Robust feature learning using contractive autoencoders for multi-omics clustering in cancer subtyping

•We propose a novel multi-omics framework using contractive autoencoder for robust feature extraction.•Cox regression integrates survival analysis to identify key survival-related features for clustering.•Experimental results demonstrate the superior performance of our method in multi-omics data ana...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Methods (San Diego, Calif.) Ročník 233; s. 52 - 60
Hlavní autoři: Guo, Mengke, Ye, Xiucai, Huang, Dong, Sakurai, Tetsuya
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States Elsevier Inc 01.01.2025
Témata:
Algorithms
Cancer subtyping
Cluster Analysis
Contractive autoencoder
Genomics - methods
Humans
Multi-omics clustering
Multiomics
Neoplasms - classification
Neoplasms - genetics
Neoplasms - metabolism
Proportional Hazards Models
Contractive autoencoder
Cancer subtyping
Multi-omics clustering
ISSN:1046-2023, 1095-9130, 1095-9130
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•We propose a novel multi-omics framework using contractive autoencoder for robust feature extraction.•Cox regression integrates survival analysis to identify key survival-related features for clustering.•Experimental results demonstrate the superior performance of our method in multi-omics data analysis. Cancer can manifest in virtually any tissue or organ, necessitating precise subtyping of cancer patients to enhance diagnosis, treatment, and prognosis. With the accumulation of vast amounts of omics data, numerous studies have focused on integrating multi-omics data for cancer subtyping using clustering techniques. However, due to the heterogeneity of different omics data, extracting important features to effectively integrate these data for accurate clustering analysis remains a significant challenge. This study proposes a new multi-omics clustering framework for cancer subtyping, which utilizes contractive autoencoder to extract robust features. By encouraging the learned representation to be less sensitive to small changes, the contractive autoencoder learns robust feature representations from different omics. To incorporate survival information into the clustering analysis, Cox proportional hazards regression is used to further select the key features significantly associated with survival for integration. Finally, we utilize K-means clustering on the integrated feature to obtain the clustering result. The proposed framework is evaluated on ten different cancer datasets across four levels of omics data and compared to other existing methods. The experimental results indicate that the proposed framework effectively integrates the four omics datasets and outperforms other methods, achieving higher C-index scores and showing more significant differences between survival curves. Additionally, differential gene analysis and pathway enrichment analysis are performed to further demonstrate the effectiveness of the proposed method framework.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1046-2023
1095-9130
1095-9130
DOI:10.1016/j.ymeth.2024.11.013