductions in adiposity, fasting blood glucose, and plasma cholesterol and triglycerides. These findings identify a potential therapy for muscle atrophy and perhaps other metabolic diseases.

Figure 1. Effect of Fasting on Skeletal Muscle mRNA Expression in Healthy Human Adults

(A) Study design. The table (insert) shows baseline circulating metabolic and inflammatory markers. The graph shows plasma glucose and insulin levels. Data are means ± SEM from the seven study subjects. In some cases, the error bars are too small to see. (B) Representative fasting-responsive human skeletal muscle mRNAs, and the effect of fasting on their log₂ hybridization signals, as assessed by Affymetrix Human Exon 1.0 ST arrays. In each subject, the fasting signal was normalized to the nonfasting signal from the same subject. Data are means ± SEM from 7 subjects. P ≤ 0.02 by paired t-test for all mRNAs shown. The complete set of 558 fasting-responsive mRNAs is shown in Table S1. See also Figure S1.

Figure 2. Identification of Ursolic Acid as an Inhibitor of Fasting-Induced Skeletal Muscle Atrophy

(A) Fasting-regulated mRNAs common to human and mouse muscle that were used to query the Connectivity Map. Inclusion criteria were: P ≤ 0.02 in fasted human muscle (by t-test), P ≤ 0.05 in fasted mouse muscle (by t-test), and the existence of complimentary probes on HG- U133A arrays. (B) Connectivity Map instances (or datasets), sorted by compound and cell line, with the most significant positive and negative correlations to the effect of fasting in human and mouse muscle. The connectivity score, represented on the y-axis, is a measure of the strength of the correlation (Lamb et al., 2006). P < 0.004 for all compounds shown. (C-D and F-H) Mice were administered metformin (250 mg / kg), ursolic acid (200 mg / kg) or an equivalent volume of vehicle alone via i.p. injection, and then fasted. After 12 hours of fasting, a second injection of metformin, ursolic acid or vehicle was administered. After 24 hours of fasting, the blood glucose was measured and muscles were harvested. (C-D) Effect of metformin (C) and ursolic acid (D) on fasting blood glucose. Data are means ± SEM from 16 mice. (E) Effect of 24 h fast (relative to ad lib feeding) on wet weight of lower hindlimb skeletal muscle (bilateral tibialis anterior (TA), gastrocnemius, and soleus). (F-G) Effect of metformin (F) and ursolic acid (G) on fasted lower hindlimb muscle weight. (H) Effect of ursolic acid on atrogin-1 and MuRF1 mRNA levels in the TA muscles of fasted mice. The data are normalized to the levels in vehicle-treated mice, which were set at 1. (E-H) Each data point represents one mouse and the horizontal bars denote the means. (C-H) P-values were determined using unpaired t-tests. See also Table S2.

Figure 3. Identification of Ursolic Acid as an Inhibitor of Denervation-Induced Skeletal Muscle Atrophy

(A) mRNAs altered by both fasting and SCI in human muscle that were used to query the Connectivity Map. Inclusion criteria were: P ≤ 0.02 in fasted human muscle (by t-test), P ≤ 0.05 in untrained, paralyzed muscle (by t-test), and the existence of complimentary probes on HG-U133A arrays. (B) Connectivity Map instances with the most significant positive and negative correlations to the effect of fasting and SCI in human muscle. P < 0.005 for all compounds shown. (C-E) On day 0, the left hindlimbs of C57BL/6 mice were denervated by transsecting the left sciatic nerve. Mice were then administered ursolic acid (200 mg / kg) or an equivalent volume of vehicle alone (corn oil) via i.p. injection twice daily for seven days. On day 7, muscles were harvested for analysis. (C) Weights of the left (denervated) lower hindlimb muscles were normalized to weights of the right (innervated) lower hindlimb muscles from the same mouse. Each data point represents one mouse, and horizontal bars denote the means. P-value was determined using an unpaired t-test. (D-E) Effect of ursolic acid on skeletal muscle fiber diameter in denervated gastrocnemius (D) and TA (E) muscles. Data are from > 2500 muscle fibers per condition; P < 0.0001 by unpaired t-test. See also Table S3.

Figure 4. Ursolic Acid Induces Skeletal Muscle Hypertrophy

Mice were provided ad lib access to either standard chow (control diet) or standard chow supplemented with 0.27% ursolic acid (ursolic acid diet) for 5 weeks before grip strength was measured and tissues were harvested. (A-C) Effect of ursolic acid on lower hindlimb muscle weight (A), quadriceps weight (B), and upper forelimb muscle (triceps and biceps) weight (C). Each data point represents one mouse, and horizontal bars denote the means. (D) Effect of ursolic acid on skeletal muscle fiber size distribution. Each distribution represents measurements of > 800 triceps muscle fibers from 7 animals (> 100 measurements / animal); P < 0.0001. (E) Effect of ursolic acid on peak grip strength, normalized to body weight. Each data point represents one mouse, and horizontal bars denote the means. Non-normalized grip strength data were 157 ± 9 g (control diet) and 181 ± 6 g (ursolic acid diet) (P = 0.04). See also Figure S2.

