Comparative analysis of clustering methods for gene expression time course data

Costa, Ivan G.; Carvalho, Francisco de A. T. de; Souto, Michael Vandesteen Silva

doi:10.1590/s1415-47572004000400025

Cited by 61 publications

(40 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The decision of the best number of clusters to perform the GK algorithm, is based on the best overall VAF. Once the decision of the number of clusters is made, and a dynamic formula is obtained, next step is to test the efficiency of the approach, through the cross-validation, so call k-fold method [6]. The main objective of this method is to verify the model behavior on multiple data groups, to be used for training and testing.…”

Section: Results Of the Fuzzy Identification Methods For The Hydrogen mentioning

confidence: 99%

Black-Box Fuzzy Identification of a Nonlinear Hydrogen Fuel Cell Model

Bertone

Martins

Yamanaka

2018

Tend. Mat. Apl. Comput.

View full text Add to dashboard Cite

ABSTRACT.A fuzzy identification of the system's dynamic is developed with a data generated by a hydrogen fuel cell simulator. The data obtained is single input/single output, without having previous knowledge of the system model, and showing nonlinear behavior. The choice of the fuzzy method for identification is based on those particular data features, and the malleability of the mathematical fuzzy technique. The objective of the fuzzy identification is to reach an analytic formula for a better understanding of the causeeffect relationships of the data, followed by its validation. The dynamic system identification process is performed using fuzzy clustering through the Gustafson and Kessel algorithm, followed by a Takagi and Sugeno fuzzy inference method. The k-fold technique, is the cross validation tool, used to confirm the lack of data over-training. The novelty of this approach covers mathematical and engineering features that makes this study interdisciplinary. For the mathematical contribution, there is a three-dimensional graphic interpretation of the data clustering geometry, obtained through own code computer simulations. Concerning to the engineering context, the novelty is based on the use of the fuzzy approach to the hydrogen fuel cell. Both contributions have no precedent in the literature. The results of the fuzzy identification show high reliability in terms of cross validation, making the fuzzy approach a promising tool for black-box identification. Combining this technique with others will provide powerful instrument for industrial problems.

show abstract

Section: Results Of the Fuzzy Identification Methods For The Hydrogen mentioning

confidence: 99%

Black-Box Fuzzy Identification of a Nonlinear Hydrogen Fuel Cell Model

Bertone

Martins

Yamanaka

2018

Tend. Mat. Apl. Comput.

View full text Add to dashboard Cite

show abstract

“…In the case of the average method, the distance between two clusters is calculated by the average distance between the patterns in one group and the patterns in the other group. Such a method has been extensively used in the literature of gene expression analysis [2], [3], [26], [27], although experimental results have shown that in many cases the complete linkage outperforms it [4].…”

Section: B Clustering Methods and Recovery Measurementioning

confidence: 99%

“…The average linkage and complete linkage methods had cR values as high as k-means for only one dataset, "Nutt-V3". While the main objective of our study is not the comparison of the clustering methods themselves, the shortcoming of hierarchical methods is noticeable in other comparative studies on gene expressions data [26], [27], [4]. However, hierarchical methods are still widely used in clustering gene expression datasets.…”

Section: Final Remarksmentioning

confidence: 99%

Comparative study on normalization procedures for cluster analysis of gene expression datasets

Souto

Araújo

Costa

et al. 2008

2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)

Self Cite

View full text Add to dashboard Cite

Abstract-Normalization before clustering is often needed for proximity indices, such as Euclidian distance, which are sensitive to differences in the magnitude or scales of the attributes. The goal is to equalize the size or magnitude and the variability of these features. This can also be seen as a way to adjust the relative weighting of the attributes. In this context, we present a first large scale data driven comparative study of three normalization procedures applied to cancer gene expression data. The results are presented in terms of the recovering of the true cluster structure as found by five different clustering algorithm.

show abstract

“…A análise de dados de expressão gênica identificada ao longo do tempo -"microarray time series" (MTS) -tem possibilitado o entendimento de diversos processos biológicos (Mukhopadhyay & Chatterjee, 2007), uma vez que o conhecimento de grupos de genes que se expressam de forma similar possibilita inferir a respeito de funções e mecanismos reguladores desses genes (Costa et al, 2004).…”

Section: Introductionunclassified

Aplicação da análise de agrupamento de dados de expressão gênica temporal a dados em painel

Nascimento

Sáfadi

Silva

2011

Pesq. agropec. bras.

View full text Add to dashboard Cite

Resumo -O objetivo deste trabalho foi determinar a melhor alternativa, entre os métodos de agrupamento hierárquico (Ward) e de otimização (Tocher), para a formação de grupos homogêneos de séries de expressão gênica, e realizar previsões quanto à expressão gênica dessas séries, a partir de pequeno número de observações temporais. Os dados utilizados referem-se à expressão de genes que atuam sobre o ciclo celular de Saccharomyces cerevisiae e corresponderam a 114 séries de expressão gênica, cada uma com dez valores de "fold-change" (medida da expressão gênica) ao longo do tempo (0, 15, 30, 45, 60, 75, 90, 105, 120 e 135 min). As estimativas dos parâmetros dos modelos autorregressivos AR(p) foram previamente ajustadas a séries individuais (de cada gene) de dados "microarray time series" e utilizadas, como variáveis, no processo de agrupamento. As previsões da expressão gênica foram feitas dentro de cada grupo formado, a partir dos ajustes no modelo AR(p) para dados em painel. O método de Ward foi o mais apropriado para a formação de grupos de genes com séries homogêneas. Uma vez obtidos esses grupos, é possível ajustar o modelo AR(2) para dados em painel e predizer a expressão gênica em um tempo futuro (135 min), a partir de um pequeno número de observações temporais (os outros nove valores de "fold-change").Termos para indexação: bioinformática, método de Tocher, método de Ward, microarranjo, modelo autorregressivo, série temporal. Application of cluster analysis of temporal gene expression data to panel dataAbstract -The objective of this work was to determine the best alternative for the formation of homogeneous groups of gene expression series among the hierarchical clustering (Ward) and optimization (Tocher) methods, and to perform predictions regarding the gene expression of these series from a small number of temporal observations. The data used refer to the expression of genes that act on cell cycle of Saccharomyces cerevisiae, and corresponded to 114 gene expression series, with ten-fold-change values (expression measure) each, over time (0, 15, 30, 45, 60, 75, 90, 105, 120, and 135 min). The parameter estimates of autoregressive models AR(p) were previously adjusted to individual series (from each gene) of microarray time series data and used as variables in the clustering process. Gene expression predictions were made within each formed group from the adjustments in AR(p) model for panel data. The Ward's method was the more suited for the formation of gene groups with homogeneous series. Once these groups are obtained, it is possible to adjust the model AR(2) for panel-data, and successfully predict gene expression at a future time (135 min) from a small number of temporal observations (the nine other fold-change values).

show abstract

Comparative analysis of clustering methods for gene expression time course data

Cited by 61 publications

References 20 publications

Black-Box Fuzzy Identification of a Nonlinear Hydrogen Fuel Cell Model

Black-Box Fuzzy Identification of a Nonlinear Hydrogen Fuel Cell Model

Comparative study on normalization procedures for cluster analysis of gene expression datasets

Aplicação da análise de agrupamento de dados de expressão gênica temporal a dados em painel

Contact Info

Product

Resources

About