Deep learning in omics: a survey and guideline.

Abstract:

:Omics, such as genomics, transcriptome and proteomics, has been affected by the era of big data. A huge amount of high dimensional and complex structured data has made it no longer applicable for conventional machine learning algorithms. Fortunately, deep learning technology can contribute toward resolving these challenges. There is evidence that deep learning can handle omics data well and resolve omics problems. This survey aims to provide an entry-level guideline for researchers, to understand and use deep learning in order to solve omics problems. We first introduce several deep learning models and then discuss several research areas which have combined omics and deep learning in recent years. In addition, we summarize the general steps involved in using deep learning which have not yet been systematically discussed in the existent literature on this topic. Finally, we compare the features and performance of current mainstream open source deep learning frameworks and present the opportunities and challenges involved in deep learning. This survey will be a good starting point and guideline for omics researchers to understand deep learning.

journal_name

Brief Funct Genomics

authors

Zhang Z,Zhao Y,Liao X,Shi W,Li K,Zou Q,Peng S

doi

10.1093/bfgp/ely030

subject

Has Abstract

pub_date

2019-02-14 00:00:00

pages

41-57

issue

1

eissn

2041-2649

issn

2041-2657

pii

5107348

journal_volume

18

pub_type

杂志文章,评审
  • Depositing annotated sequences in GenBank: there needs to be a better way.

    abstract::Submitting sequences to the National Center for Biotechnology Information (NCBI) is an integral part of research and the publication process for many disciplines within the life sciences, and it will only become more important as sequencing technologies continue to improve. Here, I argue that the available infrastruct...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章

    doi:10.1093/bfgp/elaa016

    authors: Smith DR

    更新日期:2020-12-04 00:00:00

  • Unravelling the biological secrets of microchimerism by single-cell analysis.

    abstract::The presence of microchimeric cells is known for >100 years and well documented since decades. Earlier, microchimeric cells were mainly used for cell-based non-invasive prenatal diagnostics during early pregnancy. Microchimeric cells are also present beyond delivery and are associated to various autoimmune diseases, t...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章

    doi:10.1093/bfgp/elx027

    authors: Ståhlberg A,El-Heliebi A,Sedlmayr P,Kroneis T

    更新日期:2018-07-01 00:00:00

  • The Human Cell Atlas: Technical approaches and challenges.

    abstract::The Human Cell Atlas is a large, international consortium that aims to identify and describe every cell type in the human body. The comprehensive cellular maps that arise from this ambitious effort have the potential to transform many aspects of fundamental biology and clinical practice. Here, we discuss the technical...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elx029

    authors: Hon CC,Shin JW,Carninci P,Stubbington MJT

    更新日期:2018-07-01 00:00:00

  • Conservation and diversification of polycomb repressive complex 2 (PRC2) proteins in the green lineage.

    abstract::The polycomb group (PcG) proteins are key epigenetic regulators of gene expression in animals and plants. They act in multiprotein complexes, of which the best characterized is the polycomb repressive complex 2 (PRC2), which catalyses the trimethylation of histone H3 at lysine 27 (H3K27me3) at chromatin targets. In Ar...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章

    doi:10.1093/bfgp/elw007

    authors: Huang Y,Chen DH,Liu BY,Shen WH,Ruan Y

    更新日期:2017-03-01 00:00:00

  • Significance of whole-genome duplications on the emergence of evolutionary novelties.

    abstract::Acquisition of evolutionary novelties is a fundamental process for adapting to the external environment and invading new niches and results in the diversification of life, which we can see in the world today. How such novel phenotypic traits are acquired in the course of evolution and are built up in developing embryo...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/ely007

    authors: Moriyama Y,Koshiba-Takeuchi K

    更新日期:2018-09-27 00:00:00

  • Chromatin structure of pluripotent stem cells and induced pluripotent stem cells.

    abstract::Pluripotent embryonic stem (ES) cells are specialized cells with a dynamic chromatin structure, which is intimately connected with their pluripotency and physiology. In recent years somatic cells have been reprogrammed to a pluripotent state through over-expression of a defined set of transcription factors. These cell...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elq038

    authors: Delgado-Olguín P,Recillas-Targa F

    更新日期:2011-01-01 00:00:00

  • Evolution of animal Piwi-interacting RNAs and prokaryotic CRISPRs.

    abstract::Piwi-interacting RNAs (piRNAs) and CRISPR RNAs (crRNAs) are two recently discovered classes of small noncoding RNA that are found in animals and prokaryotes, respectively. Both of these novel RNA species function as components of adaptive immune systems that protect their hosts from foreign nucleic acids-piRNAs repres...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/els016

    authors: Kumar MS,Chen KC

    更新日期:2012-07-01 00:00:00

  • Three-dimensional chromosome organization in flowering plants.

    abstract::Research on plant three-dimensional (3D) genome architecture made rapid progress over the past 5 years. Numerous Hi-C interaction data sets were generated in a wide range of plant species, allowing for a comprehensive overview on 3D chromosome folding principles in the plant kingdom. Plants lack important genes report...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章

    doi:10.1093/bfgp/elz024

    authors: Grob S

    更新日期:2020-03-23 00:00:00

  • Evolutionary genetics of insect innate immunity.

    abstract::Patterns of evolution in immune defense genes help to understand the evolutionary dynamics between hosts and pathogens. Multiple insect genomes have been sequenced, with many of them having annotated immune genes, which paves the way for a comparative genomic analysis of insect immunity. In this review, I summarize th...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elv002

    authors: Viljakainen L

    更新日期:2015-11-01 00:00:00

  • Studying protein-protein interaction networks: a systems view on diseases.

