The myokine Fibcd1 is an endogenous determinant of myofiber size and mitigates cancer-induced myofiber atrophy

Abstract

Decline in skeletal muscle cell size (myofiber atrophy) is a key feature of cancer-induced wasting (cachexia). In particular, atrophy of the diaphragm, the major muscle responsible for breathing, is an important determinant of cancer-associated mortality. However, therapeutic options are limited. Here, we have used Drosophila transgenic screening to identify muscle-secreted factors (myokines) that act as paracrine regulators of myofiber growth. Subsequent testing in mouse myotubes revealed that mouse Fibcd1 is an evolutionary-conserved myokine that preserves myofiber size via ERK signaling. Local administration of recombinant Fibcd1 (rFibcd1) ameliorates cachexia-induced myofiber atrophy in the diaphragm of mice bearing patient-derived melanoma xenografts and LLC carcinomas. Moreover, rFibcd1 impedes cachexia-associated transcriptional changes in the diaphragm. Fibcd1-induced signaling appears to be muscle selective because rFibcd1 increases ERK activity in myotubes but not in several cancer cell lines tested. We propose that rFibcd1 may help reinstate myofiber size in the diaphragm of patients with cancer cachexia.

Fig. 1. RNAi and overexpression screening identifies myokines that regulate myofiber size in Drosophila body wall skeletal muscles.

a Starting from 788 predicted secreted factors encoded by the Drosophila genome, 274 with human homology were selected based on a DIOPT homology score of ≥2. Of these, 111 secreted factors with substantial skeletal muscle expression (FPKM ≥ 4) were further chosen for screening with the UAS/Gal4 system and 508 transgenic stocks. b Transgenic RNAi or overexpression was driven in body wall skeletal muscle with Mef2-Gal4 and muscle phenotypes were identified first based on overall larval body size and secondarily with dissections and analysis of the size of a stereotypical set of skeletal muscles, ventral longitudinal VL3 and VL4 muscles, each consisting of a single myofiber. c Screen results (see Supplementary Data 1 for a full report): 31 interventions induced myofiber atrophy (6.1%), 12 led to myofiber hypertrophy (2.4%), whereas 465 led to no phenotype (91.5%). d Representative images of RNAi interventions that induce myofiber atrophy, compared to negative control RNAi. e Quantitation of the myofiber area, width, and length indicates a significant decrease; mean values ± SD and the precise n(VL3 + VL4 muscles from independent larvae) are reported in the figure; P < 0.001. Statistical analysis was done by using two-way ANOVA with Dunnett’s multiple comparison test. f Representative images of muscle size phenotypes induced by myokine overexpression, compared to a negative control (+; no transgene) and to positive controls (foxo and Insulin Receptor overexpression). g Quantitation of the myofiber area, width, and length indicates the significant induction of myofiber atrophy and hypertrophy by overexpression of the myokines indicated; mean values ± SD; the n(VL3 + VL4 muscles from independent larvae) is reported in the figure; P < 0.001. Statistical analysis was done by using two-way ANOVA with Dunnett’s multiple comparison test. Source data and complete statistical analyses are provided in the Source Data file.

Fig. 2. siRNAs for mouse Fibcd1 induce mouse C2C12 myotube atrophy.

a Transmembrane (FL) and short (SH) versions of the mouse Fibcd1 protein (orthologous to Drosophila Fibcd1/CG8642) are encoded by the mouse genome. b Western blot of HEK293 cell lysates and cell culture supernatants 2 days after transfection with either an empty vector (EV) or with a vector encoding C-terminal Flag-tagged full length (FL) or short (SH) mouse Fibcd1. Expression of FL and SH is detected at similar levels in cell lysates. However, although neither FL nor SH are detected in the culture medium, a C-terminal ~38 kDa fragment of Fibcd1 derived from the proteolytic processing of FL Fibcd1 is detected in the cell culture supernatant. Coomassie blue staining is shown as loading control. A recombinant Fibcd1 protein (rFibcd1) that resembles the cleaved Fibcd1 FL fragment has been generated a. c NT or Fibcd1 siRNAs transfection into mouse C2C12 myotube-enriched cultures for 48 h, followed by treatment for further 24 h with rFibcd1 or a vehicle control. Representative images of myotubes stained for myosin heavy chain are shown. Scale bar, 100 μm. Measurement of myotube width indicates that Fibcd1 siRNAs induce atrophy and that myotube size is rescues by rFibcd1. Data are mean ± SD with the precise n indicated in the figure; ****P < 0.0001 and ^&&P < 0.01, compared to the indicated control; P values were determined by two-way ANOVA with Sidak’s multiple comparisons test. See also Supplementary Fig. 2. d Myotube-enriched cultures treated for 48 h with cachectic cytokines (IL-6 at 20 ng/mL, LIF at 20 ng/mL, and TNF-α at 100 ng/mL) and either rFibcd1 at 10 and 100 ng/mL or vehicle-alone control at the same time of the cytokine treatment. Representative images of myotubes stained for myosin heavy chain (green) are shown. Scale bar, 200 μm. Measurement of myotube width indicates that rFibcd1 rescues atrophy induced by cachectic cytokines. Data are mean ± SD; n = 101 myotubes/group. ***P < 0.001 compared to control; ^&P < 0.05, ^&&P < 0.01, and ^&&&&P < 0.0001 compared to control within each cytokine group. Statistical analysis was done by using two-way ANOVA with Sidak’s multiple comparisons test. Source data are provided in the Source Data file.

