Antepartal insulin-like growth factor concentrations indicating differences in the metabolic adaptive capacity of dairy cows

Abstract

Cows with different Insulin-like Growth Factor-I (IGF-I) concentrations showed comparable expression levels of hepatic growth hormone receptor (GHR). Suppressor of cytokine signaling 2 (SOCS2), could be responsible for additional inhibition of the GHR signal cascade. The aims were to monitor cows with high or low antepartal IGF-I concentrations (IGF-I(high) or IGF-I(low)), evaluate the interrelationships of endocrine endpoints, and measure hepatic SOCS2 expression. Dairy cows (n = 20) were selected (240 to 254 days after artificial insemination (AI)). Blood samples were drawn daily (day -17 until calving) and IGF-I, GH, insulin, thyroid hormones, estradiol, and progesterone concentrations were measured. Liver biopsies were taken (day 264 ± 1 after AI and postpartum) to measure mRNA expression (IGF-I, IGFBP-2, IGFBP-3, IGFBP-4, acid labile subunit (ALS), SOCS2, deiodinase1, GHR1A). IGF-I concentrations in the two groups were different (p < 0.0001). However, GH concentrations and GHR1A mRNA expression were comparable (p > 0.05). Thyroxine levels and ALS expression were higher in the IGF-I(high) cows compared to IGF-I(low) cows. Estradiol concentration tended to be greater in the IGF-I(low) group (p = 0.06). It was hypothesized that low IGF-I levels are associated with enhanced SOCS2 expression although this could not be decisively confirmed by the present study.

Keywords: cattle; growth hormone; insulin-like growth factor I; metabolism; suppressor of cytokine signaling.

Fig. 1

IGF-I and GH plasma concentrations in cows. The IGF-I values were square root transformed (sqrtlIGF-I). GH values were logarithmic transformed (logGH). The table presents results of the mixed-model ANOVA with a covariance structure matrix spatial power and the random effect [SP(POW)+RE]. Data are expressed as the last square means ± SE. BIC: Bayesian-Schwarz information criterion, AIC: Akaike information criterion.

Fig. 2

T3 and T4 serum concentrations in cows grouped according to IGF-I concentration. T4 values were logarithmic transformed (logT4). The table shows results of the mixed-model ANOVA with a covariance structure matrix spatial power and the random effect [SP(POW)+RE]. Data are expressed as the last square means ± SE. Significant differences (p < 0.05) between the two groups at individual time points are indicated with the letters a^* and b. Statistical tendencies (p = 0.06) are indicated by letters c^† and d. BIC: Bayesian-Schwarz criterion.

Fig. 3

Standardized pathway diagram calculated with a structural equation model of antepartal hormones in pluriparous dairy cows. The standardized path coefficients appear over or next to the respective pathways represented by arrows (p < 0.05). Endogenous dependent variables are shown in rectangles (LogIGF-I = logarithmic transformed insulin-like growth factor-I, LogGH = logarithmic transformed growth hormone, LogT3 = logarithmic transformed triiodothyronine, T4 = thyroxine. LogInsulin = logarithmic transformed insulin, LogE2 = logarithmic transformed 17β-estradiol, P4 = progesterone, HF = Holstein Frisian). The exogenous independent variable appears in the rectangle in the middle of the diagram (time = day -43 to 0 calving) while exogenous variables errors are shown in circles (e = error: eIGF-I = error of IGF-I, eIn = error of insulin, eT3 = error of T3, eP4 = error of P4, eGH = error of GH, eE2 = error of E2, eT4 = error of T4). Double-headed errors denoted these covariances. Model of squared multiple correlations were calculated and R-square values appear next to the rectangles containing the variables.