Pattern fusion analysis by adaptive alignment of multiple heterogeneous omics data

Shi, Qianqian; Zhang, Chuanchao; Peng, Minrui; Yu, Xiangtian; Zeng, Tao; Liu, Juan; Chen, Luonan

doi:10.1093/bioinformatics/btx176

Cited by 69 publications

(47 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the performance of HOPES in fusing multi-omics data, we first tested it on simulated datasets and compared it with SNF and moCluster. The simulated dataset was generated similarly to the one reported elsewhere (Shi et al, 2017). The simulated dataset was created to recapitulate the features of actual genomic data by combining biological variation levels from real data and a pre-defined cluster structure.…”

Section: Resultsmentioning

confidence: 99%

Simultaneous Interrogation of Cancer Omics to Identify Subtypes With Significant Clinical Differences

Chen

Peng

et al. 2019

Front. Genet.

View full text Add to dashboard Cite

Recent advances in high-throughput sequencing have accelerated the accumulation of omics data on the same tumor tissue from multiple sources. Intensive study of multi-omics integration on tumor samples can stimulate progress in precision medicine and is promising in detecting potential biomarkers. However, current methods are restricted owing to highly unbalanced dimensions of omics data or difficulty in assigning weights between different data sources. Therefore, the appropriate approximation and constraints of integrated targets remain a major challenge. In this paper, we proposed an omics data integration method, named high-order path elucidated similarity (HOPES). HOPES fuses the similarities derived from various omics data sources to solve the dimensional discrepancy, and progressively elucidate the similarities from each type of omics data into an integrated similarity with various high-order connected paths. Through a series of incremental constraints for commonality, HOPES can take both specificity of single data and consistency between different data types into consideration. The fused similarity matrix gives global insight into patients' correlation and efficiently distinguishes subgroups. We tested the performance of HOPES on both a simulated dataset and several empirical tumor datasets. The test datasets contain three omics types including gene expression, DNA methylation, and microRNA data for five different TCGA cancer projects. Our method was shown to achieve superior accuracy and high robustness compared with several benchmark methods on simulated data. Further experiments on five cancer datasets demonstrated that HOPES achieved superior performances in cancer classification. The stratified subgroups were shown to have statistically significant differences in survival. We further located and identified the key genes, methylation sites, and microRNAs within each subgroup. They were shown to achieve high potential prognostic value and were enriched in many cancer-related biological processes or pathways.

show abstract

Section: Resultsmentioning

confidence: 99%

Simultaneous Interrogation of Cancer Omics to Identify Subtypes With Significant Clinical Differences

Chen

Peng

et al. 2019

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…The PFA framework established by Shi et al can perform information-alignment and bias correction for the fusion local sample-patterns originating from each dataset into a global sample-pattern corresponding to phenotypes in an automated manner. Applying PFA on the gene expression, miRNA expression, and DNA methylation profiles of the TCGA samples from clear cell carcinoma (KIRC), lung squamous cell carcinoma (LUSC), and glioblastoma (GBM) resulted in clustering patterns that were similar to SNF and iCluster but with higher clinical prognosis efficiency (Shi et al, 2017). PFA may not be suitable for biomarker discovery and gaining mechanistic insights into cancer phenotypes.…”

Section: Pattern Fusion Analysis (Pfa)mentioning

confidence: 99%

Integration of Online Omics-Data Resources for Cancer Research

et al. 2020

View full text Add to dashboard Cite

The manifestations of cancerous phenotypes necessitate alterations at different levels of information-flow from genome to proteome. The molecular alterations at different information processing levels serve as the basis for the cancer phenotype to emerge. To understand the underlying mechanisms that drive the acquisition of cancer hallmarks it is required to interrogate cancer cells using multiple levels of information flow represented by different omics-such as genomics, epigenomics, transcriptomics, and proteomics. The advantage of multi-omics data integration comes with a trade-off in the form of an added layer of complexity originating from inherently diverse types of omics-datasets that may pose a challenge to integrate the omics-data in a biologically meaningful manner. The plethora of cancer-specific online omics-data resources, if able to be integrated efficiently and systematically, may facilitate the generation of new biological insights for cancer research. In this review, we provide a comprehensive overview of the online single-and multi-omics resources that are dedicated to cancer. We catalog various online omics-data resources such as The Cancer Genome Atlas (TCGA) along with various TCGA-associated data portals and tools for multi-omics analysis and visualization, the International Cancer Genome Consortium (ICGC), Catalogue of Somatic Mutations in Cancer (COSMIC), The Pathology Atlas, Gene Expression Omnibus (GEO), and PRoteomics IDEntifications (PRIDE). By comparing the strengths and limitations of the respective online resources, we aim to highlight the current biological and technological challenges and possible strategies to overcome these challenges. We outline the available schemes for the integration of the multi-omics dimensions for stratifying cancer patients and biomarker prediction based on the integrated molecular-signatures of cancer. Finally, we propose the multi-omics driven systems-biology approaches to realize the potential of precision onco-medicine as the

show abstract

“…Through examining the different omics data, it is possible to distinguish reliably between different categories of cancer 37 . Integration of multiple omics data can better understand the underlying molecular mechanism in complex biological processes, and therefore offers more sophisticated ways to address biological or medical issues 38 , 39 . Thus, compared to single data types, multi-omics methods achieve better performance.…”

Section: Introductionmentioning

confidence: 99%

Multi-view clustering for multi-omics data using unified embedding

Mitra

Saha

Hasanuzzaman

2020

Sci Rep

View full text Add to dashboard Cite

In real world applications, data sets are often comprised of multiple views, which provide consensus and complementary information to each other. Embedding learning is an effective strategy for nearest neighbour search and dimensionality reduction in large data sets. This paper attempts to learn a unified probability distribution of the points across different views and generates a unified embedding in a low-dimensional space to optimally preserve neighbourhood identity. Probability distributions generated for each point for each view are combined by conflation method to create a single unified distribution. The goal is to approximate this unified distribution as much as possible when a similar operation is performed on the embedded space. As a cost function, the sum of Kullback-Leibler divergence over the samples is used, which leads to a simple gradient adjusting the position of the samples in the embedded space. The proposed methodology can generate embedding from both complete and incomplete multi-view data sets. Finally, a multi-objective clustering technique ( AMOSA ) is applied to group the samples in the embedded space. The proposed methodology, Multi-view Neighbourhood Embedding ( MvNE ), shows an improvement of approximately 2−3% over state-of-the-art models when evaluated on 10 omics data sets.

show abstract

Pattern fusion analysis by adaptive alignment of multiple heterogeneous omics data

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 69 publications

References 34 publications

Simultaneous Interrogation of Cancer Omics to Identify Subtypes With Significant Clinical Differences

Simultaneous Interrogation of Cancer Omics to Identify Subtypes With Significant Clinical Differences

Integration of Online Omics-Data Resources for Cancer Research

Multi-view clustering for multi-omics data using unified embedding

Contact Info

Product

Resources

About