A multi-modal clustering method for traditonal Chinese medicine clinical data via media convergence

Media convergence is a media change led by technological innovation.Applying media convergence technology to the study of clustering in Chinese medicine can significantly exploit the advantages of media fusion.Obtaining consistent and complementary information among multiple modalities through media convergence can provide technical support for clustering.This article presents an approach based on Media Convergence and Graph convolution Encoder Clustering(MCGEC)for traditonal Chinese medicine(TCM)clinical data.It feeds modal information and graph structure from media information into a multi-modal graph convolution encoder to obtain the media feature representation learnt from multiple modalities.MCGEC captures latent information from various modalities by fusion and optimises the feature representations and network architecture with learnt clustering labels.The experiment is conducted on real-world multimodal TCM clinical data,including information like images and text.MCGEC has improved clustering results compared to the generic single-modal clustering methods and the current more advanced multi-modal clustering methods.MCGEC applied to TCM clinical datasets can achieve better results.Integrating multimedia features into clustering algorithms offers significant benefits compared to single-modal clustering approaches that simply concatenate features from different modalities.It provides practical technical support for multi-modal clustering in the TCM field incorporating multimedia features.

Brands,Branding and Regional Cluster Development:The Emerging Economic Geographies of the Chinese Baijiu Industry

This paper investigates the vigorous economy of the Chinese Baijiu(a traditional liquor) with regard to the specific brands,their production and consumption and marketing,intersected with provincial and regional identities.The paper explores the ecological,cultural,social and political forces favoring or obstructing the Baijiu products’ branding across various provinces and regions.The Baijiu production largely falls into four categories,and clusters around seven distinct areas within the Upper Yangtze River Baijiu Agglomeration.These industrial areas have distinct development trajectories and branding strategies,impacted by factors such as environment,culture,brand identity and regional policy.The paper suggests that further work be done to gather research,to further strategize the branding,and to integrate the Chinese regional clusters into global value chains and global development.

中国兰花(Chinese Cymbidium)部分品种的叶片同工酶分析

利用聚丙烯酰胺凝胶电泳和淀粉胶凝胶电泳,对中国兰花的分属于六个种一个变种二十个品种的叶片过氧化物酶、酯酶、酸性磷酸酯酸、多酚氧化酶的同工酶进行了分析,共获得98条酶带,其中的95条具多态性。各个种的品种之间,有基本相似的特征酶谱。而各种间的酶谱差异较大。四种同功酶的聚类分析结果与传统分类学的划分比较接近,为中国兰花品种的鉴定和分类提供了生物化学依据。

Analysis of the Genetic Diversity and Origin of Some Chinese Domestic Duck Breeds

Twelve fluorescence-labeled microsatellite markers were used to analyze the genetic diversity of 12 domestic duck breeds and 2 wild duck breeds to determine the relationship and origin of Chinese domestic duck breeds. Gene frequency, effective number of alleles （Ne）, expected heterozygosity （He）, polymorphism information contents （PIC）, inbreeding coefficient in population （Fis）, standard genetic distance （Ds）, and genetic distance （DA） were calculated by FSTAT and distance and phylogenetic analysis after the dates which were output from the Microsatellite-Toolkit software. Genetic distances between 12 domestic duck breeds and 2 wild duck breeds were analyzed by variance analysis. Unweighted pair group method with arithmetic mean （UPGMA） and phylogenetic trees used for cluster analysis were structured. The results indicated that 11 loci had medium- or high-level genetic diversity among the 12 loci, which could be efficiently used in the detection of the genetic parameters of each population. The values of He were 0.5414 to 0.7343, those of PIC proved similar, and those of Fis were 0.1101 to 0.3381 among all populations. All breeds were clustered into three groups by UPGMA phylogenetic trees. Banzui duck was clustered into a separate group. Differences of the DA were analysed by t-test. The results showed that difference in DA between the 12 domestic duck breeds and Lvtou duck and the Banzui duck were very significant （P〈0.01）, indicating that these 12 domestic duck breeds originated from Lvtou wild duck, but not Banzui duck.

