Integrative interaction analysis using threshold gradient directed regularization

Li, Yang; Li, Rong; Qin, Yichen; Wu, Mengyun; Ma, Shuangge

doi:10.1002/asmb.2342

Cited by 6 publications

(7 citation statements)

References 18 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First developed for linear regression [ 3 ] and later extended to many other regression models [ 30 , 31 , 35 ], TGDR is a generically applicable regularized optimization technique. The key strategy is that, in gradient-based optimization, in each iteration, gradients are compared and important parameters with large gradients identified.…”

Section: Methodsmentioning

confidence: 99%

“…In regression analysis of multiple types of responses under various models, it has been shown that TGDR has an intuitive formulation, simpler computation, and satisfactory estimation and selection performance. Beyond “standard” settings, it has also been extended to complex data/model settings, for example, longitudinal data [ 29 ], interaction analysis [ 30 ], multidataset analysis [ 31 ], and others [ 32 ]. It has been shown that, for many data settings, TGDR outperforms penalization, Bayesian, boosting, and other techniques.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Survival Analysis with High-Dimensional Omics Data Using a Threshold Gradient Descent Regularization-Based Neural Network Approach

Fan

Zhang

2022

Genes

Self Cite

View full text Add to dashboard Cite

Analysis of data with a censored survival response and high-dimensional omics measurements is now common. Most of the existing analyses are based on specific (semi)parametric models, in particular the Cox model. Such analyses may be limited by not having sufficient flexibility, for example, in accommodating nonlinearity. For categorical and continuous responses, neural networks (NNs) have provided a highly competitive alternative. Comparatively, NNs for censored survival data remain limited. Omics measurements are usually high-dimensional, and only a small subset is expected to be survival-associated. As such, regularized estimation and selection are needed. In the existing NN studies, this is usually achieved via penalization. In this article, we propose adopting the threshold gradient descent regularization (TGDR) technique, which has competitive performance (for example, when compared to penalization) and unique advantages in regression analysis, but has not been adopted with NNs. The TGDR-based NN has a highly sensible formulation and an architecture different from the unregularized and penalization-based ones. Simulations show its satisfactory performance. Its practical effectiveness is further established via the analysis of two cancer omics datasets. Overall, this study can provide a practical and useful new way in the NN paradigm for survival analysis with high-dimensional omics measurements.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Survival Analysis with High-Dimensional Omics Data Using a Threshold Gradient Descent Regularization-Based Neural Network Approach

Fan

Zhang

2022

Genes

Self Cite

View full text Add to dashboard Cite

show abstract

“…15 Li et al. 19 proposed TGDR for integrative interaction analysis. The model they considered, however, is a parametric one.…”

Section: Methodsmentioning

confidence: 99%

“…From the perspective of methodology, we developed a novel TGDR for semiparametric integrative interaction analysis, as an extension to the work by Li et al. 19 Moreover, data on other cancers in TCGA have characteristics similar to those of NSCLC: multiple datasets, high dimensionality, a small sample size, gene–gene interactions, and environmental factors. Consequently, the proposed approach can be seen as a general method of analysing cancer data.…”

Section: Introductionmentioning

confidence: 99%

Semiparametric integrative interaction analysis for non-small-cell lung cancer

Wang

et al. 2020

Stat Methods Med Res

Self Cite

View full text Add to dashboard Cite

In genomic analysis, it is significant though challenging to identify markers associated with cancer outcomes or phenotypes. Based on the biological mechanisms of cancers and the characteristics of datasets, we propose a novel integrative interaction approach under a semiparametric model, in which genetic and environmental factors are included as the parametric and nonparametric components, respectively. The goal of this approach is to identify the genetic factors and gene–gene interactions associated with cancer outcomes, while estimating the nonlinear effects of environmental factors. The proposed approach is based on the threshold gradient-directed regularisation technique. Simulation studies indicate that the proposed approach outperforms alternative methods at identifying the main effects and interactions, and has favourable estimation and prediction accuracy. We analysed non-small-cell lung carcinoma datasets from the Cancer Genome Atlas, and the results demonstrate that the proposed approach can identify markers with important implications and that it performs favourably in terms of prediction accuracy, identification stability, and computation cost.

show abstract

“…To further examine the stability of the performance in screening and feature selection of these methods, we calculate the observed occurrence index (OOI). 42 A resampling of 100-times generates 100 new samples. Each sample includes the new design matrix X and the corresponding responses Y .…”

Section: Skcm Data Analysismentioning

confidence: 99%

Lq‐based robust analytics on ultrahigh and high dimensional data

Chen

Bie

Qin

et al. 2022

Statistics in Medicine

View full text Add to dashboard Cite

Ultrahigh and high dimensional data are common in regression analysis for various fields, such as omics data, finance, and biological engineering. In addition to the problem of dimension, the data might also be contaminated. There are two main types of contamination: outliers and model misspecification. We develop an unique method that takes into account the ultrahigh or high dimensional issues and both types of contamination. In this article, we propose a framework for feature screening and selection based on the minimum Lq‐likelihood estimation (MLqE), which accounts for the model misspecification contamination issue and has also been shown to be robust to outliers. In numerical analysis, we explore the robustness of this framework under different outliers and model misspecification scenarios. To examine the performance of this framework, we conduct real data analysis using the skin cutaneous melanoma data. When comparing with traditional screening and feature selection methods, the proposed method shows superiority in both variable identification effectiveness and parameter estimation accuracy.

show abstract

Integrative interaction analysis using threshold gradient directed regularization

Cited by 6 publications

References 18 publications

Survival Analysis with High-Dimensional Omics Data Using a Threshold Gradient Descent Regularization-Based Neural Network Approach

Survival Analysis with High-Dimensional Omics Data Using a Threshold Gradient Descent Regularization-Based Neural Network Approach

Semiparametric integrative interaction analysis for non-small-cell lung cancer

Lq‐based robust analytics on ultrahigh and high dimensional data

Contact Info

Product

Resources

About