Skip to content
DraconiticResearch
Search Sources API
226,742 studies31 sourcesUpdated 43 min ago
Peer-reviewedCC BY-NC-ND 4.0Animal Nutrition

A dynamic machine learning framework mitigates data drift for predicting responses to dietary arginine-to-lysine ratios in lactating sows

  1. 1State Key Laboratory of Swine and Poultry Breeding, Key Laboratory of Animal Nutrition and Feed Science in South China, Ministry of Agriculture and Rural Affairs, Guangdong Provincial Key Laboratory of Animal Breeding and Nutrition, Institute of Animal Science, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, Guangdong, China
  2. 2Guangxi Key Laboratory of Animal Breeding, Disease Control and Prevention, College of Animal Science and Technology, Guangxi University, Nanning 530004, Guangxi, China
  3. 3Institute of Agricultural Resources and Environment, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, Guangdong, China

Abstract

Arginine is critical for optimizing sow lactation, yet its dose-response relationship in low-protein (LP) diets remains poorly characterized. This study developed a dynamic machine learning (ML) framework, trained on historical sow performance data (n = 380), to predict the optimal arginine-to-lysine (A/L) ratio. Among the ensemble models, the decision tree regression model achieved the highest predictive accuracy (R2 = 0.956) and identified an A/L ratio of 1.03 as optimal. To validate this prediction, a 21-day feeding trial was conducted using 40 lactating sows (Landrace × Large White, 3rd parity, 220 ± 3 kg). Sows were randomly assigned to four treatment groups (n = 10), including a normal-protein diet (CON) with A/L ratio of 1.21 and an LP diet supplemented with A/L ratios of 0.83, 0.93, or 1.03. Results indicated that while the LP diet significantly compromised piglet growth and intestinal integrity compared to the CON diet (P < 0.05), the ML-predicted A/L ratio of 1.03 effectively restored performance. Specifically, it increased piglet average daily gain (ADG) relative to the A/L ratio of 0.83 (P = 0.030). Regarding the intestinal barrier, the A/L ratio of 1.03 enhanced piglet jejunal morphology, increased villus height to crypt depth ratio, and upregulated ZO-1 mRNA expression (P < 0.05). From a metabolic perspective, A/L ratio of 1.03 optimized systemic nutrient status by elevating sow plasma glutamine, milk cysteine, and piglet serum total protein (P < 0.05). Furthermore, A/L ratio of 1.03 mitigated LP-induced oxidative stress by increasing total superoxide dismutase (T-SOD) and glutathione peroxidase (GSH-Px) activities in sow serum and total antioxidant capacity (T-AOC) in milk, while reducing malondialdehyde (MDA) content (P < 0.05). This ratio also bolstered immunity through higher sow serum secretory immunoglobulin A (sIgA) and piglet mucosal immunoglobulin M (IgM) levels (P < 0.05). In addition, it beneficially modulated the intestinal microbiota by increasing the Shannon index and the abundance of Firmicutes (P < 0.05). Finally, newly generated experimental data were subsequently integrated into the ML framework. A Kolmogorov-Smirnov test comparing data distributions triggered incremental model updating, which mitigated data drift and maintained predictive accuracy. In summary, this study establishes a novel closed-loop ML framework that not only guides targeted nutritional experimentation but also continuously self-improves. The findings confirm that an A/L ratio of 1.03 optimizes LP diets for lactating sows and provides a scalable drift-resilient tool for precision nutrition in animal production.

