l1-Penalized censored Gaussian graphical model

Antonino Abbruzzo, Luigi Augugliaro, Veronica Vinciotti

Risultato della ricerca: Article

Abstract

Graphical lasso is one of the most used estimators for inferring genetic networks. Despite its diffusion, there are several fields in applied research where the limits of detection of modern measurement technologies make the use of this estimator theoretically unfounded, even when the assumption of a multivariate Gaussian distribution is satisfied. Typical examples are data generated by polymerase chain reactions and flow cytometer. The combination of censoring and high-dimensionality make inference of the underlying genetic networks from these data very challenging. In this article, we propose an $ell_1$-penalized Gaussian graphical model for censored data and derive two EM-like algorithms for inference. We evaluate the computational efficiency of the proposed algorithms by an extensive simulation study and show that, when censored data are available, our proposal is superior to existing competitors both in terms of network recovery and parameter estimation. We apply the proposed method to gene expression data generated by microfluidic Reverse Transcription quantitative Polymerase Chain Reaction technology in order to make inference on the regulatory mechanisms of blood development. A software implementation of our method is available on github (https://github.com/LuigiAugugliaro/cglasso).
Lingua originaleEnglish
Numero di pagine16
RivistaBiostatistics
Volumekxy043
Stato di pubblicazionePublished - 2018

Fingerprint

Gaussian Model
Graphical Models
Genetic Network
Polymerase Chain Reaction
Censored Data
Estimator
Lasso
Microfluidics
Multivariate Distribution
Censoring
Gene Expression Data
Computational Efficiency
Transcription
Dimensionality
Blood
Gaussian distribution
Parameter Estimation
Reverse
Recovery
Simulation Study

Cita questo

l1-Penalized censored Gaussian graphical model. / Abbruzzo, Antonino; Augugliaro, Luigi; Vinciotti, Veronica.

In: Biostatistics, Vol. kxy043, 2018.

Risultato della ricerca: Article

@article{f4805605c0034464a7b9160078a2b9bf,
title = "l1-Penalized censored Gaussian graphical model",
abstract = "Graphical lasso is one of the most used estimators for inferring genetic networks. Despite its diffusion, there are several fields in applied research where the limits of detection of modern measurement technologies make the use of this estimator theoretically unfounded, even when the assumption of a multivariate Gaussian distribution is satisfied. Typical examples are data generated by polymerase chain reactions and flow cytometer. The combination of censoring and high-dimensionality make inference of the underlying genetic networks from these data very challenging. In this article, we propose an $ell_1$-penalized Gaussian graphical model for censored data and derive two EM-like algorithms for inference. We evaluate the computational efficiency of the proposed algorithms by an extensive simulation study and show that, when censored data are available, our proposal is superior to existing competitors both in terms of network recovery and parameter estimation. We apply the proposed method to gene expression data generated by microfluidic Reverse Transcription quantitative Polymerase Chain Reaction technology in order to make inference on the regulatory mechanisms of blood development. A software implementation of our method is available on github (https://github.com/LuigiAugugliaro/cglasso).",
author = "Antonino Abbruzzo and Luigi Augugliaro and Veronica Vinciotti",
year = "2018",
language = "English",
volume = "kxy043",
journal = "Biostatistics",
issn = "1465-4644",
publisher = "Oxford University Press",

}

TY - JOUR

T1 - l1-Penalized censored Gaussian graphical model

AU - Abbruzzo, Antonino

AU - Augugliaro, Luigi

AU - Vinciotti, Veronica

PY - 2018

Y1 - 2018

N2 - Graphical lasso is one of the most used estimators for inferring genetic networks. Despite its diffusion, there are several fields in applied research where the limits of detection of modern measurement technologies make the use of this estimator theoretically unfounded, even when the assumption of a multivariate Gaussian distribution is satisfied. Typical examples are data generated by polymerase chain reactions and flow cytometer. The combination of censoring and high-dimensionality make inference of the underlying genetic networks from these data very challenging. In this article, we propose an $ell_1$-penalized Gaussian graphical model for censored data and derive two EM-like algorithms for inference. We evaluate the computational efficiency of the proposed algorithms by an extensive simulation study and show that, when censored data are available, our proposal is superior to existing competitors both in terms of network recovery and parameter estimation. We apply the proposed method to gene expression data generated by microfluidic Reverse Transcription quantitative Polymerase Chain Reaction technology in order to make inference on the regulatory mechanisms of blood development. A software implementation of our method is available on github (https://github.com/LuigiAugugliaro/cglasso).

AB - Graphical lasso is one of the most used estimators for inferring genetic networks. Despite its diffusion, there are several fields in applied research where the limits of detection of modern measurement technologies make the use of this estimator theoretically unfounded, even when the assumption of a multivariate Gaussian distribution is satisfied. Typical examples are data generated by polymerase chain reactions and flow cytometer. The combination of censoring and high-dimensionality make inference of the underlying genetic networks from these data very challenging. In this article, we propose an $ell_1$-penalized Gaussian graphical model for censored data and derive two EM-like algorithms for inference. We evaluate the computational efficiency of the proposed algorithms by an extensive simulation study and show that, when censored data are available, our proposal is superior to existing competitors both in terms of network recovery and parameter estimation. We apply the proposed method to gene expression data generated by microfluidic Reverse Transcription quantitative Polymerase Chain Reaction technology in order to make inference on the regulatory mechanisms of blood development. A software implementation of our method is available on github (https://github.com/LuigiAugugliaro/cglasso).

UR - http://hdl.handle.net/10447/366807

M3 - Article

VL - kxy043

JO - Biostatistics

JF - Biostatistics

SN - 1465-4644

ER -