Fig. 3. rFibcd1 preserves myotube size via inducing ERK signaling but does not activate this pathway in some cancer cells.

a Transfection of C2C12 myotubes for 48 h with Fibcd1 siRNAs reduces ERK signaling, as indicated by lower P-p44/42 MAPK compared to NT siRNAs. A 30-min treatment with rFibcd1 rescues P-p44/42 MAPK. See also Supplementary Fig. 3a. b NT or Fibcd1 siRNAs transfection into mouse C2C12 myotube-enriched cultures for 48 h, followed by treatment for further 24 h with Pyrazolylpyrrole (ERK inhibitor) at 2.5 ng/mL, indicates that ERK is needed for the preservation of myotube size by rFibcd1. Data are mean ± SD, with n indicated in the figure, and ***P < 0.001 (two-way ANOVA with Sidak’s multiple comparisons test). c P-p44/42 MAPK levels do not substantially change upon treatment of LLC, 4T1, and Saos-2 metastatic cancer cells with rFibcd1 (10 and 100 ng/mL for 30 and 120 min), apart for Saos-2 cells treated with the highest rFibcd1 dose. d rFibcd1 induces limited/minimal changes in P-p44/42 MAPK in most osteosarcoma, colorectal adenocarcinoma, melanoma, and breast cancer cell lines. However, rFibcd1 induces P-p44/42 in 67NR and 143B-Luc cells. See also Supplementary Fig. 3b. e rFibcd1 primarily consists of a fibrinogen-related domain (Fig. 2a). Combinations of a and b integrins are known to act as receptors for fibrinogen, including a2b-b3 integrins. f RNA-seq and qRT-PCR indicate that integrin a2b is expressed in C2C12 myotubes, which respond to rFibcd1 by increasing P-p44/42 levels but is not expressed in cancer cells that do not readily respond to rFibcd1 (LLC, 4T1, E0771, Ep5). 67NR cancer cells that respond to rFibcd1 (as indicated by higher P-p44/42; Fig. 3d and Supplementary Fig. 3b) display Itga2b mRNA levels similar to those of C2C12 myotubes, suggesting that Itga2b might be a receptor for rFibcd1; n = 2 (RNA preps from independent cell cultures).   g Itga2b siRNAs impede the rFibcd1-mediated increase in P-ERK, indicating that Itga2b is needed for the optimal response of muscle cells to rFibcd1. The quantitation of P-ERK levels relative to tubulin is shown in a, c, g. Source data are provided in the Source Data file.

Fig. 4. rFibcd1 rescues LLC cancer-induced myofiber atrophy of the diaphragm.

