Abstract
Numerous influential animal breeds and plant varieties provide high-quality and nutritious foods for human. The popularity and high profit of premium foods usually accompany with adulterated products, which harmed rights of both consumers and law-abiding producers. So, it is necessary to build an effective breed identification system using genetic markers genotyped from meat products to safeguard public and increase confidence of consumers. To improve the accuracy of breed identification, six machine learning methods were evaluated using different number of breed tag single nucleotide polymorphisms (SNPs) and different size of training sets from 13 pig breeds. Herein, six machine learning methods were Naïve Bayes, Support Vector Machine (SVM), k-Nearest Neighbor, Random Forest (RF), Artificial Neural Networks and Decision Tree. Results showed that using breed tag SNPs increased identification accuracy compared with random SNPs. For SVM, accuracy of using 20 breed tag SNPs and 200 random SNPs were 99.30 (±0.14%) and 99.13 (±0.11%), respectively. Among the six methods, both RF and SVM methods were robust across all tested scenarios. Additionally, the accuracy of breed identification first increased with the size of training set and then remained stable in Test-in-training breeds test set. Overall, it can be deduced that breed tag SNPs, machine learning methods and training set size play important roles in ensuring the accuracy of breed identification.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.