Identification of Age-Specific and Common Key Regulatory Mechanisms Governing Eggshell Strength in Chicken Using Random Forests

Abstract

In today’s chicken egg industry, maintaining the strength of eggshells in longer laying cycles is pivotal for improving the persistency of egg laying. Eggshell development and mineralization underlie a complex regulatory interplay of various proteins and signaling cascades involving multiple organ systems. Understanding the regulatory mechanisms influencing this dynamic trait over time is imperative, yet scarce. To investigate the temporal changes in the signaling cascades, we considered eggshell strength at two different time points during the egg production cycle and studied the genotype–phenotype associations by employing the Random Forests algorithm on chicken genotypic data. For the analysis of corresponding genes, we adopted a well established systems biology approach to delineate gene regulatory pathways and master regulators underlying this important trait. Our results indicate that, while some of the master regulators (Slc22a1 and Sox11) and pathways are common at different laying stages of chicken, others (e.g., Scn11a, St8sia2, or the TGF- β pathway) represent age-specific functions. Overall, our results provide: (i) significant insights into age-specific and common molecular mechanisms underlying the regulation of eggshell strength; and (ii) new breeding targets to improve the eggshell quality during the later stages of the chicken production cycle.

Combining Random Forests and a Signal Detection Method Leads to the Robust Detection of Genotype-Phenotype Associations

“…In addition, the application of the RF classifier provides 3726 and 1815 SNPs which map to 405 and 253 genes associated with ESS1 and ESS2, respectively. The lists of these SNPs and their corresponding genes are taken from our previous study [ 30 ]. The investigation of these SNPs in the identified QTLs reveals 158 and 14 robust SNPs related to ESS1 and ESS2, respectively (the list of the SNPs is given in Table S1 ).…”

“…Dataset 1: The first dataset contains eggshell strength recorded at two time points during the lifetime of the birds. We have previously used this dataset in Reference [ 30 ] to identify the key regulatory mechanisms governing eggshell strength in chicken. The dataset consists of 892 birds from six generations of a purebred commercial brown layer line genotyped with the Affymetrix Axiom ® 600 K Chicken Genotyping Array.…”

“…Phase 5: Adopting the strategy from our previous study [ 30 ], the Random Forests (RF) algorithm was used to estimate the relative importance of each SNP (attribute) for the prediction of the response variable (phenotype). For this purpose, we applied the Boruta algorithm [ 54 ] which is a powerful wrapper for the RF based feature selection approach to assess the importance of SNPs.…”

“…Recently, the growing application of machine learning approaches in different fields of science has incited their use in assessing the genotype-phenotype association as well [ 25 , 26 , 27 , 28 , 29 ]. Multiple studies have confirmed the superiority of machine learning algorithms compared to GWAS approaches by identifying genes having small effects on the phenotype [ 26 , 29 , 30 ]. Machine learning methods do not require prior assumptions about the distribution of the SNP effects, hence can be used for a wide variety of traits in humans [ 31 ], plants [ 28 ] and livestock [ 32 , 33 ].…”

“…Machine learning methods do not require prior assumptions about the distribution of the SNP effects, hence can be used for a wide variety of traits in humans [ 31 ], plants [ 28 ] and livestock [ 32 , 33 ]. In particular, Random Forests (RF) models have been praised for their ability to analyze a large number of loci simultaneously and to identify promising associations [ 29 , 30 ].…”