Search

Aim of study: To investigate the effect of fermented soybean meal (FSBM) on responses of broiler chickens exposed to stress condition. Material and methods: Two hundred and eighty-eight day-old male chickens were allocated to six treatments in a 2 × 3 completely randomized factorial design involving two factors: factor 1 was the subcutaneous injections of CORT or corn oil (as control) at 2 mg/kg body weight twice per day during 3 days; and factor 2 were 3 levels (0, 10 and 20%) of FSBM in replacement of the original soybean meal. Main results: The replacement of soybean meal by FSBM increased FI and BWG without any significant effect on FCR (10 days), while FCR was increased significantly by CORT injection. Corticosterone injection caused a significant decrease in the ratio of villus height (VH) to crypt depth (CD) in the duodenum and jejunum. The height of villi in the duodenum increased significantly at 20% FSBM replacement. The antibody titers against Newcastle disease (28 and 2 day), coliform count (28 day) and activity of digestive enzymes (10 day) were not affected by either FSBM replacement or CORT injections. Corticosterone injection significantly increased tall-like receptor-4 (TLR4) and immunoglobulin A (IgA) expression, while decreased heat shock protein-70 (HSP70) expression. FSBM replacement down-regulated the expression of TLR4, HSP70, and IgA in small intestine compared to the control group. In stress condition induced by CORT injection, 10% FSBM replacement decreased HSP70 and IgA expression in the jejunum and ileum, while had no effects on TLR4. Research highlights: Partial replacement of soybean meal by FSBM in diets had positive effects on performance, intestinal morphology and immune response in chicks exposed to stress.

Artificial neural network models offer an alternative to linear regression analysis for predicting the amino acid content of feeds from their chemical composition. A group method of data handling-type neural network (GMDH-type NN), with an evolutionary method of genetic algorithm, was used to predict methionine (Met) and lysine (Lys) contents of soybean meal (SBM) and fish meal (FM) from their proximate analyses (i.e. crude protein, crude fat, crude fibre, ash and moisture). A data set with 119 data lines for Met and 116 lines for Lys was used to develop GMDH-type NN models with two hidden layers. The data lines were divided into two groups to produce training and validation sets. The data sets were imported into the GEvoM software for training the networks. The predictive capability of the constructed models was evaluated by their abilities to estimate the validation data sets accurately. A quantitative examination of goodness of fit for the predictive models was made using a number of precision, concordance and bias statistics. The statistical performance of the models developed revealed close agreement between observed and predicted Met and Lys contents for SBM and FM. The results of this study clearly illustrate the validity of GMDH-type NN models to estimate accurately the amino acid content of poultry feed ingredients from their chemical composition.