Skip to content
DraconiticResearch
Search Sources API
203,948 studies31 sourcesUpdated 10 min ago
Peer-reviewedCC BYiMeta

From prediction to actionable mechanisms: Explainable multi‑omics AI for farm‑to‑fork postharvest preservation

  • Peihua Ma1
  • Xiaoxue Jia1
  • Bei Fan1
  • Boqiang Li2
  • Tao Lin3
  • Jiping Sheng4
  • Cheng–I Wei5
  • Yingjian Lu6
  • Yizhou Ma7
  • L Chen8
  • Songtao Jiu9
  • Fengzhong Wang1
9 affiliations
  1. 1Institute of Food Science and Technology, Chinese Academy of Agricultural Sciences, Key Laboratory of Agro‐products Processing Ministry of Agriculture and Rural Affairs Beijing China
  2. 2State Key Laboratory of Plant Diversity and Specialty Crops, Institute of Botany Chinese Academy of Sciences Beijing China
  3. 3Beijing Key Laboratory of Growth and Developmental Regulation for Protected Vegetable Crops, College of Horticulture China Agricultural University Beijing China
  4. 4School of Agricultural Economics and Rural Development Renmin University of China Beijing China
  5. 5Department of Nutrition and Food Science, College of Agriculture and Natural Resources University of Maryland, College Park College Park Maryland USA
  6. 6College of Food Science and Engineering Nanjing University of Finance and Economics Nanjing China
  7. 7Laboratory of Food Process Engineering Wageningen University & Research Wageningen The Netherlands
  8. 8School of Chemistry, Chemical Engineering and Biotechnology Nanyang Technological University Singapore Singapore
  9. 9Department of Plant Science, School of Agriculture and Biology Shanghai Jiao Tong University Shanghai China
Open at sourceDOICite

Abstract

Graphical overview of explainable artificial intelligence (XAI) for farm-to-fork postharvest preservation. Postharvest deterioration accumulates across orchard, packhouse, refrigerated transportation, warehouse, and distribution stages under fluctuating temperature, humidity, atmosphere, and mechanical stress. Multimodal data streams, including host omics, microbiome profiles, environmental sensing, RGB/hyperspectral/thermal imaging, spectroscopy, key genes, and logistics records, are integrated through a data lakehouse and analyzed by postharvest XAI models. Explainable modules, including SHapley Additive exPlanations (SHAP)/local attribution, graph neural network (GNN) explanation, pathway-constrained models, counterfactual reasoning, and stability/faithfulness auditing, convert black-box spoilage-risk prediction into interpretable biological mechanisms. These mechanisms guide actionable interventions such as antioxidant coating, elicitor spray, biocontrol consortia, packaging optimization, and gene-targeted strategies. Validation through storage trials, sensory evaluation, microbial testing, and sequencing closes the loop from prediction to explanation, intervention, and validated decision support.

Related

  1. Edible Biopolymer Coatings for Postharvest Preservation in Warm-Chain Horticultural Supply Chain: Mechanisms, Materials, Design Strategies, and Future Directions.
    Olaoluwa Omoniyi Olarewaju, Olufunke Omowumi Fajinmi
    Comprehensive reviews in food science and food safetyPeer-reviewedCC BYFull textPlant biologyEurope PMC
  2. Biopolymer-Based Nanocomposite Edible Coatings for Postharvest Preservation of Horticultural Crops: Mechanisms, Functional Additives, and Safety Perspectives
    Mukhtar Iderawumi Abdulraheem, Yusuf Ola Mukaila, Marissa Pérez-Alvarez +2
    PolymersPeer-reviewedCC BY 4.0Plant biologyCrossref
  3. Postharvest senescence of broccoli in the multi-omics era: molecular mechanisms, regulatory networks, and prospects for germplasm innovation
    Han-Min Jiang, Li-Li Liu, Zheng-Hua Wen +5
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Plant biologyFrontiersCrossref
  4. Post-slaughter poultry meat preservation for sustainable food systems: Mechanisms, microbial safety, shelf-life extension, and emerging preservation strategies
    Rabin Raut, Zahidul Hasan Tushar, Roshik Shrestha +4
    Poultry sciencePeer-reviewedCC BY-NC-NDFull textZoology & animal behaviourEurope PMC
  5. Formation and preservation mechanisms of ultra-deep microbialite-dominated reservoirs in the ediacaran dengying formation from the central to Northern Sichuan Basin, SW China
    Zhehang Xu, Wenzheng Li, Zhanfeng Qiao +9
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textEvolutionary biologyCrossref

Cite

BibTeXRIS
BibTeX
@article{ma2026from,
  title = {{From prediction to actionable mechanisms: Explainable multi‑omics AI for farm‑to‑fork postharvest preservation}},
  author = {Peihua Ma and Xiaoxue Jia and Bei Fan and Boqiang Li and Tao Lin and Jiping Sheng and Cheng–I Wei and Yingjian Lu and Yizhou Ma and L Chen and Songtao Jiu and Fengzhong Wang},
  journal = {iMeta},
  year = {2026},
  month = jun,
  doi = {10.1002/imt2.70139},
  url = {https://doi.org/10.1002/imt2.70139},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - From prediction to actionable mechanisms: Explainable multi‑omics AI for farm‑to‑fork postharvest preservation
AU  - Peihua Ma
AU  - Xiaoxue Jia
AU  - Bei Fan
AU  - Boqiang Li
AU  - Tao Lin
AU  - Jiping Sheng
AU  - Cheng–I Wei
AU  - Yingjian Lu
AU  - Yizhou Ma
AU  - L Chen
AU  - Songtao Jiu
AU  - Fengzhong Wang
PY  - 2026
DA  - 2026/06/01
JO  - iMeta
DO  - 10.1002/imt2.70139
UR  - https://doi.org/10.1002/imt2.70139
AB  - Graphical overview of explainable artificial intelligence (XAI) for farm-to-fork postharvest preservation. Postharvest deterioration accumulates across orchard, packhouse, refrigerated transportation, warehouse, and distribution stages under fluctuating temperature, humidity, atmosphere, and mechanical stress. Multimodal data streams, including host omics, microbiome profiles, environmental sensing, RGB/hyperspectral/thermal imaging, spectroscopy, key genes, and logistics records, are integrated through a data lakehouse and analyzed by postharvest XAI models. Explainable modules, including SHapley Additive exPlanations (SHAP)/local attribution, graph neural network (GNN) explanation, pathway-constrained models, counterfactual reasoning, and stability/faithfulness auditing, convert black-box spoilage-risk prediction into interpretable biological mechanisms. These mechanisms guide actionable interventions such as antioxidant coating, elicitor spray, biocontrol consortia, packaging optimization, and gene-targeted strategies. Validation through storage trials, sensory evaluation, microbial testing, and sequencing closes the loop from prediction to explanation, intervention, and validated decision support.
SN  - 2770-596X
SN  - 2770-5986
ER  -