PigLeg: prediction of swine phenotype using machine learning

Siroj Bakoev; Lyubov Getmantseva; Maria Kolosova; Olga Kostyunina; Duane R Chartier; Tatiana V Tatarinova

doi:10.7717/peerj.8764

PigLeg: prediction of swine phenotype using machine learning

PeerJ. 2020 Mar 23:8:e8764. doi: 10.7717/peerj.8764. eCollection 2020.

Authors

Siroj Bakoev¹, Lyubov Getmantseva¹, Maria Kolosova², Olga Kostyunina¹, Duane R Chartier³, Tatiana V Tatarinova^{4

5

6

7}

Affiliations

¹ L.K. Ernst Federal Science Center for Animal Husbandry, Moscow, Russia.
² Don State Agrarian University, Persianovsky, Rostov Region, Russia.
³ ICAI, Culver City, CA, United States of America.
⁴ Department of Biology, University of La Verne, La Verne, CA, United States of America.
⁵ Institute for Information Transmission Problems, Russian Academy of Sciences, Moscow, Russia.
⁶ Vavilov Institute for General Genetics, Moscow, Russia.
⁷ Siberian Federal University, Krasnoyarsk, Russia.

Abstract

Industrial pig farming is associated with negative technological pressure on the bodies of pigs. Leg weakness and lameness are the sources of significant economic loss in raising pigs. Therefore, it is important to identify the predictors of limb condition. This work presents assessments of the state of limbs using indicators of growth and meat characteristics of pigs based on machine learning algorithms. We have evaluated and compared the accuracy of prediction for nine ML classification algorithms (Random Forest, K-Nearest Neighbors, Artificial Neural Networks, C50Tree, Support Vector Machines, Naive Bayes, Generalized Linear Models, Boost, and Linear Discriminant Analysis) and have identified the Random Forest and K-Nearest Neighbors as the best-performing algorithms for predicting pig leg weakness using a small set of simple measurements that can be taken at an early stage of animal development. Measurements of Muscle Thickness, Back Fat amount, and Average Daily Gain were found to be significant predictors of the conformation of pig limbs. Our work demonstrates the utility and relative ease of using machine learning algorithms to assess the state of limbs in pigs based on growth rate and meat characteristics.

Keywords: Animal behavior; Artificial intelligence; Bioinformatics; Computational biology; Data mining and machine learning; Evolutionary studies; Mathematical biology.

Grants and funding

Funding was provided by the Russian Foundation for Basic Research 19-016-00068 A. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.