Related

  1. Functional guild analysis characterizes gut microbiome responses to heat stress in thermotolerant and thermosensitive lactating sows across three omics layers
    Christian Maltecca, Chiara Gini, Hui Wen +6
    BMC GenomicsPeer-reviewedCC BY-NC-ND 4.0Zoology & animal behaviourCrossref
  2. SPECTRA: predicting cellular perturbation responses with Graph Learning over Gene Regulatory Networks
    M. Calabro, P. Sheehan, F. Cambuli +1
    bioRxivPreprintCC BYFull textSystems & synthetic biologybioRxiv
  3. Data paper: Cross-species datasets on individual associative learning to regulate access to shared resources in group-housed gestating sows and lactating dairy cows
    Charlotte Gaillard, Anna Blanc, Clémentine Deroiné +5
    Animal - Open SpacePeer-reviewedCC BY 4.0Full textGeneral biologyHAL
  4. Multiparametric MRI Radiomics and Machine Learning Framework for Predicting Treatment Response in Glioblastoma
    Suchibrata Patra
    arXivPreprintCC BY 4.0Full textBioinformatics & computational biologyStatisticsarXiv
  5. Spermidine Mitigates Immune Cell Senescence and Boosts Vaccine Responses in Healthy Older Adults—A Pilot Study
    Ghada Alsaleh, Mohammad Ali, Amir Hossein Kayvanjoo +23
    Aging CellPeer-reviewedCC BY7 citedImmunologyOpenAlex
BibTeX
@article{li2026dynamic,
  title = {{A dynamic machine learning framework mitigates data drift for predicting responses to dietary arginine-to-lysine ratios in lactating sows}},
  author = {Shuai Li and Fang Gu and Huangjiaqi Kong and Xiangyang Ye and Yusheng Lu and Kaiguo Gao and Li Wang and Zhiwei Kong and Xingwei Liang and Hao Xiao},
  journal = {Animal Nutrition},
  year = {2026},
  month = oct,
  doi = {10.1016/j.aninu.2026.05.008},
  url = {https://doi.org/10.1016/j.aninu.2026.05.008},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - JOUR
TI  - A dynamic machine learning framework mitigates data drift for predicting responses to dietary arginine-to-lysine ratios in lactating sows
AU  - Shuai Li
AU  - Fang Gu
AU  - Huangjiaqi Kong
AU  - Xiangyang Ye
AU  - Yusheng Lu
AU  - Kaiguo Gao
AU  - Li Wang
AU  - Zhiwei Kong
AU  - Xingwei Liang
AU  - Hao Xiao
PY  - 2026
DA  - 2026/10/09
JO  - Animal Nutrition
DO  - 10.1016/j.aninu.2026.05.008
UR  - https://doi.org/10.1016/j.aninu.2026.05.008
AB  - Arginine is critical for optimizing sow lactation, yet its dose-response relationship in low-protein (LP) diets remains poorly characterized. This study developed a dynamic machine learning (ML) framework, trained on historical sow performance data (n = 380), to predict the optimal arginine-to-lysine (A/L) ratio. Among the ensemble models, the decision tree regression model achieved the highest predictive accuracy (R2 = 0.956) and identified an A/L ratio of 1.03 as optimal. To validate this prediction, a 21-day feeding trial was conducted using 40 lactating sows (Landrace × Large White, 3rd parity, 220 ± 3 kg). Sows were randomly assigned to four treatment groups (n = 10), including a normal-protein diet (CON) with A/L ratio of 1.21 and an LP diet supplemented with A/L ratios of 0.83, 0.93, or 1.03. Results indicated that while the LP diet significantly compromised piglet growth and intestinal integrity compared to the CON diet (P < 0.05), the ML-predicted A/L ratio of 1.03 effectively restored performance. Specifically, it increased piglet average daily gain (ADG) relative to the A/L ratio of 0.83 (P = 0.030). Regarding the intestinal barrier, the A/L ratio of 1.03 enhanced piglet jejunal morphology, increased villus height to crypt depth ratio, and upregulated ZO-1 mRNA expression (P < 0.05). From a metabolic perspective, A/L ratio of 1.03 optimized systemic nutrient status by elevating sow plasma glutamine, milk cysteine, and piglet serum total protein (P < 0.05). Furthermore, A/L ratio of 1.03 mitigated LP-induced oxidative stress by increasing total superoxide dismutase (T-SOD) and glutathione peroxidase (GSH-Px) activities in sow serum and total antioxidant capacity (T-AOC) in milk, while reducing malondialdehyde (MDA) content (P < 0.05). This ratio also bolstered immunity through higher sow serum secretory immunoglobulin A (sIgA) and piglet mucosal immunoglobulin M (IgM) levels (P < 0.05). In addition, it beneficially modulated the intestinal microbiota by increasing the Shannon index and the abundance of Firmicutes (P < 0.05). Finally, newly generated experimental data were subsequently integrated into the ML framework. A Kolmogorov-Smirnov test comparing data distributions triggered incremental model updating, which mitigated data drift and maintained predictive accuracy. In summary, this study establishes a novel closed-loop ML framework that not only guides targeted nutritional experimentation but also continuously self-improves. The findings confirm that an A/L ratio of 1.03 optimizes LP diets for lactating sows and provides a scalable drift-resilient tool for precision nutrition in animal production.
SN  - 2405-6545
SN  - 2405-6383
ER  -