A hybrid inductive model for gene expression data processing using spectral clustering

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13440%2F24%3A43898913" target="_blank" >RIV/44555601:13440/24:43898913 - isvavai.cz</a>

Výsledek na webu

<a href="https://ceur-ws.org/Vol-3892/paper2.pdf" target="_blank" >https://ceur-ws.org/Vol-3892/paper2.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

A hybrid inductive model for gene expression data processing using spectral clustering

Popis výsledku v původním jazyce

One of the key directions in modern bioinformatics is the development of systems for diagnosing various diseases usinggene expression data. Clustering gene expression profiles is a critical step in disease diagnosis systems. In this study, wepropose a hybrid inductive model for clustering gene expression profiles using the spectral clustering algorithm. Theimplementation of this model aims to reduce reproducibility errors by serializing the data processing flow and optimizingclustering based on both internal and external quality criteria. The model is presented as a block diagram, and its practicalimplementation has demonstrated the high effectiveness of the proposed approach. The model&apos;s performance wasevaluated using a convolutional neural network. The experimental dataset consisted of gene expression values assigned tothe identified clusters. The simulation results indicate that the highest classification accuracy was achieved with a three-cluster structure, which corresponded to the highest balance between internal and external clustering quality criteria. Thesefindings create opportunities for enhancing existing gene expression clustering models through more precise tuning ofclustering algorithm hyperparameters, guided by the principles of inductive methods for analyzing complex systems

Název v anglickém jazyce

A hybrid inductive model for gene expression data processing using spectral clustering

Popis výsledku anglicky

One of the key directions in modern bioinformatics is the development of systems for diagnosing various diseases usinggene expression data. Clustering gene expression profiles is a critical step in disease diagnosis systems. In this study, wepropose a hybrid inductive model for clustering gene expression profiles using the spectral clustering algorithm. Theimplementation of this model aims to reduce reproducibility errors by serializing the data processing flow and optimizingclustering based on both internal and external quality criteria. The model is presented as a block diagram, and its practicalimplementation has demonstrated the high effectiveness of the proposed approach. The model&apos;s performance wasevaluated using a convolutional neural network. The experimental dataset consisted of gene expression values assigned tothe identified clusters. The simulation results indicate that the highest classification accuracy was achieved with a three-cluster structure, which corresponded to the highest balance between internal and external clustering quality criteria. Thesefindings create opportunities for enhancing existing gene expression clustering models through more precise tuning ofclustering algorithm hyperparameters, guided by the principles of inductive methods for analyzing complex systems

Druh

W - Uspořádání workshopu

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

Místo konání akce

Birmingham

Stát konání akce

GB - Spojené království Velké Británie a Severního Irska

Datum zahájení akce

—

Datum ukončení akce

—

Celkový počet účastníků

85

Počet zahraničních účastníků

64

Typ akce podle státní přísl. účastníků

WRD - Celosvětová akce