Restricted accessResearch articleFirst published online 2024-10
Machine Learning-Aided Ultra-Low-Density Single Nucleotide Polymorphism Panel Helps to Identify the Tharparkar Cattle Breed: Lessons for Digital Transformation in Livestock Genomics
Cattle breed identification is crucial for livestock research and sustainable food systems, and advances in genomics and artificial intelligence present new opportunities to address these challenges. This study investigates the identification of the Tharparkar cattle breed using genomics tools combined with machine learning (ML) techniques. By leveraging data from the Bovine SNP 50K chip, we developed a breed-specific panel of single nucleotide polymorphisms (SNPs) for Tharparkar cattle and integrated data from seven other Indian cattle populations to enhance panel robustness. Genome-wide association studies (GWAS) and principal component analysis were employed to identify 500 SNPs, which were then refined using ML models—AdaBoost, bagging tree, gradient boosting machines, and random forest—to determine the minimal number of SNPs needed for accurate breed identification. Panels of 23 and 48 SNPs achieved accuracy rates of 95.2–98.4%. Importantly, the identified SNPs were associated with key productive and adaptive traits, thus attesting to the value and potentials of digital transformation in livestock genomics. The ML-aided ultra-low-density SNP panel approach reported here not only facilitates breed identification but also contributes to preserving genetic diversity and guiding future breeding programs.
BertoliniF, ElbeltagyA, RothschildM. Evaluation of the application of bovine, ovine and caprine SNP chips to dromedary genotyping. Lives Res Rural Dev, 2017; 29.
3.
BertoliniF, GalimbertiG, CalòDG, et al.Combined use of principal component analysis and random forests identify population-informative single nucleotide polymorphisms: Application in cattle breeds. J Anim Breed Genet, 2015; 132(5):346–356; doi: 10.1111/jbg.12155
4.
BharatiJ, DangiSS, ChouhanVS, et al.Expression dynamics of HSP70 during chronic heat stress in Tharparkar cattle. Int J Biometeorol, 2017; 61(6):1017–1027; doi: 10.1007/s00484-016-1281-1
5.
BiscariniF, MariniS, StevanatoP, et al.Developing a parsimonius predictor for binary traits in sugar beet (Beta vulgaris). Mol Breeding, 2015; 35(1); doi: 10.1007/s11032-015-0197-5
BrooksA, CreightonEK, GandolfiB, et al.SNP miniplexes for individual identification of random-bred domestic cats. J Forensic Sci, 2016; 61(3):594–606; doi: 10.1111/1556-4029.13026
8.
CastricV, BernatchezL. Individual assignment test reveals differential restriction to dispersal between two salmonids despite no increase of genetic differences with distance. Mol Ecol, 2004; 13(5):1299–1312; doi: 10.1111/j.1365-294X.2004.02129.x
9.
CegelskiCC, WaitsLP, AndersonNJ. Assessing population structure and gene flow in Montana wolverines (Gulo gulo) using assignment-based approaches. Mol Ecol, 2003; 12(11):2907–2918; doi: 10.1046/j.1365-294x.2003.01969.x
10.
ChangCC, ChowCC, TellierLC, et al.Second-generation PLINK: Rising to the challenge of larger and richer datasets. Gigascience, 2015; 4(1):7; doi: 10.1186/s13742-015-0047-8
11.
ÇınarMU, AkyüzB, ArslanK, et al.The EDN2 rs110287192 gene polymorphism is associated with paratuberculosis susceptibility in multibreed cattle population. PLoS One, 2020; 15(9):e0238631; doi: 10.1371/journal.pone.0238631
12.
DalvitC, De MarchiM, Dal ZottoR, et al.Breed assignment test in four Italian beef cattle breeds. Meat Sci, 2008; 80(2):389–395; doi: 10.1016/j.meatsci.2008.01.001
13.
FontanesiL, BerettiF, Dall’OlioS, et al.A melanocortin 1 receptor (MC1R) gene polymorphism is useful for authentication of Massese sheep dairy products. J Dairy Res, 2011; 78(1):122–128; doi: 10.1017/S0022029910000890
14.
GarnerJB, ChamberlainAJ, Vander JagtC, et al.Gene expression of the heat stress response in bovine peripheral white blood cells and milk somatic cells in vivo. Sci Rep, 2020; 10(1):19181; doi: 10.1038/s41598-020-75438-2
15.
HulseggeB, CalusMPL, WindigJJ, et al.Selection of SNP from 50K and 777K arrays to predict breed of origin in cattle. J Anim Sci, 2013; 91(11):5128–5134; doi: 10.2527/jas.2013-6678
16.
IquebalMA, AnsariMS, DixitSP, et al.Locus minimization in breed prediction using artificial neural network approach. Anim Genet, 2014; 45(6):898–902; doi: 10.1111/age.12208
17.
Iung LH deS, MulderHA, Neves HH deR, et al.Genomic regions underlying uniformity of yearling weight in Nellore cattle evaluated under different response variables. BMC Genomics, 2018; 19(1):619; doi: 10.1186/s12864-018-5003-4
18.
JudgeMM, KelleherMM, KearneyJF, et al.Ultra-low-density genotype panels for breed assignment of Angus and Hereford cattle. Animal, 2017; 11(6):938–947; doi: 10.1017/S1751731116002457
19.
KéglB. The return of adaboost.MH: Multi-class Hamming trees. 2013; doi: 10.48550/ARXIV.1312.6086
20.
KimK, SeoM, KangH, et al.Application of logitboost classifier for traceability using SNP chip data. PLoS One, 2015; 10(10):e0139685; doi: 10.1371/journal.pone.0139685
21.
