检索结果-内蒙古大学图书馆

A novel method for clustering cellular data to improve classification

Neural Regeneration Research 2025年第9期20卷 2697-2705页

作者： Diek W.Wheeler Giorgio A.Ascoli Center for Neural Informatics Structures&PlasticityKrasnow Institute for Advanced Study Bioengineering Department Volgenau School of Engineering George Mason University FairfaxVAUSA

Many fields,such as neuroscience,are experiencing the vast prolife ration of cellular data,underscoring the need fo r organizing and interpreting large datasets.A popular approach partitions data into manageable subsets via hierarchical clustering,but objective methods to determine the appropriate classification granularity are *** recently introduced a technique to systematically identify when to stop subdividing clusters based on the fundamental principle that cells must differ more between than within *** we present the corresponding protocol to classify cellular datasets by combining datadriven unsupervised hierarchical clustering with statistical *** general-purpose functions are applicable to any cellular dataset that can be organized as two-dimensional matrices of numerical values,including molecula r,physiological,and anatomical *** demonstrate the protocol using cellular data from the Janelia MouseLight project to chara cterize morphological aspects of neurons.

关键词： cellular data clustering dendrogram data classification Levene's one-tailed statistical test unsupervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Identification of markers predicting clinical course in patients with Behcet disease by combination of machine learning and unbiased clustering analysis

引用

Graefe's Archive for Clinical and Experimental Ophthalmology 2025年 1-10页

作者： Tsubota, Kinya Usui, Yoshihiko Shimizu, Hiroyuki Goto, Hiroshi Department of Ophthalmology Tokyo Medical University 6-7-1 Nishishinjuku Shinjuku-Ku Tokyo 160-0023 Japan

Purpose: Behçet's disease (BD) is a multisystem inflammatory disorder with diverse clinical manifestations. Identifying biomarkers predictive of clinical outcomes, such as tumor necrosis factor (TNF) inhibitor initiation and ocular inflammatory attack frequency, is critical for improving management. This study aimed to identify biomarkers predicting the clinical course of BD using peripheral blood test data and unbiased clustering combined with machine learning. Methods: A retrospective cohort study of 238 BD patients diagnosed at Tokyo Medical University Hospital (2004–2020) was conducted. unsupervised hierarchical clustering was applied to peripheral blood data, dividing patients into distinct groups. Machine learning techniques were used to explore biomarkers predicting the clinical course. Results: Cluster analysis identified four groups: Group A (low C-reactive protein), Group B (high angiotensin-converting enzyme), Group C (high anti-streptolysin O), and Group D (low neutrophil count). Group C had a higher rate of TNF inhibitor initiation (47%, p = 0.04), while Group D had fewer ocular inflammation attacks per year (1.4, p = 0.04). Logistic regression analysis identified red blood cell count (p < 0.01) and monocyte percentage (p = 0.02) as predictive biomarkers for TNF inhibitor initiation. Machine learning further confirmed mean corpuscular hemoglobin concentration (MCHC) as a significant predictor of TNF inhibitor initiation. Additionally, multiple regression analysis identified the neutrophil/lymphocyte ratio as a predictor of the number of inflammatory attacks per year (p = 0.02). Conclusions: unsupervised clustering of blood test data identified distinct BD clinical phenotypes. Monocyte percentage may predict TNF inhibitor initiation, while neutrophil/lymphocyte ratio may predict ocular inflammation frequency, highlighting pathophysiologic heterogeneity in BD. © The Author(s) 2025.

关键词： Behçet’s disease Machine learning Monocyte percentage Neutrophil/lymphocyte ratio TNF inhibitor unsupervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

PROBABILISTIC VALIDATION APPROACH FOR clustering

引用

PATTERN RECOGNITION LETTERS 1995年第11期16卷 1189-1196页

作者： HAREVEN, M BRAILOVSKY, VL TEL AVIV UNIV DEPT COMP SCIIL-69978 RAMAT AVIVISRAEL

The suggested approach combines the phases of cluster validity and cluster tendency inside the scope of the clustering algorithm. The algorithm is based on a probabilistic approach and is invariant to the scaling of f... 详细信息

关键词： CLUSTER ANALYSIS PROBABILISTIC VALIDATION PROJECTION PURSUIT SIMULATING ANNEALING unsupervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Mining hierarchical relations in building management variables

