Consensus clustering with missing labels (ccml): a consensus clustering tool for multi-omics integrative prediction in cohorts with unequal sample coverage

doi:10.1093/bib/bbad501

科研成果详情

题名	Consensus clustering with missing labels (ccml): a consensus clustering tool for multi-omics integrative prediction in cohorts with unequal sample coverage
作者	Li, Chuan-Xing 1; Chen, Hongyan 2; Zounemat-Kermani, Nazanin 3; Adcock, Ian M.4; Sköld, C. Magnus 5; Zhou, Meng2; Wheelock, Åsa M.6
发表日期	2024-01
发表期刊	BRIEFINGS IN BIOINFORMATICS 影响因子和分区
语种	英语
原始文献类型	Article
关键词	multi-omics integration consensus clustering missing labels unequal sample coverage predictive labels
其他关键词	SEVERE ASTHMA ; CLASS DISCOVERY ; FLUID
摘要	Multi-omics data integration is a complex and challenging task in biomedical research. Consensus clustering, also known as meta-clustering or cluster ensembles, has become an increasingly popular downstream tool for phenotyping and endotyping using multiple omics and clinical data. However, current consensus clustering methods typically rely on ensembling clustering outputs with similar sample coverages (mathematical replicates), which may not reflect real-world data with varying sample coverages (biological replicates). To address this issue, we propose a new consensus clustering with missing labels (ccml) strategy termed ccml, an R protocol for two-step consensus clustering that can handle unequal missing labels (i.e. multiple predictive labels with different sample coverages). Initially, the regular consensus weights are adjusted (normalized) by sample coverage, then a regular consensus clustering is performed to predict the optimal final cluster. We applied the ccml method to predict molecularly distinct groups based on 9-omics integration in the Karolinska COSMIC cohort, which investigates chronic obstructive pulmonary disease, and 24-omics handprint integrative subgrouping of adult asthma patients of the U-BIOPRED cohort. We propose ccml as a downstream toolkit for multi-omics integration analysis algorithms such as Similarity Network Fusion and robust clustering of clinical data to overcome the limitations posed by missing data, which is inevitable in human cohorts consisting of multiple data modalities. The ccml tool is available in the R language (https://CRAN.R-project.org/package=ccml, https://github.com/pulmonomics-lab/ccml, or https://github.com/ZhoulabCPH/ccml).
资助项目	Swedish Research Council [2018-00520, 2017-01142]; Swedish Heart Lung Foundation [20190017, 20190421]; National Natural Science Foundation of China [62372331]
出版者	OXFORD UNIV PRESS
ISSN	1467-5463
EISSN	1477-4054
卷号	25 期号:1
DOI	10.1093/bib/bbad501
页数	7
WOS类目	Biochemical Research Methods ; Mathematical & Computational Biology
WOS研究方向	Biochemistry & Molecular Biology ; Mathematical & Computational Biology
WOS记录号	WOS:001173375300027
收录类别	SCIE ; SCOPUS
URL	查看原文
PubMed ID	38205966
SCOPUSEID	2-s2.0-85183620093
通讯作者地址	[Wheelock, Åsa M.]Respiratory Medicine Unit,Department of Medicine Solna,Centre for Molecular Medicine,Karolinska Institutet,Stockholm,171 76,Sweden ; [Zhou, Meng]School of Biomedical Engineering,Wenzhou Medical University,Wenzhou,325027,China
Scopus学科分类	Information Systems;Molecular Biology
TOP期刊	TOP期刊
引用统计
文献类型	期刊论文
条目标识符	https://kms.wmu.edu.cn/handle/3ETUA0LF/209448
专题	仁济学院_眼视光、生物医学工程学部
通讯作者	Zhou, Meng; Wheelock, Åsa M.
作者单位	1.The Karolinska Institute,Sweden; 2.The School of Biomedical Engineering,Wenzhou Medical University,China; 3.The Data Science Institute,National Heart & Lung Institute,United Kingdom; 4.Imperial College London,United Kingdom; 5.Karolinska University Hospital,Stockholm,Sweden; 6.The Karolinska Institute,Stockholm,Sweden
通讯作者单位	仁济学院_眼视光、生物医学工程学部
推荐引用方式 GB/T 7714	Li, Chuan-Xing,Chen, Hongyan,Zounemat-Kermani, Nazanin,et al. Consensus clustering with missing labels (ccml): a consensus clustering tool for multi-omics integrative prediction in cohorts with unequal sample coverage[J]. BRIEFINGS IN BIOINFORMATICS,2024,25(1).
APA	Li, Chuan-Xing., Chen, Hongyan., Zounemat-Kermani, Nazanin., Adcock, Ian M.., Sköld, C. Magnus., ... & Wheelock, Åsa M.. (2024). Consensus clustering with missing labels (ccml): a consensus clustering tool for multi-omics integrative prediction in cohorts with unequal sample coverage. BRIEFINGS IN BIOINFORMATICS, 25(1).
MLA	Li, Chuan-Xing,et al."Consensus clustering with missing labels (ccml): a consensus clustering tool for multi-omics integrative prediction in cohorts with unequal sample coverage".BRIEFINGS IN BIOINFORMATICS 25.1(2024).