Sheep category can be classified using machine learning techniques applied to fatty acid profiles derivatised as trimethylsilyl esters
P. J. Watkins A B C F G , D. Clifford D , G. Rose B , D. Allen B , R. D. Warner A B , F. R. Dunshea A E and D. W. Pethick A CA Cooperative Research Centre for Sheep Industry Innovation, CJ Hawkins Homestead, University of New England, Armidale, NSW 2351, Australia.
B Department of Primary Industries, 600 and 621 Sneydes Road, Werribee, Vic. 3030, Australia.
C School of Veterinary and Biomedical Sciences, Murdoch University, Murdoch, WA 6150, Australia.
D CSIRO Mathematics, Informatics and Statistics, Locked Bag 17, North Ryde, NSW 1670, Australia.
E Melbourne School of Land and Environment, University of Melbourne, Parkville, Vic. 3051, Australia.
F Present address: CSIRO Food and Nutritional Sciences, Private Bag 16, Werribee, Vic. 3030, Australia.
G Corresponding author. Email: peter.watkins@csiro.au
Animal Production Science 50(8) 782-791 https://doi.org/10.1071/AN10034
Submitted: 24 February 2010 Accepted: 10 June 2010 Published: 31 August 2010
Abstract
Eruption of permanent incisors (dentition) is used as a proxy for age for defining meat quality in Australian sheep meat. However, this approach may not be reliable. While not presently available, an objective method could be used to determine sheep age, and thus sheep category, which would then potentially remove any inaccuracies that may occur in classifying sheep meat product. Statistical classification algorithms have been successfully used in bioinformatics. In this paper we review the performance of three algorithms (support vector machines, recursive partitioning and random forests) for determining sheep age. The algorithms were applied to the measured fatty acid profiles of fat samples from 533 carcasses; 254 lamb (<1 year old), 131 hogget (~1–2 years old) and 148 mutton (>2 years old) samples. Three data pretreatments (range transformation, column mean centering and range transformation with mean centering) were also examined to determine their impact on the performance of the algorithms. The random forests algorithm, when applied to mean-centred data, gave 100% predictive accuracy when classifying sheep category. This approach could be used for the development of an objective test for determining sheep age and category.
Acknowledgements
This work was funded by the Cooperative Research Centre for Sheep Industry Innovation and this is gratefully acknowledged. We are grateful to Jan Gerretzen and Tom Bloemberg, of Radboud University in The Netherlands, for making an early version of the PTW package available to us. We are also grateful to Alec Zwart of CSIRO Mathematics, Informatics and Statistics, who made useful comments on the paper.
Armstrong N, Hibbert DB
(2009) An introduction to Bayesian methods for analyzing chemistry data. Part 1: an introduction to Bayesian theory and methods. Chemometrics and Intelligent Laboratory Systems 97, 194–210.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
[Verified 10 August 2010]
Clifford D,
Stone G,
Montoliu I,
Rezzi S,
Martin FP,
Guy P,
Bruce S, Kochhar S
(2009) Alignment using variable penalty dynamic time warping. Analytical Chemistry 81(3), 1000–1007.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
[Verified 18 November 2008]
Diri B, Albayrak S
(2008) Visualization and analysis of classifiers performance in multi-class medical data. Expert Systems with Applications 34(1), 628–634.
| Crossref | GoogleScholarGoogle Scholar |
[Verified 14 July 2010]
Granitto PM,
Furlanello C,
Biasioli F, Gasperi F
(2006) Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial products. Chemometrics and Intelligent Laboratory Systems 83, 83–90.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
[Verified 18 November 2010]
Robinson M,
De Souza D,
Keen W,
Saunders E,
McConville M,
Speed T, Likic V
(2007) A dynamic programming approach for the alignment of signal peaks in multiple gas chromatography–mass spectrometry experiments. BMC Bioinformatics 8, 419.
| Crossref | GoogleScholarGoogle Scholar | PubMed |
[Verified 18 November 2010]
Tian F,
Yang L,
Lv F, Zhou P
(2009) Predicting liquid chromatographic retention times of peptides from the Drosophila melanogaster proteome by machine learning approaches. Analytica Chimica Acta 644, 10–16.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
van Mispelaar VG,
Janssen HG,
Tas AC, Schoenmakers PJ
(2005) Novel system for classifying chromatographic applications, exemplified by comprehensive two-dimensional gas chromatography and multivariate analysis. Journal of Chromatography. A 1071(1–2), 229–237.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
van Nederkassel AM,
Daszykowski M,
Eilers PHC, Heyden YV
(2006) A comparison of three algorithms for chromatograms alignment. Journal of Chromatography. A 1118(2), 199–210.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
Watkins PJ,
Rose G,
Salvatore L,
Allen D,
Tucman D,
Warner RD,
Dunshea FR, Pethick DW
(2010) Factors influencing the concentrations of three branched fatty acids in ovine fat from Australian commercial abbatoirs. Meat Science in press. ,
| Crossref | GoogleScholarGoogle Scholar | PubMed |
Wilson RT, Durkin JW
(1984) Age at permanent incisor eruption in indigenous goats and sheep in semi-arid Africa. Livestock Production Science 11, 451–455.
| Crossref | GoogleScholarGoogle Scholar |
Xia J,
Psychogios N,
Young N, Wishart DS
(2009) MetaboAnalyst: a web server for metabolomic data analysis and interpretation. Nucleic Acids Research 37(Suppl. 2), W652–W660.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
Young OA,
Berdagué JL,
Viallon C,
Rousset-Akrim S, Theriez M
(1997) Fat-borne volatiles and sheepmeat odour. Meat Science 45(2), 183–200.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
Young OA,
Lane GA,
Podmore C,
Fraser K,
Agnew MJ,
Cummings TL, Cox NR
(2006) Changes in composition and quality characteristics of ovine meat and fat from castrates and rams aged to 2 years. New Zealand Journal of Agricultural Research 49, 419–430.
|
CAS |
Crossref |
Zheng L,
Watson DG,
Johnston BF,
Clark RL,
Edrada-Ebel R, Elseheri W
(2009) A chemometric study of chromatograms of tea extracts by correlation optimization warping in conjunction with PCA, support vector machines and random forest data modeling. Analytica Chimica Acta 642(1–2), 257–265.
| Crossref | GoogleScholarGoogle Scholar |
CAS |
PubMed |
