Principal components analysis as a tool to identify lesional skin patterns in cutaneous lupus erythematosus

Prasad, Smriti; Raman, Justin; Ogunsanya, Motolani E.; Chong, Benjamin F.

doi:10.1016/j.jaad.2020.01.010

Cited by 2 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PCA was also used to determine which groups of cytokines have the greatest influence across disease activity states helping to describe the influence of complex cytokine interactions in SLE ( Raymond et al, 2019 ). The PCA was also applied as a tool to identify lesioned skin patterns in cutaneous lupus erythematosus, helping to characterize where on the body lesions of cutaneous lupus erythematosus tend to occur in patients ( Prasad et al, 2020 ).…”

Section: Discussionmentioning

confidence: 99%

Cytoarchitectureal changes in hippocampal subregions of the NZB/W F1 mouse model of lupus

Graïc

Finos

Vadori

et al. 2023

Brain, Behavior, & Immunity - Health

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Cytoarchitectureal changes in hippocampal subregions of the NZB/W F1 mouse model of lupus

Graïc

Finos

Vadori

et al. 2023

Brain, Behavior, & Immunity - Health

View full text Add to dashboard Cite

“…Arguably, the most common systematic approach for defining de novo subtypes in a data-driven fashion with no prior information is data clustering and dimensionality reduction. This subtyping approach employs methods ranging from classical clustering and dimensionality reduction methods, such as K-means [31], hierarchical clustering [38, 39], and principal components analysis (PCA) [40–42], to more modern deep-learning based methods, including various types of autoencoders and other generative network models (see [43] for a review). These methods can possibly be used in combination with feature selection or feature weighting based on domain-specific prior knowledge [44, 45].…”

Section: Introductionmentioning

confidence: 99%

Phenotypic subtyping via contrastive learning

Gorla

Sankararaman

Burchard

et al. 2023

Preprint

View full text Add to dashboard Cite

Defining and accounting for subphenotypic structure has the potential to increase statistical power and provide a deeper understanding of the heterogeneity in the molecular basis of complex disease. Existing phenotype subtyping methods primarily rely on clinically observed heterogeneity or metadata clustering. However, they generally tend to capture the dominant sources of variation in the data, which often originate from variation that is not descriptive of the mechanistic heterogeneity of the phenotype of interest; in fact, such dominant sources of variation, such as population structure or technical variation, are, in general, expected to be independent of subphenotypic structure. We instead aim to find a subspace with signal that is unique to a group of samples for which we believe that subphenotypic variation exists (e.g., cases of a disease). To that end, we introduce Phenotype Aware Components Analysis (PACA), a contrastive learning approach leveraging canonical correlation analysis to robustly capture weak sources of subphenotypic variation. In the context of disease, PACA learns a gradient of variation unique to cases in a given dataset, while leveraging control samples for accounting for variation and imbalances of biological and technical confounders between cases and controls. We evaluated PACA using an extensive simulation study, as well as on various subtyping tasks using genotypes, transcriptomics, and DNA methylation data. Our results provide multiple strong evidence that PACA allows us to robustly capture weak unknown variation of interest while being calibrated and well-powered, far superseding the performance of alternative methods. This renders PACA as a state-of-the-art tool for defining de novo subtypes that are more likely to reflect molecular heterogeneity, especially in challenging cases where the phenotypic heterogeneity may be masked by a myriad of strong unrelated effects in the data.

show abstract

Principal components analysis as a tool to identify lesional skin patterns in cutaneous lupus erythematosus

Cited by 2 publications

References 2 publications

Cytoarchitectureal changes in hippocampal subregions of the NZB/W F1 mouse model of lupus

Cytoarchitectureal changes in hippocampal subregions of the NZB/W F1 mouse model of lupus

Phenotypic subtyping via contrastive learning

Contact Info

Product

Resources

About