引用

PERVASIVE AND MOBILE COMPUTING 2016年 26卷 91-101页

作者： Gonzalez, Luis I. Lopera Amft, Oliver Univ Passau ACTLab Passau Germany

We present a framework to relate variables as they occur in a modern building management system (BMS) that processes data from building-installed sensor and actuators. Our group mining framework extracts a unified event time series as changes in building management variables, derives prepositional variable association rules, and extracts hierarchical variable groups from the derived rules. Variable changes typically occur by either occupants interacting with the building or as response to outdoor environmental changes. As a user enters a building, a sequence of sensor activations will create a specific temporal event pattern that is mapped into a variable hierarchy by our framework. Similarly, as outdoor lighting changes, a variable hierarchy appears that relates variables to the change. To extract variable groups, we introduce a novel hierarchical transitive clustering (HTC) algorithm that constructs a rooted variable tree and then clusters the tree to represent variable group relations. HTC is parameter-free and works unsupervised. We evaluated the group mining framework in living-lab data recorded in different office environments during 14 months. As typical for BMS operation, variables in our dataset represent measurements and control states of building-installed devices and processed context information. HTC showed a correctness of over 0.91 and an average variable coverage of 75%, this improving variable coverage by 40 p.p. compared to previous work. We successfully detected alternative hierarchies and show how variables relate across office rooms. (C) 2016 Published by Elsevier B.V.

关键词： Activity hierarchical activity recognition Activity discovery Prepositional rule clustering unsupervised hierarchical clustering Building automation

来源：评论

学校读者我要写书评

暂无评论

Uncovering hierarchical structure in data using the growing hierarchical self-organizing map

引用

NEUROCOMPUTING 2002年第1-4期48卷 199-216页

作者： Dittenbach, M Rauber, A Merkl, D Vienna Univ Technol Inst Software Technol A-1040 Vienna Austria

Discovering the inherent structure in data has become one of the major challenges in data mining applications. It requires stable and adaptive models that are capable of handling the typically very high-dimensional feature spaces. In particular, the representation of hierarchical relations and intuitively visible cluster boundaries are essential for a wide range of data mining applications. Current approaches based on neural networks hardly fulfill these requirements within a single model. In this paper we present the growing hierarchical self-organizing map (GHSOM), a neural network model based on the self-organizing map. The main feature of this novel architecture is its capability of growing both in terms of map size as well as in a three-dimensional tree-structure in order to represent the hierarchical structure present in a data collection during an unsupervised training process. This capability, combined with the stability of the self-organizing map for high-dimensional feature space representation, makes it an ideal tool for data analysis and exploration. We demonstrate the potential of the GHSOM with an application from the information retrieval domain, which is prototypical both of the high-dimensional feature spaces frequently encountered in today's applications as well as of the hierarchical nature of data. (C) 2002 Elsevier Science B.V. All rights reserved.

关键词： self-organizing map (SOM) unsupervised hierarchical clustering document classification data mining exploratory data analysis

来源：评论

学校读者我要写书评

暂无评论

A MUCINs expression signature impacts overall survival in patients with clear cell renal cell carcinoma

引用

CANCER MEDICINE 2021年第17期10卷 5823-5838页

作者： Meng, Hui Jiang, Xuewen Huang, Huangwei Shen, Neng Guo, Changsheng Yu, Chunxiao Yin, Gang Wang, Yu Qilu Hosp Dept Urol Jinan Shandong Peoples R China Shandong Univ Cheeloo Coll Med Jinan Shandong Peoples R China Taian TSCM Hosp Dept Surg Tai An Shandong Peoples R China Liaoning Hosp Tradit Chinese Med Dept Urol Shandong Peoples R China Cent Hosp Zaozhuang Min Grp Dept Urol Shandong Peoples R China Qilu Hosp Dept Obstet & Gynecol Ctr Reprod Med Jinan Shandong Peoples R China

Background Kidney cancer, especially clear cell renal cell carcinoma (ccRCC), is one of the most common cancers in the urinary system. Previous studies suggested that certain members of MUCINs could serve as independent predictors for the survival of ccRCC patients. None of them, however, is robust enough to predict prognosis accurately. Objective To analyze the correlation of MUCINs alterations and their expression levels with the prognosis of ccRCC patients and develop a prognosis-related predictor. Methods We applied whole-exome sequencing in samples from 22 Chinese ccRCC patients to identify genetic alterations in MUCIN genes and analyzed their genetic alterations, expression, and correlation with survival using the TCGA, , and datasets. Result Genetic alternations in MUCINs were identified in 91% and 51% of ccRCC patients in our cohort and the TCGA database, respectively. No correlation with survival was found for the genetic alterations. Using unsupervised clustering analysis of gene expression, we identified two major clusters of MUCIN expression patterns. Cluster 1 was characterized by a global overexpression of MUC1, MUC12, MUC13, MUC16, and OVGP1;and cluster 2 was characterized by a global overexpression of MUC4, MUC5B, MUC6, MUC20, EMCN, and MCAM. Patients with cluster 1 expression pattern had significantly shorter overall survival time and worse clinical features, including higher tumor grades and metastasis. Meanwhile, they had a higher level of mutation counts and more infiltrated immune cells, but lower enrichment in angiogenesis signature genes. A five-MUCINs expression signature was constructed from cluster 1, and notably, it was demonstrated to be associated with shorter overall survival. A similar worse clinical feature, lower angiogenesis but the more immune signature, was identified in samples presented with signature 1. In the validation data set , patients with signature 1 were also associated with a trend of poor survival outcomes. Conclusion

