Screening Discriminating SNPs for Chinese Indigenous Pig Breeds Identification Using a Random Forests Algorithm

Abstract

Chinese indigenous pig breeds have unique genetic characteristics and a rich diversity; however, effective breed identification methods have not yet been well established. In this study, a genotype file of 62,822 single-nucleotide polymorphisms (SNPs), which were obtained from 1059 individuals of 18 Chinese indigenous pig breeds and 5 cosmopolitan breeds, were used to screen the discriminating SNPs for pig breed identification. After linkage disequilibrium (LD) pruning filtering, this study excluded 396 SNPs on non-constant chromosomes and retained 20.92~−27.84% of SNPs for each of the 18 autosomes, leaving a total of 14,823 SNPs. The principal component analysis (PCA) showed the largest differences between cosmopolitan and Chinese pig breeds (PC1 = 10.452%), while relatively small differences were found among the 18 indigenous pig breeds from the Yangtze River Delta region of China. Next, a random forest (RF) algorithm was used to filter these SNPs and obtain the optimal number of decision trees (ntree = 1000) using corresponding out-of-bag (OOB) error rates. By comparing two different SNP ranking methods in the RF analysis, the mean decreasing accuracy (MDA) and mean decreasing Gini index (MDG), the effects of panels with different numbers of SNPs on the assignment accuracy, and the statistics of SNP distribution on each chromosome in the panels, a panel of 1000 of the most breed-discriminative tagged SNPs were finally selected based on the MDA screening method. A high accuracy (>99.3%) was obtained by the breed prediction of 318 samples in the RF test set; thus, a machine learning classification method was established for the multi-breed identification of Chinese indigenous pigs based on a low-density panel of SNPs.

Determination of soil source using laser induced breakdown spectroscopy combined with feature selection

“…24 The greater the impact of a feature variable on the final prediction result in an RF model, the greater its importance. 25…”

Identification of population‐informative markers from high‐density genotyping data through combined feature selection and machine learning algorithms: Application to European autochthonous and cosmopolitan pig breeds

“…These ensemble prediction rules can be applied to assign an unknown sample to one of the pre-determined groups. Recently, several authors have tested some RF-based approaches to identify breed informative SNPs in cattle and pig breeds (Bertolini et al, 2015(Bertolini et al, , 2018Gao et al, 2022;Schiavo et al, 2020). As RF is prone to being biased by high linkage disequilibrium between markers, it might become computationally very demanding when using thousands of markers (Meng et al, 2009).…”

Comparison of meat quality and glycolysis potential of two hybrid pigs in three-way hybrid model

“…As one of the largest pig producers worldwide, China has many indigenous pig breeds with unique genetic characteristics that have developed over thousands of years due to domestication and natural selection (6). Saba pigs, which are produced in high-altitude areas of Yunnan, exhibit excellent characteristics in meat quality, crude feed utilization rate, and reproduction rate (7).…”

“…Owing to heterosis and breed complementarity, hybrid offspring frequently exhibit better performance than their paternal and maternal lines. Local animal breeds (especially pigs and poultry) are often used in two-way and three-way crossbreeding systems to produce progenies with superior meat quality (6,8). Three-way terminal crosses are widely used in commercial pig production and show higher production efficiency than pure breeds or two-way crosses (9).…”