Analysis of active patents to investigate the frequency and patterns of Chinese herbal extract combinations claiming to treat heart disease

Objective:Using Chinese patents in force to investigate the frequency and patterns of Chinese herbal extract combinations claiming to treat heart disease.Methods:Patent documents were retrieved from the official website of the State Intellectual Property Office of the People’s Republic China.Cluster,frequency,and fuzzy cluster analyses were applied.Results:A high number of patents in force included high-frequency herbs such as Salvia miltiorrhiza,Panax ginseng,and Panax notoginseng,as well as high-frequency herbal families such as Araliaceae,Leguminosae,Labiatae,and Umbelliferae.Herb pairs such as P.ginsengþOphiopogon japonicus,S.miltiorrhizaþDalbergia odorifera,and P.ginsengþSchisandra chinensis are also commonly used,as well as herbal family pairs such as AraliaceaeþLiliaceae,LauraceaeþLeguminosae,and AraliaceaeþSchisandraceae.Traditional treatment principles for preventing and treating heart diseases was most-commonly based on simultaneously treating the liver and heart and treating the lung and spleen secondarily for choosing herbal combinations.Conclusion:Most of the high-frequency Chinese herbs in the patents investigated belong to the high-frequency herbal families,and herb pairs were commonly selected to coincide with the commonly-used herbal family pairs.Low-frequency Chinese herbs were also used,but generally belonged to the high-frequency herbal families,and were therefore similar to the highfrequency herbs in terms of traditional categories of taste and channel entered.The results reflect the use of traditional principles of formula composition,and suggest that these principles may indeed be an effective guide for further research and development of Chinese herbal extract combinations to prevent and treat heart diseases.

基于Chinese Whispers的人脸动态聚类

针对Chinese Whispers算法对于小规模数据聚类随机性大,对于大规模数据聚类速度缓慢的问题,提出了一种改进的Chinese Whispers算法用于人脸的动态聚类。新增了一个阈值P,用Chinese Whispers算法对数据规模为P的数据进行聚类时,既可以保证聚类结果的稳定性,又可以保证聚类算法的高效性;利用代表点而不是所有点完成聚类更新,能够有效减少对增量数据聚类时的数据量,从而达到提升聚类速度的目的。采用CNN+ArcFace Loss方法提取人脸特征,采用余弦距离作为相似性度量的方式,采用类中心作为代表点来描述类别信息,采用增量聚类的算法架构实现对于大规模数据的人脸动态聚类,并完成在LFW、VGGFace2和CASIA-Webface三个公开人脸数据集的测试。实验结果表明,基于Chinese Whispers人脸动态聚类算法可有效提高聚类的时间效率,时间复杂性由原来的O(n 2)变为O(n p)。

Chinese multi-document personal name disambiguation

This paper presents a new approach to determining whether an interested personal name across documents refers to the same entity. Firstly, three vectors for each text are formed: the personal name Boolean vectors denoting whether a personal name occurs in the text, the biographical word Boolean vector representing title, occupation and so forth, and the feature vector with real values. Then, by combining a heuristic strategy based on Boolean vectors with an agglomerative clustering algorithm based on feature vectors, it seeks to resolve multi-document personal name coreference. Experimental results show that this approach achieves a good performance by testing on 'Wang Gang' corpus.

Comparison of Analyses of Genetic Structure among Chinese Indigenous Chicken Breeds using Distance-based and Model-based Methods

The Nei's improved genetic distance(DA)and gene flow(Nm)were measured using sixteen microsatellite markers.Dendograms based on DA genetic distance using the neighbor-joining(NJ)method and STRUCTURE program were constructed to analyze the genetic structure and relationship among 10 Chinese indigenous chicken breeds.The results showed that dendograms of DA genetic distance using the NJ method divided the 10 chicken breeds into two main clusters;one consisted of breeds of low weight body(CHA,TTB,XIA,GUS and BAI),the other contained heavier breeds(LAN,DAG,YOU,XIS and LUY).In the lighter breeds,TIB and CHA clustered together,as did XIA and GUS.In the heavier breeds,XIS and LUY was clustered together in one branch,but LAN,DAG and YOU clustered in independent branches.The results were consistent with Nm estimates among the 10 indigenous chicken breeds.The STRUCTURE program properly inferred the presence of genetic structure despite not pre-defining the origin of individuals.The genetic cluster inferred by STRUCTURE was basically the same as that from the DA distance clustering method.An advantage of the STRUCTURE program was its ability to identify the migrants and admixed individuals in the 10 chicken populations;this could not be achieved by use of the DA distance clustering method.

