Decomposition Approach for Learning Large Gene Regulatory Network

Leung-yau LO, Man Leung WONG, Kwong Sak LEUNG, Wing Lun Alan LAM, Chi-wai Chung

Research output: Journal PublicationsJournal Article (refereed)

Abstract

Gene Regulatory Network (GRN) represents the complex interaction between Transcription Factors (TFs) and other genes with time delays. They are important in the working of the cell. Learning GRN is an important first step towards understanding the working of the cell and consequently curing diseases related to malfunctioning of the cell. One significant problem in learning GRN is that the available time series expression data is still limited compared to the network size. To alleviate this problem, besides using multiple expression replicates, we propose to decompose large network into small subnetwork without prior knowledge. Our algorithm first infers an initial GRN using CLINDE, then decomposes it into possibly overlapping subnetworks, then infers each subnetwork by either CLINDE or DD-lasso and finally merges the subnetworks. We have tested this algorithm on synthetic data of many networks with 500 and 1000 genes. We have also tested on real data on 41 human TF regulatory networks. Results show that our proposed algorithm does improve the GRN learning performance of using either CLINDE or DD-lasso alone on the large network.
Original languageEnglish
Article number315
JournalJournal of Health & Medical Informatics
Volume9
Issue number3
DOIs
Publication statusPublished - 20 Jun 2018

Fingerprint

Genes
Decomposition
Transcription factors
Curing
Time series
Time delay

Cite this

@article{bdf2994d4da0475c92b5db19ce0774a8,
title = "Decomposition Approach for Learning Large Gene Regulatory Network",
abstract = "Gene Regulatory Network (GRN) represents the complex interaction between Transcription Factors (TFs) and other genes with time delays. They are important in the working of the cell. Learning GRN is an important first step towards understanding the working of the cell and consequently curing diseases related to malfunctioning of the cell. One significant problem in learning GRN is that the available time series expression data is still limited compared to the network size. To alleviate this problem, besides using multiple expression replicates, we propose to decompose large network into small subnetwork without prior knowledge. Our algorithm first infers an initial GRN using CLINDE, then decomposes it into possibly overlapping subnetworks, then infers each subnetwork by either CLINDE or DD-lasso and finally merges the subnetworks. We have tested this algorithm on synthetic data of many networks with 500 and 1000 genes. We have also tested on real data on 41 human TF regulatory networks. Results show that our proposed algorithm does improve the GRN learning performance of using either CLINDE or DD-lasso alone on the large network.",
author = "Leung-yau LO and WONG, {Man Leung} and LEUNG, {Kwong Sak} and LAM, {Wing Lun Alan} and Chi-wai Chung",
year = "2018",
month = "6",
day = "20",
doi = "10.4172/2157-7420.1000315",
language = "English",
volume = "9",
journal = "Journal of Health & Medical Informatics",
issn = "2157-7420",
number = "3",

}

Decomposition Approach for Learning Large Gene Regulatory Network. / LO, Leung-yau; WONG, Man Leung; LEUNG, Kwong Sak; LAM, Wing Lun Alan; Chung, Chi-wai.

In: Journal of Health & Medical Informatics, Vol. 9, No. 3, 315, 20.06.2018.

Research output: Journal PublicationsJournal Article (refereed)

TY - JOUR

T1 - Decomposition Approach for Learning Large Gene Regulatory Network

AU - LO, Leung-yau

AU - WONG, Man Leung

AU - LEUNG, Kwong Sak

AU - LAM, Wing Lun Alan

AU - Chung, Chi-wai

PY - 2018/6/20

Y1 - 2018/6/20

N2 - Gene Regulatory Network (GRN) represents the complex interaction between Transcription Factors (TFs) and other genes with time delays. They are important in the working of the cell. Learning GRN is an important first step towards understanding the working of the cell and consequently curing diseases related to malfunctioning of the cell. One significant problem in learning GRN is that the available time series expression data is still limited compared to the network size. To alleviate this problem, besides using multiple expression replicates, we propose to decompose large network into small subnetwork without prior knowledge. Our algorithm first infers an initial GRN using CLINDE, then decomposes it into possibly overlapping subnetworks, then infers each subnetwork by either CLINDE or DD-lasso and finally merges the subnetworks. We have tested this algorithm on synthetic data of many networks with 500 and 1000 genes. We have also tested on real data on 41 human TF regulatory networks. Results show that our proposed algorithm does improve the GRN learning performance of using either CLINDE or DD-lasso alone on the large network.

AB - Gene Regulatory Network (GRN) represents the complex interaction between Transcription Factors (TFs) and other genes with time delays. They are important in the working of the cell. Learning GRN is an important first step towards understanding the working of the cell and consequently curing diseases related to malfunctioning of the cell. One significant problem in learning GRN is that the available time series expression data is still limited compared to the network size. To alleviate this problem, besides using multiple expression replicates, we propose to decompose large network into small subnetwork without prior knowledge. Our algorithm first infers an initial GRN using CLINDE, then decomposes it into possibly overlapping subnetworks, then infers each subnetwork by either CLINDE or DD-lasso and finally merges the subnetworks. We have tested this algorithm on synthetic data of many networks with 500 and 1000 genes. We have also tested on real data on 41 human TF regulatory networks. Results show that our proposed algorithm does improve the GRN learning performance of using either CLINDE or DD-lasso alone on the large network.

U2 - 10.4172/2157-7420.1000315

DO - 10.4172/2157-7420.1000315

M3 - Journal Article (refereed)

VL - 9

JO - Journal of Health & Medical Informatics

JF - Journal of Health & Medical Informatics

SN - 2157-7420

IS - 3

M1 - 315

ER -