Towards Formal Interpretation of Linear Models Learnt from Genome-wide Data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F16%3A00243199" target="_blank" >RIV/68407700:21230/16:00243199 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Towards Formal Interpretation of Linear Models Learnt from Genome-wide Data

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 present the discoveries and nuggets we have made by tuning regularization parameters of our method we have recently developed. We extracted nuggets supported by relevant literature record. The main contribution is that these nuggets are relevant to potentially causal mutations, though extracted from solely gene expression, i.e. non-mutational data.

Název v anglickém jazyce

Towards Formal Interpretation of Linear Models Learnt from Genome-wide Data

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 present the discoveries and nuggets we have made by tuning regularization parameters of our method we have recently developed. We extracted nuggets supported by relevant literature record. The main contribution is that these nuggets are relevant to potentially causal mutations, though extracted from solely gene expression, i.e. non-mutational data.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 20th International Scientific Student Conferenece POSTER 2016

ISBN

978-80-01-05950-0

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

1-4

Název nakladatele

Czech Technical University in Prague

Místo vydání

Praha

Místo konání akce

Praha

Datum konání akce

24. 5. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—