Computational Epigenetics in Lung Cancer

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13440%2F19%3A43894516" target="_blank" >RIV/44555601:13440/19:43894516 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1016/B978-0-12-814513-5.00023-4" target="_blank" >http://dx.doi.org/10.1016/B978-0-12-814513-5.00023-4</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/B978-0-12-814513-5.00023-4" target="_blank" >10.1016/B978-0-12-814513-5.00023-4</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Computational Epigenetics in Lung Cancer

Popis výsledku v původním jazyce

This chapter introduces the technology of gene expression profiles preprocessing based on the complex use of bicluster analysis and objective clustering inductive technology with the use of self-organizing SOTA and density DBSCAN clustering algorithms. Implementation of this technology allows us to increase the quality of epigenetics investigation in lung cancer based on the use of gene regulatory network. Inductive methods of complex system analysis were used as the basis to implement the objective clustering inductive technology of gene expression profiles. To estimate the clustering quality for equal power subsets (including the same quantity of pairwise similar objects) the complex multiplicative criterion was calculated as a combination of Calinski-Harabasz and WB index criteria. External clustering quality criteria were calculated as a normalized difference of internal clustering quality criteria for equal power subsets. Final decision concerning the determination of optimal parameters of clustering algorithm operation has been done based on the maximum value of Harrington desirability function that takes into account both the character of the objects and clusters distribution in various clustering and the differences between clustering, which are implemented on equal power data subsets. To estimate the effectiveness of the proposed technology, the data set of lung cancer patients were used. This data set includes the gene expression profiles of 96 patients, 10 of which were healthy, and 86 patients were divided according to the degree of disease severity into three groups (well, moderate, poor). The results of the simulation allow us to propose the hybrid model of step-by-step process of gene expression profiles, whereby grouping is based on the complex use of clustering and biclustering algorithms.

Název v anglickém jazyce

Computational Epigenetics in Lung Cancer

Popis výsledku anglicky

This chapter introduces the technology of gene expression profiles preprocessing based on the complex use of bicluster analysis and objective clustering inductive technology with the use of self-organizing SOTA and density DBSCAN clustering algorithms. Implementation of this technology allows us to increase the quality of epigenetics investigation in lung cancer based on the use of gene regulatory network. Inductive methods of complex system analysis were used as the basis to implement the objective clustering inductive technology of gene expression profiles. To estimate the clustering quality for equal power subsets (including the same quantity of pairwise similar objects) the complex multiplicative criterion was calculated as a combination of Calinski-Harabasz and WB index criteria. External clustering quality criteria were calculated as a normalized difference of internal clustering quality criteria for equal power subsets. Final decision concerning the determination of optimal parameters of clustering algorithm operation has been done based on the maximum value of Harrington desirability function that takes into account both the character of the objects and clusters distribution in various clustering and the differences between clustering, which are implemented on equal power data subsets. To estimate the effectiveness of the proposed technology, the data set of lung cancer patients were used. This data set includes the gene expression profiles of 96 patients, 10 of which were healthy, and 86 patients were divided according to the degree of disease severity into three groups (well, moderate, poor). The results of the simulation allow us to propose the hybrid model of step-by-step process of gene expression profiles, whereby grouping is based on the complex use of clustering and biclustering algorithms.

Druh

C - Kapitola v odborné knize

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

2019

Kód důvěrnosti údajů

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

Název knihy nebo sborníku

Computational Epigenetics and Diseases

ISBN

978-0-12-814513-5

Počet stran výsledku

23

Strana od-do

397-418

Počet stran knihy

430

Název nakladatele

Academic Press

Místo vydání

London

Kód UT WoS kapitoly

—