Microsatellites and artificial neural networks: tools for the discrimination between natural and hatchery brown trout (Salmo trutta, L.) in Atlantic populations

摘要: Abstract Artificial Neural Networks (ANN) were applied to microsatellite data (highly variable genetic markers) separate genetically differentiated forms of brown trout ( Salmo trutta ) in south-western France. A classic feed-forward network with one hidden layer was used. Training performed using a back-propagation algorithm and reference samples representing the different types. The hold-out leave-one-out procedures used test validity network. They chosen according populations questions analysed. informative content variables for distinction (the alleles loci) also evaluated Garson–Goh algorithm. results learning gave high percentages well-classified individuals (up 95% analysis). This confirms that ANNs are suitable such analyses populations. From biological point view, study enabled evaluation composition differentiation river impact stocking.