Study on medication regularity of traditional Chinese medicine cases in treatment of neoplastic fever based on data mining

Objective:To analyze the medication regularity of traditional Chinese medicine cases in treatment of neoplastic fever in order to guide clinical medication.Methods:The database of China National Knowledge Infrastructure,Vip database and WanFang medical network were searched.The cases involving traditional Chinese medicine prescription in the treatment of neoplastic fever were screened.After extracting the prescriptions and Chinese medicines,make statistics according to frequency analysis,cluster analysis and association analysis.Results:79 literatures were included which involving 123 decoctions.221 traditionalChinese medicines were included in the statistics,the most frequently used traditional Chinese medicines were Gancao,Chaihu,Huangqi and Shengdihuang.The proportion of heat-clearing drugs in Chinese medicines was the largest(23.98%).The most common property of the Chinese medicines is cold property,accounting for 51.13%.The higher frequencies of flavors of the Chinese medicines are bitter,sweet and acrid,the sum of which is 84.66%.The most common meridian of Chinese medicines is liver meridian,accounting for 19.82%.The cluster analysis and association analysis of high frequency Chinese medicines showed that high frequency Chinese medicines could form three clustering formulas,and could get 18 pairs of high frequency drug combinations.Conclusion:Traditional Chinese medicines for heat-clearing,deficiencytonifying,phlegm-resolving,blood stasis-dispeling are mostly used to the treatment of neoplastic fever.The results of cluster analysis and association analysis of high frequency traditional Chinese medicines can provide certain reference and guidance for clinical medication.

Analysis of novel coronavirus pneumonia treatment with Chinese herbal compound

Objective: To analyze the prescription law of TCM compound in the treatment of new coronavirus pneumonia, and provides reference for the clinical treatment of new coronavirus pneumonia. Methods: Collected Collected 24 novel coronavirus pneumonia related diagnostic and therapeutic plans issued by the National Health Council and the Chinese medicine authority from January 26, 2020 to March 8th ,the filtered solution involved in the formula, establishing database of traditional Chinese medicine compound prescription for the treatment of new crown pneumonia, the frequency of using frequency analysis methods of analysis and clustering analysis and association rules analysis to sort out data mining analysis of traditional Chinese medicine compound. Results: In this study, a total of 159 TCM compounds were included in the treatment of new crown pneumonia from the country and 23 provinces, municipalities and autonomous regions, involving 189 TCM compounds. A total of 62 high-frequency traditional Chinese medicines (frequency ≥ 11) were obtained, mainly including licorice, almond, ephedra, gypsum, Poria cocos, Huoxiang, etc The drug types are mainly heat-clearing drugs, vacuous drugs, moisture-curing drugs, and surfactant drugs. The main effect of the medicine was warm, cold, lukewarm and flat, the main effect of the medicine was bitter and bitter, and the main effect of the medicine was the lung, stomach and spleen. Cluster analysis results according to the performance of traditional Chinese medicine treatment of new crown pneumonia high frequency drugs into 7 classes;Association rule analysis results in 29 common drug pairs. Conclusion: In the treatment of pneumonia caused by new coronavirus infection with traditional Chinese medicine, the following characteristics are presented: the number of times of supplementing qi and Yin is more than that of attacking evil and maintaining health;The method of dispersing and solving the attack of wet, beneficial, wet, permeable and wet medicine fully embodies a variety of ways to drive away evil;In terms of drugs, heat-clearing drugs, deficiency drugs, dampness drugs and surface drugs are the main ones, highlighting that the basic treatment method is to dissolve dampness and detoxify, and replenish qi and Yin. In summary, this study can provide reference for guiding clinical drug use and developing new drugs.

