Formation and Analysis of Gene Expression Data Based on the Joint Use of Data Mining and Machine Learning Techniques

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13440%2F23%3A43897656" target="_blank" >RIV/44555601:13440/23:43897656 - isvavai.cz</a>

Výsledek na webu

<a href="https://ceur-ws.org/Vol-3373/" target="_blank" >https://ceur-ws.org/Vol-3373/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Formation and Analysis of Gene Expression Data Based on the Joint Use of Data Mining and Machine Learning Techniques

Popis výsledku v původním jazyce

Creating a system of complex disease diagnosis based on gene expression data using modern data mining and machine learning techniques is one of the topical areas of recent bioinformatics. The main problem in this subject area consists of a large volume of experimental data; each investigated object contains approximately 20000 genes. In this paper, we propose the technique of both formation and analysis of gene expression data based on the joint use of various computational and intelligent methods of complex data processing. As the experimental data, we use the gene expression data of patients who were investigated for various types of cancer diseases. Initially, the data was formed and analyzed using the functions and modules of TCGAbiolinks and Bioconductor packages. Then, the non-informative genes in terms of both the statistical and entropy criteria were removed from the initial database. To identify the level of significance of gene expression profiles, we have applied the general Harrington desirability index, which contains, as the components, transformed statistical and entropies criteria. Finally, we applied the random forest classifier and convolutional neural network with the calculation of various types of classification quality criteria for the binary and multi-classification of the investigated objects in the first and the second cases, respectively. Analyzing the simulation results has shown that the identification accuracy of the examined samples is high in all cases. To our mind, the proposed technique creates the basis for improving complex disease diagnosis systems based on gene expression data.

Název v anglickém jazyce

Formation and Analysis of Gene Expression Data Based on the Joint Use of Data Mining and Machine Learning Techniques

Popis výsledku anglicky

Creating a system of complex disease diagnosis based on gene expression data using modern data mining and machine learning techniques is one of the topical areas of recent bioinformatics. The main problem in this subject area consists of a large volume of experimental data; each investigated object contains approximately 20000 genes. In this paper, we propose the technique of both formation and analysis of gene expression data based on the joint use of various computational and intelligent methods of complex data processing. As the experimental data, we use the gene expression data of patients who were investigated for various types of cancer diseases. Initially, the data was formed and analyzed using the functions and modules of TCGAbiolinks and Bioconductor packages. Then, the non-informative genes in terms of both the statistical and entropy criteria were removed from the initial database. To identify the level of significance of gene expression profiles, we have applied the general Harrington desirability index, which contains, as the components, transformed statistical and entropies criteria. Finally, we applied the random forest classifier and convolutional neural network with the calculation of various types of classification quality criteria for the binary and multi-classification of the investigated objects in the first and the second cases, respectively. Analyzing the simulation results has shown that the identification accuracy of the examined samples is high in all cases. To our mind, the proposed technique creates the basis for improving complex disease diagnosis systems based on gene expression data.

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

2023

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

12

Strana od-do

87-98

Název nakladatele

CEUR-WS

Místo vydání

Germany

Místo konání akce

Khmenytskyi

Datum konání akce

22. 3. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—