[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3858":3,"related-3858":90},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":18,"tags":20,"primary_topic":9,"secondary_topics":25,"classification":26,"search_phrases":60,"slug":63,"view_count":64,"doi":65,"paper":66,"created_at":89},3858,"Applications of artificial intelligence in personalized nutrition interventions","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffnut.2026.1974199","Unhealthy dietary patterns remain a major modifiable contributor to the global burden of obesity, type 2 diabetes mellitus (T2DM), cardiovascular disease, and cancer. However, individuals can respond markedly differently to identical foods, limiting the effectiveness of one-size-fits-all dietary guidance. This review examines the application of artificial intelligence (AI) to personalized nutrition interventions across three interconnected layers. At the biological level, inter-individual variability can be characterized by three mechanistic dimensions: nutrigenomic variation, which influences nutrient metabolism and disease susceptibility; metabolomic biomarkers, which objectively capture dietary exposure and early metabolic alterations; and the gut microbiome, which bidirectionally mediates diet–host interactions. At the technological level, AI integrates these dimensions into multimodal digital profiles. Machine learning models predict individual postprandial glycemic and lipemic responses, with reported correlations of up to r = 0.77 in large cohorts; deep learning and computer vision automate dietary assessment; natural language processing and large language models (LLMs) support nutrition counseling; knowledge graphs enable constraint-aware food recommendations; and digital-twin and adaptive closed-loop systems incorporating continuous glucose monitoring and wearable-device data support real-time nutritional interventions. However, the strength of clinical evidence varies across disease domains. Glycemic management in T2DM and prediabetes currently has the most mature randomized controlled trial evidence: an AI-enabled personalized intervention combining algorithmic dietary personalization with CGM-linked feedback improved glycemic endpoints compared with a Mediterranean diet, while a fully automated AI-delivered diabetes prevention program achieved outcomes non-inferior to those of human coaching. In obesity, cardiovascular disease, oncology, and gastrointestinal disorders, the evidence remains mixed or preliminary. Clinical translation also faces substantial challenges, including biased and inconsistently standardized dietary and multi-omics data; the underrepresentation of non-European populations, which limits model generalizability and raises concerns about health equity; limited model explainability; privacy and data-governance challenges; immature regulatory pathways for adaptive software as a medical device; and specific risks associated with LLMs, such as hallucinated or guideline-discordant dietary advice. AI-enabled personalized nutrition is therefore progressing from proof of concept toward clinical translation. Realizing its potential equitably will require multi-ethnic nutrition–omics cohorts, privacy-preserving multicenter collaboration, dietitian-led human–AI collaboration, and lifecycle safety governance for generative models.","不健康的饮食模式仍是全球肥胖、2型糖尿病(T2DM)、心血管疾病和癌症负担的主要可改变因素。然而，个体对相同食物的反应可能显著不同，这限制了一刀切式饮食指导的有效性。本综述从三个相互关联的层面考察人工智能(AI)在个性化营养干预中的应用。在生物学层面，个体间差异可通过三个机制维度加以表征：营养基因组学变异，其影响营养素代谢和疾病易感性；代谢组学生物标志物，其可客观反映膳食暴露和早期代谢改变；以及肠道微生物组，其双向介导饮食–宿主相互作用。在技术层面，AI将这些维度整合为多模态数字画像。机器学习模型可预测个体餐后血糖和血脂反应，在大型队列中报告的相关性高达r = 0.77；深度学习和计算机视觉可自动化膳食评估；自然语言处理和大语言模型(LLMs)可支持营养咨询；知识图谱可实现约束感知的食物推荐；结合连续血糖监测和可穿戴设备数据的数字孪生和自适应闭环系统可支持实时营养干预。然而，临床证据强度在不同疾病领域存在差异。T2DM和糖尿病前期的血糖管理目前拥有最成熟的随机对照试验证据：一项AI赋能的个性化干预将算法驱动的饮食个性化与CGM关联反馈相结合，与地中海饮食相比改善了血糖终点，而一项完全自动化、由AI实施的糖尿病预防项目取得了不劣于人工指导的结果。在肥胖、心血管疾病、肿瘤学和胃肠道疾病中，证据仍不一致或处于初步阶段。