Bootstrapped neural network models for analyzing the responses of broiler chicks to dietary protein and branched chain amino acids

2014 ◽  
Vol 94 (1) ◽  
pp. 79-85 ◽  
Author(s):  
A. Faridi ◽  
A. Golian ◽  
A. Heravi Mousavi ◽  
J. France

Faridi, A., Golian, A., Heravi Mousavi, A. and France, J. 2014. Bootstrapped neural network models for analyzing the responses of broiler chicks to dietary protein and branched chain amino acids. Can. J. Anim. Sci. 94: 79–85. Reliable prediction of avian responses to dietary nutrients is essential for planning, management, and optimization activities in poultry nutrition. In this study, two bootstrapped neural network (BNN) models, each containing 100 separated neural networks (SNN), were developed for predicting average daily gain (ADG) and feed efficiency (FE) of broiler chicks in response to intake of protein and branched chain amino acids (BCAA) in the starter period. Using a re-sampling method, 100 different batches of data were generated for both the ADG and FE sets. Starting with 270 data lines extracted from eight studies in the literature, SNN models were trained, tested, and validated with 136, 67, and 67 data lines, respectively. All 200 SNN models developed, along with their respective BNN ones, were subjected to optimization (to find the optimum dietary protein and BCAA levels that maximize ADG and FE). Statistical analysis indicated that based on R 2, the BNN models were more accurate in 76 and 56 cases (out of 100) compared with the SNN models developed for ADG and FE, respectively. Optimization of the BNN models showed protein, isoleucine, leucine, and valine requirements for maximum ADG were 231.80, 9.05, 14.03 and 10.90 g kg−1 of diet, respectively. Also, maximum FE was obtained when the diet contained 232.30, 9.07, 14.50, and 11.04 g kg−1 of protein, isoleucine, leucine, and valine, respectively. The results of this study suggest that in meta-analytic modelling, bootstrap re-sampling algorithms should be used to better analyze available data and thereby take full advantage of them. This issue is of importance in the animal sciences as producing reliable data is both expensive and time-consuming.

2012 ◽  
Vol 150 (6) ◽  
pp. 775-786 ◽  
Author(s):  
A. FARIDI ◽  
A. GOLIAN ◽  
H. AHMADI

SUMMARYThe current study was conducted to compare the responses of broiler chicks (average daily gain (ADG) and feed efficiency (FE)) raised before and after 2000 to dietary protein and lysine through neural networks (NN). The available lysine dose-response data were extracted from the literature and arbitrarily divided into two sets of before and after 2000. The training and testing data sets derived from each group were used to develop the NN models. The developed models were subjected to a sensitivity analysis test to assess the relative importance of dietary protein and lysine on chicks’ responses. An optimization algorithm was used to find the dietary protein and lysine required for maximum ADG and FE, based on each dataset. The results showed that the NN models developed could predict ADG and FE efficiently in broiler chicks of before and after 2000, and the higher accuracies of prediction were attained by these models compared to those of regression models. Sensitivity analysis indicated that ADG and FE were more sensitive to dietary lysine, compared to protein, in both time periods. Based on the optimization results, the protein and lysine requirements for maximum ADG or FE for birds reared after 2000 were lower and higher, respectively, compared to those reared before 2000. The protein requirements for maximum ADG and FE for birds reared before 2000 were 241·3 and 247·0 g/kg diet and for lysine 10·76 and 11·18 g/kg diet, respectively. In birds reared after 2000, maximum ADG was obtained when the diet contained 224·30 g protein/kg diet and 11·75 g lysine/kg diet, whereas maximum FE was achieved with a diet containing 228·3 g protein and 13·1 g lysine.


2017 ◽  
Vol 6 (8) ◽  
pp. 873-881 ◽  
Author(s):  
Adriano Maida ◽  
Jessica S.K. Chan ◽  
Kim A. Sjøberg ◽  
Annika Zota ◽  
Dieter Schmoll ◽  
...  

Circulation ◽  
2018 ◽  
Vol 137 (suppl_1) ◽  
Author(s):  
Deirdre K Tobias ◽  
Patrick R Lawler ◽  
Paulo H Harada ◽  
Olga V Demler ◽  
Paul M Ridker ◽  
...  