a–f Myofiber size of diaphragms from control mice treated with mock (n = 9) or with rFibcd1 (n = 10), and from mice that carry LLC tumors and that are treated with mock (n = 5) or with rFibcd1 (n = 5). Treatment consisted of 3 intraperitoneal injections of rFibcd1 (1 mg/Kg) or mock injection of 1% BSA (vehicle). a Feret’s minimal diameter of type 1, 2a, and 2x/2b myofibers. b Feret’s minimal diameter normalized to controls. rFibcd1 partially rescues cancer-induced myofiber atrophy. c Percentage of type 1, 2a, and 2x/2b myofibers. In (a–c), mean ± SD are shown and analyzed with two-way ANOVA with Sidak’s multiple comparisons. d–f Frequency and gaussian distribution of Feret’s minimal diameters for type 1 d, type 2a e, and type 2x/2b myofibers f. g Representative images of diaphragm strips immunostained for type 1 (red), type 2a (green), and type 2x/2b myofibers (black). Laminin (white) delineates all myofibers, and DAPI (blue) the nuclei. h-i, Body weight and tumor-free body mass decrease in response to LLC tumor growth. i–j Intraperitoneal injection of rFibcd1 does not affect the tumor-free body mass and the tumor mass, indicating that rFibcd1 exerts local rather than system effects. N/A, not applicable. Data are mean ± SD. *P < 0.05 (two-way ANOVA with Sidak’s multiple comparisons test). The n is the same as reported in (a) and refers to mice in h–i, and to the mass of tumors in j. k Heatmap of 2043 differentially-expressed genes in diaphragms from control mice treated with mock (n = 5) or with rFibcd1 (n = 5), and mice that carry LLC tumors and are treated with mock (n = 3) or with rFibcd1 (n = 4). l GO term analysis of genes (Supplementary Data 2) that are upregulated (230) and downregulated (17) (P < 0.05 and Log2R < -0.5 and Log2R > 0.5) in the diaphragm of mice with LLC but not if treated with rFibcd1. m These include genes related to inflammation (Cxcl13), proteolysis (Ctss and Napsa) and metabolism (Ppargc1a). Data are means ± SD with n indicated; *P < 0.05 and **P < 0.01 (two-way ANOVA with Tukey’s multiple comparisons). Source data are provided in the Source Data file.

Fig. 5. Cachexia caused by a pediatric melanoma xenograft induces myofiber atrophy in the diaphragm.

a–p Analysis of myofiber size in diaphragm muscles of mice undergoing wasting at 2 a–d, 4 e–h, 6 i–l, and 8 m–p weeks post implantation of a cachexia-inducing (“cachectic”) melanoma xenograft, compared to a cachexia-non-inducing (“non-cachectic”) melanoma xenograft or mock injection of PBS (n = 5/group). At the early stages of cachexia progression (2-4 weeks), there is no substantial decline in myofiber size, as indicated by the analysis of the Feret’s minimal diameter a–b, e–f. At later stages (6–8 weeks), there is a trend towards a decline in the size of type 1, 2a, and 2x/2b myofibers at 6 weeks of age i, j, l, which however is significant only after 8 weeks from cancer cell injection m, n, p. There are no changes in the relative proportion of myofiber types found in diaphragm muscles c, g, o, apart for a slight increase in type 2x/2b myofibers at 6 weeks (k). Mean values ± SD are shown in panels b–c, f–g, j–k, and n–o. Statistical analysis was done by using two-way ANOVA with Sidak’s multiple comparisons test. q Heatmap of 1033 genes that are most highly modulated by melanoma-induced cachexia in the diaphragm, compared to controls. r Upregulated genes include secreted proteins, proteins involved in innate immunity and neutrophil chemotaxis, and metalloprotease inhibitors. s Downregulated genes are also enriched for secreted and extracellular matrix proteins. Genes modulated with P < 0.05 and Log2R > 1 r and Log2R < -1 s in cachectic versus control at 8 weeks post tumor implantation are shown. Source data are provided in the Source Data file.

Fig. 6. rFibcd1 rescues diaphragm myofiber atrophy induced by a patient-derived melanoma xenograft.

a–f Myofiber size from diaphragms of control mice with a non-cachectic melanoma and treated with mock (n = 10) or with rFibcd1 (n = 10), and from mice that carry a cachectic melanoma and are treated with mock (n = 7) or with rFibcd1 (n = 6). Treatment with rFibcd1 consisted of 3 intraperitoneal injections of rFibcd1 (3 mg/Kg) or of the vehicle (1% BSA). a Feret’s minimal diameter of type 1, 2a, and 2x/2b myofibers. b Feret’s minimal diameter normalized to controls. c Percentage of type 1, 2a, and 2x/2b myofibers. In a–c, mean values ± SD are shown, and were analyzed with two-way ANOVA with Sidak’s multiple comparisons and with two-tailed unpaired t-tests. d–f Frequency and gaussian distribution of Feret’s minimal diameters for type 1 d, type 2a e, and type 2x/2b myofibers f. g Representative micrographs of diaphragm strips immunostained for type 1 (red), type 2a (green), and type 2x/2b myofibers (black). Laminin (white) delineates myofibers, and DAPI (blue) the nuclei. h–i Body weight and tumor-free body mass progressively decline in response to growth of a cachectic melanoma but not in response to a control non-cachectic melanoma. h-j, Intraperitoneal injection of rFibcd1 does not affect the body weight, tumor-free body mass, and the tumor mass, indicating that rFibcd1 does not rescue myofiber atrophy by impacting tumor growth and general body wasting. In h–j data are mean ± SD; ***P < 0.0001 compared to control non-cachectic melanoma group; ^&P < 0.05 compared to the control cachectic melanoma group. Statistical analysis was done by using two-way ANOVA with Tukey’s multiple comparisons test and two-tailed unpaired t-test. See also Supplementary Fig. 5. k Heatmap showing the levels of cytokines (pg/mL) from the plasma of mice from the groups described above. Lack of Fibcd1 treatment is indicated by a (−), whereas (+) denotes rFibcd1 administration. Color key indicates low plasma levels (light gray) and high plasma levels (high gray) of cytokines. See also Supplementary Fig. 7. Source data are provided in the Source Data file.