临床转化还面临重大挑战，包括膳食和多组学数据存在偏倚且标准化不一致；非欧洲人群代表性不足，这限制了模型可泛化性并引发对健康公平性的担忧；模型可解释性有限；隐私和数据治理挑战；作为医疗器械的自适应软件监管路径尚不成熟；以及与",null,"Frontiers in Nutrition","2026-09-28T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该文为医学营养领域的AI综述，与三农、农业信息化、智慧农业无直接关联，不建议进入每日精选。",[19],{"name":10,"url":6},[21,22,23,24],"农业人工智能","多组学","数字健康","精准营养",[],{"status":27,"locked":14,"version":28,"method":29,"evidence":30},"needs_review","2026-10-22.2","rules",{"candidates":31,"agricultural_evidence":14,"reason":59},[32,46,53],{"code":33,"score":34,"supported":35,"title":36,"abstract":38,"tags":45},"I2",18,true,[37],"artificial intelligence",[39,40,41,42,43,37,44],"深度学习","机器学习","计算机视觉","machine learning","deep learning","computer vision",[21],{"code":47,"score":48,"supported":35,"title":49,"abstract":50,"tags":52},"I1",3,[],[51],"数字孪生",[],{"code":54,"score":55,"supported":14,"title":56,"abstract":57,"tags":58},"F2",1,[],[],[22],"农业相关性需要复核",[61,62],"AI 个性化营养","肠道微生物 营养干预","AI个性化营养-3858",4,"10.3389\u002Ffnut.2026.1974199",{"doi":65,"openalex_id":67,"authors":68,"venue":10,"cited_by_count":15,"oa_url":80,"card":81,"direction":87,"ingested_from":88},"W7214581081",[69,72,74,76,78],{"name":70,"orcid":71},"Ya Zhang","https:\u002F\u002Forcid.org\u002F0000-0003-0894-4922",{"name":73,"orcid":9},"Meijing Feng",{"name":75,"orcid":9},"Qiuyan Xue",{"name":77,"orcid":9},"Rui Ma",{"name":79,"orcid":9},"Fangming Liu","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fnutrition\u002Farticles\u002F10.3389\u002Ffnut.2026.1974199\u002Fpdf",{"tldr":82,"method":83,"finding":84,"direction":85,"opportunity":86},"综述AI在个性化营养干预中的应用，涵盖生物、技术、临床三层并评估证据强度。","综述多组学、机器学习、深度学习、LLM、知识图谱、数字孪生与CGM闭环系统。","T2DM\u002F糖尿病前期证据最成熟，AI个性化干预优于地中海饮食；肥胖、心血管、肿瘤等证据仍混合或初步。","农业人工智能与决策模型","可探索将AI个性化营养与农业食品生产、膳食推荐及可穿戴设备数据闭环结合，并关注数据偏差与公平性。","数字乡村与农业信息化","openalex","2026-09-30T23:30:41.633764Z",{"total":91,"page":55,"page_size":91,"items":92},6,[93,233,307,414,461,529],{"id":94,"title":95,"url":96,"summary":97,"summary_zh":98,"content":9,"source_name":99,"source_url":96,"published_at":100,"category":12,"cover_url":9,"hotness":13,"is_selected":35,"score":101,"score_detail":102,"sources":108,"tags":110,"primary_topic":115,"secondary_topics":121,"classification":122,"search_phrases":199,"slug":202,"view_count":15,"doi":203,"paper":204,"created_at":232},4832,"Applications and Future Prospects of Plant Multi-Omics Technologies in Precision Agriculture","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fijms27209034","Against the backdrop of global population growth, intensifying climate change, and limited arable land, ensuring food security and promoting sustainable agriculture have become critical issues. The limitations of conventional agricultural systems are becoming increasingly apparent, creating an urgent need for innovation driven by science and technology. In this context, plant multi-omics technologies serve as the foundational data and technical cornerstone of systems biology and precision agriculture. Integrating multi-level data from genomics, transcriptomics, proteomics, metabolomics, epigenomics, and microbiomics offers substantial advantages for systematically understanding and improving plants. Unlike previous reviews that mainly catalog omics technologies or focus on individual crops, this review adopts a unified discovery-to-translation framework and critically evaluates the strength of evidence across applications. This review focuses on cutting-edge applications of multi-omics in three key areas: improving the traits of cereal crops (rice, wheat and maize), remediating soil health, and innovating products such as biofertilizers and biostimulants for agriculture. We systematically explore the roles of multi-omics in accelerating breeding processes, deciphering complex agronomic traits, restoring soil ecosystems, and constructing intelligent decision-support systems. The review also examines current challenges, including the complexity of data integration and the difficulties of predicting genotype-by-environment interactions. Furthermore, it outlines future directions involving deeper convergence with artificial intelligence, high-throughput phenomics, and digital twins. In summary, plant multi-omics technology is a vital tool for unravelling the mysteries of plant life and is also a key enabler of intelligent, precise and sustainable agricultural transformation.","在全球人口增长、气候变化加剧和耕地有限的背景下，保障粮食安全和促进可持续农业已成为关键议题。传统农业系统的局限性日益显现，迫切需要由科学和技术驱动的创新。在此背景下，植物多组学技术作为系统生物学和精准农业的基础数据与技术基石，整合基因组学、转录组学、蛋白质组学、代谢组学、表观基因组学和微生物组学等多层次数据，为系统理解和改良植物提供了显著优势。与以往主要罗列组学技术或聚焦单一作物的综述不同，本综述采用统一的“从发现到转化”框架，并批判性评估各应用中的证据强度。本综述聚焦多组学在三个关键领域的前沿应用：改良谷类作物（水稻、小麦和玉米）的性状、修复土壤健康，以及创新生物肥料和生物刺激素等农业产品。我们系统探讨了多组学在加速育种进程、解析复杂农艺性状、恢复土壤生态系统和构建智能决策支持系统中的作用。本综述还审视了当前挑战，包括数据整合的复杂性和预测基因型与环境互作的困难。此外，文章展望了未来方向，涉及与人工智能、高通量表型组学和数字孪生的更深层次融合。