Introduction: Recent metabolomics studies have identified circulating levels of branched-chain amino acids (BCAAs; isoleucine, leucine, valine) as strong predictors of type 2 diabetes (T2D). Whether BCAAs are implicated in cardiovascular disease (CVD) risk has not been established. Hypothesis: We hypothesized that higher baseline levels of plasma BCAAs are associated with an elevated risk of incident CVD events, and evaluated whether this relationship was dependent on an intermediate diagnosis of T2D. Methods: Participants enrolled in the Women’s Health Study prospective cohort were eligible if they did not report CVD or cancer prior to baseline blood collection (N=27,172, mean baseline age=54.7 years). Plasma BCAA metabolites were measured via proton NMR spectroscopy, ln-transformed, and standardized for analysis. We used multivariable Cox proportional regression models to estimate hazard ratios (HR) and 95% confidence intervals (CI) per standard deviation (SD) of total and individual BCAAs with incident CVD (myocardial infarction [MI], stroke, coronary revascularization). Results: 1,917 confirmed CVD events occurred over follow-up (mean 18.6 years). In models adjusted for age, body mass index, smoking status, diet quality, physical activity, and other established CVD risk factors, total BCAAs were positively associated with CVD (per SD, HR=1.13, CI=1.08 to 1.19), comparable in magnitude to the association of LDL cholesterol with CVD (per SD, HR=1.15, CI=1.09 to 1.21). In particular, BCAAs were associated with coronary events (MI: HR=1.21, CI=1.10 to 1.33; revascularization: HR=1.15, CI=1.07 to 1.23), but not with stroke (HR=1.07, CI=0.98 to 1.15). The BCAA-CVD relationship was notably greater (p-interaction=0.008) among participants who developed T2D prior to a CVD event (HR=1.25, CI=1.13 to 1.39), vs. women without T2D (HR=1.07, CI=1.01 to 1.13). Isoleucine, leucine, and valine were each associated with CVD (p<0.05). Further adjusting for biomarkers of potential intermediates, HbA1c, lipids, and a lipoprotein-based insulin resistance score entirely eliminated the associations of BCAAs with CVD. Conclusions: Circulating plasma BCAAs were positively associated with long-term incident CVD in a cohort of US women, in particular among women who developed T2D prior to a CVD event. Impaired BCAA metabolism may represent a shared pathway of insulin resistance that links the risks of T2D and CVD.


2021 ◽  
Vol 5 (Supplement_2) ◽  
pp. 1072-1072
Author(s):  
Akinkunmi Okekunle ◽  
Heejin Lee ◽  
Sherlyn Mae Provido ◽  
Grace Chung ◽  
Sangmo Hong ◽  
...  

Abstract Objectives Migration plays a significant role in dietary choices and health of populations. Studies on dietary intakes of branched-chain amino acids (BCAA) and health status of migrant populations are scarce. This study examined the association between dietary BCAA intake and risk of obesity among migrant Filipino women in Korea. Methods This study included 428 women (20–57years) enrolled in the FiLWHEL study. Demographic information and anthropometric measurements (weight and height) were obtained using a standard protocol. Dietary BCAA (isoleucine, leucine, and valine) intakes were derived from a one-day 24-hour dietary recall. Body mass index (BMI) was calculated from weight and height. Obesity was defined as BMI ≥ 25 kg/m2. Energy-adjusted BCAA intakes were categorized in quartile distribution with the lowest quartile as a reference and multivariable-adjusted odds ratio (OR) with 95% confidence interval (CI) of obesity risk were estimated using logistic regression at a statistical significance of P &lt; 0.05. Results Mean age and BMI were 35.0 ± 8.1 years and 23.6 ± 3.9 kg/m2 respectively. 30.8% had BMI ≥ 25 kg/m2. Also, median and interquartile range of BCAA intakes (mg/day) were isoleucine: 1920.9 (1231.9–2719.1), leucine: 3318.9 (2134.2–4774.1), valine: 2257.3 (1442.6–3283.1) and total BCAA: 7519.0 (4762.0–10,726.9). Multivariable-adjusted OR and 95% CI for obesity risk given dietary BCAA intakes for each subsequent quartile compared to the bottom quartile were; isoleucine: 0.48 (0.27–0.89), 0.67 (0.37–1.02), and 0.49 (0.27–0.89) P for trend = 0.09; leucine: 0.69 (0.37–1.28), 0.80 (0.44–1.46), and 0.62 (0.34–1.13) P for trend = 0.23; valine: 0.51 (0.27–0.95), 0.77 (0.43–1.37), and 0.52 (0.28–0.95) P for trend = 0.15 and total BCAA: 0.58 (0.31–1.09), 0.82 (0.45–1.48), and 0.56 (0.31–1.03) P for trend = 0.23. Conclusions Dietary BCAA intake appears inversely related to the odds of obesity in this sample of Filipino migrants in Korea. Cohort studies among migrant population might significantly benefit the validation of these observations. Funding Sources This work was supported by the Hanmi Pharmaceutical Co., Ltd, (No. 201300000001270), Chong Kun Dang Pharm. Seoul, Korea (No. 201600000000225) and the Brain Pool Program through the National Research Foundation of Korea funded by the Ministry of Science and ICT (No. 2020H1D3A1A04081265).


