Locus minimization in breed prediction using artificial neural network approach

Abstract

Molecular markers, viz. microsatellites and single nucleotide polymorphisms, have revolutionized breed identification through the use of small samples of biological tissue or germplasm, such as blood, carcass samples, embryos, ova and semen, that show no evident phenotype. Classical tools of molecular data analysis for breed identification have limitations, such as the unavailability of referral breed data, causing increased cost of collection each time, compromised computational accuracy and complexity of the methodology used. We report here the successful use of an artificial neural network (ANN) in background to decrease the cost of genotyping by locus minimization. The webserver is freely accessible (http://nabg.iasri.res.in/bisgoat) to the research community. We demonstrate that the machine learning (ANN) approach for breed identification is capable of multifold advantages such as locus minimization, leading to a drastic reduction in cost, and web availability of reference breed data, alleviating the need for repeated genotyping each time one investigates the identity of an unknown breed. To develop this model web implementation based on ANN, we used 51,850 samples of allelic data of microsatellite-marker-based DNA fingerprinting on 25 loci covering 22 registered goat breeds of India for training. Minimizing loci to up to nine loci through the use of a multilayer perceptron model, we achieved 96.63% training accuracy. This server can be an indispensable tool for identification of existing breeds and new synthetic commercial breeds, leading to protection of intellectual property in case of sovereignty and bio-piracy disputes. This server can be widely used as a model for cost reduction by locus minimization for various other flora and fauna in terms of variety, breed and/or line identification, especially in conservation and improvement programs.

The assignment success for 22 horse breeds registered in the Czech Republic: The machine learning perspective

“…In cattle, the assignment success rate ranged from 55% to 70%, involving eight purebred populations and 27 loci (Talle et al 2005). Nevertheless, the assignment accuracy value for MLP observed in this study (46.2%) is not in good agreement with the value found by Iquebal et al (2014) for goat breeds (96.6%).…”

“…Today, well-defined breed descriptors based on morphology are used to categorize breeds. These phenotypic tools have certain limitations, as they 01): 1-12 https://doi.org/10.17221/120/2020-CJAS cannot identify semen, ova, embryo, or a breed product; moreover, they are unable to predict a breed in an admixture, namely, a non-descriptive population (Iquebal et al 2014).…”

“…Breed descriptors were developed to identify a breed, but these cover only "pure breed" or true to breed animals, excluding undefined or admixed populations. Molecular marker polymorphisms revolutionised breed identification through using small samples of biological tissue or germplasm, including specimens of blood, embryos, ova, semen, and carcass that do not show any evident phenotype (Iquebal et al 2014). A breed signature using single nucleotide polymorphism (SNP) or microsatellite DNA markers has the potential to discriminate between pure breeds and breed crosses, an aspect important for population management and the conservation of animal genetic resources (Bjornstad and Roed 2002).…”

Modeling Oil Content of Sesame (Sesamum indicum L.) Using Artificial Neural Network and Multiple Linear Regression Approaches

“…However, these techniques were neither sufficient nor comprehensive enough to clearly show the interactions of parameters and crop yield and could not capture the highly nonlinear and complex relationships between OC and other traits (Khairunniza‐Bejo, Mustaffha, & Ismail, ; Singh, Kanchan, Verma, & Singh, ). These complex relationships need nonlinear methods such as artificial neural networks (ANN), genetic expression programming (GEP), adaptive neuro‐fuzzy inference system (ANFIS), or Bayesian classification (BC) to overcome the drawbacks of linear methods (Goel, Bapat, Vyas, Tambe, & Tambe, ; Iquebal et al, ; Khoshnevisan, Rafiee, & Mousazadeh, ; Samadianfard, Nazemi, & Ashraf Sadraddini, ; Silva et al, ; Zeng, Xu, Wu, & Huang, ). In the last few decades, ANN have been widely used to predict SY in different crops like soybean, corn (Kaul, Hill, & Walthall, ), rice (Ji, Sun, Yang, & Wan, ), wheat (Alvarez, ), barley (Gholipour, Rohani, & Torani, ), sunflower (Zeng et al, ), and sesame (Emamgholizadeh, Parsaeian, & Baradaran, ) as well as genomic selection (Yong‐Jun, Lei, Wang, & Chang‐Hong, ).…”

Seed yield prediction of sesame using artificial neural network

“…In contrast to the traditional methods such MLR and PA models, the application of artificial intelligence (AI) models such as artificial neural networks (ANN), genetic expression programming (GEP) and adaptive neuro-fuzzy inference system (ANFIS) were recently attracted the attention of researchers in agriculture science (Azamathulla and Ghani, 2011;Shahinfar et al, 2012;Emamgholizadeh et al, 2013a,b;Samadianfard et al, 2014;Silva et al, 2014;Iquebal et al, 2014). Alvarez (2007) used the ANN approach to predict average regional yield and production of wheat in the Argentine Pampas.…”