This feasibility study (purchase required) showed that lipid profiling can discriminate lamb breed and also (unlike stable isotope or elemental profile) the cut of meat. The authors used Ninxia Tan sheep, a premium breed in China, as proof of concept. They measured a large panel of lipids in reference populations of authentic and inauthentic breeds and cuts. They then assessed different Machine Learning protocols for feature selection.
1230 molecules across 29 lipid classes were identified in longissimus dorsi and knuckle meat of both Tan sheep and Bahan crossbreed sheep. Applying multivariate statistical methods, 12 lipid molecules were identified as potential markers for breed and and 7 as potential markers for the cut of meat. Stepwise linear discriminant analysis was applied to select 3 and 4 lipid molecules, respectively, for discriminating lamb breed and cut, achieving correct rates of discrimination of 100 % and 95 %.
They conclude that back-propagation neural network was superior to other machine learning approaches for this application. Integrating lipidomics with back-propagation neural network approach can provide an effective strategy to trace and certify lamb products, ensuring their quality and protecting consumer rights.
Photo by Pinaak Kumar on Unsplash
Comments