Fig. 7. rFibcd1 reduces transcriptional and functional changes induced by cachectic melanomas.

a Heatmap of 599 genes that are differentially expressed in diaphragm muscles of mice bearing non-cachectic melanomas and either mock-treated (n = 9) or treated with rFibcd1 (n = 10), and mice that carry a cachectic melanoma and that are either mock-treated (n = 7) or treated with rFibcd1 (n = 6). rFibcd1 represses some of the gene expression changes that characterize diaphragms from mice implanted with cachectic versus the non-cachectic melanomas. The heatmaps are based on z-scores of group averages from baseline-adjusted log2(TMP) for genes with at least one significant call among the related comparison sets. b GO term analysis of genes that are significantly regulated (34 upregulated, 32 downregulated; P < 0.05 and 50% change; Supplementary Data 5) in the diaphragm of mice with cachectic melanomas, treated with rFibcd1 versus mock. c Expression of genes related to myofiber atrophy from dataset in b and Supplementary Data 5. Data are means ± SD. P values were determined as reported in the RNA-seq methods and refer to cachectic versus non-cachectic, and to cachectic+rFibcd1 versus cachectic; *P < 0.05, **P < 0.01, ***P < 0.001. The N refers to diaphragm muscles and it is indicated in the legend of a. d Analysis of motor function in mice with either cachectic or non-cachectic orthotopic melanoma xenografts, and which received 3 i.p. injections of either rFibcd1 or mock (BSA) a week before testing. Melanoma-induced cachexia significantly reduces motor function compared to mice implanted with non-cachectic cancer cells. Comparison of the treadmill capacity of rFibcd1- versus mock-treated cachectic mice shows a trend towards improved treadmill performance in response to rFibcd1 injection but this difference does not reach statistical significance. However, cachectic mice treated with rFibcd1 have a treadmill capacity that is also not statistically different from that of non-cachectic mice. Data are means ± SD, with mice bearing non-cachectic melanomas and either mock-treated (n = 7) or treated with rFibcd1 (n = 7), and mice bearing cachectic melanomas and either mock-treated (n = 8) or treated with rFibcd1 (n = 8). P values were determined by one-way ANOVA with Tukey’s post hoc test; *P < 0.05 and **P < 0.01. Source data are provided in the Source Data file.

Fig. 8. rFibcd1 partially rescues cancer-induced myofiber atrophy and transcriptional changes in the diaphragm muscle of cachectic mice.

a Fibcd1 (CG8642) was identified in a Drosophila RNAi screen as a myokine necessary for skeletal muscle growth. b Subsequent testing of mouse Fibcd1 in cultured C2C12 myotubes confirmed that Fibcd1 is necessary for muscle cell growth: siRNAs for Fibcd1 reduced myotube size and this was rescued by administration of recombinant Fibcd1 (rFibcd1). c, d Mice implanted with different pediatric melanoma xenografts. c A first xenograft consists of cancer cells that do not induce body wasting (“non-cachectic”, i.e. cachexia-non-inducing): intraperitoneal (i.p.) injection of rFibcd1 does not impact myofiber size and transcriptional changes in the diaphragm muscle of these mice. d Profound (~25%) body weight loss (cachexia) is caused by a different melanoma xenograft (“cachectic”, i.e. cachexia-inducing); cancer-induced myofiber atrophy and gene expression changes in the diaphragm are partially rescued by i.p. injection of rFibcd1. Similar results are also found in a cachexia model caused by subcutaneous injection of LLC cancer cells.