关键词： ccRCC MUCIN overall survival prognosis unsupervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Immunophenotyping of male breast cancer

引用

HISTOPATHOLOGY 2012年第6期61卷 1145-1155页

作者： Kornegoor, Robert Verschuur-Maes, Anoek H. J. Buerger, Horst Hogenes, Marieke C. de Bruin, Peter C. Oudejans, Joost J. Hinrichs, Bernd van Diest, Paul J. Univ Med Ctr Utrecht Dept Pathol NL-3508 GA Utrecht Netherlands Inst Pathol Paderborn Germany Lab Pathol E Netherlands Enschede Netherlands St Antonius Hosp Dept Pathol Nieuwegein Netherlands Diakonessen Hosp Dept Pathol Utrecht Netherlands Ctr Pathol & Cytodiagnost Cologne Germany

Kornegoor R, Verschuur-Maes A H J, Buerger H, Hogenes M C, de Bruin P C, Oudejans J J, Hinrichs B & van Diest P J ?(2012) Histopathology?Immunophenotyping of male breast cancer Aims: Male breast cancer is a rare disease, and knowledge of carcinogenesis is limited. Conflicting results, based on small series, have been reported for clinically relevant biomarkers. Methods and results: One hundred and thirty-four cases of male breast cancer were immunohistochemically stained on tissue microarrays for oestrogen receptor (ER), progesterone receptor (PR), androgen receptor, human epidermal growth factor receptor 2 (HER2), BRST2, cyclin D1, bcl-2, p53, p16, p21, Ki67, cytokeratin (CK) 5/6, CK14, and epidermal growth factor receptor. Data were correlated with clinicopathological features and patient outcome. High mitotic count and high grade were correlated with high Ki67, HER2 amplification/overexpression, p53 accumulation, high p21 expression, low PR expression, and low bcl-2 expression. PR negativity (P = 0.009) and p53 accumulation (P = 0.042) were correlated with decreased 5-year survival and were independent markers for patient outcome in Cox regression. In unsupervised hierarchical clustering, four groups were identified that were correlated with distinctive clinicopathological features. The hormone negative/ER-positive/high-grade cluster was significantly associated with decreased survival (P = 0.011) and was an independent prognostic factor in Cox regression. Conclusions: Several tissue biomarkers are associated with an aggressive phenotype in male breast cancer. PR and p53 are the most promising individual prognostic markers. On the basis of immunophenotype, four distinctive and prognostically relevant male breast cancer groups were identified, indicating that protein expression profiling may be clinically useful in male breast cancer.

关键词： breast cancer immunohistochemistry male prognosis unsupervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

NKp30 isoforms in patients with chronic hepatitis C virus infection

引用

IMMUNOLOGY 2015年第2期146卷 234-242页

作者： Mantovani, Stefania Mele, Dalila Oliviero, Barbara Barbarini, Giorgio Varchetta, Stefania Mondelli, Mario U. Fdn IRCCS Policlin San Matteo Dept Infect Dis Res Labs Pavia Italy Fdn IRCCS Policlin San Matteo Dept Infect Dis Div Trop Med Pavia Italy Univ Pavia Dept Internal Med & Therapeut I-27100 Pavia Italy

Natural killer (NK) cells play an important role in virus infection, their action being regulated by several activating and inhibitory receptors. The NKp30 activating receptor and its isoforms have recently emerged as important determinants of efficient NK cell responses. We determined the relative proportions of NKp30 isoforms in patients with chronic hepatitis C virus (HCV) infection and healthy donors (HD). NK cell function (degranulation and cytokine production) and correlations with clinical parameters were assessed following unsupervised hierarchical clustering of patients according to isoform expression. NKp30 receptor expression on NK cells and all isoforms were reduced in HCV-infected patients. Patients were clustered into two groups: the HCV-1 group had similar isoform expression to the HD group, whereas the HCV-2 group had lower expression. The latter showed a better functional activity, and a higher proportion of the activating a isoform and of the NKp30 isoform a/c ratio compared with the HCV-1 cluster. There was a positive correlation between the activating a isoform and liver stiffness and an inverse relationship between the immunosuppressive c isoform and the fibrosis 4 score, suggesting a potentially important role of NKp30 isoforms in influencing liver damage and ensuing fibrosis.

