Integrative sparse $K$-means with overlapping group lasso in genomic applications for disease subtype discovery

Huo, Zhiguang; Tseng, George C.

doi:10.1214/17-aoas1033

Cited by 26 publications

(22 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our study, we adopt the GAP approach that has been the most common choice in single dataset‐based clustering analysis. It has been also suggested in recent clustering studies with multidimensional data and shown to behave well in numerical analyses . Thus, it may be reasonable to conjecture that the GAP statistic is also valid for multidimensional data.…”

Section: Discussionmentioning

confidence: 73%

See 1 more Smart Citation

Assisted gene expression‐based clustering with AWNCut

Bie

Hidalgo

et al. 2018

Statistics in Medicine

View full text Add to dashboard Cite

In the research on complex diseases, gene expression (GE) data have been extensively used for clustering samples. The clusters so generated can serve as the basis for disease subtype identification, risk stratification, and many other purposes. With the small sample sizes of genetic profiling studies and noisy nature of GE data, clustering analysis results are often unsatisfactory. In the most recent studies, a prominent trend is to conduct multidimensional profiling, which collects data on GEs and their regulators (copy number alterations, microRNAs, methylation, etc.) on the same subjects. With the regulation relationships, regulators contain important information on the properties of GEs. We develop a novel assisted clustering method, which effectively uses regulator information to improve clustering analysis using GE data. To account for the fact that not all GEs are informative, we propose a weighted strategy, where the weights are determined data-dependently and can discriminate informative GEs from noises. The proposed method is built on the NCut technique and effectively realized using a simulated annealing algorithm. Simulations demonstrate that it can well outperform multiple direct competitors. In the analysis of TCGA cutaneous melanoma and lung adenocarcinoma data, biologically sensible findings different from the alternatives are made.

show abstract

Section: Discussionmentioning

confidence: 73%

“…It has been also suggested in recent clustering studies with multidimensional data and shown to behave well in numerical analyses. 44,45 Thus, it may be reasonable to conjecture that the GAP statistic is also valid for multidimensional data. Detailed studies are deferred to future investigation.…”

Section: Discussionmentioning

confidence: 99%

Assisted gene expression‐based clustering with AWNCut

Bie

Hidalgo

et al. 2018

Statistics in Medicine

View full text Add to dashboard Cite

show abstract

“…IS- K means Huo and Tseng [97] has developed an integrative sparse K-means approach with overlapping group LASSO to perform omics feature selection and cancer subtype identification. The formulation of feature group is flexible, which can be the ones from multi-level omics data (such as mRNA, CNV and Methylation) with the same cis-regulatory information or from the pathway-guided clustering scenario.…”

Section: Multi-omics Data Integrationmentioning

confidence: 99%

“…It has rooted in the dual ascent and augmented Lagrangian methods from convex optimization, yet combines the strength of both. ADMM can handle multiple constraints in optimization, which is of great importance in integrating multi-level omics data as the complex data structure and the way of conducting integration can be modelled by imposing constraints to the objective function [68,97]. In addition, EM algorithm plays an important role in traditional clustering analysis, such as the K-means clustering since whether a sample belongs to a certain cluster can be treated as a missing data problem.…”

Section: Multi-omics Data Integrationmentioning

confidence: 99%

A Selective Review of Multi-Level Omics Data Integration Using Variable Selection

et al. 2019

View full text Add to dashboard Cite

High-throughput technologies have been used to generate a large amount of omics data. In the past, single-level analysis has been extensively conducted where the omics measurements at different levels, including mRNA, microRNA, CNV and DNA methylation, are analyzed separately. As the molecular complexity of disease etiology exists at all different levels, integrative analysis offers an effective way to borrow strength across multi-level omics data and can be more powerful than single level analysis. In this article, we focus on reviewing existing multi-omics integration studies by paying special attention to variable selection methods. We first summarize published reviews on integrating multi-level omics data. Next, after a brief overview on variable selection methods, we review existing supervised, semi-supervised and unsupervised integrative analyses within parallel and hierarchical integration studies, respectively. The strength and limitations of the methods are discussed in detail. No existing integration method can dominate the rest. The computation aspects are also investigated. The review concludes with possible limitations and future directions for multi-level omics data integration.

show abstract

“…In the K-cluster method, a cluster is included in the collection of data with specific similarities. The K-cluster may not appropriate enough for small sizes and density of clusters; however, this method is well-scaled for large data sets and is considered the fastest technique of clustering [ 58 ]. Overall, unsupervised learning is mainly used to find patterns and clustering data set which are not known before in the dataset.…”

Section: Machine Learning In Nutrition Studiesmentioning

confidence: 99%

Statistical and Machine-Learning Analyses in Nutritional Genomics Studies

et al. 2020

View full text Add to dashboard Cite

Nutritional compounds may have an influence on different OMICs levels, including genomics, epigenomics, transcriptomics, proteomics, metabolomics, and metagenomics. The integration of OMICs data is challenging but may provide new knowledge to explain the mechanisms involved in the metabolism of nutrients and diseases. Traditional statistical analyses play an important role in description and data association; however, these statistical procedures are not sufficiently enough powered to interpret the large integrated multiple OMICs (multi-OMICS) datasets. Machine learning (ML) approaches can play a major role in the interpretation of multi-OMICS in nutrition research. Specifically, ML can be used for data mining, sample clustering, and classification to produce predictive models and algorithms for integration of multi-OMICs in response to dietary intake. The objective of this review was to investigate the strategies used for the analysis of multi-OMICs data in nutrition studies. Sixteen recent studies aimed to understand the association between dietary intake and multi-OMICs data are summarized. Multivariate analysis in multi-OMICs nutrition studies is used more commonly for analyses. Overall, as nutrition research incorporated multi-OMICs data, the use of novel approaches of analysis such as ML needs to complement the traditional statistical analyses to fully explain the impact of nutrition on health and disease.

show abstract

Integrative sparse $K$-means with overlapping group lasso in genomic applications for disease subtype discovery

Cited by 26 publications

References 53 publications

Assisted gene expression‐based clustering with AWNCut

Assisted gene expression‐based clustering with AWNCut

A Selective Review of Multi-Level Omics Data Integration Using Variable Selection

Statistical and Machine-Learning Analyses in Nutritional Genomics Studies

Contact Info

Product

Resources

About