Integrative Approach to Gene Expression Data Analysis: Combining Biclustering Techniques with Gene Ontology

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13440%2F24%3A43899002" target="_blank" >RIV/44555601:13440/24:43899002 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-70959-3_8" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-70959-3_8</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-70959-3_8" target="_blank" >10.1007/978-3-031-70959-3_8</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Integrative Approach to Gene Expression Data Analysis: Combining Biclustering Techniques with Gene Ontology

Popis výsledku v původním jazyce

This study refined biclustering methods for gene expression analysis, introducing quality criteria based on mutual information for defining bicluster structures. A hybrid biclustering model utilizing ensemble algorithms and Bayesian optimization was developed to optimize these criteria effectively. Tested on cancer gene expression data, the model used objective functions based on mean squared residue (MSR) and mutual information. Results showed the mutual information criterion to be superior, leading to fewer, more informative biclusters, enhancing gene subset identification for diagnostic purposes. Additionally, gene ontology analysis was integrated into the bicluster quality evaluation, facilitating significant gene subset formation. The findings confirmed that biclustering based on mutual information is more effective than the MSR metric for classifying samples with significant gene subsets, demonstrating the model&apos;s utility in identifying relevant genetic markers for disease diagnosis.

Název v anglickém jazyce

Integrative Approach to Gene Expression Data Analysis: Combining Biclustering Techniques with Gene Ontology

Popis výsledku anglicky

This study refined biclustering methods for gene expression analysis, introducing quality criteria based on mutual information for defining bicluster structures. A hybrid biclustering model utilizing ensemble algorithms and Bayesian optimization was developed to optimize these criteria effectively. Tested on cancer gene expression data, the model used objective functions based on mean squared residue (MSR) and mutual information. Results showed the mutual information criterion to be superior, leading to fewer, more informative biclusters, enhancing gene subset identification for diagnostic purposes. Additionally, gene ontology analysis was integrated into the bicluster quality evaluation, facilitating significant gene subset formation. The findings confirmed that biclustering based on mutual information is more effective than the MSR metric for classifying samples with significant gene subsets, demonstrating the model&apos;s utility in identifying relevant genetic markers for disease diagnosis.

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

Proceedings of the 17th Conference Intellectual Systems of Decision-making and Problems of Computational Intelligence

ISBN

978-3-031-70958-6

ISSN

—

e-ISSN

—

Počet stran výsledku

29

Strana od-do

149-177

Název nakladatele

Springer

Místo vydání

Curych

Místo konání akce

Ústí nad Labem

Datum konání akce

19. 6. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—