Integrative analysis of prognosis data on multiple cancer subtypes

Liu, Jin; Huang, Jian; Zhang, Yawei; Lan, Qing; Rothman, Nathaniel; Zheng, Tongzhang; Ma, Shuangge

doi:10.1111/biom.12177

Cited by 19 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another limitation is that the theoretical aspect has not been well developed. For a few specific models and penalization methods, we have shown that they enjoy the selection and estimation consistency properties. Especially this result holds if log( p )/ N → 0 as N , p → ∞, where N is the combined sample size across datasets.…”

Section: Discussionmentioning

confidence: 99%

Integrative analysis of ‘‐omics’ data using penalty functions

Zhao

Shi

Huang

et al. 2014

WIREs Computational Stats

Self Cite

View full text Add to dashboard Cite

In the analysis of omics data, integrative analysis provides an effective way of pooling information across multiple datasets or multiple correlated responses, and can be more effective than single-dataset (response) analysis. Multiple families of integrative analysis methods have been proposed in the literature. The current review focuses on the penalization methods. Special attention is paid to sparse meta-analysis methods that pool summary statistics across datasets, and integrative analysis methods that pool raw data across datasets. We discuss their formulation and rationale. Beyond “standard” penalized selection, we also review contrasted penalization and Laplacian penalization which accommodate finer data structures. The computational aspects, including computational algorithms and tuning parameter selection, are examined. This review concludes with possible limitations and extensions.

show abstract

Section: Discussionmentioning

confidence: 99%

Integrative analysis of ‘‐omics’ data using penalty functions

Zhao

Shi

Huang

et al. 2014

WIREs Computational Stats

Self Cite

View full text Add to dashboard Cite

show abstract

“…There is a lack of objective measure which set of identified genes is “biologically more meaning”. Prediction evaluation is conducted, which may provide some insights on the identified genes, using a random sampling approach (Liu et al, 2014b). Specifically, each dataset is randomly split into a training and a testing set, with sizes 2:1.…”

Section: Analysis Of Lung Cancer Datamentioning

confidence: 99%

“…However it is still reasonable to expect that the sets of identified important covariates are similar across datasets to a large extent. As the second example, consider the integrative analysis of genetic data on different cancer types (Liu et al, 2014b). Here the similarity in sparsity structures correspond to genes associated with multiple cancer types, which represent the more essential features of cancer and can be of more interest than type-specific cancer genes.…”

Section: Introductionmentioning

confidence: 99%

“…Even when multiple studies measure the same response variable and covariates, as for example in Section 5, it is difficult to achieve full comparability of measurements across datasets (Guerra and Goldstein, 2009). When for example different studies are on different disease types as in Liu et al (2014b), it is not sensible to compare the magnitudes of regression coefficients across datasets. Under these scenarios, it is appropriate to directly work with the sparsity structures but not the magnitudes of regression coefficients.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Promoting Similarity of Sparsity Structures in Integrative Analysis With Penalization

Huang

Zhang

et al. 2017

Journal of the American Statistical Association

Self Cite

View full text Add to dashboard Cite

For data with high-dimensional covariates but small sample sizes, the analysis of single datasets often generates unsatisfactory results. The integrative analysis of multiple independent datasets provides an effective way of pooling information and outperforms single-dataset and several alternative multi-datasets methods. Under many scenarios, multiple datasets are expected to share common important covariates, that is, the corresponding models have similarity in their sparsity structures. However, the existing methods do not have a mechanism to promote the similarity in sparsity structures in integrative analysis. In this study, we consider penalized variable selection and estimation in integrative analysis. We develop an L0-penalty based method, which explicitly promotes the similarity in sparsity structures. Computationally it is realized using a coordinate descent algorithm. Theoretically it has the selection and estimation consistency properties. Under a wide spectrum of simulation scenarios, it has identification and estimation performance comparable to or better than the alternatives. In the analysis of three lung cancer datasets with gene expression measurements, it identifies genes with sound biological implications and satisfactory prediction performance.

show abstract

“…A comprehensive review of meta-analysis and its applications in genomic studies can be found in [24]. The other is the integrative analysis using individual patient data (IPD) from multiple studies [14, 15, 16]. In the era of big data, IPD becomes more accessible from large genomic consortia such as Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA).…”

Section: Introductionmentioning

confidence: 99%

A statistical framework for pathway and gene identification from integrative analysis

Wang

2017

Journal of Multivariate Analysis

View full text Add to dashboard Cite

In the era of big data, integrative analyses that pool data from different sources are now extensively conducted in order to improve performance. Among many interesting applications, genomics research is an area where integrative methods become popular tools to identify prognostic biomarkers for various diseases. In this paper, we propose such a framework for pathway and gene identification. Our method employs a hierarchical decomposition on genes’ effects followed by a proper regularization to identify important pathways and genes across multiple studies. Asymptotic theories are provided to show that our method is both pathway and gene selection consistent. More importantly, we explicitly show that pathway selection consistency needs milder statistical conditions than gene selection consistency, as it would allow false positives and negatives at the gene selection level. Finite-sample performance of our method is shown to be superior than other ad hoc methods in various simulation studies. We further apply our method to analyze five cardiovascular disease studies. Our method is intrinsically a general method on group-wise and element-wise selections from integrative analysis, which can have other applications beyond genomic research.

show abstract

Integrative analysis of prognosis data on multiple cancer subtypes

Cited by 19 publications

References 18 publications

Integrative analysis of ‘‐omics’ data using penalty functions

Integrative analysis of ‘‐omics’ data using penalty functions

Promoting Similarity of Sparsity Structures in Integrative Analysis With Penalization

A statistical framework for pathway and gene identification from integrative analysis

Contact Info

Product

Resources

About