中国式现代化视域下的测度、演化与模式

文章基于新发展理念并结合中国式现代化的五大特征,构建了经济现代化、创新现代化、共享现代化、生态现代化、治理现代化五个维度的中国式现代化指标体系,依据各省统计年鉴和百度指数数据使用熵权法测算2012-2021年中国31个省份的中国式现代化水平。采用核密度估计、σ收敛模型、β收敛模型和基于动态时间规整的面板数据K中心点聚类算法,分析了中国式现代化的动态演化特征、收敛机制以及发展的模式。研究结果表明:2012-2021年中国式现代化水平逐步提升;东部地区的中国式现代化水平最高,中部地区的增速最高,西部和东北地区存在中国式现代化水平低且增长乏力的问题;全国各省份的中国式现代化水平绝对收敛速度为0.7%,条件收敛速度为3%,不存在σ收敛;聚类分析发现存在发展型和变革型两类中国式现代化模式:发展型中国式现代化以经济现代化为抓手,在共享现代化和生态现代化上表现优异;变革型中国式现代化勇于变革制度寻求突破创新,侧重于治理现代化和创新现代化。

中医问诊研究热点主题与趋势——基于CiteSpace的文献计量分析

目的探讨国内中医问诊的研究热点主题及趋势,为未来中医四诊研究的发展提供思路。方法通过中国知网(CNKI)进行文献检索,文献发表时间限定为1956年1月1日至2021年6月30日;应用CiteSpace软件,对关键词、作者共现、机构共现等进行聚类分析;选择浅语义索引算法标记聚类。结果共纳入193篇文献;自1956年以来,有关中医问诊研究的发文量总体呈上升趋势,通过定量分析找到了该研究领域的高产机构、研究团队、研究学者。其中上海中医药大学发表论文31篇,是发文量最大的研究机构;王忆勤等共发表论文19篇,是最高产作者;《中华中医药杂志》共发表论文12篇,是载文量最多的期刊。关键词聚类形成了4个较为合理的聚类标签,即临床教学、教学模式、信息技术、信息采集。结论临床教学、教学模式、信息技术、信息采集为中医问诊研究的热点主题;中医问诊在未来发展道路上需进一步改革与创新。

基于HPLC特征图谱结合化学计量学方法评价不同产地角倍和肚倍的质量

高效液相色谱法(HPLC)测定对不同来源五倍子两种形态肚倍和角倍进行HPLC特征指纹图谱研究,并通过聚类分析和主成分分析深入研究五倍子药材不同形态中有效成分差异,为五倍子药材质量控制做奠基。采用HPLC梯度洗脱法对肚倍和角倍样品进行测定,并记录色谱图,按《中药色谱指纹图谱相似度评价系统(2012版)》对色谱图进行匹配生成肚倍和角倍的特征图谱,进行相似度分析。采用化学计量学软件origin 2018对肚倍和角倍进行聚类分析、主成分分析(PCA)研究。结果显示:分别建立了肚倍和角倍的HPLC特征指纹图谱共有模式,标识了没食子酸、没食子酸甲酯、1,2,3,6-四-O-没食子酰葡萄糖、1,2,3,4,6-五-O-没食子酰葡萄糖4个特征峰。角倍与肚倍相似度低,可通过聚类分析、主成分分析将其分为2大类。从两者的HPLC特征指纹图谱相比,肚倍比角倍多了5个峰,保留时间为20.3、26.0、27.6、54.6、75.9 min,同时少了49.1 min相对位置的保留峰。通过分析不同产地的五倍子角倍和肚倍中特征性化学成分,表明肚倍的有效成分多于角倍。利用相似度研究、聚类分析技术及主成分分析,可有效区分二者,为五倍子药材质量综合评价和利用提供参考。

基于RAD-seq的菜心InDel标记开发及应用

【目的】开发多态性丰富的的InDel分子标记,为菜心育种提供研究基础。【方法】以Chiifu-401-42的基因组序列为模板,利用4份菜心材料的RAD-seq重测序数据,在全基因组范围内鉴定InDel位点。利用生物信息学方法筛选4份菜心材料间具有潜在多态性的InDel位点,挑选分布于10条染色体的80个InDel位点设计引物,对55份菜心种质材料进行遗传多样评价。【结果】通过与参考基因组序列比对,在4份菜心材料的重测序数据中共鉴定出84510个InDel位点,其中插入/缺失长度大于5 bp的3609个InDel位点在4份菜心材料间具有潜在多态性。挑选80个InDel位点进行PCR扩增验证,58个(72.5%)在4份测序样品中具有多态性,在55份菜心种质材料中检测到133个等位位点,多态性信息含量(PIC)为0.263~0.618,平均值为0.443。基于InDel标记的检测结果可知,55份菜心种质的遗传相似系数在0.366~0.756,平均值为0.570;在遗传相似系数为0.564时55份菜心种质被分为4个类群,但各类群间的耐热性没有明显差异。【结论】本研究开发的InDel标记具有良好的多态性,能有效地揭示不同菜心种质材料间的遗传距离,可为菜心遗传种质分析、新品种选育等方面提供可利用的标记信息。

