Sparse Omics-network Regularization to Increase Interpretability and Performance of Linear Classification Models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00234068" target="_blank" >RIV/68407700:21230/15:00234068 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Sparse Omics-network Regularization to Increase Interpretability and Performance of Linear Classification Models

Popis výsledku v původním jazyce

Current high-throughput technologies lead to the boost of omics data with thousands of features measured in parallel. The phenotype specific markers are learned from the data to better understand the disease mechanism and to build predictive models. However, the learning is prone to overfitting, caused by a small sample size and large feature space dimension. Consequently, resulting models are inaccurate and difficult to interpret due to the complex nature of omics processes. In this paper, we propose a methodology for learning simple yet biologically meaningful linear classification models. A linear support vector machine is trained; the learning is regularized by prior knowledge. Regularization parameters enable the expert to operatively adjust the interpretation of the models and their conformity with recent domain research while maintaining their accuracy. We performed robust experiments showing empirical validity of our methodology. In the study related to myelodysplastic syndrome we demonstrate the performance and interpretation of disease classification models. These models are consistent with recent progress in myelodysplastic syndrome research.

Název v anglickém jazyce

Sparse Omics-network Regularization to Increase Interpretability and Performance of Linear Classification Models

Popis výsledku anglicky

Current high-throughput technologies lead to the boost of omics data with thousands of features measured in parallel. The phenotype specific markers are learned from the data to better understand the disease mechanism and to build predictive models. However, the learning is prone to overfitting, caused by a small sample size and large feature space dimension. Consequently, resulting models are inaccurate and difficult to interpret due to the complex nature of omics processes. In this paper, we propose a methodology for learning simple yet biologically meaningful linear classification models. A linear support vector machine is trained; the learning is regularized by prior knowledge. Regularization parameters enable the expert to operatively adjust the interpretation of the models and their conformity with recent domain research while maintaining their accuracy. We performed robust experiments showing empirical validity of our methodology. In the study related to myelodysplastic syndrome we demonstrate the performance and interpretation of disease classification models. These models are consistent with recent progress in myelodysplastic syndrome research.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of 2014 IEEE International Conference on Bioinformatics and Biomedicine

ISBN

978-1-4673-6798-1

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

615-620

Název nakladatele

IEEE

Místo vydání

Piscataway (New Jersey)

Místo konání akce

Washington

Datum konání akce

9. 11. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—