Changes in the liver transcriptome of farmed Atlantic salmon (Salmo salar) fed experimental diets based on terrestrial alternatives to fish meal and fish oil

Abstract

Background: Dependence on marine natural resources threatens the sustainability of Atlantic salmon aquaculture. In the present study, Atlantic salmon fed for 14 weeks with an experimental diet based on animal by-products and vegetable oil (ABP) exhibited reduced growth performance compared with others fed a fish meal/fish oil based experimental diet (MAR) and a plant protein/vegetable oil-based experimental diet (VEG). To characterize the molecular changes underlying the differences in growth performance, we conducted a 44 K microarray study of the liver transcriptome of the three dietary groups.

Results: The microarray experiment identified 122 differentially expressed features (Rank Products, PFP < 10%). Based on their associated Gene Ontology terms, 46 probes were classified as metabolic and growth-relevant genes, 25 as immune-related, and 12 as related to oxidation-reduction processes. The microarray results were validated by qPCR analysis of 29 microarray-identified transcripts. Diets significantly modulated the transcription of genes involved in carbohydrate metabolism (gck and pfkfb4), cell growth and proliferation (sgk2 and htra1), apoptosis (gadd45b), lipid metabolism (fabp3, idi1, sqs), and immunity (igd, mx, ifit5, and mhcI). Hierarchical clustering and linear correlation analyses were performed to find gene expression patterns among the qPCR-analyzed transcripts, and connections between them and muscle and liver lipid composition. Overall, our results indicate that changes in the liver transcriptome and tissue lipid composition were driven by cholesterol synthesis up-regulation by ABP and VEG diets, and the lower carbohydrate intake in the ABP group. Two of the microarray-identified genes (sgk2 and htra1) might be key to explaining glucose metabolism regulation and the dietary-modulation of the immune system in fish. To evaluate the potential of these genes as predictive biomarkers, we subjected the qPCR data to a stepwise discriminant analysis. Three sets of no more than four genes were found to be able to predict, with high accuracy (67-94%), salmon growth and fatty acid composition.

Conclusions: This study provides new findings on the impact of terrestrial animal and plant products on the nutrition and health of farmed Atlantic salmon, and a new method based on gene biomarkers for potentially predicting desired phenotypes, which could help formulate superior feeds for the Atlantic salmon aquaculture industry.

Keywords: Aquaculture; Atlantic salmon; Cholesterol; Lipid composition; Liver transcriptome; Marine ingredients; Microarray; Nutrigenomics; Predictive biomarkers; Terrestrial ingredients.

Fig. 1

Scatter plot of gene expression fold-changes between diets calculated from the microarray log₂ ratios and log₂-transformed qPCR relative quantity (RQ) ratios. Each dot represents either an ABP vs MAR, VEG vs MAR, or VEG vs ABP comparison for a given gene

Fig. 2

Results from the qPCR analysis of selected transcripts involved in carbohydrate (A: gck, pfkfb4, 6pgd), nucleotide (A: adssl1a), and lipid metabolism (A: acac, dgat2a, dgat2b; B: fabp3a, fabp3b, acox1, cpt1, acly, idi1, sqs). Columns and error bars represent mean relative quantity (RQ) values and S.E., respectively. Different letters above error bars represent significant differences between diets [one-way ANOVA, Tukey’s (homogeneity of variances among groups) or Games-Howell (variances not homogeneous across groups) post-hoc test, p < 0.05]. Gene abbreviations (below their corresponding columns) are according to UniProt terminology

Fig. 3

Results from the qPCR analysis of selected transcripts involved in cell growth and proliferation (sgk2a, sgk2b, htra1a, htra1b), and apoptosis (gadd45ba, gadd45bb). Columns and error bars represent mean relative quantity (RQ) values and S.E., respectively. Different letters above error bars represent significant differences between diets [one-way ANOVA, Tukey’s (homogeneity of variances among groups) or Games-Howell (variances not homogeneous across groups) post-hoc test, p < 0.05]. Gene abbreviations (below their corresponding columns) are according to UniProt terminology

Fig. 4

Results from the qPCR analysis of selected antibacterial (A: lect2a, lect2b, igma, igmb, igd), antiviral (B: mxa, mxb, ifit5), and other immune-related (A: mhcI) transcripts, as well as transcripts involved in oxidation-reduction processes (A: mtco1, mtco2a, mtco2b). Columns and error bars represent mean relative quantity (RQ) values and S.E., respectively. Different letters above error bars represent significant differences between diets [one-way ANOVA, Tukey’s (homogeneity of variances among groups) or Games-Howell (variances not homogenous across groups) post-hoc test, p < 0.05]. Gene abbreviations (below their corresponding columns) are according to UniProt terminology

Fig. 5

Matrix representing Pearson’s correlation coefficients between log₂-transformed RQs of the qPCR-analyzed transcripts (rows) and the log₂-transformed levels of different lipid composition parameters (columns) in the liver of salmon fed the experimental diets. Significant differences among diets (one-way ANOVA, p < 0.05) are indicated on the right of the transcript abbreviations and below the phenotypic variables. Transcriptomic and phenotypic data were arranged based on a hierarchical clustering performed using Pearson correlation resemblance matrices (PRIMER, Version 6.1.15, Ivybridge, UK). Dendrograms next to transcript abbreviations and above lipid parameters represent the results of the hierarchical clustering analyses. EPA: eicosapentaenoic acid (20:5ω3); ARA: arachidonic acid (20:4ω6); SFA: saturated fatty acids; PUFA: polyunsaturated fatty acid; DHA: docosahexaenoic acid (22:6ω3)

Fig. 6

Matrix representing Pearson’s correlation coefficients between log₂-transformed RQs of hepatic transcripts (rows) and phenotypic features such as omega-3 and omega-6 FAs levels in muscle and weight gains (columns) of the salmon fed the experimental diets. Significant differences among diets (one-way ANOVA, p < 0.05) are indicated on the right of the transcript abbreviations and below the phenotypic variables. Transcriptomic and phenotypic data were arranged based on a hierarchical clustering performed using Pearson correlation resemblance matrices (PRIMER, Version 6.1.15, Ivybridge, UK). Dendrograms next to transcript abbreviations and above phenotypic parameters represent the results of the hierarchical clustering analysis. PUFA: polyunsaturated fatty acid; SFA: saturated fatty acids; DHA: docosahexaenoic acid (22:6ω3); EPA: eicosapentaenoic acid (20:5ω3); WG: weight gain; ARA: arachidonic acid (20:4ω6)