Applying biclustering technique and gene ontology analysis for gene expression data processing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13440%2F24%3A43898429" target="_blank" >RIV/44555601:13440/24:43898429 - isvavai.cz</a>

Výsledek na webu

<a href="http://chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://ceur-ws.org/Vol-3675/paper2.pdf" target="_blank" >http://chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://ceur-ws.org/Vol-3675/paper2.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Applying biclustering technique and gene ontology analysis for gene expression data processing

Popis výsledku v původním jazyce

This study details the biclustering methods for gene expression data, focusing on the refinement of quality criteria essential for evaluating the generated bicluster structures. An internal biclustering quality criterion is introduced, leveraging mutual information evaluation across both rows and columns within a bicluster. Additionally, the research proposes a novel hybrid biclustering model, which amalgamates the ensemble biclustering algorithm with Bayesian optimization techniques to optimize the algorithm&apos;s parameters effectively. This model is grounded on a target objective function derived from the newly proposed quality criterion. Simulations carried out on gene expression data from patients afflicted with various cancer types demonstrate the efficacy of the model. Specifically, the application of the mutual information-based criterion within the objective function results in the formation of a bicluster structure comprising 18 distinct biclusters. Furthermore, the study expands upon a method that employs gene ontology analysis, facilitating the identification of subsets of significant gene expression data from bicluster analysis results. A comprehensive procedure for identifying significant gene subsets through a combination of bicluster and gene ontology analyses is executed. The evaluation of sample classification results, characterized by these significant gene subsets, underscores the method&apos;s effectiveness. The classification quality criteria exhibit relatively high values, even with a reduced number of genes, indicating the method&apos;s efficiency

Název v anglickém jazyce

Applying biclustering technique and gene ontology analysis for gene expression data processing

Popis výsledku anglicky

This study details the biclustering methods for gene expression data, focusing on the refinement of quality criteria essential for evaluating the generated bicluster structures. An internal biclustering quality criterion is introduced, leveraging mutual information evaluation across both rows and columns within a bicluster. Additionally, the research proposes a novel hybrid biclustering model, which amalgamates the ensemble biclustering algorithm with Bayesian optimization techniques to optimize the algorithm&apos;s parameters effectively. This model is grounded on a target objective function derived from the newly proposed quality criterion. Simulations carried out on gene expression data from patients afflicted with various cancer types demonstrate the efficacy of the model. Specifically, the application of the mutual information-based criterion within the objective function results in the formation of a bicluster structure comprising 18 distinct biclusters. Furthermore, the study expands upon a method that employs gene ontology analysis, facilitating the identification of subsets of significant gene expression data from bicluster analysis results. A comprehensive procedure for identifying significant gene subsets through a combination of bicluster and gene ontology analyses is executed. The evaluation of sample classification results, characterized by these significant gene subsets, underscores the method&apos;s effectiveness. The classification quality criteria exhibit relatively high values, even with a reduced number of genes, indicating the method&apos;s efficiency

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

CEUR Workshop Proceedings

ISBN

—

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

15

Strana od-do

14-28

Název nakladatele

CEUR-WS

Místo vydání

Aachen

Místo konání akce

Khmelnytskyi

Datum konání akce

28. 3. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—