A Granular Self-Organizing Map for Clustering and Gene Selection in Microarray Data

Ray, Swati; Ganivada, Avatharam; Pal, Sankar K.

doi:10.1109/tnnls.2015.2460994

Cited by 29 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cluster analyses were examined with self-organizing maps (SOM) using Euclidean distances and calculated 2 to 6 clusters [80]. It was iterated 100,000 times.…”

Section: Methodsmentioning

confidence: 99%

Impact of suppression of tumorigenicity 14 (ST14)/serine protease 14 (Prss14) expression analysis on the prognosis and management of estrogen receptor negative breast cancer

et al. 2016

View full text Add to dashboard Cite

To elucidate the role of a type II transmembrane serine protease, ST14/Prss14, during breast cancer progression, we utilized publically accessible databases including TCGA, GEO, NCI-60, and CCLE. Survival of breast cancer patients with high ST14/Prss14 expression is significantly poor in estrogen receptor (ER) negative populations regardless of the ratios of ST14/Prss14 to its inhibitors, SPINT1 or SPINT2. In a clustering of 1085 selected EMT signature genes, ST14/Prss14 is located in the same cluster with CDH3, and closer to post-EMT markers, CDH2, VIM, and FN1 than to the pre-EMT marker, CDH1. Coexpression analyses of known ST14/Prss14 substrates and transcription factors revealed context dependent action. In cell lines, paradoxically, ST14/Prss14 expression is higher in the ER positive group and located closer to CDH1 in clustering. This apparent contradiction is not likely due to ST14/Prss14 expression in a cancer microenvironment, nor due to negative regulation by ER. Genes consistently coexpressed with ST14/Prss14 include transcription factors, ELF5, GRHL1, VGLL1, suggesting currently unknown mechanisms for regulation. Here, we report that ST14/Prss14 is an emerging therapeutic target for breast cancer where HER2 is not applicable. In addition we suggest that careful conclusions should be drawn not exclusively from the cell line studies for target development.

show abstract

“…Cluster analyses were examined with self-organizing maps (SOM) using Euclidean distances and calculated 2 to 6 clusters [80]. It was iterated 100,000 times.…”

Section: Methodsmentioning

confidence: 99%

Impact of suppression of tumorigenicity 14 (ST14)/serine protease 14 (Prss14) expression analysis on the prognosis and management of estrogen receptor negative breast cancer

et al. 2016

View full text Add to dashboard Cite

show abstract

“…In our former studies we have shown that even relatively large maps equipped with the TNF allow for achieving learning quality comparable when the Gaussian neighborhood function (GNF). It is worth to say that the GNF is commonly used in the learning algorithms of the SOMs [25,36,37]. The presented investigations that aim at the comparison between various neighborhood functions (NF) are important in situations when a transistor level realization is considered.…”

Section: State-of-the-art Background In the Nm Designmentioning

confidence: 99%

An Energy-Efficient, Parallel Neighborhood and Adaptation Functions for Hardware Implemented Self-Organizing Maps Applied in Smart Grid

Kolasa

2020

Energies

View full text Add to dashboard Cite

Smart Grids (SGs) can be successfully supported by Wireless Sensor Networks (WSNs), especially through these consisting of intelligent sensors, which are able to efficiently process the still growing amount of data. We propose a contribution to the development of such intelligent sensors, which in an advanced version can be equipped with embedded low-power artificial neural networks (ANNs), supporting the analysis and the classification of collected data. This approach allows to reduce the energy consumed by particular sensors during the communication with other nodes of a larger WSN. This in turn, facilitates the maintenance of a net of such sensors, which is a paramount feature in case of their application in SG devices distributed over a large area. In this work, we focus on a novel, energy-efficient neighborhood mechanism (NM) with the neighborhood function (NF). This mechanism belongs to main components of self learning ANNs. We propose a realization of this component as a specialized chip in the CMOS technology and its optimization in terms of the circuit complexity and the consumed energy. The circuit was realized as a prototype chip in the CMOS 130 nm technology, and verified by means of transistor level simulations and measurements.

show abstract

“…Eissa et al 2016;Skowron et al 2012;Stepaniuk 2008;Pal et al 2005) and fuzzy set (e.g. Ray et al 2016;Kundu and Pal 2015;Pal et al 2012;Ganivada et al 2011) approaches.…”

Section: Granular Computingmentioning

confidence: 99%

Recent granular computing frameworks for mining relational data

Hońko

2018

Artif Intell Rev

View full text Add to dashboard Cite

A lot of data currently being collected is stored in databases with a relational structure. The process of knowledge discovery from such data is a more challenging task compared with single table data. Granular computing, which has successfully been applied to mining data storable in single tables, is a promising direction for discovering knowledge from relational data. This paper summarizes some recent developments in the area of application of granular computing to mining relational data. Four granular computing frameworks for processing relational data are introduced and compared. The paper shows how each of the frameworks represents relational data, constructs information granules and build patterns based on the granules. A generic system that can employ any of the frameworks to discover knowledge from relational data is also outlined.

show abstract

A Granular Self-Organizing Map for Clustering and Gene Selection in Microarray Data

Cited by 29 publications

References 34 publications

Impact of suppression of tumorigenicity 14 (ST14)/serine protease 14 (Prss14) expression analysis on the prognosis and management of estrogen receptor negative breast cancer

Impact of suppression of tumorigenicity 14 (ST14)/serine protease 14 (Prss14) expression analysis on the prognosis and management of estrogen receptor negative breast cancer

An Energy-Efficient, Parallel Neighborhood and Adaptation Functions for Hardware Implemented Self-Organizing Maps Applied in Smart Grid

Recent granular computing frameworks for mining relational data

Contact Info

Product

Resources

About