Learning the Regulatory Code of Gene Expression
Data-driven machine learning is the method of choice for predicting molecular phenotypes from nucleotide sequence, modeling gene expression events including protein-DNA binding, chromatin states as well as mRNA and protein levels. Deep neural networks automatically learn informative sequence represe...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-06-01
|
Series: | Frontiers in Molecular Biosciences |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fmolb.2021.673363/full |
id |
doaj-c0e2ccb1487a456a858ac610a874838c |
---|---|
record_format |
Article |
spelling |
doaj-c0e2ccb1487a456a858ac610a874838c2021-06-10T08:54:40ZengFrontiers Media S.A.Frontiers in Molecular Biosciences2296-889X2021-06-01810.3389/fmolb.2021.673363673363Learning the Regulatory Code of Gene ExpressionJan Zrimec0Filip Buric1Mariia Kokina2Mariia Kokina3Victor Garcia4Aleksej Zelezniak5Aleksej Zelezniak6Department of Biology and Biological Engineering, Chalmers University of Technology, Gothenburg, SwedenDepartment of Biology and Biological Engineering, Chalmers University of Technology, Gothenburg, SwedenDepartment of Biology and Biological Engineering, Chalmers University of Technology, Gothenburg, SwedenNovo Nordisk Foundation Center for Biosustainability, Technical University of Denmark, Kongens Lyngby, DenmarkSchool of Life Sciences and Facility Management, Zurich University of Applied Sciences, Wädenswil, SwitzerlandDepartment of Biology and Biological Engineering, Chalmers University of Technology, Gothenburg, SwedenScience for Life Laboratory, Stockholm, SwedenData-driven machine learning is the method of choice for predicting molecular phenotypes from nucleotide sequence, modeling gene expression events including protein-DNA binding, chromatin states as well as mRNA and protein levels. Deep neural networks automatically learn informative sequence representations and interpreting them enables us to improve our understanding of the regulatory code governing gene expression. Here, we review the latest developments that apply shallow or deep learning to quantify molecular phenotypes and decode the cis-regulatory grammar from prokaryotic and eukaryotic sequencing data. Our approach is to build from the ground up, first focusing on the initiating protein-DNA interactions, then specific coding and non-coding regions, and finally on advances that combine multiple parts of the gene and mRNA regulatory structures, achieving unprecedented performance. We thus provide a quantitative view of gene expression regulation from nucleotide sequence, concluding with an information-centric overview of the central dogma of molecular biology.https://www.frontiersin.org/articles/10.3389/fmolb.2021.673363/fullgene expression predictioncis-regulatory grammargene regulatory structuremRNA & protein abundancechromatin accessibilityregulatory genomics |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jan Zrimec Filip Buric Mariia Kokina Mariia Kokina Victor Garcia Aleksej Zelezniak Aleksej Zelezniak |
spellingShingle |
Jan Zrimec Filip Buric Mariia Kokina Mariia Kokina Victor Garcia Aleksej Zelezniak Aleksej Zelezniak Learning the Regulatory Code of Gene Expression Frontiers in Molecular Biosciences gene expression prediction cis-regulatory grammar gene regulatory structure mRNA & protein abundance chromatin accessibility regulatory genomics |
author_facet |
Jan Zrimec Filip Buric Mariia Kokina Mariia Kokina Victor Garcia Aleksej Zelezniak Aleksej Zelezniak |
author_sort |
Jan Zrimec |
title |
Learning the Regulatory Code of Gene Expression |
title_short |
Learning the Regulatory Code of Gene Expression |
title_full |
Learning the Regulatory Code of Gene Expression |
title_fullStr |
Learning the Regulatory Code of Gene Expression |
title_full_unstemmed |
Learning the Regulatory Code of Gene Expression |
title_sort |
learning the regulatory code of gene expression |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Molecular Biosciences |
issn |
2296-889X |
publishDate |
2021-06-01 |
description |
Data-driven machine learning is the method of choice for predicting molecular phenotypes from nucleotide sequence, modeling gene expression events including protein-DNA binding, chromatin states as well as mRNA and protein levels. Deep neural networks automatically learn informative sequence representations and interpreting them enables us to improve our understanding of the regulatory code governing gene expression. Here, we review the latest developments that apply shallow or deep learning to quantify molecular phenotypes and decode the cis-regulatory grammar from prokaryotic and eukaryotic sequencing data. Our approach is to build from the ground up, first focusing on the initiating protein-DNA interactions, then specific coding and non-coding regions, and finally on advances that combine multiple parts of the gene and mRNA regulatory structures, achieving unprecedented performance. We thus provide a quantitative view of gene expression regulation from nucleotide sequence, concluding with an information-centric overview of the central dogma of molecular biology. |
topic |
gene expression prediction cis-regulatory grammar gene regulatory structure mRNA & protein abundance chromatin accessibility regulatory genomics |
url |
https://www.frontiersin.org/articles/10.3389/fmolb.2021.673363/full |
work_keys_str_mv |
AT janzrimec learningtheregulatorycodeofgeneexpression AT filipburic learningtheregulatorycodeofgeneexpression AT mariiakokina learningtheregulatorycodeofgeneexpression AT mariiakokina learningtheregulatorycodeofgeneexpression AT victorgarcia learningtheregulatorycodeofgeneexpression AT aleksejzelezniak learningtheregulatorycodeofgeneexpression AT aleksejzelezniak learningtheregulatorycodeofgeneexpression |
_version_ |
1721385299498500096 |