[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fRs2pKq61B6BoDIYCdBtgrTlbvhSESTctDfUrkTxg3ms":3},{"item":4,"storyV2":72},{"slug":5,"type":6,"track":7,"season":8,"date":9,"featured":10,"teamName":11,"institution":13,"projectTitle":15,"summary":18,"body":20,"tags":24,"aiTags":27,"wetlabTags":30,"awards":33,"logoUrl":36,"materials":37,"gallery":38,"editorial":47,"cover":70},"atcg","image","T1","2026","2026-01-01",false,{"zh":12,"en":12},"ATCG 碱基互补配队",{"zh":14,"en":14},"天津大学合成生物与生物制造学院",{"zh":16,"en":17},"miR-AclE —— 基于 AI 优化的 DNA 逻辑网络与分子信标肿瘤精准诊断系统","miR-AclE — AI-optimized DNA logic networks and molecular beacons for precision tumor diagnostics",{"zh":19,"en":19},"用 AI 优化 DNA 分子探针，构建能同时感知外泌体和肿瘤相关 miRNA 的比值化传感系统",{"zh":21,"en":23},[22],"天津大学 ATCG 碱基互补配队做的是液体活检里的一个具体麻烦：不同样本中外泌体数量差异很大，只看单一荧光信号，很容易把「样本多」误认成「靶标多」。团队采用双通道比值化 —— 一个信号报告外泌体捕获量，另一个报告其中的 miRNA 丰度，用内部校准把误差消掉。",[22],{"zh":25,"en":26},[],[],{"zh":28,"en":29},[],[],{"zh":31,"en":32},[],[],{"zh":34,"en":35},[],[],"\u002Fapi\u002Fteam-showcase\u002Fatcg\u002Fmedia\u002Fcd9b69ddfecce6401b4027a6e",{},[39],{"imageUrl":40,"alt":41,"title":43,"description":45,"position":46},"\u002Fapi\u002Fteam-showcase\u002Fatcg\u002Fmedia\u002Fce248dacaa88a7f70d2ca0e10",{"zh":42,"en":42},"海报呈现双通道 DNA 分子探针、外泌体捕获、miRNA 比值化检测与模型分析的整体方案。",{"zh":44,"en":44},"miR-AclE 项目海报",{"zh":42,"en":42},"center center",{"proposition":48,"listEvidence":49},{"zh":19,"en":19},[50,55,60,65],{"value":51,"label":53},{"zh":52,"en":52},"5 人",{"zh":54,"en":54},"成员人数",{"value":56,"label":58},{"zh":57,"en":57},"韩金汐",{"zh":59,"en":59},"队长",{"value":61,"label":63},{"zh":62,"en":62},"miR-AclE",{"zh":64,"en":64},"项目对象",{"value":66,"label":68},{"zh":67,"en":67},"分子信标荧光",{"zh":69,"en":69},"验证方式",{"tone":71,"heroImageUrl":40,"heroImagePosition":46},"bio",{"version":73,"publicSlug":5,"identity":74,"proposition":78,"lead":79,"listEvidence":80,"narrativeTendency":93,"hero":94,"presentation":99,"chapters":110},2,{"teamName":75,"projectTitle":76,"institution":77,"track":7},{"zh":12,"en":12},{"zh":16,"en":17},{"zh":14,"en":14},{"zh":19,"en":19},{"zh":22,"en":22},[81,84,87,90],{"value":82,"label":83},{"zh":52,"en":52},{"zh":54,"en":54},{"value":85,"label":86},{"zh":57,"en":57},{"zh":59,"en":59},{"value":88,"label":89},{"zh":62,"en":62},{"zh":64,"en":64},{"value":91,"label":92},{"zh":67,"en":67},{"zh":69,"en":69},"evidence-led",{"role":95,"title":96,"caption":97,"alt":98,"position":46,"imageUrl":40},"HERO",{"zh":44,"en":44},{"zh":42,"en":42},{"zh":42,"en":42},{"template":100,"variant":101,"logo":102,"openingMedia":109},"documentary-profile","rich",{"role":103,"title":104,"caption":106,"alt":108,"position":46,"imageUrl":36},"LOGO",{"zh":105,"en":105},"项目标识 miR-AcIE",{"zh":107,"en":107},"齿轮、叶片与波形叠在一起。",{"zh":107,"en":107},[],[111,122,131,163,197,218],{"id":112,"eyebrow":113,"title":115,"theme":117,"type":118,"quote":119,"attribution":121},"team-motto",{"zh":114,"en":114},"队伍口号",{"zh":116,"en":116},"队伍声音","people","quote",{"zh":120,"en":120},"ATCG，智配生命，精准出击",{"zh":12,"en":12},{"id":123,"eyebrow":124,"title":126,"body":128,"theme":130,"type":130},"project-background",{"zh":125,"en":125},"项目背景",{"zh":127,"en":127},"用双通道比值校准样本差异",{"zh":129,"en":129},"不同样本中的外泌体数量存在差异，单看一条荧光信号，难以区分样本量变化与目标 miRNA 丰度变化。