总之，植物多组学技术是揭示植物生命奥秘的重要工具，也是智能、精准和可持续农业转型的关键使能技术。","International Journal of Molecular Sciences","2026-10-12T00:00:00Z",83,{"impact":103,"substance":104,"depth":34,"authority":105,"freshness":106,"relevant":55,"comment":107},22,21,14,8,"核心期刊综述，系统梳理植物多组学在精准农业中的应用与AI、数字孪生等未来方向，专业深度与信源权威度俱佳，值得进入每日精选。",[109],{"name":99,"url":96},[111,21,112,113,114,22],"智慧农业","种业振兴","精准农业","土壤健康",{"code":116,"slug":117,"name":118,"path":119,"parent_code":120},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[],{"status":123,"locked":14,"version":28,"method":29,"evidence":124},"classified",{"candidates":125,"agricultural_evidence":35},[126,132,138,145,152,159,166,173,180,184,190,195],{"code":47,"score":127,"supported":35,"title":128,"abstract":130,"tags":131},19,[129],"precision agriculture",[113,51,129],[111,113],{"code":116,"score":133,"supported":35,"title":134,"abstract":135,"tags":137},7,[],[136,117],"土壤",[114],{"code":139,"score":91,"supported":35,"title":140,"abstract":141,"tags":144},"A1",[],[142,143],"水稻","rice",[],{"code":146,"score":91,"supported":35,"title":147,"abstract":148,"tags":151},"A2",[],[149,150],"小麦","wheat",[],{"code":153,"score":91,"supported":35,"title":154,"abstract":155,"tags":158},"A3",[],[156,157],"玉米","maize",[],{"code":160,"score":91,"supported":35,"title":161,"abstract":162,"tags":165},"A8",[],[163,164],"粮食安全","food security",[],{"code":167,"score":91,"supported":35,"title":168,"abstract":169,"tags":172},"H7",[],[170,171],"气候变化","climate change",[],{"code":174,"score":91,"supported":35,"title":175,"abstract":176,"tags":179},"H8",[],[177,178],"可持续农业","sustainable agriculture",[],{"code":33,"score":64,"supported":35,"title":181,"abstract":182,"tags":183},[],[37],[21],{"code":185,"score":48,"supported":35,"title":186,"abstract":187,"tags":189},"F3",[],[188],"肥料",[],{"code":191,"score":55,"supported":14,"title":192,"abstract":193,"tags":194},"F1",[],[],[112],{"code":54,"score":55,"supported":14,"title":196,"abstract":197,"tags":198},[],[],[22],[200,201],"植物多组学 精准农业","多组学 智能育种","植物多组学精准农业-4832","10.3390\u002Fijms27209034",{"doi":203,"openalex_id":205,"authors":206,"venue":99,"cited_by_count":15,"oa_url":96,"card":227,"direction":87,"ingested_from":88},"W7221567543",[207,210,212,215,217,219,222,225],{"name":208,"orcid":209},"Tao Tong","https:\u002F\u002Forcid.org\u002F0000-0002-9003-9667",{"name":211,"orcid":9},"Wang Qingxia",{"name":213,"orcid":214},"Fanrong Zeng","https:\u002F\u002Forcid.org\u002F0000-0001-7742-5195",{"name":216,"orcid":9},"Shuzhen Ye",{"name":218,"orcid":9},"Zhijuan Ji",{"name":220,"orcid":221},"Zhong‐Hua Chen","https:\u002F\u002Forcid.org\u002F0000-0002-7531-320X",{"name":223,"orcid":224},"Jiaoyu Wang","https:\u002F\u002Forcid.org\u002F0000-0002-0249-808X",{"name":226,"orcid":9},"Younan Ouyang",{"tldr":228,"method":229,"finding":230,"direction":85,"opportunity":231},"综述植物多组学在精准农业中的应用，涵盖作物改良、土壤修复和生物产品创新。","整合基因组、转录组、蛋白组、代谢组等多组学数据，采用发现到转化框架。","多组学可加速育种、解析复杂农艺性状、修复土壤生态并构建智能决策系统。","多组学与AI、高通量表型、数字孪生融合，解决基因型-环境互作预测难题。","2026-10-13T23:30:29.504594Z",{"id":234,"title":235,"url":236,"summary":237,"summary_zh":238,"content":9,"source_name":239,"source_url":236,"published_at":240,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":241,"score_detail":242,"sources":245,"tags":247,"primary_topic":250,"secondary_topics":256,"classification":257,"search_phrases":289,"slug":292,"view_count":55,"doi":293,"paper":294,"created_at":306},3665,"ASAS-NANP SYMPOSIUM: MATHEMATICAL MODELING IN ANIMAL NUTRITION: The Evolution of Large Language Models and Their Impact on Animal Sciences","https:\u002F\u002Fdoi.org\u002F10.1093\u002Fjas\u002Fskag306","The rapid rise of large language models (LLM) is reshaping the scientific landscape, transitioning from early statistical language models to advanced transformer-based architectures capable of synthesizing knowledge across disciplines. While their predictive capacity and scalability have opened new avenues in data analysis, hypothesis generation, and decision support, concerns remain regarding bias, hallucination, reproducibility, and ethical governance. In animal sciences, LLM are gradually applied to challenges in nutrition modeling, animal health, genetic selection, and sustainability. Precision nutrition has benefited from LLM-driven synthesis of feed and metabolic data, enabling individualized feeding strategies and improved resource efficiency. In animal health, domain-specific systems have demonstrated applications in diagnostics and epidemiological monitoring. LLM is augmenting genomic analyses to accelerate