Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Proceedings of the Forum "Math-for-Industry" 2019Prediction of Gene Expression Level Using Hierarchical Generalized Linear Model

Proceedings of the Forum "Math-for-Industry" 2019: Prediction of Gene Expression Level Using... [Histone modifications are common phenomena in organisms, which can affect gene expression in various ways. With the rapid development of high-throughput sequencing technology, massive data make it possible to explore the relationship between histone modifications and gene expression through machine learning approaches. In this paper, we proposed a master-slave model based on the generalized linear model framework in order to predict gene expression levels dependent on histone modification signals with high precision. First, the gene expression data go through a pretreatment process, where the genes with complete loci information are screened out based on the genome-wide annotation file. Then, according to the loci information of the filtered genes, the histone modification data at the corresponding locations are extracted as explanatory variables. Finally, a master-slave model taking the characteristic of zero inflation of variable data into consideration is implemented, whose effectiveness has been proven by applying it to the human GM12878 cell line data.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Proceedings of the Forum "Math-for-Industry" 2019Prediction of Gene Expression Level Using Hierarchical Generalized Linear Model

Part of the Mathematics for Industry Book Series (volume 36)
Editors: McKibbin, Robert; Wake, Graeme; Saeki, Osamu
Wang, Zeyuan; Gu, Hong; Qin, Pan
Proceedings of the Forum "Math-for-Industry" 2019 — Sep 11, 2022
Download PDF
11 pages

Loading next page...
 
/lp/springer-journals/proceedings-of-the-forum-math-for-industry-2019-prediction-of-gene-C0cuG0uNhH
Publisher
Springer Nature Singapore
Copyright
© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2022
ISBN
978-981-19-1153-8
Pages
131 –142
DOI
10.1007/978-981-19-1154-5_8
Publisher site
See Chapter on Publisher Site

Abstract

[Histone modifications are common phenomena in organisms, which can affect gene expression in various ways. With the rapid development of high-throughput sequencing technology, massive data make it possible to explore the relationship between histone modifications and gene expression through machine learning approaches. In this paper, we proposed a master-slave model based on the generalized linear model framework in order to predict gene expression levels dependent on histone modification signals with high precision. First, the gene expression data go through a pretreatment process, where the genes with complete loci information are screened out based on the genome-wide annotation file. Then, according to the loci information of the filtered genes, the histone modification data at the corresponding locations are extracted as explanatory variables. Finally, a master-slave model taking the characteristic of zero inflation of variable data into consideration is implemented, whose effectiveness has been proven by applying it to the human GM12878 cell line data.]

Published: Sep 11, 2022

Keywords: generalized linear model; master-slave model; histone modification; gene expression

There are no references for this article.