一种大规模稀疏中国邮递员问题快速求解方法

针对现有中国邮递员问题求解方法在大规模稀疏路网图上求解效率的瓶颈,提出一种在可接受时间范围内求得可行解的基于蚁群优化的快速求解方法.该方法针对Euler回路求解的奇偶点图上作业法的第二阶段,采用蚁群算法进行求解,同时根据大规模稀疏路网图的特性基于密度峰值聚类算法对方法进行改进:首先在蚁群算法求解前对大规模稀疏路网图进行聚类分割;其次根据邻近节点覆盖率对分割后的节点群进行合并;最后通过改变部分节点所属聚类使各节点群内部节点个数均为偶数.实验结果表明:在奇偶点图上作业法所能支持的节点规模下,该方法可求得与确定性算法相同的最优解,并在运算时间上达到约10倍的效率优化;且该方法在大规模稀疏路网图下可有效提高计算效率,并在可控时间范围内得到优化的可行解,针对5000个节点规模的路网图最快可在60 s内完成求解.

基于《中华医典》文献挖掘中医治疗积聚的用药规律研究

目的:探讨《中华医典》中治疗积聚方剂的用药特点及其规律。方法:检索《中华医典》治疗积聚的方剂,按照纳入和排除标准筛选治疗积聚的方剂,建立Excel数据库,进行用药频次、性味、归经分析。并使用R语言arules包及arulesViz包对筛选处方中的药物进行关联规则分析及可视化,使用IBM SPSS Modeler 18.0对药物进行复杂网络分析,采用SPSS Statistics 26.0对聚类方剂进行分析。结果:筛选后共纳入方剂426首,包含中药303种,总用药频次4075次;四气9种,总频次3214次;五味8种,总频次5490次;十二经总频次11936次。治疗积聚应用频次较高的药物前3位为木香、肉桂、当归;关联性药对以三棱、木香出现频次最高。复杂网络分析,木香-肉桂、木香-三棱之间的关联性较强。聚类图谱显示,皮尔逊相关性为20时,高频药物可聚为5类。结论:历代医家在积聚治疗时,所用药物药性以温性为主,药味以辛味和苦味为主,归经侧重于脾胃经,功效以理气药、温里药、补益药为主。通过对《中华医典》中治疗积聚的用药规律研究,为临床实践中药治疗积聚相关疾病提供参考。

中国樱桃不同品种(优系)果实品质分析

对中国樱桃果实品质进行分析,有利于选育适合区域发展的樱桃品种,为中国樱桃种质资源的保护奠定理论基础。本研究结合主成分分析、相关性分析和聚类分析,选取相同栽培条件下30个不同品种(优系)的中国樱桃果实进行内、外品质分析。结果表明:在相同的栽培条件下,不同品种(优系)的中国樱桃果实品质存在显著差异,综合性状评价得分排名依次为C78、C6、C14、C34和C32,C20(贵州玛瑙红)这一品种在各地栽培均表现优异,本次综合评价排名为11。9个果实内在品质指标存在不同程度的变异,变异系数为11.27%~36.32%。果实品质指标间存在相关系数,其中12项在0.01水平下极显著相关,17项在0.05水平下显著相关。主成分分析结果显示,前7个主成分的累计贡献率为88.196%,能够反映数量性状的基本特征。欧氏聚类分析结果显示,30个不同的中国樱桃品种(优系)初步聚为4大类。该研究得到的果实品质分析结果可以初步探索中国樱桃资源的遗传变异图谱,同时也可以作为新品种选育的参考依据。