marker discovery and breeding optimization, while sustainability efforts employ them to model greenhouse gas emissions, feed additives, and adaptation to climatic stressors. Notably, decision-support platforms demonstrate how domain-specialized LLM can bridge mechanistic knowledge with predictive analytics, enhancing knowledge transfer and empowering livestock producers. However, risks associated with overreliance, recursive reuse of LLM outputs in model development, and pseudo-expertise underscore the critical importance of human oversight. Unlike mechanistic models, which embed biological causality, LLM are entirely data-driven and may confidently propagate errors if trained on ill-conditioned datasets. Responsible use requires transparent reporting, validation, and bias auditing, with domain-specific fine-tuning. Open-source models can enhance reproducibility and trust, but they also raise financial and security concerns. LLM must be guided by transparency, accountability, and fairness to ensure they complement, rather than replace, human expertise. By advancing inquiry and livestock management, LLM hold the potential to support sustainable food production systems if deployed responsibly. Rather than full training, most applications will rely on fine-tuning and augmentation, which are more sustainable and adaptable strategies. This review intends to promote critical literacy and responsible adoption of LLM in research, education, and livestock decision-support systems for animal scientists, nutrition modelers, and extension professionals.","大语言模型（LLM）的迅速崛起正在重塑科学格局，从早期的统计语言模型过渡到能够跨学科综合知识的先进基于Transformer的架构。尽管其预测能力和可扩展性在数据分析、假设生成和决策支持方面开辟了新途径，但围绕偏见、幻觉、可重复性和伦理治理的担忧依然存在。在动物科学领域，LLM正逐步应用于营养建模、动物健康、遗传选择和可持续性等方面的挑战。精准营养已受益于LLM驱动的饲料与代谢数据综合，从而实现个体化饲喂策略并提高资源效率。在动物健康方面，领域专用系统已在诊断和流行病学监测中展现出应用价值。LLM正在增强基因组分析，以加速标记发现和育种优化，而可持续性工作则利用其建模温室气体排放、饲料添加剂及对气候胁迫的适应性。值得注意的是，决策支持平台展示了领域专用LLM如何将机制性知识与预测分析相衔接，促进知识转化并赋能畜牧生产者。然而，过度依赖、在模型开发中递归复用LLM输出以及伪专业知识等风险，凸显了人类监督的至关重要性。与嵌入生物学因果关系的机制性模型不同，LLM完全由数据驱动，若在病态数据集上训练，可能自信地传播错误。负责任的使用需要透明报告、验证和偏见审计，并进行领域专用微调。开源模型可以增强可重复性和信任，但也引发财务和安全方面的担忧。LLM必须以透明性、问责制和公平性为指引，以确保其补充而非取代人类专业知识。通过在研究和畜牧管理中推动探究，LLM在负责任部署的前提下具有支持可持续食品生产系统的潜力。大多数应用将依赖微调和增强，而非完整训练，这是更具可持续性和适应性的策略。本综述旨在促进动物科学家、营养建模人员和推广专业人员在研究、教育和畜牧决策支持系统中对LLM的批判性素养和负责任采用。","Journal of Animal Science","2026-09-25T00:00:00Z",78,{"impact":34,"substance":243,"depth":34,"authority":105,"freshness":106,"relevant":55,"comment":244},20,"核心期刊综述，系统梳理大语言模型在动物营养、健康与育种中的应用与风险，专业深度高但属综述性论文，产业级影响有限。",[246],{"name":239,"url":236},[111,21,248,24,249],"大语言模型","动物科学",{"code":251,"slug":252,"name":253,"path":254,"parent_code":255},"B7","protected-horticulture","设施园艺与植物工厂","\u002Ftopic\u002Fhorticulture\u002Fprotected-horticulture","B",[],{"status":123,"locked":14,"version":28,"method":29,"evidence":258},{"candidates":259,"agricultural_evidence":35},[260,266,273,279,285],{"code":251,"score":91,"supported":35,"title":261,"abstract":262,"tags":265},[],[263,264],"温室","greenhouse",[],{"code":267,"score":91,"supported":35,"title":268,"abstract":269,"tags":272},"C",[],[270,271],"畜牧","livestock",[],{"code":33,"score":274,"supported":35,"title":275,"abstract":276,"tags":278},5,[],[277],"decision support",[21,248],{"code":280,"score":48,"supported":35,"title":281,"abstract":282,"tags":284},"C4",[],[283],"饲料",[],{"code":47,"score":55,"supported":14,"title":286,"abstract":287,"tags":288},[],[],[111],[290,291],"大语言模型 动物科学","LLM 精准营养","大语言模型动物科学-3665","10.1093\u002Fjas\u002Fskag306",{"doi":293,"openalex_id":295,"authors":296,"venue":239,"cited_by_count":15,"oa_url":299,"card":300,"direction":305,"ingested_from":88},"W7214347972",[297],{"name":298,"orcid":9},"Luis O Tedeschi","https:\u002F\u002Facademic.oup.com\u002Fjas\u002Fadvance-article-pdf\u002Fdoi\u002F10.1093\u002Fjas\u002Fskag306\u002F71398322\u002Fskag306.pdf",{"tldr":301,"method":302,"finding":303,"direction":85,"opportunity":304},"综述大语言模型在动物科学中的应用、风险与负责任使用路径。","文献综述，梳理LLM在营养、健康、遗传和可持续性中的应用。","LLM可辅助精准营养与决策支持，但需人类监督、验证和领域微调。","可探索面向畜牧生产的领域专用LLM微调与可验证决策支持系统，并建立偏差审计与可复现评估框架。","智慧农业 \u002F 农业物联网","2026-09-28T23:30:12.831387Z",{"id":308,"title":309,"url":310,"summary":311,"summary_zh":312,"content":9,"source_name":313,"source_url":310,"published_at":314,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":315,"score_detail":316,"sources":319,"tags":321,"primary_topic":325,"secondary_topics":330,"classification":341,"search_phrases":395,"slug":398,"view_count":399,"doi":400,"paper":401,"created_at":413},2625,"Multi-omics