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

Result code in 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>

Result on the web

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

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

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

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2023

Confidentiality

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

Article name in the collection

CEUR Workshop Proceedings

ISBN

—

ISSN

1613-0073

e-ISSN

—

Number of pages

12

Pages from-to

87-98

Publisher name

CEUR-WS

Place of publication

Germany

Event location

Khmenytskyi

Event date

Mar 22, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—