关键词： interferon-gamma liver fibrosis natural killer cells unsupervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Progression risk assessments of individual non-invasive gastric neoplasms by genomic copy-number profile and mucin phenotype

引用

BMC MEDICAL GENOMICS 2015年第1期8卷 1-13页

作者： Diem Thi-Ngoc Vo Nakayama, Takahisa Yamamoto, Hiroto Mukaisho, Ken-ichi Hattori, Takanori Sugihara, Hiroyuki Shiga Univ Med Sci Div Mol & Diagnost Pathol Dept Pathol Otsu Shiga 5202192 Japan

Background: Early detection and treatment of non-invasive neoplasms can effectively reduce the incidence of advanced gastric carcinoma (GC), but only when the lineage is continuous between non-invasive and advanced tumours. Although a fraction of non-invasive neoplasms progress to invasive GC, it is difficult to identify individual progression-prone non-invasive neoplasms. To classify non-invasive gland-forming gastric neoplasms into clusters of different levels of progression risk, we applied mucin phenotyping and genomic DNA microarray analyses to intramucosal gland-forming gastric neoplasms. Methods: Formalin-fixed, paraffin-embedded tissues from 19 non-invasive and 24 invasive gland-forming neoplasms were obtained via endoscopic submucosal dissection or surgical excision. According to the Vienna classification, intramucosal neoplasms were classified as low-grade or high-grade non-invasive neoplasms (LGNs [category 3] and HGNs [category 4], respectively) or invasive carcinomas (intramucosal GCs and mucosal parts of submucosal or deeper GCs [category 5]). Neoplastic lesions were characterized by mucin phenotypes determined using monoclonal antibodies against MUC2, MUC5AC, MUC6, and CD10. Genomic DNA samples from mucosal neoplasms were subjected to array-based comparative genomic hybridization and subsequent unsupervised, hierarchical clustering with selected large-sized genes. Results: There was no significant difference in mucin phenotype between HGNs/LGNs and invasive carcinomas. The clustering classified samples into stable, unstable, and intermediate. The histological tumour grade or mucin phenotype of non-invasive neoplasms did not correlate with the clustering results. Each cluster may represent an independent lineage of different outcome because the size distribution of non-invasive tumours among the 3 clusters almost overlapped. In contrast, the unstable cluster alone included invasive carcinomas. Conclusions: These findings suggest that the outcome of ind

关键词： Copy-number variation Microarray Non-invasive neoplasia Gastric cancer Mucin phenotype Array-based comparative genomic hybridization unsupervised hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

DNA methylation profiling of meningiomas highlights clinically distinct molecular subgroups

引用

JOURNAL OF NEURO-ONCOLOGY 2023年第2期161卷 339-356页

作者： Singh, Jyotsna Sharma, Ravi Shukla, Nidhi Narwal, Priya Katiyar, Amit Mahajan, Swati Sahu, Saumya Garg, Ajay Sharma, Mehar C. C. Suri, Ashish Sarkar, Chitra Suri, Vaishali All India Inst Med Sci Neurosci Ctr Neuropathol Lab New Delhi India All India Inst Med Sci Dept Neurosurg New Delhi India All India Inst Med Sci CCRF New Delhi India All India Inst Med Sci Dept Neuroradiol New Delhi India All India Inst Med Sci Dept Pathol New Delhi India

Background Introduction of the classification of brain tumours based on DNA methylation profile has significantly changed the diagnostic approach. Due to the paucity of data on the molecular profiling of meningiomas and their clinical implications, no effective therapies and new treatments have been implemented. Methods DNA methylation profiling, copy number analysis, targeted sequencing and H3K27me3 expression was performed on 35 meningiomas and 5 *** unsupervised hierarchical clustering (UHC) analysis revealed four distinct molecular subgroups: Malignant;Intermediate;Benign A, and Benign B. Molecular heterogeneity was observed within the same grade as the Intermediate, Benign A, and Benign B subgroups were composed of WHO grade 1 as well as grade 2 cases. There was association of mutations with distinct methylation subgroups (NF2, AKT1, SMO, TRAF7 and pTERT). Loss of chromosome 22q was observed across all subgroups. 1p/14q co-deletion was seen in 50% of malignant and intermediate while CDKN2A loss was predominantly observed in malignant subgroup (50%). Majority of malignant (75%) and a small proportion of other subgroups (Intermediate: 25%, Benign A: 38.5%, and Benign B: 20%) harboured H3K27me3 loss. 38,734 genes were dysregulated amongst the four subgroups. DKFZ classified 71% cases with acceptable score. On survival analysis, methylation profiling had significant impact on progression-free-survival in WHO grade1 and 2 meningiomas (p = 0.0051).Conclusion Genome-wide DNA methylation profiling highlights clinically distinct molecular subgroups and heterogeneity within the same grade of meningiomas. Molecular profiling can usher in a paradigm shift in meningioma classification, prognostic prediction, and treatment strategy.

关键词： Methylation profiling Targeted sequencing unsupervised hierarchical clustering Methylation subgroups DKFZ classifier

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：