and artificial intelligence for climate-resilient and nutrient-enriched food crops: advances, applications and future perspectives","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1931230","Climate change has intensified both abiotic and biotic stresses, threatening global crop productivity, nutritional quality, and agricultural sustainability. These challenges have accelerated the adoption of advanced multi-omics technologies, including genomics, transcriptomics, proteomics, and metabolomics, together with artificial intelligence (AI) to accelerate the development of climate-resilient and nutrient-enriched crops. This review provides an integrated view of the recent advances in AI-enabled multi-omics, genome editing and precision agriculture for climate-resilient and nutrient-rich crops along with emerging trends, current challenges, and future research priorities. Machine learning-enhanced genomic selection approaches such as convolutional neural network (CNN)-based models and transformer models enhance the accuracy of predictions for complex stress-tolerant and nutritional traits. AI-assisted unmanned aerial vehicle (UAV) remote sensing allows measurement of traits at an unprecedented scale and with high-throughput and quantitative phenotyping. AI-driven multi-omics integration approaches, such as pan-omics pipelines, decipher abiotic stress tolerance regulatory networks. The AI-assisted CRISPR-Cas9 genome editing systems have accelerated crop biofortification outcomes by improving target prioritization and guide RNA design. Genome-editing studies have reported enhanced iron and zinc bioavailability in experimental wheat lines, reduced phytic acid content in soybean, and enhanced vitamin and amino acid content in cassava and maize, highlighting the potential of AI-assisted genome-editing approaches for crop biofortification. AI-enabled precision agriculture platforms use AI together with satellite data and Internet of Things (IoT) sensors and predictive modeling to enhance crop management while decreasing environmental resource usage. This review examines data standardization and model interpretability together with access and regulations while it presents a future roadmap for achieving 2050 food security targets. By integrating multi-omics, artificial intelligence, genome engineering, and precision agriculture into a unified framework, this review identifies future research directions and key knowledge gaps for the development of climate-resilient and nutrient-rich crops.","气候变化加剧了非生物与生物胁迫，对全球作物生产力、营养品质和农业可持续性构成威胁。这些挑战加速了先进多组学技术（包括基因组学、转录组学、蛋白质组学和代谢组学）以及人工智能（AI）的应用，以加快气候韧性及营养强化作物的开发。本综述综合阐述了AI赋能的多组学、基因组编辑和精准农业在气候韧性及营养丰富作物方面的最新进展，以及新兴趋势、当前挑战和未来研究重点。机器学习增强的基因组选择方法，如基于卷积神经网络（CNN）的模型和Transformer模型，提高了对复杂耐逆性和营养性状预测的准确性。AI辅助的无人机（UAV）遥感能够以前所未有的规模进行高通量定量表型测量。AI驱动的多组学整合方法，如泛组学流程，可解析非生物胁迫耐受调控网络。AI辅助的CRISPR-Cas9基因组编辑系统通过改进靶标优先级排序和引导RNA设计，加速了作物生物强化成果。基因组编辑研究报告了实验小麦品系中铁和锌生物利用度的提高、大豆中植酸含量的降低，以及木薯和玉米中维生素和氨基酸含量的增强，凸显了AI辅助基因组编辑方法在作物生物强化方面的潜力。AI赋能的精准农业平台利用AI结合卫星数据、物联网（IoT）传感器和预测建模，在减少环境资源使用的同时增强作物管理。本综述审视了数据标准化和模型可解释性以及可及性和监管问题，同时提出了实现2050年粮食安全目标的未来路线图。通过将多组学、人工智能、基因组工程和精准农业整合为统一框架，本综述确定了开发气候韧性及营养丰富作物的未来研究方向和关键知识空白。","Frontiers in Sustainable Food Systems","2026-09-16T00:00:00Z",86,{"impact":103,"substance":103,"depth":127,"authority":105,"freshness":317,"relevant":55,"comment":318},9,"核心期刊综述，系统梳理AI驱动多组学、基因编辑与精准农业在气候韧性及营养强化作物上的进展，方法新颖、结论可靠，对智慧育种与农业AI方向有较高参考价值。",[320],{"name":313,"url":310},[21,113,322,323,324,22],"基因编辑","气候韧性","智慧育种",{"code":33,"slug":326,"name":327,"path":328,"parent_code":329},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[331,336],{"code":54,"slug":332,"name":333,"path":334,"parent_code":335},"biotechnology","生物育种与基因技术","\u002Ftopic\u002Finputs-equipment\u002Fbiotechnology","F",{"code":337,"slug":338,"name":339,"path":340,"parent_code":329},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":123,"locked":14,"version":28,"method":29,"evidence":342},{"candidates":343,"agricultural_evidence":35},[344,348,354,361,365,369,373,377,384,388],{"code":33,"score":34,"supported":35,"title":345,"abstract":346,"tags":347},[37],[40,42,37],[21],{"code":54,"score":317,"supported":35,"title":349,"abstract":350,"tags":353},[],[351,352],"基因组选择","genomic selection",[322,22,324],{"code":337,"score":317,"supported":35,"title":355,"abstract":356,"tags":360},[],[357,358,359],"物联网","internet