Napredna pretraga

Pregled bibliografske jedinice broj: 640239

Investigation of coevolutionary approach in gene regulatory network inference


Komlen, Danko; Jakobović, Domagoj
Investigation of coevolutionary approach in gene regulatory network inference // MIPRO 2013 Int. Conf. Proceedings
Opatija: IEEE, 2013. str. 1253-1259 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Investigation of coevolutionary approach in gene regulatory network inference

Autori
Komlen, Danko ; Jakobović, Domagoj

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
MIPRO 2013 Int. Conf. Proceedings / - Opatija : IEEE, 2013, 1253-1259

ISBN
978-953-233-074-8

Skup
MIPRO 2013

Mjesto i datum
Opatija, Hrvatska, 20-24.05.2013

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Gene regulatory network; evolutionary algorithm

Sažetak
Inference of gene regulatory networks is currently an active field of research in system biology. Evolutionary computation algorithms are lately applied for finding the optimal parameters of models. This paper presents a comparison of four evolutionary algorithms (DE, GA, PSO and the hybrid Hooke-Jeeves GA) used with a linear time-variant gene network model. The paper also investigates the efficiency of cooperative coevolution approach to cope with the increased complexity of networks with large number of genes. Experiments were performed on two artificially generated and one real microarray data set. The results are twofold: the efficiency comparison may serve as a guideline for future research, and the application of coevolution proved to be successful for most algorithms.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekt / tema
036-0362980-1921 - Računalne okoline za sveprisutne raspodijeljene sustave (Siniša Srbljić, )

Ustanove
Fakultet elektrotehnike i računarstva, Zagreb

Autor s matičnim brojem:
Domagoj Jakobović, (223294)