Network Regularization in Imaging Genetics Improves Prediction Performances and Model Interpretability on Alzheimer’s Disease

Guigui, Nicolas; Philippe, Cathy; Gloaguen, Arnaud; Karkar, Skander; Guillemot, Vincent; Löfstedt, Tommy; Frouin, Vincent

doi:10.1109/isbi.2019.8759593

Cited by 2 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graph-net 10 , similar to SCCAN 11 , 12 , uses ℓ 1 regularization to constrain embedding vectors to be sparse and reduce over-fitting in high-dimensional problems. Relatedly, graph-regularization has been used to improve prediction in imaging genetics 10 , 13 , 14 and may be combined with canonical correlation analysis (as in SCCAN 11 ). Non-negative factorization methods provide a second degree of interpretability by guaranteeing that factorizations are unsigned and, therefore, these methods allow components to be interpreted in terms of their original units (e.g.…”

Section: Introductionmentioning

confidence: 99%

Similarity-driven multi-view embeddings from high-dimensional biomedical data

2021

View full text Add to dashboard Cite

Diverse, high-dimensional modalities collected in large cohorts present new opportunities for the formulation and testing of integrative scientific hypotheses. Similarity-driven multi-view linear reconstruction (SiMLR) is an algorithm that exploits inter-modality relationships to transform large scientific datasets into smaller, more well-powered and interpretable low-dimensional spaces. SiMLR contributes an objective function for identifying joint signal, regularization based on sparse matrices representing prior within-modality relationships and an implementation that permits application to joint reduction of large data matrices. We demonstrate that SiMLR outperforms closely related methods on supervised learning problems in simulation data, a multi-omics cancer survival prediction dataset and multiple modality neuroimaging datasets. Taken together, this collection of results shows that SiMLR may be applied to joint signal estimation from disparate modalities and may yield practically useful results in a variety of application domains.

show abstract

Section: Introductionmentioning

confidence: 99%

Similarity-driven multi-view embeddings from high-dimensional biomedical data

2021

View full text Add to dashboard Cite

show abstract

“…The problem expressed in Equation (2) belongs to a class of multiconvex optimization problems with nonsmooth constraints. The feasibility of the using of the GraphNet penalty with the SGCCA framework has already been presented by Guigui et al (2019) . Multiple solvers for this problem have been proposed and studied ( Hadj-Selem et al 2018 ).…”

Section: Methodsmentioning

confidence: 99%

Integrating multiomics and prior knowledge: a study of the Graphnet penalty impact

et al. 2023

View full text Add to dashboard Cite

Motivation In the field of oncology, statistical models are used for the discovery of candidate factors that influence the development of the pathology or its outcome. These statistical models can be designed in a multi-block framework to study the relationship between different multi-omic data, and variable selection is often achieved by imposing constraints on the model parameters. A priori graph constraints have been used in the literature as a way to improve feature selection in the model, yielding more interpretability. However, it is still unclear how these graphs interact with the models and how they impact the feature selection. Additionally, with the availability of different graphs encoding different information, one can wonder how the choice of the graph meaningfully impacts the results obtained. Results We proposed to study the graph penalty impact on a multi-block model. Specifically, we used the SGCCA as the multi-block framework. We studied the effect of the penalty on the model using the TCGA-LGG dataset. Our findings are threefold. We showed that the graph penalty increases the number of selected genes from this dataset, while selecting genes already identified in other works as pertinent biomarkers in the pathology. We demonstrated that using different graphs leads to different though consistent results, but that graph density is the main factor influencing the obtained results. Finally, we showed that the graph penalty increases the performance of the survival prediction from the model-derived components and the interpretability of the results. Availability Source code is freely available at https://github.com/neurospin/netSGCCA Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Network Regularization in Imaging Genetics Improves Prediction Performances and Model Interpretability on Alzheimer’s Disease

Cited by 2 publications

References 16 publications

Similarity-driven multi-view embeddings from high-dimensional biomedical data

Similarity-driven multi-view embeddings from high-dimensional biomedical data

Integrating multiomics and prior knowledge: a study of the Graphnet penalty impact

Contact Info

Product

Resources

About