of things","IoT",[],{"code":167,"score":133,"supported":35,"title":362,"abstract":363,"tags":364},[],[170,171],[323],{"code":47,"score":133,"supported":35,"title":366,"abstract":367,"tags":368},[],[113,129],[113],{"code":146,"score":91,"supported":35,"title":370,"abstract":371,"tags":372},[],[149,150],[],{"code":153,"score":91,"supported":35,"title":374,"abstract":375,"tags":376},[],[156,157],[],{"code":378,"score":91,"supported":35,"title":379,"abstract":380,"tags":383},"A4",[],[381,382],"大豆","soybean",[],{"code":160,"score":91,"supported":35,"title":385,"abstract":386,"tags":387},[],[163,164],[],{"code":389,"score":91,"supported":35,"title":390,"abstract":391,"tags":394},"I3",[],[392,393],"遥感","remote sensing",[],[396,397],"农业人工智能 基因编辑 智慧育种 气候韧性","农业人工智能 基因编辑","农业人工智能基因编辑智慧育种气候韧性-2625",2,"10.3389\u002Ffsufs.2026.1931230",{"doi":400,"openalex_id":402,"authors":403,"venue":313,"cited_by_count":15,"oa_url":310,"card":408,"direction":305,"ingested_from":88},"W7213241547",[404,406],{"name":405,"orcid":9},"Surasreeta Paul",{"name":407,"orcid":9},"Sandeep Singh Rana",{"tldr":409,"method":410,"finding":411,"direction":85,"opportunity":412},"综述AI赋能多组学、基因编辑与精准农业，培育气候韧性与营养强化作物。","整合基因组、转录组、蛋白与代谢组学，结合CNN、Transformer、UAV遥","AI辅助多组学与基因编辑可提升耐逆与营养性状预测及生物强化效率。","多组学数据标准化与模型可解释性不足，可研究跨物种可迁移的AI决策框架。","2026-09-16T23:30:07.496425Z",{"id":415,"title":416,"url":417,"summary":418,"summary_zh":419,"content":9,"source_name":420,"source_url":417,"published_at":421,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":422,"sources":424,"tags":426,"primary_topic":9,"secondary_topics":428,"classification":429,"search_phrases":441,"slug":444,"view_count":55,"doi":445,"paper":446,"created_at":460},2336,"System architecture and interactive LLM prompt framework for the integration of clinical and mitochondrial data in obesity: a software prototype and feasibility study","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrai.2026.1923426","Introduction Obesity is a critical global health challenge due to its close association with cardiovascular and metabolic risk. At the molecular level, the lipotoxic environment alters the structure, dynamics, and connectivity of the mitochondrial network. Despite advances in cell biology and digital health, there is a lack of lightweight computational tools capable of integrating clinical records with molecular and photomicrographic data in a standardized way. This study presents the design, development, and feasibility assessment of a decoupled software prototype and an interactive prompt engineering framework for integrating clinical and histological mitochondrial data in molecular obesity research. Methodology A client-side software architecture was designed using HTML5, CSS3, and the IndexedDB API for the transactional and anonymized persistence of medical records (coded using the ICD-10 classification) and micrographs of human placental tissue (obtained using transmission electron microscopy, immunofluorescence, and immunohistochemistry for the evaluation of mitochondrial fusion molecular markers such as Mitofusin-2, nitrotyrosine). For interpretive processing, a framework of prompts structured under the Chain-of-Thought paradigm was built, designed to interact with Large-Scale Language Models (LLMs). The interface’s usability, local storage performance, and the consistency of AI-assisted reasoning were evaluated. Results The developed platform enabled the seamless and instantaneous management of independent patient tabs (unique storage keys mitochondria_001 to 010), achieving local read\u002Fwrite latency without reliance on external servers or transmission of sensitive personal data. The prompt framework proved effective in guiding LLMs in translating mitochondrial biomarkers and clinical data into structured summaries of oxidative stress status and metabolic risk. The lack of a trained computer vision model for automatic segmentation is declared as the main limitation of the current study. Conclusion The software prototype and prompt interface provide a low-cost, secure (data privacy-oriented), and clinically intuitive solution for translational data management in obesity. This work demonstrates the feasibility of integrating heterogeneous biomedical parameters using conversational AI tools and local storage, laying the groundwork for the future incorporation of image segmentation algorithms.","引言 肥胖因其与心血管和代谢风险的密切关联，已成为全球性的重大健康挑战。