Prediction of the true digestible amino acid contents from the chemical composition of sorghum grain for poultry

摘要: ABSTRACT Accurate knowledge of true digestible amino acid (TDAA) contents feedstuffs is necessary to accurately formulate poultry diets for profitable production. Several experimental approaches that are highly expensive and time consuming have been used determine available acids. Prediction the nutritive value a feed ingredient from its chemical composition via regression methodology has attempted many years. The artificial neural network (ANN) model powerful method may describe relationship between composition. Therefore, multiple linear regressions (MLR) ANN models were developed predicting TDAA sorghum grain based on A precision-fed assay trial using cecectomized roosters was performed in 48 samples 12 varieties differing input variables both MLR CP, ash, crude fiber, ether extract, total phenols whereas output variable each individual every sample. results this study revealed it possible satisfactorily estimate through seems influence when considering components such as ash phenols. It also equations with reasonable accuracy depending However, more satisfactory prediction be achieved all R2 values corresponding testing training parameters showed higher than established by method. In addition, current data confirmed composition, often considered prediction, could useful predictor selected acids poultry.