Improving clustering with metabolic pathway data
Background: It is a common practice in bioinformatics to validate each group returned by a clustering algorithm through manual analysis, according to a-priori biological knowledge. This procedure helps finding functionally related patterns to propose hypotheses for their behavior and the biological processes involved. Therefore, this knowledge is used only as a second step, after data are just clustered according to their expression patterns. Thus, it could be very useful to be able to improve the clustering of biological data by incorporating prior knowledge into the cluster formation itself, in order to enhance the biological value of the clusters. Results: A novel training algorithm for clustering is presented, which evaluates the biological internal connections of the data points while the clusters are being formed. Within this training algorithm, the calculation of distances among data points and neurons centroids includes a new term based on information from well-known metabolic pathways. The standard self-organizing map (SOM) training versus the biologically-inspired SOM (bSOM) training were tested with two real data sets of transcripts and metabolites from Solanum lycopersicum and Arabidopsis thaliana species. Classical data mining validation measures were used to evaluate the clustering solutions obtained by both algorithms. Moreover, a new measure that takes into account the biological connectivity of the clusters was applied. The results of bSOM show important improvements in the convergence and performance for the proposed clustering method in comparison to standard SOM training, in particular, from the application point of view. Conclusions: Analyses of the clusters obtained with bSOM indicate that including biological information during training can certainly increase the biological value of the clusters found with the proposed method. It is worth to highlight that this fact has effectively improved the results, which can simplify their further analysis.
Main Authors: | , , , , |
---|---|
Format: | info:ar-repo/semantics/artículo biblioteca |
Language: | eng |
Published: |
BMC
2014-04
|
Subjects: | Bioinformática, Datos, Bioinformatics, Data, Agrupamiento, Clustering, |
Online Access: | https://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-15-101 http://hdl.handle.net/20.500.12123/4292 https://doi.org/10.1186/1471-2105-15-101 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
oai:localhost:20.500.12123-4292 |
---|---|
record_format |
koha |
spelling |
oai:localhost:20.500.12123-42922019-01-18T12:51:31Z Improving clustering with metabolic pathway data Milone, Diego Humberto Stegmayer, Georgina Lopez, Mariana Gabriela Kamenetzky, Laura Carrari, Fernando Bioinformática Datos Bioinformatics Data Agrupamiento Clustering Background: It is a common practice in bioinformatics to validate each group returned by a clustering algorithm through manual analysis, according to a-priori biological knowledge. This procedure helps finding functionally related patterns to propose hypotheses for their behavior and the biological processes involved. Therefore, this knowledge is used only as a second step, after data are just clustered according to their expression patterns. Thus, it could be very useful to be able to improve the clustering of biological data by incorporating prior knowledge into the cluster formation itself, in order to enhance the biological value of the clusters. Results: A novel training algorithm for clustering is presented, which evaluates the biological internal connections of the data points while the clusters are being formed. Within this training algorithm, the calculation of distances among data points and neurons centroids includes a new term based on information from well-known metabolic pathways. The standard self-organizing map (SOM) training versus the biologically-inspired SOM (bSOM) training were tested with two real data sets of transcripts and metabolites from Solanum lycopersicum and Arabidopsis thaliana species. Classical data mining validation measures were used to evaluate the clustering solutions obtained by both algorithms. Moreover, a new measure that takes into account the biological connectivity of the clusters was applied. The results of bSOM show important improvements in the convergence and performance for the proposed clustering method in comparison to standard SOM training, in particular, from the application point of view. Conclusions: Analyses of the clusters obtained with bSOM indicate that including biological information during training can certainly increase the biological value of the clusters found with the proposed method. It is worth to highlight that this fact has effectively improved the results, which can simplify their further analysis. Instituto de Biotecnología Fil: Milone, Diego Humberto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina Fil: Stegmayer, Georgina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina Fil: Lopez, Mariana Gabriela. