[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2124":3},{"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":24,"tags":26,"view_count":32,"doi":33,"paper":34,"created_at":64},2124,"Cysteine quantification in pea cultivars from SERS spectra using AI","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102557","Rapid quantification of sulfur-containing amino acids, particularly cysteine, in legumes is critical for assessing nutritional quality, supporting breeding program screening, and ensuring consistency in quality control processes. However, conventional methods, such as high-performance liquid chromatography (HPLC), are time-consuming and resource-intensive for high-throughput applications. This study evaluated artificial intelligence models for predicting cultivar-level mean cysteine concentration from surface-enhanced Raman spectroscopy (SERS) spectra of pea extracts. SERS spectra were acquired from 20 cultivars grown at three field locations, with HPLC measurements across the three locations averaged to provide a cultivar-level mean cysteine reference value. Linear regression, partial least squares regression, support vector regression, random forest regression, and a one-dimensional convolutional neural network (1D-CNN) were compared using within-cultivar splits and leave-one-cultivar-out (LOCO) evaluation. The 1D-CNN achieved good predictive performance for the represented cultivars, with an RMSE of 0.005 g\u002F100 g and an MAE of 0.004 g\u002F100 g. Under LOCO evaluation, RMSE and MAE increased to 0.013 and 0.012 g\u002F100 g, respectively. These results provide proof of concept for SERS\u002FAI prediction of multi-environment, cultivar-level mean cysteine concentration, with LOCO providing encouraging evidence of transferability to unseen cultivars within the represented environments and analytical conditions. Shapley Additive Explanations analysis identified contributions from both substrate-related and molecular spectral features. Broader validation using independent samples, locations, extractions, substrates, and reference measurements is required to establish general analytical applicability. A simulated additive-noise sensitivity analysis further evaluated model performance under increasing spectral noise.","豆类中含硫氨基酸，尤其是半胱氨酸的快速定量，对于评估营养品质、支持育种项目筛选以及确保质量控制流程的一致性至关重要。然而，传统方法如高效液相色谱法（HPLC）在高通量应用中耗时且资源密集。本研究评估了人工智能模型从豌豆提取物的表面增强拉曼光谱（SERS）中预测品种水平平均半胱氨酸浓度的能力。SERS光谱采集自三个田间地点种植的20个品种，并将三个地点的HPLC测量值取平均以提供品种水平的平均半胱氨酸参考值。采用品种内划分和留一品种法（LOCO）评估，比较了线性回归、偏最小二乘回归、支持向量回归、随机森林回归和一维卷积神经网络（1D-CNN）。1D-CNN对所代表品种取得了良好的预测性能，RMSE为0.005 g\u002F100 g，MAE为0.004 g\u002F100 g。在LOCO评估下，RMSE和MAE分别增至0.013和0.012 g\u002F100 g。这些结果为SERS\u002F人工智能预测多环境、品种水平平均半胱氨酸浓度提供了概念验证，LOCO为在已代表的环境和分析条件下向未见品种的可迁移性提供了令人鼓舞的证据。Shapley加性解释分析识别了底物相关和分子光谱特征的贡献。需要使用独立样本、地点、提取方法、底物和参考测量进行更广泛的验证，以确立普遍的分析适用性。模拟加性噪声敏感性分析进一步评估了模型在光谱噪声增加条件下的性能。",null,"Smart Agricultural Technology","2026-09-08T00:00:00Z","论文",10,false,71,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},15,20,17,13,6,1,"SERS光谱结合AI实现豌豆半胱氨酸快速定量，为育种筛选与品质控制提供概念验证，方法新颖但尚需更广泛验证。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","品质育种","豌豆","光谱检测",0,"10.1016\u002Fj.atech.2026.102557",{"doi":33,"openalex_id":35,"authors":36,"venue":10,"cited_by_count":32,"oa_url":56,"card":57,"direction":61,"ingested_from":63},"W7211935637",[37,40,43,46,49,51,53],{"name":38,"orcid":39},"Elham Gorgannejad","https:\u002F\u002Forcid.org\u002F0009-0001-6375-0429",{"name":41,"orcid":42},"Qian Liu","https:\u002F\u002Forcid.org\u002F0000-0001-9832-596X",{"name":44,"orcid":45},"Catherine Rui Jin Findlay","https:\u002F\u002Forcid.org\u002F0000-0002-9304-1033",{"name":47,"orcid":48},"Mohammad Nadimi","https:\u002F\u002Forcid.org\u002F0000-0002-4550-7572",{"name":50,"orcid":9},"Alex Chun-Te Ko",{"name":52,"orcid":9},"Pankaj Bhowmik",{"name":54,"orcid":55},"Jitendra Paliwal","https:\u002F\u002Forcid.org\u002F0000-0002-1665-3626","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2772375526007823\u002Fpdf",{"tldr":58,"method":59,"finding":60,"direction":61,"opportunity":62},"用SERS光谱结合AI预测豌豆品种半胱氨酸含量，1D-CNN表现最佳。","SERS光谱、HPLC参考值、多种回归模型及1D-CNN，采用LOCO评估。","1D-CNN在品种内预测RMSE为0.005 g\u002F100g，LOCO下为0.013 g\u002F100g，具","农业人工智能与决策模型","可扩展至其他氨基酸或作物，结合便携SERS与迁移学习实现田间高通量品质筛查。","openalex","2026-09-11T23:30:03.956325Z"]