KlingströmT, Zonabend KönigE, ZwaneAA, et al.Beyond the hype: Using AI, big data, wearable devices, and the internet of things for high-throughput livestock phenotyping. Brief Funct Genomics, 2024:elae032; doi: 10.1093/bfgp/elae032
22.
KuhnM, WingJ, WestonS, et al.Classification and Regression Training. Package ‘Caret, 2022:223.
23.
KumarH, PanigrahiM, ChhotarayS, et al.Comparative analysis of five different methods to design a breed-specific SNP panel for cattle. Anim Biotechnol, 2021; 32(1):130–136; doi: 10.1080/10495398.2019.1646266
24.
KumarH, PanigrahiM, SaravananKA, et al.SNPs with intermediate minor allele frequencies facilitate accurate breed assignment of Indian Tharparkar cattle. Gene, 2021; 777:145473; doi: 10.1016/j.gene.2021.145473
25.
LewisJ, AbasZ, DadousisC, et al.Tracing cattle breeds with principal components analysis ancestry informative SNPs. PLoS One, 2011; 6(4):e18007; doi: 10.1371/journal.pone.0018007
26.
LinB, WuS. Digital transformation in personalized medicine with artificial intelligence and the internet of medical things. OMICS, 2022; 26(2):77–81; doi: 10.1089/omi.2021.0037
27.
LiuR, XuZ, TengJ, et al.Evaluation of six machine learning classification algorithms in pig breed identification using SNPs array data. Anim Genet, 2023; 54(2):113–122; doi: 10.1111/age.13279
PantSD, SchenkelFS, VerschoorCP, et al.Use of breed-specific single nucleotide polymorphisms to discriminate between Holstein and Jersey dairy cattle breeds. Anim Biotechnol, 2012; 23(1):1–10; doi: 10.1080/10495398.2012.636224
30.
PasupaK, RathasamuthW, TongsimaS. Discovery of significant porcine SNPs for swine breed identification by a hybrid of information gain, genetic algorithm, and frequency feature selection technique. BMC Bioinformatics, 2020; 21(1):216; doi: 10.1186/s12859-020-3471-4
31.
PeterC, BrufordM, PeretzT, et al.The ECONOGENE consortium genetic diversity and sub-division of 57 European and middle-eastern sheep breeds. Anim Genet, 2006; 38:37–44.
32.
PurcellS, NealeB, Todd-BrownK, et al.PLINK: A tool set for whole-genome association and population-based linkage analyses. Am J Hum Genet, 2007; 81(3):559–575; doi: 10.1086/519795
33.
RamosAM, MegensHJ, CrooijmansRPMA, et al.Identification of high utility SNPs for population assignment and traceability purposes in the pig using high-throughput sequencing: Identification of high utility SNPs. Anim Genet, 2011; 42(6):613–620; doi: 10.1111/j.1365-2052.2011.02198.x
34.
ReinhartE. The political education of US physicians. JAMA Netw Open, 2023; 6(6):e2320447; doi: 10.1001/jamanetworkopen.2023.20447
35.
RussoV, FontanesiL, ScottiE, et al.Analysis of melanocortin 1 receptor (MC1R) gene polymorphisms in some cattle breeds: Their usefulness and application for breed traceability and authentication of Parmigiano Reggiano cheese. Ital J Anim Sci, 2007; 6(3):257–272; doi: 10.4081/ijas.2007.257
36.
SaravananKA, PanigrahiM, KumarH, et al.Genome-wide assessment of genetic diversity, linkage disequilibrium and haplotype block structure in Tharparkar cattle breed of India. Anim Biotechnol, 2022; 33(2):297–311; doi: 10.1080/10495398.2020.1796696
37.
SchiavoG, BertoliniF, GalimbertiG, et al.A machine learning approach for the identification of population-informative markers from high-throughput genotyping data: Application to several pig breeds. Animal, 2020; 14(2):223–232; doi: 10.1017/S1751731119002167
38.
SeoD, ChoS, ManjulaP, et al.Identification of target chicken populations by machine learning models using the minimum number of SNPs. Animals (Basel), 2021; 11(1):241; doi: 10.3390/ani11010241
39.
ShackellGH, TateML, AndersonRM. Installing a DNA-based traceability system in the meat industry. Proc Assoc Adv Anim Breed Genet, 2001; 14:533–536.
40.
SinghR, IquebalMA, MishraCN, et al.Development of model web-server for crop variety identification using throughput SNP genotyping data. Sci Rep, 2019; 9(1):5122; doi: 10.1038/s41598-019-41204-2
41.
SuekawaY, AiharaH, ArakiM, et al.Development of breed identification markers based on a bovine 50K SNP array. Meat Sci, 2010; 85(2):285–288; doi: 10.1016/j.meatsci.2010.01.015
42.
TrenkelVM, BoudryP, Verrez-BagnisV, et al.Methods for identifying and interpreting sex-linked SNP markers and carrying out sex assignment: Application to thornback ray (Raja clavata). Mol Ecol Resour, 2020; 20(6):1610–1619; doi: 10.1111/1755-0998.13225
43.
WilkinsonS, WienerP, ArchibaldAL, et al.Evaluation of approaches for identifying population informative markers from high density SNP chips. BMC Genet, 2011; 12:45; doi: 10.1186/1471-2156-12-45
44.
XuZ, DiaoS, TengJ, et al.Breed identification of meat using machine learning and breed tag SNPs. Food Control, 2021; 125(107971; doi: 10.1016/j.foodcont.2021.107971
45.
YetiskinE. Biopolitics of “acquired immunity”: The war discourse and feminist response-abilities in art, science, and technology during COVID-19. OMICS, 2022; 26(10):552–566; doi: 10.1089/omi.2022.0091
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