在分子层面，脂毒性环境会改变线粒体网络的结构、动力学及连接性。尽管细胞生物学和数字健康领域取得了进展，但目前仍缺乏能够以标准化方式将临床记录与分子及显微图像数据整合的轻量级计算工具。本研究介绍了一种解耦软件原型和交互式提示工程框架的设计、开发及可行性评估，旨在整合分子肥胖研究中的临床与组织学线粒体数据。方法 采用HTML5、CSS3和IndexedDB API设计了客户端软件架构，用于医学记录（采用ICD-10分类编码）和人类胎盘组织显微图像（通过透射电子显微镜、免疫荧光和免疫组织化学获得，用于评估线粒体融合分子标志物如Mitofusin-2、硝基酪氨酸）的事务性匿名持久化存储。在解释性处理方面，构建了基于思维链（Chain-of-Thought）范式结构的提示框架，旨在与大语言模型（LLMs）进行交互。对界面的可用性、本地存储性能以及AI辅助推理的一致性进行了评估。结果 所开发的平台实现了独立患者标签页（唯一存储键mitochondria_001至010）的无缝即时管理，在无需依赖外部服务器或传输敏感个人数据的情况下，实现了本地读写延迟。提示框架在引导LLMs将线粒体生物标志物和临床数据转化为氧化应激状态和代谢风险的结构化摘要方面被证明有效。缺乏用于自动分割的经过训练的计算机视觉模型被声明为本研究的主要局限性。结论 该软件原型和提示界面为肥胖领域的转化数据管理提供了一种低成本、安全（以数据隐私为导向）且临床直观的解决方案。本研究证明了使用对话式AI工具和本地存储整合异构生物医学参数的可行性，为未来纳入图像分割算法奠定了基础。","Frontiers in Artificial Intelligence","2026-09-10T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":423},"该研究聚焦肥胖临床与线粒体数据整合的软件原型，属医学信息学领域，与三农、农业信息化、智慧农业无直接关联，不建议进入每日精选。",[425],{"name":420,"url":417},[21,23,427],"数据隐私",[],{"status":27,"locked":14,"version":28,"method":29,"evidence":430},{"candidates":431,"agricultural_evidence":14,"reason":59},[432,436],{"code":33,"score":133,"supported":35,"title":433,"abstract":434,"tags":435},[],[41,44],[21],{"code":437,"score":55,"supported":14,"title":438,"abstract":439,"tags":440},"I6",[],[],[427],[442,443],"农业人工智能 数字健康 数据隐私","农业人工智能 数字健康","农业人工智能数字健康数据隐私-2336","10.3389\u002Ffrai.2026.1923426",{"doi":445,"openalex_id":447,"authors":448,"venue":420,"cited_by_count":15,"oa_url":454,"card":455,"direction":85,"ingested_from":88},"W7212155685",[449,452],{"name":450,"orcid":451},"Karenth Milena Rodríguez-Córdoba","https:\u002F\u002Forcid.org\u002F0000-0003-4010-2813",{"name":453,"orcid":9},"William Darío Ávila-Díaz","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fartificial-intelligence\u002Farticles\u002F10.3389\u002Ffrai.2026.1923426\u002Fpdf",{"tldr":456,"method":457,"finding":458,"direction":85,"opportunity":459},"开发轻量本地软件原型与LLM提示框架，整合肥胖临床与线粒体数据。","HTML5\u002FIndexedDB本地存储临床与电镜图像，结合思维链提示调用大语言模","实现无服务器、隐私安全的异构数据管理，提示框架可有效生成氧化应激与代谢风险摘要。","可迁移至农业场景，构建本地化多模态数据管理与LLM辅助决策工具，并补足自动图像分割能力。","2026-09-13T23:30:41.079545Z",{"id":462,"title":463,"url":464,"summary":465,"summary_zh":9,"content":9,"source_name":466,"source_url":9,"published_at":467,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":101,"score_detail":468,"sources":471,"tags":473,"primary_topic":9,"secondary_topics":474,"classification":475,"search_phrases":516,"slug":518,"view_count":399,"doi":519,"paper":520,"created_at":528},1364,"【综述】多组学与人工智能赋能气候适应型和营养强化作物：进展、应用与未来展望","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1931230\u002Ffull","综述整合 AI 驱动的多组学、基因编辑与精准农业进展。机器学习增强的基因组选择（如 CNN、Transformer）提高复杂抗逆与营养性状预测准确度；AI+无人机遥感实现高通量表型；AI+CRISPR-Cas9 加速生物强化目标筛选（小麦铁锌生物有效性、大豆植酸降低、木薯\u002F玉米维生素提升）；为 2050 年粮食安全提出路线图。","Frontiers in Sustainable Food Systems · 2026-09","2026-08-31T16:00:00Z",{"impact":103,"substance":103,"depth":127,"authority":469,"freshness":133,"relevant":55,"comment":470},13,"综述整合AI与多组学在作物育种中的应用，提出2050年路线图，具有产业前瞻性。",[472],{"name":466,"url":464},[21,163,113,322,22],[],{"status":27,"locked":14,"version":28,"method":29,"evidence":476},{"candidates":477,"agricultural_evidence":35,"reason":515},[478,482,487,491,495,499,503,507,511],{"code":54,"score":106,"supported":35,"title":479,"abstract":480,"tags":481},[],[322,351],[322,22],{"code":167,"score":106,"supported":35,"title":483,"abstract":485,"tags":486},[484],"气候适应",[],[],{"code":160,"score":64,"supported":35,"title":488,"abstract":489,"tags":490},[],[163],[163],{"code":47,"score":64,"supported":35,"title":492,"abstract":493,"tags":494},[],[113],[113],{"code":33,"score":64,"supported":35,"title":496,"abstract":497,"tags":498},[],[40],[21],{"code":146,"score":48,"supported":35,"title":500,"abstract":501,"tags":502},[],[149],[],{"code":153,"score":48,"supported":35,"title":504,"abstract":505,"tags":506},[],[156],[],{"code":378,"score":48,"supported":35,"title":508,"abstract":509,"tags":510},[],[381],[],{"code":389,"score":48,"supported":35,"title":512,"abstract":513,"tags":514},[],[392],[],"多个产业证据相当，需要确认主归属",[517,397],"农业人工智能 基因编辑 粮食安全 