MDICC: novel method for multi-omics data integration and cancer subtype identification

Yang, Ying; Tian, Sha; Qiu, Yin Long; Zhao, Pu; Zou, Quan

doi:10.1093/bib/bbac132

Cited by 26 publications

(31 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that cancer subtypes that are biologically different may have similar survival, and this is also true for enrichment of clinical parameters. However, these measures are widely used for clustering assessment, including in the most multi-omics clustering studies (12,26,(36)(37)(38).…”

Section: Evaluation Criteria and Comparison Algorithmsmentioning

confidence: 99%

MCluster-VAEs: An end-to-end variational deep learning-based clustering method for subtype discovery using multi-omics data

Rong¹,

Song²,

Cao³

et al. 2022

Computers in Biology and Medicine

View full text Add to dashboard Cite

Section: Evaluation Criteria and Comparison Algorithmsmentioning

confidence: 99%

MCluster-VAEs: An end-to-end variational deep learning-based clustering method for subtype discovery using multi-omics data

Rong¹,

Song²,

Cao³

et al. 2022

Computers in Biology and Medicine

View full text Add to dashboard Cite

“…Here we select Breast Cancer(BRCA) in the TCGA project. Breast cancer is one of the most common cancers of women, and the detection of subtypes of BRCA has attracted many studies' attention 17,18 . Most used PAM50 19 subtyping can be used to select an appropriate treatment for patients.…”

Section: Case Study: Transcriptome Of Breast Cancermentioning

confidence: 99%

MATTE: anti-noise module alignment for phenotype-gene-related analysis

Cai

Zhou

2022

Preprint

View full text Add to dashboard Cite

Purpose: Although many transcriptome analysis methods find fundamental interactions or markers of some phenotypes, preservation of module or network is still a challenge. Methods: The study developed a method to directly compare the transcriptome data of phenotypes and present the differences modularly, called Module Alignment of TranscripTomE(MATTE). Results: MATTE performs better under high noise than differential co-expression(DC) clustering in the simulation experiments but still detects differential expression(DE) and DC genes. After subsequent annotation of cell types in single-cell data, MATTE obtained the best scores in both supervised and unsupervised learning, i. e. MATTE found meaningful markers. Finally, we apply MATTE in analyzing the transcriptome of Breast Cancer(BRCA). We have found five BRCA subtypes, and the characteristic of one subtype is detected in the form of a module network. Conclusion: MATTE can find meaningful genes and modules, thus facilitating the downstream analysis task to obtain insight into biology.

show abstract

“…Yang et al. [ 31 ] proposed a novel multi-omics network fusion method for cancer subtype classification. This method constructs an omics affinity matrix based on Gaussian kernel functions and utilizes low-rank subspace representations for network fusion to classify cancer subtypes.…”

Section: Introductionmentioning

confidence: 99%

DeepKEGG: a multi-omics data integration framework with biological insights for cancer recurrence prediction and biomarker discovery

Lan,

Liao,

Chen

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

Deep learning-based multi-omics data integration methods have the capability to reveal the mechanisms of cancer development, discover cancer biomarkers and identify pathogenic targets. However, current methods ignore the potential correlations between samples in integrating multi-omics data. In addition, providing accurate biological explanations still poses significant challenges due to the complexity of deep learning models. Therefore, there is an urgent need for a deep learning-based multi-omics integration method to explore the potential correlations between samples and provide model interpretability. Herein, we propose a novel interpretable multi-omics data integration method (DeepKEGG) for cancer recurrence prediction and biomarker discovery. In DeepKEGG, a biological hierarchical module is designed for local connections of neuron nodes and model interpretability based on the biological relationship between genes/miRNAs and pathways. In addition, a pathway self-attention module is constructed to explore the correlation between different samples and generate the potential pathway feature representation for enhancing the prediction performance of the model. Lastly, an attribution-based feature importance calculation method is utilized to discover biomarkers related to cancer recurrence and provide a biological interpretation of the model. Experimental results demonstrate that DeepKEGG outperforms other state-of-the-art methods in 5-fold cross validation. Furthermore, case studies also indicate that DeepKEGG serves as an effective tool for biomarker discovery. The code is available at https://github.com/lanbiolab/DeepKEGG.

show abstract

MDICC: novel method for multi-omics data integration and cancer subtype identification

Cited by 26 publications

References 35 publications

MCluster-VAEs: An end-to-end variational deep learning-based clustering method for subtype discovery using multi-omics data

MCluster-VAEs: An end-to-end variational deep learning-based clustering method for subtype discovery using multi-omics data

MATTE: anti-noise module alignment for phenotype-gene-related analysis

DeepKEGG: a multi-omics data integration framework with biological insights for cancer recurrence prediction and biomarker discovery

Contact Info

Product

Resources

About