Application of Convolutional Neural Network for Gene Expression Data Classification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13440%2F23%3A43897056" target="_blank" >RIV/44555601:13440/23:43897056 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-16203-9_1" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-16203-9_1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-16203-9_1" target="_blank" >10.1007/978-3-031-16203-9_1</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Application of Convolutional Neural Network for Gene Expression Data Classification

Popis výsledku v původním jazyce

The results of research regarding the development of a gene expression data classification system based on a convolutional neural network are presented. Gene expression data of patients who were studied for lung cancer were used as experimental data. 156 patients were studied, of which 65 were identified as healthy and 91 patients were diagnosed with cancer. Each of the DNA microchips contained 54,675 genes. Data processing was carried out in two stages. In the first stage, 10,000 of the most informative genes in terms of statistical criteria and Shannon entropy were allocated. In the second stage, the classification of objects containing as attributes the expression of the allocated genes was performed by using a convolutional neural network. The obtained diagrams of the data classification accuracy during both the neural network model learning and validation indicate the absence of the network retraining since the character of changing the accuracy and loss values on trained and validated subsets during the network learning procedure implementation is the same within the allowed error. The analysis of the obtained results has shown, that the accuracy of the object?s classification on the test data subset reached 97%. Only one object of 39 was identified incorrectly. This fact indicates the high efficiency of the proposed model

Název v anglickém jazyce

Application of Convolutional Neural Network for Gene Expression Data Classification

Popis výsledku anglicky

The results of research regarding the development of a gene expression data classification system based on a convolutional neural network are presented. Gene expression data of patients who were studied for lung cancer were used as experimental data. 156 patients were studied, of which 65 were identified as healthy and 91 patients were diagnosed with cancer. Each of the DNA microchips contained 54,675 genes. Data processing was carried out in two stages. In the first stage, 10,000 of the most informative genes in terms of statistical criteria and Shannon entropy were allocated. In the second stage, the classification of objects containing as attributes the expression of the allocated genes was performed by using a convolutional neural network. The obtained diagrams of the data classification accuracy during both the neural network model learning and validation indicate the absence of the network retraining since the character of changing the accuracy and loss values on trained and validated subsets during the network learning procedure implementation is the same within the allowed error. The analysis of the obtained results has shown, that the accuracy of the object?s classification on the test data subset reached 97%. Only one object of 39 was identified incorrectly. This fact indicates the high efficiency of the proposed model

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

Lecture Notes on Data Engineering and Communications Technologies

ISBN

978-3-031-16202-2

ISSN

2367-4512

e-ISSN

—

Počet stran výsledku

21

Strana od-do

3-24

Název nakladatele

Springer Nature

Místo vydání

Basel

Místo konání akce

Zalizniy Port

Datum konání akce

23. 5. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—