maTE: discovering expressed interactions between microRNAs and their targets

Malik Yousef*, Loai Abddallah, Jens Allmer

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Motivation

Disease is often manifested via changes in transcript and protein abundance. MicroRNAs (miRNAs) are instrumental in regulating protein abundance and may measurably influence transcript levels. MicroRNAs often target more than one mRNA (for humans, the average is three), and mRNAs are often targeted by more than one miRNA (for the genes considered in this study, the average is also three). Therefore, it is difficult to determine the miRNAs that may cause the observed differential gene expression.

We present a novel approach, maTE, which is based on machine learning, that integrates information about miRNA target genes with gene expression data. maTE depends on the availability of a sufficient amount of patient and control samples. The samples are used to train classifiers to accurately classify the samples on a per miRNA basis. Multiple high scoring miRNAs are used to build a final classifier to improve separation.
Original languageEnglish
Article numberbtz204
Pages (from-to)4020-2028
JournalBioinformatics
Volume35
Issue number20
Early online date21 Mar 2019
DOIs
Publication statusPublished - 15 Oct 2019

Fingerprint

MicroRNA
MicroRNAs
Gene expression
Classifiers
Genes
Proteins
Target
Interaction
Learning systems
Availability
Messenger RNA
Classifier
Gene
Protein
Gene Expression
Differential Expression
Gene Expression Data
Scoring
Machine Learning
Classify

Cite this

Yousef, Malik ; Abddallah, Loai ; Allmer, Jens. / maTE: discovering expressed interactions between microRNAs and their targets. In: Bioinformatics. 2019 ; Vol. 35, No. 20. pp. 4020-2028.
@article{4b4dae56851c43ad811d160792352e38,
title = "maTE: discovering expressed interactions between microRNAs and their targets",
abstract = "MotivationDisease is often manifested via changes in transcript and protein abundance. MicroRNAs (miRNAs) are instrumental in regulating protein abundance and may measurably influence transcript levels. MicroRNAs often target more than one mRNA (for humans, the average is three), and mRNAs are often targeted by more than one miRNA (for the genes considered in this study, the average is also three). Therefore, it is difficult to determine the miRNAs that may cause the observed differential gene expression.We present a novel approach, maTE, which is based on machine learning, that integrates information about miRNA target genes with gene expression data. maTE depends on the availability of a sufficient amount of patient and control samples. The samples are used to train classifiers to accurately classify the samples on a per miRNA basis. Multiple high scoring miRNAs are used to build a final classifier to improve separation.",
author = "Malik Yousef and Loai Abddallah and Jens Allmer",
year = "2019",
month = "10",
day = "15",
doi = "10.1093/bioinformatics/btz204",
language = "English",
volume = "35",
pages = "4020--2028",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "20",

}

maTE: discovering expressed interactions between microRNAs and their targets. / Yousef, Malik; Abddallah, Loai; Allmer, Jens.

In: Bioinformatics, Vol. 35, No. 20, btz204, 15.10.2019, p. 4020-2028.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - maTE: discovering expressed interactions between microRNAs and their targets

AU - Yousef, Malik

AU - Abddallah, Loai

AU - Allmer, Jens

PY - 2019/10/15

Y1 - 2019/10/15

N2 - MotivationDisease is often manifested via changes in transcript and protein abundance. MicroRNAs (miRNAs) are instrumental in regulating protein abundance and may measurably influence transcript levels. MicroRNAs often target more than one mRNA (for humans, the average is three), and mRNAs are often targeted by more than one miRNA (for the genes considered in this study, the average is also three). Therefore, it is difficult to determine the miRNAs that may cause the observed differential gene expression.We present a novel approach, maTE, which is based on machine learning, that integrates information about miRNA target genes with gene expression data. maTE depends on the availability of a sufficient amount of patient and control samples. The samples are used to train classifiers to accurately classify the samples on a per miRNA basis. Multiple high scoring miRNAs are used to build a final classifier to improve separation.

AB - MotivationDisease is often manifested via changes in transcript and protein abundance. MicroRNAs (miRNAs) are instrumental in regulating protein abundance and may measurably influence transcript levels. MicroRNAs often target more than one mRNA (for humans, the average is three), and mRNAs are often targeted by more than one miRNA (for the genes considered in this study, the average is also three). Therefore, it is difficult to determine the miRNAs that may cause the observed differential gene expression.We present a novel approach, maTE, which is based on machine learning, that integrates information about miRNA target genes with gene expression data. maTE depends on the availability of a sufficient amount of patient and control samples. The samples are used to train classifiers to accurately classify the samples on a per miRNA basis. Multiple high scoring miRNAs are used to build a final classifier to improve separation.

U2 - 10.1093/bioinformatics/btz204

DO - 10.1093/bioinformatics/btz204

M3 - Article

VL - 35

SP - 4020

EP - 2028

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 20

M1 - btz204

ER -