Figure 5. Ursolic Acid Promotes Muscle Growth by Repressing Atrophic Gene Expression, Inducing Trophic Gene Expression, and Enhancing Skeletal Muscle IGF-I Signaling

(A-B) Mice were provided ad lib access to either standard chow (control diet) or standard chow supplemented with 0.27% ursolic acid (ursolic acid diet) for 5 weeks before tissues were harvested. (A) Ursolic acid-induced changes in the log₂ hybridization signals of skeletal muscle mRNAs, as assessed by Affymetrix Mouse Exon 1.0 ST arrays. n = 4 arrays per diet; each array assessed gastrocnemius RNA pooled from two mice. Data were filtered for P ≤ 0.005 by unpaired t-test and log₂ hybridization signal ≥ 8. Table shows the top 6 mRNAs most induced or repressed by dietary ursolic acid. (B) Effect of ursolic acid on IGF1, atrogin-1 and MuRF1 mRNA levels, as assessed by qPCR. Data are means ± SEM. (C) Mice were provided ad lib access to either standard chow (control diet) or standard chow supplemented with the indicated concentration of ursolic acid for 7 weeks before plasma IGF-I levels were measured. Each data point represents one mouse, and horizontal bars denote the means. P-values were determined by one-way ANOVA with Dunnett’s post-test. (D-E) Mice were provided ad lib access to either standard chow (control diet) or standard chow supplemented with 0.27% ursolic acid for 16 weeks. Total protein extracts from quadriceps muscles were subjected to SDS-PAGE, followed by immunoblot analysis for phosphorylated and total Akt, as indicated. (D) Representative immunoblot. (E) In each mouse, the level of phospho-Akt was normalized to the level of total Akt. These ratios were then normalized to the average phospho-Akt/total Akt ratio from control mice. Data are means ± SEM from 9 mice per diet. P-value was determined by unpaired t-test. (F-K) Serum-starved C2C12 myotubes were treated in the absence or presence of ursolic acid (10 μM) and/or IGF-I (10 nM), as indicated. For studies of the IGF-I receptor, cells were harvested 2 min later, and protein extracts were subjected to immunoprecipitation with anti-IGF-I receptor β antibody, followed by immunoblot analysis with anti-phospho-tyrosine or anti-IGF-I receptor β antibodies to assess phospho- and total IGF-I receptor, respectively. For other studies, cells were harvested 20 min after addition of ursolic acid and/or IGF-I, and immunoblot analyses were performed using total cellular protein extracts and antibodies specific for the phosphorylated or total proteins indicated. (F-H) Representative immunoblots showing effect of ursolic acid on IGF-I-mediated phosphorylation of Akt (F), S6K (G) and IGF-I receptor (H). (I) Quantification of the effect of ursolic acid on IGF-I-dependent phosphorylation of the IGF-I receptor, Akt and S6K. Levels in the presence of ursolic acid and IGF-I are normalized to levels in the presence of IGF-I alone, which were set at 1 and are indicated by the dashed line. Data are means ± SEM from ≥ 3 experiments. (J-K) Ursolic acid enhances IGF-I-mediated phosphorylation of ERK (J) and FoxO3a/FoxO1 (K). See also Table S4 and Figure S3.

Figure 6. Ursolic Acid Reduces Adiposity

(A-B) Mice were provided ad lib access to standard chow supplemented with the indicated concentration of ursolic acid for 7 weeks before tissues were harvested for analysis. Data are means ± SEM from 10 mice per diet. (A) Effects of ursolic acid on weights of skeletal muscle (quadriceps + triceps), epididymal fat, retroperitoneal fat and heart. P-values (determined by one-way ANOVA with post-test for linear trend) were < 0.001 for muscle; 0.01 and 0.04 for epididymal and retroperitoneal fat, respectively; and 0.46 for heart. (B) Total body weights before and after 7 weeks of the indicated concentration of dietary ursolic acid. P-values were 0.71 and 0.80 for initial and final weights, respectively. (C-F) Mice were provided ad lib access to either standard chow (control diet) or standard chow supplemented with 0.27% ursolic acid (ursolic acid diet) for 5 weeks, as in Figure 4. (C) Relationship between skeletal muscle weight (quadriceps, triceps, biceps, TA, gastrocnemius and soleus) and retroperitoneal adipose weight. Each data point represents one mouse. P < 0.001 for both muscle and adipose by unpaired t-test. (D) Representative H&E stain of retroperitoneal fat. (E) Effect of ursolic acid on average retroperitoneal adipocyte diameter. Each data point represents the average diameter of ≥ 125 retroperitoneal adipocytes from one mouse. (F) Effect of ursolic acid on retroperitoneal adipocyte size distribution. Each distribution represents combined adipocyte measurements (> 1000 per diet) from (E). (G-H) Mice were fed as in (A-B). (G) Plasma leptin. Each data point represents one mouse, and horizontal bars denote the means. P-values were determined by t-test. (H) Relationship between adipose weight and plasma leptin. Each data point represents one mouse. (I-J) Mice were fed as in (C-F) before plasma triglycerides (I) and cholesterol (J) were measured. Each data point represents one mouse, and horizontal bars denote the means. P-values were determined by unpaired t-test. See also Figure S4.