基于数据挖掘的杨志敏教授治疗中青年失眠用药规律研究

目的 对杨志敏教授门诊治疗中青年失眠的方剂进行数据挖掘,探究杨志敏教授治疗中青年失眠的用药规律。方法 通过收集杨志敏教授近2021年1月1日—2023年1月1日门诊医案,筛选中药方剂治疗中青年失眠的医案。采用Excel整理统计所有方药的信息,包括中药的使用频率、归经、功效,利用IBM SPSS Statistics 27进行聚类分析,运用IBM SPSS Modeler 18.0进行关联规则分析及关联网络图绘制,分析杨志敏教授治疗中青年失眠的使用的中药间的联系和规律。结果 共纳入272个医案,中药的总频次为2452次。高频中药分别是炙甘草、桂枝、生姜、人参、黄芩、大枣、半夏、赤芍等;归经首归脾经,补虚类药物利用度最高,其次是解表药、清热药,药性药味最常用温甘,关联程度最高的主要药对为炙甘草-人参、生姜-大枣、大枣-半夏-黄芩等。结论 杨志敏教授治疗中青年失眠药物多以调和营卫、益气补血、平调寒热等为主,主要药物包括桂枝、炙甘草、人参、生姜、大枣、半夏、柴胡等。

桥本甲状腺炎并发甲状腺毒症人群临床症状及证型分布规律研究

背景中国传统医学对桥本甲状腺炎并发甲状腺毒症的发生、发展和诊疗已经有了系统的认识,但是目前关于本病人群中医临床症状和证型分布情况研究甚少,国家行业标准中亦缺乏关于本病的证型分布及证候诊断标准的描述。目的运用因子分析联合聚类分析探讨桥本甲状腺炎并发甲状腺毒症人群临床症状及证型分布规律,为临床辨证提供依据,促进桥本甲状腺炎并发甲状腺毒症证候标准化研究。方法收集2020年12月—2021年12月就诊于北京中医药大学东直门医院东城院区、通州院区、北京中医药大学孙思邈医院甲状腺病科门诊符合诊断标准的171例桥本甲状腺炎并发甲状腺毒症患者,使用《桥本甲状腺炎并发甲状腺毒症中医四诊信息采集表》对症状/体征、舌、脉等四诊信息进行采集,基于因子分析和聚类分析研究桥本甲状腺炎并发甲状腺毒症的症状及证型分布规律。结果171例桥本甲状腺炎并发甲状腺毒症患者中男17例、女154例,平均年龄(39.98±13.30)岁,其中20~60岁患者占87.72%。症状分布方面出现频率较高的症状有神疲乏力、心慌心悸、烦躁或急躁易怒,体征有颈前肿大、手指震颤,频率较高的舌象有舌红、舌瘦薄和舌有齿痕,苔质为苔白和苔薄,脉象是脉弦、脉数。收集调查表的82个四诊条目因子分析,提取出25个公因子,累计方差贡献率为70.562%,筛选出具有意义的症状62项。利用因子分析得到的25个公因子结果作为变量对其进行R型系统聚类分析,共得到5类证候分型,分别是:肝郁痰凝证、阴虚火旺证、脾肾阳虚证、肝郁气滞证、气阴两虚证。结论桥本甲状腺炎并发甲状腺毒症的基本中医证候可分为肝郁痰凝证、阴虚火旺证、脾肾阳虚证、肝郁气滞证、气阴两虚证。

基于数据挖掘分析中成药治疗肺炎的用药规律

目的 探究中成药治疗肺炎的用药规律及组方特点。方法 收集并筛选《中国药典》《中国临床药物大辞典·中药成方制剂》《国家中成药标准汇编》以及《新编国家中成药》中记录的主要治疗肺炎的中成药处方。聚类分析处方组方用药规律、药物的使用频次、性味归经及功效。结果 共纳入118个中成药处方,包括了16种不同的中医证候,其中最常见的证型为痰热壅肺证。涉及220种中药,主要根据其功效分为清热、化痰止咳、平喘、补虚等不同类别。药性中,寒性最为常见,其次是温性和平性;药味以苦味和辛味为主,主要归属于肺经,其次是胃、脾和肝经。通过关联规则分析,得出了25组核心药物的组合。通过系统聚类分析,归类为8个不同的类别。结论 肺炎的核心中医证候主要为痰热闭肺证,其病机基础涉及痰、瘀、热和毒,病理基础在于肺气郁闭。因此,在治疗中,强调宣肺气、消痰瘀、清热毒、润肺阴等功效的综合运用。