Flexible Self-Organizing Maps in <b>kohonen</b> 3.0

Wehrens, Ron; Kruisselbrink, Johannes W.

doi:10.18637/jss.v087.i07

Cited by 216 publications

(152 citation statements)

References 22 publications

Supporting

Mentioning

148

Contrasting

Order By: Relevance

“…The three SOMs were created by 10,000 iterations over a hexagonal grid. In the case of gridded data, each grid cell was attributed to a single node of the output layer (unified-distance matrix or U-Matrix), according to its Euclidian distance (for details in the application of SOM algorithm, see Wehrens and Kruisselbrink (2018)). Then, we utilized the agglomerative clustering method to create the second layer and determine the homogeneous regions as suggested by Kaufman and Rousseeuw (1990) and elaborated in Murtagh and Legendre (2014).…”

Section: Methodsmentioning

confidence: 99%

“…The classification framework was developed in R statistical software and the SOM algorithm was developed by Wehrens and Kruisselbrink (2018) in kohonen package. The spatial SOM methodology presented here, was also developed as a stand-alone package, namely somspace, which is freely available and can be downloaded through CRAN server or alternatively at https://github.com/imarkonis/somspace.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Representation of European hydroclimatic patterns with self-organizing maps

Markonis

Strnad

2020

The Holocene

View full text Add to dashboard Cite

Self-organizing maps provide a powerful, non-linear technique of dimensionality reduction that can be used to identify clusters with similar attributes. Here, they were constructed from a 1000-year-long gridded palaeoclimatic dataset, namely the Old World Drought Atlas, to detect regions of homogeneous hydroclimatic variability across the European continent. A classification scheme of 10 regions was found to describe most efficiently the spatial properties of Europe’s hydroclimate. These regions were mainly divided into a northern and a southern subset, linked together with a northwest-to-southeast orientation. Further analysis of the classification scheme with complex networks confirmed the divergence between the northern and southern components of European hydroclimate, also revealing that is not strongly correlated to the Iberian Peninsula. On the contrary, the region covering the British Isles, France and Germany appeared to be linked to both branches, implying links of hydroclimate with atmospheric/oceanic circulation.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Representation of European hydroclimatic patterns with self-organizing maps

Markonis

Strnad

2020

The Holocene

View full text Add to dashboard Cite

show abstract

“…Self-organizing map (SOM) analysis (11) was performed on the list of 571 differentially expressed genes using the R statistical programming language. SOM analysis was performed individually for each cell type with the R package Kohonen (12) at default parameters. According to 16 identified SOM clusters outlier analysis was performed to identify specific gene expression patterns.…”

Section: Methodsmentioning

confidence: 99%

Distinct features of human myeloid cell cytokine response profiles identify neutrophil activation by cytokines as a prognostic feature during tuberculosis and cancer1

Devlin

Zwack

Tang

et al. 2019

Preprint

View full text Add to dashboard Cite

ABSTRACTMyeloid cells are a vital component of innate immunity and comprise of monocytes, macrophages, dendritic cells and granulocytes. How myeloid cell lineage affects activation states in response to cytokines remains poorly understood. The cytokine environment and cellular infiltrate during an inflammatory response may contain prognostic features that could predict disease outcome. Here we analyzed the transcriptional responses of human monocytes, macrophages, dendritic cells and neutrophils in response to stimulation by IFN-γ, IFN-β IFN-λ, IL-4, IL-13 and IL-10 cytokines, to better understand the heterogeneity of activation states in inflammatory conditions. This generated a myeloid cell cytokine specific response matrix that can infer representation of myeloid cells and the cytokine environment they encounter during infection and in tumors. Neutrophils were highly responsive to type 1 and type 2 cytokine stimulation but did not respond to IL-10. We identified transcripts specific to IFN-β stimulation, whereas other IFN signature genes were upregulated by both IFN-γ and IFN-β. When we used our matrix to deconvolute blood profiles from tuberculosis patients, the IFN-β specific neutrophil signature was reduced in TB patients with active disease whereas the shared response to IFN-γ and IFN-β in neutrophils was increased. When applied to glioma patients, transcripts of neutrophils exposed to IL-4 or IL-13 and monocyte responses to IFN-γ or IFN-β emerged as opposing predictors of patient survival. Hence, by dissecting how different myeloid cells respond to cytokine activation, we can delineate biological roles for myeloid cells in different cytokine environments during disease processes, especially during infection and tumor progression.

show abstract

“…(E) In contrast, FSS includes a portion FS1-FS4, but largely consists of general signs of deterioration (e.g. systolic blood pressure, temperature, white blood cell count (WBC)), which have been found to be good indicators of mortality, but non-discriminative between septic and non-septic patients [31]. (F) shows the out-bag-error rates over 1,000 iterations of bootstrapped feature selection.…”

Section: Livermentioning

confidence: 99%

On classifying sepsis heterogeneity in the ICU: insight using machine learning

Ibrahim

Hamoud

et al. 2020

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

Tel: +44 (0) 758 285 9501 Mesh TermsMachine Learning, Sepsis Syndrome Word Count: 2,000 ABSTRACT Current machine learning models aiming to predict sepsis from Electronic Health Records (EHR) do not account for the heterogeneity of the condition, despite its emerging importance in prognosis and treatment. This work demonstrates the added value of stratifying the types of organ dysfunction observed in patients who develop sepsis in the ICU in improving the ability to recognise patients at risk of sepsis from their EHR data. Using an ICU dataset of 13,728 records, we identify clinically significant sepsis subpopulations with distinct organ dysfunction patterns. Classification experiments using Random Forest, Gradient Boost Trees and Support Vector Machines, aiming to distinguish patients who develop sepsis in the ICU from those who do not, show that features selected using sepsis subpopulations as background knowledge yield a superior performance regardless of the classification model used. Our findings can steer machine learning efforts towards more personalised models for complex conditions including sepsis.

show abstract

Flexible Self-Organizing Maps in kohonen 3.0

Cited by 216 publications

References 22 publications

Representation of European hydroclimatic patterns with self-organizing maps

Representation of European hydroclimatic patterns with self-organizing maps

Distinct features of human myeloid cell cytokine response profiles identify neutrophil activation by cytokines as a prognostic feature during tuberculosis and cancer1

On classifying sepsis heterogeneity in the ICU: insight using machine learning

Contact Info

Product

Resources

About