Sparse Treatment-Effect Model for Taxon Identification with High-Dimensional Metagenomic Data

Zhenqiu Liu, Shili Lin

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

To identify disease-associated taxa is an important task in metagenomics. To date, many methods have been proposed for feature selection and prediction. However, those proposed methods are either using univariate (generalized) regression approaches to get the corresponding P-values without considering the interactions among taxa, or using lasso or L0 type sparse modeling approaches to identify taxa with best predictions without providing P-values. To the best of our knowledge, there are no available methods that consider taxon interactions and also generate P-values. In this paper, we propose a treatment-effect model for identifying taxa (STEMIT) and performing statistical inference with high-dimensional metagenomic data. STEMIT will provide a P-value for a taxon through a two-step treatment-effect maximization. It will provide causal inference if the study is a clinical trial. We first identify taxa associated with the treatment-effect variable and the targeting feature with sparse modeling, and then estimate the P-value of the targeting gene with ordinary least square (OLS) regression. We demonstrate that the proposed method is efficient and can identify biologically important taxa with a real metagenomic data set. The software for L0 sparse modeling can be downloaded at https://cran.r-project.org/web/packages/l0ara/.

Original languageEnglish (US)
Title of host publicationMethods in Molecular Biology
PublisherHumana Press Inc.
Pages309-318
Number of pages10
DOIs
StatePublished - Jan 1 2018

Publication series

NameMethods in Molecular Biology
Volume1849
ISSN (Print)1064-3745

Fingerprint

Metagenomics
Gene Targeting
Least-Squares Analysis
Software
Clinical Trials

All Science Journal Classification (ASJC) codes

  • Molecular Biology
  • Genetics

Cite this

Liu, Z., & Lin, S. (2018). Sparse Treatment-Effect Model for Taxon Identification with High-Dimensional Metagenomic Data. In Methods in Molecular Biology (pp. 309-318). (Methods in Molecular Biology; Vol. 1849). Humana Press Inc.. https://doi.org/10.1007/978-1-4939-8728-3_19
Liu, Zhenqiu ; Lin, Shili. / Sparse Treatment-Effect Model for Taxon Identification with High-Dimensional Metagenomic Data. Methods in Molecular Biology. Humana Press Inc., 2018. pp. 309-318 (Methods in Molecular Biology).
@inbook{d44266c311144b76943ed643252358c4,
title = "Sparse Treatment-Effect Model for Taxon Identification with High-Dimensional Metagenomic Data",
abstract = "To identify disease-associated taxa is an important task in metagenomics. To date, many methods have been proposed for feature selection and prediction. However, those proposed methods are either using univariate (generalized) regression approaches to get the corresponding P-values without considering the interactions among taxa, or using lasso or L0 type sparse modeling approaches to identify taxa with best predictions without providing P-values. To the best of our knowledge, there are no available methods that consider taxon interactions and also generate P-values. In this paper, we propose a treatment-effect model for identifying taxa (STEMIT) and performing statistical inference with high-dimensional metagenomic data. STEMIT will provide a P-value for a taxon through a two-step treatment-effect maximization. It will provide causal inference if the study is a clinical trial. We first identify taxa associated with the treatment-effect variable and the targeting feature with sparse modeling, and then estimate the P-value of the targeting gene with ordinary least square (OLS) regression. We demonstrate that the proposed method is efficient and can identify biologically important taxa with a real metagenomic data set. The software for L0 sparse modeling can be downloaded at https://cran.r-project.org/web/packages/l0ara/.",
author = "Zhenqiu Liu and Shili Lin",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-1-4939-8728-3_19",
language = "English (US)",
series = "Methods in Molecular Biology",
publisher = "Humana Press Inc.",
pages = "309--318",
booktitle = "Methods in Molecular Biology",

}

Liu, Z & Lin, S 2018, Sparse Treatment-Effect Model for Taxon Identification with High-Dimensional Metagenomic Data. in Methods in Molecular Biology. Methods in Molecular Biology, vol. 1849, Humana Press Inc., pp. 309-318. https://doi.org/10.1007/978-1-4939-8728-3_19

Sparse Treatment-Effect Model for Taxon Identification with High-Dimensional Metagenomic Data. / Liu, Zhenqiu; Lin, Shili.

Methods in Molecular Biology. Humana Press Inc., 2018. p. 309-318 (Methods in Molecular Biology; Vol. 1849).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Sparse Treatment-Effect Model for Taxon Identification with High-Dimensional Metagenomic Data

AU - Liu, Zhenqiu

AU - Lin, Shili

PY - 2018/1/1

Y1 - 2018/1/1

N2 - To identify disease-associated taxa is an important task in metagenomics. To date, many methods have been proposed for feature selection and prediction. However, those proposed methods are either using univariate (generalized) regression approaches to get the corresponding P-values without considering the interactions among taxa, or using lasso or L0 type sparse modeling approaches to identify taxa with best predictions without providing P-values. To the best of our knowledge, there are no available methods that consider taxon interactions and also generate P-values. In this paper, we propose a treatment-effect model for identifying taxa (STEMIT) and performing statistical inference with high-dimensional metagenomic data. STEMIT will provide a P-value for a taxon through a two-step treatment-effect maximization. It will provide causal inference if the study is a clinical trial. We first identify taxa associated with the treatment-effect variable and the targeting feature with sparse modeling, and then estimate the P-value of the targeting gene with ordinary least square (OLS) regression. We demonstrate that the proposed method is efficient and can identify biologically important taxa with a real metagenomic data set. The software for L0 sparse modeling can be downloaded at https://cran.r-project.org/web/packages/l0ara/.

AB - To identify disease-associated taxa is an important task in metagenomics. To date, many methods have been proposed for feature selection and prediction. However, those proposed methods are either using univariate (generalized) regression approaches to get the corresponding P-values without considering the interactions among taxa, or using lasso or L0 type sparse modeling approaches to identify taxa with best predictions without providing P-values. To the best of our knowledge, there are no available methods that consider taxon interactions and also generate P-values. In this paper, we propose a treatment-effect model for identifying taxa (STEMIT) and performing statistical inference with high-dimensional metagenomic data. STEMIT will provide a P-value for a taxon through a two-step treatment-effect maximization. It will provide causal inference if the study is a clinical trial. We first identify taxa associated with the treatment-effect variable and the targeting feature with sparse modeling, and then estimate the P-value of the targeting gene with ordinary least square (OLS) regression. We demonstrate that the proposed method is efficient and can identify biologically important taxa with a real metagenomic data set. The software for L0 sparse modeling can be downloaded at https://cran.r-project.org/web/packages/l0ara/.

UR - http://www.scopus.com/inward/record.url?scp=85054630198&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054630198&partnerID=8YFLogxK

U2 - 10.1007/978-1-4939-8728-3_19

DO - 10.1007/978-1-4939-8728-3_19

M3 - Chapter

T3 - Methods in Molecular Biology

SP - 309

EP - 318

BT - Methods in Molecular Biology

PB - Humana Press Inc.

ER -

Liu Z, Lin S. Sparse Treatment-Effect Model for Taxon Identification with High-Dimensional Metagenomic Data. In Methods in Molecular Biology. Humana Press Inc. 2018. p. 309-318. (Methods in Molecular Biology). https://doi.org/10.1007/978-1-4939-8728-3_19