其中一个通道反映外泌体捕获量，另一个通道反映其中的 miRNA 丰度；两者取比值，用样本自身信号作内部校准，以减少样本量差异和背景信号对读数的影响。","problem",{"id":132,"eyebrow":133,"title":135,"body":137,"theme":139,"type":140,"facts":141},"research-context",{"zh":134,"en":134},"研究路径",{"zh":136,"en":136},"探针为什么难设计",{"zh":138,"en":138},"DNA 探针的表现同时受序列、二级结构、稳定性和非特异性作用影响。团队用机器学习分析这些特征与实验响应之间的关系，对候选探针进行评价和排序；计算用于缩小候选范围，实验数据用于检验并修正排序。","source","source-context",[142,149,156],{"label":143,"value":145,"note":147},{"zh":144,"en":144},"设计前提",{"zh":146,"en":146},"探针必须专一",{"zh":148,"en":148},"双通道比值化需要稳定区分目标 miRNA 与背景信号，候选探针首先要对目标序列保持足够专一。",{"label":150,"value":152,"note":154},{"zh":151,"en":151},"优化约束",{"zh":153,"en":153},"序列与结构协同",{"zh":155,"en":155},"序列、二级结构、稳定性与非特异性作用会同时影响响应，设计时不能只优化单一指标。",{"label":157,"value":159,"note":161},{"zh":158,"en":158},"筛选方式",{"zh":160,"en":160},"AI 多目标筛选",{"zh":162,"en":162},"计算筛选用于降低人工逐条试筛成本，再通过交叉特异性矩阵检查候选探针对非目标序列的响应。",{"id":164,"eyebrow":165,"title":167,"theme":169,"type":170,"semantics":171,"steps":172},"project-process",{"zh":166,"en":166},"项目过程",{"zh":168,"en":168},"项目推进与验证路径","process","process-flow","hybrid",[173,182,189],{"order":174,"phase":175,"title":177,"body":179,"status":181},1,{"zh":176,"en":176},"阶段 1",{"zh":178,"en":178},"闭环走到哪一步了",{"zh":180,"en":180},"Design：根据核酸序列与结构特征筛选候选探针。Build、Test：在实验中完成探针构建，测量荧光响应、背景信号、特异性等指标。Learn：把这些真实实验结果整理成机器学习可用的数据，让模型学习什么样的探针表现更好。进度本身：目前已经获得了包括多组分子信标交叉特异性在内的实验数据，正在建立第一版机器学习模型。那张交叉特异性矩阵就是这批数据的样子：对角线亮，非对角线暗。","described",{"order":73,"phase":183,"title":185,"body":187,"status":181},{"zh":184,"en":184},"阶段 2",{"zh":186,"en":186},"荧光读数区分目标与非目标序列",{"zh":188,"en":188},"分子信标在目标序列打开其发夹结构后恢复荧光。当前实验中，实验组出现荧光恢复，非目标组保持较低背景，团队据此比较候选分子信标对目标与非目标序列的响应。",{"order":190,"phase":191,"title":193,"body":195,"status":181},3,{"zh":192,"en":192},"阶段 3",{"zh":194,"en":194},"先明确科学问题，再选择方法",{"zh":196,"en":196},"团队熟悉生物实验，但起初不熟悉机器学习的数据格式、特征工程和模型选择；有限的湿实验数据也促使团队调整最初的计算方案。由此形成的工作原则是先明确科学问题和可用数据，再选择合适的方法，并让实验与计算持续沟通、修正。",{"id":198,"eyebrow":199,"title":201,"theme":203,"type":204,"items":205},"project-figure",{"zh":200,"en":200},"项目证据",{"zh":202,"en":202},"项目图表与方法记录","evidence","figures",[206,211],{"role":207,"title":208,"caption":209,"alt":210,"position":46,"imageUrl":40},"RESULT",{"zh":44,"en":44},{"zh":42,"en":42},{"zh":42,"en":42},{"role":207,"title":212,"caption":214,"alt":216,"position":46,"imageUrl":217},{"zh":213,"en":213},"交叉特异性矩阵",{"zh":215,"en":215},"矩阵对角线信号高、非对角线信号低，记录不同分子信标对目标与非目标序列的响应差异。",{"zh":215,"en":215},"\u002Fapi\u002Fteam-showcase\u002Fatcg\u002Fmedia\u002Fc2219fe00eb7a01fd3e02b2d0",{"id":219,"eyebrow":220,"title":222,"theme":224,"type":225,"highlight":226,"full":235},"team-interview",{"zh":221,"en":221},"队伍专访",{"zh":223,"en":223},"听 ATCG 碱基互补配队 讲述项目路径","media","interview",{"version":227,"title":228,"description":230,"durationSeconds":232,"videoUrl":233,"posterUrl":234},"highlight",{"zh":229,"en":229},"项目精华",{"zh":231,"en":231},"项目核心内容与队伍表达的精华剪辑。",177.912042,"\u002Fapi\u002Fteam-showcase\u002Fatcg\u002Fmedia\u002Fc3e2aad82140661f76c7dba1f","\u002Fapi\u002Fteam-showcase\u002Fatcg\u002Fmedia\u002Fcfcb0f0f3bcbf8bfa72a67aee",{"version":236,"title":237,"description":239,"durationSeconds":241,"videoUrl":242,"posterUrl":234},"full",{"zh":238,"en":238},"完整访谈",{"zh":240,"en":240},"按采访问题完整收录的队伍访谈。",284.045375,"\u002Fapi\u002Fteam-showcase\u002Fatcg\u002Fmedia\u002Fccc38dbdae38fd06dd87413b9"]