Genome-wide detection of CNVs and their association with performance traits in broilers

Abstract

Background: Copy number variations (CNVs) are a major type of structural genomic variants that underlie genetic architecture and phenotypic variation of complex traits, not only in humans, but also in livestock animals. We identified CNVs along the chicken genome and analyzed their association with performance traits. Genome-wide CNVs were inferred from Affymetrix® high density SNP-chip data for a broiler population. CNVs were concatenated into segments and association analyses were performed with linear mixed models considering a genomic relationship matrix, for birth weight, body weight at 21, 35, 41 and 42 days, feed intake from 35 to 41 days, feed conversion ratio from 35 to 41 days and, body weight gain from 35 to 41 days of age.

Results: We identified 23,214 autosomal CNVs, merged into 5042 distinct CNV regions (CNVRs), covering 12.84% of the chicken autosomal genome. One significant CNV segment was associated with BWG on GGA3 (q-value = 0.00443); one significant CNV segment was associated with BW35 (q-value = 0.00571), BW41 (q-value = 0.00180) and BW42 (q-value = 0.00130) on GGA3, and one significant CNV segment was associated with BW on GGA5 (q-value = 0.00432). All significant CNV segments were verified by qPCR, and a validation rate of 92.59% was observed. These CNV segments are located nearby genes, such as KCNJ11, MyoD1 and SOX6, known to underlie growth and development. Moreover, gene-set analyses revealed terms linked with muscle physiology, cellular processes regulation and potassium channels.

Conclusions: Overall, this CNV-based GWAS study unravels potential candidate genes that may regulate performance traits in chickens. Our findings provide a foundation for future functional studies on the role of specific genes in regulating performance in chickens.

Keywords: CNVs; GWAS; Performance; QTLs; qPCR.

Fig. 1

Manhattan plots for CNV segments across the 33 autosomal chromosomes associated with a birth weight, b body weight at 35 days, c body weight at 41 days and d body weight at 42 days and e body weight gain. The X-axis represents the somatic chromosomes, and Y-axis shows the corresponding -log₁₀ q-value. Red and blue lines indicate FDR-corrected p-values of 0.05 and 0.1, respectively

Fig. 2

a Birth weight, b body weight at 35 days, c body weight at 41 days and d body weight at 42 days and e body weight gain distribution in each CN state for the significant CNV segment. Each dot represents an animal in the corresponding copy number state (0-3n) on the X-axis and the observed phenotypic value on the Y-axis. The legend on the right displays the color code for the CN state. See the main text for a detailed description of each segment

Fig. 3

Quantitative PCR was carried out for significantly associated CNV segments on a GGA3 at 64 Mb, b GGA3 at 97 Mb and c GGA5 at 12 Mb using two groups (control (2n) and experimental) with three different animal samples per group and three distinct primer pairs per CNV. In each panel, bars in different colors represent distinct experimental animals for each segment. The right-most bars depict the relative copy number estimated for each animal in PennCNV. Each bar was calculated from three technical replicates. The error bars show the minimum and maximum value encountered among the replicates

Fig. 4

Confidence view of the network created by the STRING software. Nodes represent proteins produced by a single protein-coding gene locus. Edges represent protein-protein associations. Line colors indicate types of interaction evidence: known interactions from curated databases (cyan) or experimentally determined (pink); predicted interactions from gene neighborhood (green); and other sorts of interactions such as co-expression (black). The large network, in the middle, and smaller networks, on the right and left extremes, both relate to cell differentiation and muscle functioning