Network Constrained Forest to Improve Gene Expression Data Classification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00219787" target="_blank" >RIV/68407700:21230/14:00219787 - isvavai.cz</a>

Výsledek na webu

<a href="http://radio.feld.cvut.cz/conf/poster2014/" target="_blank" >http://radio.feld.cvut.cz/conf/poster2014/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Network Constrained Forest to Improve Gene Expression Data Classification

Popis výsledku v původním jazyce

Onset and progression of genetically determined diseases depend on complex process called gene expression. Integrating genomic measurements of multiple character from multiple stages of that process should improve diagnosis and and overall comprehensionof the diseases. We propose a method, based on a concept of random forests, that utilizes traditional messenger RNA features and quite novel microRNA features. The methods integrates the features through domain knowledge in terms of interactions betweenmicroRNAs and their targeted messenger RNA, and interactions between proteins corresponding to the messenger RNA transcripts. Introducing prior knowledge should increase learning bias and consequently improve overall predictive accuracy, stability and comprehensibility of resulting model. We run several robust experiments to validate our method in comparison with state of the art methods. Our results suggest that out method in most of the cases achieves better or equal results. Hencefort

Název v anglickém jazyce

Network Constrained Forest to Improve Gene Expression Data Classification

Popis výsledku anglicky

Onset and progression of genetically determined diseases depend on complex process called gene expression. Integrating genomic measurements of multiple character from multiple stages of that process should improve diagnosis and and overall comprehensionof the diseases. We propose a method, based on a concept of random forests, that utilizes traditional messenger RNA features and quite novel microRNA features. The methods integrates the features through domain knowledge in terms of interactions betweenmicroRNAs and their targeted messenger RNA, and interactions between proteins corresponding to the messenger RNA transcripts. Introducing prior knowledge should increase learning bias and consequently improve overall predictive accuracy, stability and comprehensibility of resulting model. We run several robust experiments to validate our method in comparison with state of the art methods. Our results suggest that out method in most of the cases achieves better or equal results. Hencefort

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2014

Kód důvěrnosti údajů

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

Název statě ve sborníku

POSTER 2014 - 18th International Student Conference on Electrical Engineering

ISBN

978-80-01-05499-4

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

—

Název nakladatele

Czech Technical University

Místo vydání

Prague

Místo konání akce

Praha

Datum konání akce

15. 5. 2014

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—