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Biotecnología; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Fil: Kamenetzky, Laura. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Biotecnología; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Fil: Carrari, Fernando Oscar. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Biotecnología; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. 2019-01-18T12:45:32Z 2019-01-18T12:45:32Z 2014-04 info:ar-repo/semantics/artículo info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion https://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-15-101 http://hdl.handle.net/20.500.12123/4292 1471-2105 https://doi.org/10.1186/1471-2105-15-101 eng info:eu-repo/semantics/openAccess application/pdf BMC BMC Bioinformatics 15 : 101 (2014) |
institution |
INTA AR |
collection |
DSpace |
country |
Argentina |
countrycode |
AR |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-inta-ar |
tag |
biblioteca |
region |
America del Sur |
libraryname |
Biblioteca Central del INTA Argentina |
language |
eng |
topic |
Bioinformática Datos Bioinformatics Data Agrupamiento Clustering Bioinformática Datos Bioinformatics Data Agrupamiento Clustering |
spellingShingle |
Bioinformática Datos Bioinformatics Data Agrupamiento Clustering Bioinformática Datos Bioinformatics Data Agrupamiento Clustering Milone, Diego Humberto Stegmayer, Georgina Lopez, Mariana Gabriela Kamenetzky, Laura Carrari, Fernando Improving clustering with metabolic pathway data |
description |
Background: It is a common practice in bioinformatics to validate each group returned by a clustering algorithm through manual analysis, according to a-priori biological knowledge. This procedure helps finding functionally related patterns to propose hypotheses for their behavior and the biological processes involved. Therefore, this knowledge is used only as a second step, after data are just clustered according to their expression patterns. Thus, it could be very useful to be able to improve the clustering of biological data by incorporating prior knowledge into the cluster formation itself, in order to enhance the biological value of the clusters.
Results: A novel training algorithm for clustering is presented, which evaluates the biological internal connections of the data points while the clusters are being formed. Within this training algorithm, the calculation of distances among data points and neurons centroids includes a new term based on information from well-known metabolic pathways. The standard self-organizing map (SOM) training versus the biologically-inspired SOM (bSOM) training were tested with two real data sets of transcripts and metabolites from Solanum lycopersicum and Arabidopsis thaliana species. Classical data mining validation measures were used to evaluate the clustering solutions obtained by both algorithms. Moreover, a new measure that takes into account the biological connectivity of the clusters was applied. The results of bSOM show important improvements in the convergence and performance for the proposed clustering method in comparison to standard SOM training, in particular, from the application point of view.
Conclusions: Analyses of the clusters obtained with bSOM indicate that including biological information during training can certainly increase the biological value of the clusters found with the proposed method. It is worth to highlight that this fact has effectively improved the results, which can simplify their further analysis. |
format |
info:ar-repo/semantics/artículo |
topic_facet |
Bioinformática Datos Bioinformatics Data Agrupamiento Clustering |
author |
Milone, Diego Humberto Stegmayer, Georgina Lopez, Mariana Gabriela Kamenetzky, Laura Carrari, Fernando |
author_facet |
Milone, Diego Humberto Stegmayer, Georgina Lopez, Mariana Gabriela Kamenetzky, Laura Carrari, Fernando |
author_sort |
Milone, Diego Humberto |
title |
Improving clustering with metabolic pathway data |
title_short |
Improving clustering with metabolic pathway data |
title_full |
Improving clustering with metabolic pathway data |
title_fullStr |
Improving clustering with metabolic pathway data |
title_full_unstemmed |
Improving clustering with metabolic pathway data |
title_sort |
improving clustering with metabolic pathway data |
publisher |
BMC |
publishDate |
2014-04 |
url |
https://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-15-101 http://hdl.handle.net/20.500.12123/4292 https://doi.org/10.1186/1471-2105-15-101 |
work_keys_str_mv |
AT milonediegohumberto improvingclusteringwithmetabolicpathwaydata AT stegmayergeorgina improvingclusteringwithmetabolicpathwaydata AT lopezmarianagabriela improvingclusteringwithmetabolicpathwaydata AT kamenetzkylaura improvingclusteringwithmetabolicpathwaydata AT carrarifernando improvingclusteringwithmetabolicpathwaydata |
_version_ |
1756007367123664896 |