Animals ◽  
2019 ◽  
Vol 9 (11) ◽  
pp. 981 ◽  
Author(s):  
L. Grispoldi ◽  
M. Karama ◽  
F. Ianni ◽  
A. La Mantia ◽  
L. Pucciarini ◽  
...  

The early diagnosis of mastitis is an essential factor for the prompt detection of the animal for further actions. In fact, if not culled, infected cows must be segregated from the milking herd and milked last, or milked with separate milking units. Besides microbiological analysis, the somatic cell count (SCC) commonly used as predictor of intramammary infection, frequently lead to a misclassification of milk samples. To overcome these limitations, more specific biomarkers are continuously evaluated. The total amino acid content increases significantly in mastitic milk compared to normal milk. S. aureus requires branched-chain amino acids (BCAAs—isoleucine, leucine, and valine) for protein synthesis, branched-chain fatty acids synthesis, and environmental adaptation by responding to their availability via transcriptional regulators. The increase of BCAAs in composite milk has been postulated to be linked to mammary infection by S. aureus. The aim of this work is to demonstrate, by a direct ion-pairing reversed-phase method, based on the use of the evaporative light-scattering detector (IP-RP-HPLC-ELSD), applied to 65 composite cow milk samples, a correlation between the concentration of isoleucine and leucine, and S. aureus load. The correlation coefficient, r, was found to be 0.102 for SCC (p = 0.096), 0.622 for isoleucine (p < 0.0001), 0.586 for leucine (p < 0.0001), 0.013 for valine (p = 0.381), and 0.07 for tyrosine (p = 0.034), standing for a positive correlation between S. aureus and isoleucine and leucine concentration. The link between the content of BCAAs, isoleucine and leucine, and udder infection by S. aureus demonstrated with our study has an important clinical value for the rapid diagnosis of S. aureus mastitis in cows.


2020 ◽  
Vol 98 (Supplement_3) ◽  
pp. 18-18
Author(s):  
Maroua Zouaoui ◽  
Aude Simongiovanni ◽  
Marie-Pierre Létourneau-Montminy

Abstract Branched chain amino acids (BCAA), valine (Val), isoleucine (Ile) and leucine (Leu) share the same metabolic pathways. An excess of Leu stimulates the catabolism of Val and Ile that may lead to a decrease in piglet growth performance. The objective of this study is to quantify the response of piglets to dietary Val and the influence of Leu and Ile on this response through a meta-analysis approach. A total of 16 articles published between 2001 and 2018, including 23 experiments and 126 treatments were used. Multiple regression models were fitted with the MIXED procedure of Minitab software with the random effect of the experiment. The Y variables were Average Daily Gain (ADG), Average Daily Feed Intake (ADFI) and Feed Conversion Ratio (FCR). The main X variable was the Standardized Ileal Digestible Val (ValSID) and the other ones were Leu (LeuSID) and Ile (IleSID). The response of ADG, ADFI and FCR to ValSID was curvilinear (P&lt; 0.001: ADG, R2 = 0.93%; ADFI, R2= 0.97%; FCR, R2=0.93%). Results showed that increasing dietary LeuSID reduced ADG and ADFI (P&lt; 0.05) but also that the response of piglets to ValSID was stronger in high LeuSID diet (P &lt; 0.05; Interaction ValSIDxLeuSID; ADG and ADFI). Based on these models, increasing dietary ValSID from 7 to 8.5g/kg generates in wheat-based diets (10 g /kg of LeuSID) an improvement of ADG of 4.7% and ADFI of 2.5% compared to 7.4% for ADG and 5.2% for ADFI in corn-based diets (14 g/ kg of LeuSID). The response of ADG, ADFI and FCR to ValSID was not modified by IleSID. This study showed that ADG, ADFI and FCR are improved with increasing dietary Val and this effect was modulated by dietary Leu content except for FCR. Results can help piglet nutritionists to optimize dietary Val levels based on other BCAA content.


Sign in / Sign up

Export Citation Format

Share Document