A Pathway-Centered Analysis of Pig Domestication and Breeding in Eurasia

Abstract

Ascertaining the molecular and physiological basis of domestication and breeding is an active area of research. Due to the current wide distribution of its wild ancestor, the wild boar, the pig (Sus scrofa) is an excellent model to study these processes, which occurred independently in East Asia and Europe ca. 9000 yr ago. Analyzing genome variability patterns in terms of metabolic pathways is attractive since it considers the impact of interrelated functions of genes, in contrast to genome-wide scans that treat genes or genome windows in isolation. To that end, we studied 40 wild boars and 123 domestic pig genomes from Asia and Europe when metabolic pathway was the unit of analysis. We computed statistical significance for differentiation (Fst) and linkage disequilibrium (nSL) statistics at the pathway level. In terms of Fst, we found 21 and 12 pathways significantly differentiated at a q-value < 0.05 in Asia and Europe, respectively; five were shared across continents. In Asia, we found six significant pathways related to behavior, which involved essential neurotransmitters like dopamine and serotonin. Several significant pathways were interrelated and shared a variable percentage of genes. There were 12 genes present in >10 significant pathways (in terms of Fst), comprising genes involved in the transduction of a large number of signals, like phospholipase PCLB1, which is expressed in the brain, or ITPR3, which has an important role in taste transduction. In terms of nSL, significant pathways were mainly related to reproductive performance (ovarian steroidogenesis), a similarly important target trait during domestication and modern animal breeding. Different levels of recombination cannot explain these results, since we found no correlation between Fst and recombination rate. However, we did find an increased ratio of deleterious mutations in domestic vs. wild populations, suggesting a relaxed functional constraint associated with the domestication and breeding processes. Purifying selection was, nevertheless, stronger in significantly differentiated pathways than in random pathways, mainly in Europe. We conclude that pathway analysis facilitates the biological interpretation of genome-wide studies. Notably, in the case of pig, behavior played an important role, among other physiological and developmental processes.

Keywords: behavior; domestication; genome sequence data; pathway analysis; pig.

Figure 1

(A) Heatmap of the European individuals using the molecular relationship matrix, computed using all available autosomal single nucleotide polymorphisms (SNPs). (B) Heatmap of the Asian pigs. In Europe, breed codes are DU, Duroc; IB, Iberian; LR, Landrace; LW, Large White; MG, Mangalitza; PI, Pietrain; and YU, Yucatan minipig. In Asia, breed codes are BX, Bamaxiang; HT, Hetao; LA, Laiwu; LU, Luchuan; MI, Minzhu; MS, Meishan; ST, Sichuan; TT, Tibet; WU, Wuzhishan; and YT, Yunnan. Colors are used to differentiate among the populations: ASDM (Asian domestic, blue), ASWB (Asian wild boar, purple), EUDM (European domestic, green), and EUWB (European wild boar, dark red).

Figure 2

Gene P-values (−log10) of significant genes at the 1% nominal level in Europe (red bars), in Asia (blue bars,) or both continents (black bars) from the significant differentiated (Fst) pathways involved in behavior. When a gene was significant in both continents, the smallest P-value is plotted. Gene symbols are provided when available; otherwise numbers indicate ensembl ENSSSCG id.

Figure 3

Significant genes at the 1% nominal level either in Europe, Asia or both, present in the significant pathways obtained from the nSL (linkage disequilibrium) analysis. Gene symbols are provided when available; otherwise numbers indicate ensembl ENSSSCG id.

Figure 4

Coassociation network among the 31 interconnected significant pathways. Each node represents a pathway that is connected by an edge if partial correlation with another pathway is significant and >0.8 (in absolute value). Node size is proportional to number of genes in the pathways. Node shapes represent pathway source: triangles for REACTOME and circles for KEGG. Colors indicate the population with lowest Fst (statistical significance for differentiation) P-value: pink for Asia, blue for Europe, and green for equal significance. Node line width to pathway variability: thin and thick lines for pathways with variability below and above average, respectively. Black and red edges represent positive and negative correlations between pathways, respectively. The three main pathway clusters are identified with letters A–C.