精准农业","农业人工智能基因编辑粮食安全精准农业-1364","10.3389\u002Ffsufs.2026.1931230\u002Ffull",{"doi":519,"openalex_id":9,"authors":521,"venue":9,"cited_by_count":15,"oa_url":9,"card":522,"direction":85,"ingested_from":527},[],{"tldr":523,"method":524,"finding":525,"direction":85,"opportunity":526},"综述AI与多组学、基因编辑、精准农业结合，提升作物抗逆与营养性状改良效率。","综述AI驱动的多组学、基因编辑与精准农业技术，包括机器学习基因组选择、无人机遥感","AI增强基因组选择、表型分析和基因编辑，可加速气候适应与营养强化作物育种。","可探索AI与多组学整合在特定作物（如小麦、大豆）营养强化中的实际应用与模型优化。","agent","2026-09-02T00:05:06.849146Z",{"id":530,"title":531,"url":532,"summary":533,"summary_zh":534,"content":9,"source_name":535,"source_url":532,"published_at":536,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":537,"score_detail":538,"sources":541,"tags":543,"primary_topic":547,"secondary_topics":553,"classification":555,"search_phrases":571,"slug":574,"view_count":15,"doi":575,"paper":576,"created_at":590},5592,"Evaluation of Concept-Rank Collapse Audits for Computer Vision Agriculture Disease Classifiers Under Low-Label Regimes: An Interpretability Capacity Bound for Smallholder Fungicide Selectivity","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545193","Concept-based interpretability methods for plant-disease classifiers are typically evaluated by whether their concept activations correlate with human-annotated labels, but this criterion is silent on a prior question: whether the classifier's internal representation retains enough concept-rank structure for any audit to be informative. the present analysis formalises that prior question as an interpretability capacity bound. A classifier is modelled as a concept-rank operator whose singular values govern how much concept-level signal survives the projection from pixel space to class logits, and a collapse audit is defined as the ratio of retained concept-rank energy to total concept energy. Under a low-label regime, where concept annotations are scarce and the audit must be estimated from few labelled examples, the bound predicts that audit reliability degrades as a function of the concept-rank spectrum and the label budget. The analysis is a theoretical and methodological contribution: it derives the bound, states the conditions under which a collapse audit is identifiable, and characterises the operating characteristics of the audit as a decision procedure under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64). Power was estimated across 2000 design cells for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points; 52 clusters were required for 5 percentage points at 80% power. The bound reframes concept audits as capacity tests rather than fidelity tests, with consequences for how smallholder fungicide-selectivity decisions should be supported by interpretable disease classifiers.","面向植物病害分类器的基于概念的可解释性方法，通常以其概念激活是否与人工标注标签相关作为评价标准，但该标准对一个更先前的问题保持沉默：分类器的内部表征是否保留了足够的概念秩结构，从而使任何审计具有信息量。本分析将该先前问题形式化为一个可解释性容量上界。分类器被建模为概念秩算子，其奇异值支配着从像素空间到类别logits的投影中概念级信号得以保留的程度，并将坍缩审计定义为保留的概念秩能量与总概念能量之比。在低标签情形下，概念标注稀缺且审计必须由少量标注样本估计，该上界预测审计可靠性会随概念秩谱和标签预算的函数而退化。本分析是一项理论和方法论贡献：推导出该上界，陈述坍缩审计可识别的条件，并在声明的方差结构（簇间SD = 6.0，残差SD = 4.5，组内相关系数 = 0.64）下刻画审计作为决策程序的操作特征。在2000个设计单元中，针对簇数为8、16、24和32以及效应量为3、5和8个百分点的情形估计了功效；在80%功效下达到5个百分点需要52个簇。该上界将概念审计重新框定为容量检验而非保真度检验，并对可解释病害分类器应如何支持小农杀菌剂选择性决策具有启示意义。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",69,{"impact":106,"substance":104,"depth":34,"authority":539,"freshness":13,"relevant":55,"comment":540},12,"理论方法论文，提出可解释性容量上界并给出审计功效分析，对智慧农业病害识别可信度有参考价值，但属小众方法学研究、缺乏田间实证，暂不宜进入每日精选。",[542],{"name":535,"url":532},[111,21,544,545,546],"小农户","植物病害识别","可解释性",{"code":548,"slug":549,"name":550,"path":551,"parent_code":552},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[554],{"code":33,"slug":326,"name":327,"path":328,"parent_code":329},{"status":123,"locked":14,"version":28,"method":29,"evidence":556},{"candidates":557,"agricultural_evidence":35},[558,563,567],{"code":548,"score":539,"supported":35,"title":559,"abstract":561,"tags":562},[560],"smallholder",[560],[544],{"code":33,"score":13,"supported":35,"title":564,"abstract":565,"tags":566},[44],[],[21,545],{"code":47,"score":55,"supported":14,"title":568,"abstract":569,"tags":570},[],[],[111],[572,573],"农业人工智能 植物病害识别 可解释性 智慧农业","农业人工智能 植物病害识别","农业人工智能植物病害识别可解释性智慧农业-5592","10.5281\u002Fzenodo.23545193",{"doi":575,"openalex_id":577,"authors":578,"venue":535,"cited_by_count":15,"oa_url":532,"card":585,"direction":85,"ingested_from":88},"W7223137323",[579,581,583],{"name":580,"orcid":9},"Akshay Ramgoolam",{"name":582,"orcid":9},"Priya Bundhoo Appadoo",{"name":584,"orcid":9},"Jean-Noël LEspérance",{"tldr":586,"method":587,"finding":588,"direction":85,"opportunity":589},"提出可解释性容量上界，评估低标签下概念秩崩溃审计的可靠性。","将分类器建模为概念秩算子，推导容量上界并做2000格功效模拟。","审计可靠性随概念秩谱与标签预算下降；5个百分点效应需52个聚类达80%功效。","可将容量上界用于小农户杀菌剂选择性决策的可解释模型审计与标签预算设计。","2026-10-22T11:21:10.425290Z"]