Multi-view manifold regularized compact low-rank representation for cancer samples clustering on multi-omics data

BMC Bioinformatics

Research

Xiang-Zhen Kong¹  Ling-Yun Dai¹  Shasha Yuan¹  Juan Wang¹  Cong-Hai Lu¹  Xiaofeng Zhang² 

[1] School of Computer Science, Qufu Normal University, 276826, Rizhao, China;School of Information and Electrical Engineering, Ludong University, 264025, Yantai, China;

关键词: Low-rank subspace clustering;    Concept factorization;    Manifold regularization;    Cancer multi-omics Data;   

DOI  :  10.1186/s12859-021-04220-6

 received in 2021-05-25, accepted in 2021-05-27,  发布年份 2021

来源: Springer

【 摘 要 】

BackgroundThe identification of cancer types is of great significance for early diagnosis and clinical treatment of cancer. Clustering cancer samples is an important means to identify cancer types, which has been paid much attention in the field of bioinformatics. The purpose of cancer clustering is to find expression patterns of different cancer types, so that the samples with similar expression patterns can be gathered into the same type. In order to improve the accuracy and reliability of cancer clustering, many clustering methods begin to focus on the integration analysis of cancer multi-omics data. Obviously, the methods based on multi-omics data have more advantages than those using single omics data. However, the high heterogeneity and noise of cancer multi-omics data pose a great challenge to the multi-omics analysis method.ResultsIn this study, in order to extract more complementary information from cancer multi-omics data for cancer clustering, we propose a low-rank subspace clustering method called multi-view manifold regularized compact low-rank representation (MmCLRR). In MmCLRR, each omics data are regarded as a view, and it learns a consistent subspace representation by imposing a consistence constraint on the low-rank affinity matrix of each view to balance the agreement between different views. Moreover, the manifold regularization and concept factorization are introduced into our method. Relying on the concept factorization, the dictionary can be updated in the learning, which greatly improves the subspace learning ability of low-rank representation. We adopt linearized alternating direction method with adaptive penalty to solve the optimization problem of MmCLRR method.ConclusionsFinally, we apply MmCLRR into the clustering of cancer samples based on multi-omics data, and the clustering results show that our method outperforms the existing multi-view methods.

【 授权许可】

CC BY   
© The Author(s) 2021

【 图 表 】

Fig. 1

Fig. 1

Fig. 5

Fig. 7

Fig. 9

Fig. 2

Fig. 6

40854_2023_457_Article_IEq35.gif

Fig. 1

Fig. 3

Fig. 6

Fig. 1

Fig. 3

Fig. 2

Fig. 4

Fig. 1

40249_2023_1060_Article_IEq4.gif

40249_2023_1060_Article_IEq2.gif

40249_2023_1060_Article_IEq1.gif

Fig. 1

40854_2023_451_Article_IEq5.gif

40854_2023_451_Article_IEq4.gif

Fig. 4

Fig. 5

Fig. 8

Fig. 4

Fig. 3

Fig. 4

Fig. 3

Fig. 6

Fig. 2

Fig. 2

Fig. 3

Fig. 6

Fig. 1

Fig. 4

Fig. 6

Fig. 2

Fig. 5

Fig. 2

Fig. 1

Fig. 8

Fig. 4

Fig. 7

Fig. 1

Fig. 2

Fig. 2

Fig. 2

Fig. 1

Fig. 1

40854_2023_461_Article_IEq30.gif

Fig. 5

Fig. 1

Fig. 7

40854_2023_461_Article_IEq24.gif

Fig. 3

Fig. 4

Fig. 2

Scheme 1

Fig. 3

Fig. 3

Fig. 2

40463_2023_625_Article_IEq11.gif

Fig. 1

Fig. 3

Fig. 2

Fig. 2

40463_2023_625_Article_IEq6.gif

40463_2023_625_Article_IEq5.gif

Fig. 1

40463_2023_625_Article_IEq3.gif

40463_2023_625_Article_IEq2.gif

40463_2023_625_Article_IEq1.gif

40854_2023_458_Article_IEq119.gif

Fig. 5

40854_2023_458_Article_IEq108.gif

Fig. 2

Fig. 4

Fig. 1

40854_2023_458_Article_IEq103.gif

Fig. 6

Fig. 3

Fig. 10

Fig. 5

Fig. 4

Fig. 7

Fig. 1

Fig. 6

Fig. 3

40854_2023_458_Article_IEq72.gif

Fig. 2

Fig. 5

Fig. 2

Fig. 1

Fig. 8

Fig. 9

Fig. 10

Fig. 9

Fig. 1

Fig. 6

Fig. 2

Fig. 8

40854_2023_458_Article_IEq60.gif

Fig. 4

Fig. 7

Fig. 2

Fig. 2

Fig. 5

Fig. 4

Fig. 6

40854_2023_458_Article_IEq55.gif

42004_2023_830_Article_IEq46.gif

Fig. 1

Fig. 5

Fig. 2

Fig. 4

Fig. 2

42004_2023_830_Article_IEq43.gif

Fig. 1

Fig. 4

Fig. 3

Fig. 4

Fig. 6

Fig. 7

Fig. 2

Fig. 2

Fig. 3

Fig. 1

42004_2023_830_Article_IEq36.gif

42004_2023_830_Article_IEq35.gif

Fig. 6

Fig. 2

Fig. 5

Fig. 4

Fig. 4

Fig. 3

42004_2023_830_Article_IEq31.gif

Fig. 5

40854_2022_419_Article_IEq25.gif

Fig. 2

Fig. 5

Fig. 4

Fig. 7

Fig. 4

42004_2023_830_Article_IEq22.gif

42004_2023_830_Article_IEq20.gif