    abstract::In order to better understand several cellular processes, it is helpful to study how various components make up the system. This systems perspective is supported by several modelling tools including network analysis. Networks of protein-protein interactions (PPI networks) offer a way to depict, visualize and quantify ...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/els035

    authors: Jordán F,Nguyen TP,Liu WC

    更新日期:2012-11-01 00:00:00

  • The structural variability of the influenza A hemagglutinin receptor-binding site.

    abstract::Hemagglutinin (HA) is a transmembrane protein of the influenza A virus and a key component in its life cycle. The protein allows the virus to enter a host cell by recognizing specific glycans attached to transmembrane proteins of the host, which leads to viral endocytosis. In recent years, significant progress has bee...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elx042

    authors: Lazniewski M,Dawson WK,Szczepinska T,Plewczynski D

    更新日期:2018-11-26 00:00:00

  • Plant carotenoid cleavage oxygenases: structure-function relationships and role in development and metabolism.

    abstract::A plant communicates within itself and with the outside world by deploying an array of agents that include several attractants by virtue of their color and smell. In this category, the contribution of 'carotenoids and apocarotenoids' is very significant. Apocarotenoids, the carotenoid-derived compounds, show wide repr...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elz037

    authors: Dhar MK,Mishra S,Bhat A,Chib S,Kaul S

    更新日期:2020-01-22 00:00:00

  • Cancers with wrong HATs: the impact of acetylation.

    abstract::Lysine N-ε-acetylation is a post-translational modification that regulates the function of histone and non-histone proteins. In several malignancies, histone acetyltransferase (HAT) activities are disturbed as a consequence of various genetic or epigenetic alterations. In particular, HATs can function as tumor suppres...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/els065

    authors: Di Cerbo V,Schneider R

    更新日期:2013-05-01 00:00:00

  • Transcription attenuation in bacteria: theme and variations.

    abstract::Premature termination of transcription, or attenuation, is an efficient RNA-based regulatory strategy that is commonly used in bacterial organisms. Attenuators are generally located in the 50 untranslated regions of genes or operons and combine a Rho-independent terminator, controlling transcription, with an RNA eleme...

    journal_title:Briefings in functional genomics

    pub_type: 更正并重新发布的文章,杂志文章,评审

    doi:10.1093/bfgp/elq008

    authors: Naville M,Gautheret D

    更新日期:2010-03-01 00:00:00

  • Proteomics in epigenetics: new perspectives for cancer research.

    abstract::The involvement of epigenetic processes in the origin and progression of cancer is now widely appreciated. Consequently, targeting the enzymatic machinery that controls the epigenetic regulation of the genome has emerged as an attractive new strategy for therapeutic intervention. The development of epigenetic drugs re...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elt002

    authors: Bartke T,Borgel J,DiMaggio PA

    更新日期:2013-05-01 00:00:00

  • Germ line genome editing in clinics: the approaches, objectives and global society.

    abstract::Genome editing allows for the versatile genetic modification of somatic cells, germ cells and embryos. In particular, CRISPR/Cas9 is worldwide used in biomedical research. Although the first report on Cas9-mediated gene modification in human embryos focused on the prevention of a genetic disease in offspring, it raise...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elv053

    authors: Ishii T

    更新日期:2017-01-01 00:00:00

  • RNA regulatory networks in animals and plants: a long noncoding RNA perspective.

    abstract::A recent highlight of genomics research has been the discovery of many families of transcripts which have function but do not code for proteins. An important group is long noncoding RNAs (lncRNAs), which are typically longer than 200 nt, and whose members originate from thousands of loci across genomes. We review prog...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elu017

    authors: Bai Y,Dai X,Harrison AP,Chen M

    更新日期:2015-03-01 00:00:00

  • Gene-specific metrics to facilitate identification of disease genes for molecular diagnosis in patient genomes: a systematic review.

    abstract::The evolution of next-generation sequencing technologies has facilitated the detection of causal genetic variants in diseases previously undiagnosed at a molecular level. However, in genome sequencing studies, the identification of disease genes among a candidate gene list is often difficult because of the large numbe...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章

    doi:10.1093/bfgp/ely033

    authors: Alyousfi D,Baralle D,Collins A

    更新日期:2019-02-14 00:00:00

  • Barley genetic variation: implications for crop improvement.

    abstract::Genetic variation is crucial for successful barley improvement. Genomic technologies are improving dramatically and are providing access to the genetic diversity within this important crop species. Diverse collections of barley germplasm are being assembled and mined via genome-wide association studies and the identif...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章

    doi:10.1093/bfgp/elu006

    authors: Muñoz-Amatriaín M,Cuesta-Marcos A,Hayes PM,Muehlbauer GJ

    更新日期:2014-07-01 00:00:00

  • Measuring differential gene expression with RNA-seq: challenges and strategies for data analysis.

    abstract::RNA-seq is a methodology for RNA profiling based on next-generation sequencing that enables to measure and compare gene expression patterns at unprecedented resolution. Although the appealing features of this technique have promoted its application to a wide panel of transcriptomics studies, the fast-evolving nature o...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elu035

    authors: Finotello F,Di Camillo B

    更新日期:2015-03-01 00:00:00

  • Systematic review of next-generation sequencing simulators: computational tools, features and perspectives.

    abstract::High-throughput next-generation sequencing (NGS) technologies have rapidly generated a large volume of genomic data. To aid the development and evaluation of new statistical models and computational methods, NGS-based simulators have been proposed to construct better experimental workflows. However, the comparative pe...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elw012

    authors: Zhao M,Liu D,Qu H

    更新日期:2017-05-01 00:00:00

  • Noncoding RNAs: modulators and modulatable players during infection-induced stress response.

    abstract::The human genome has an almost equal distribution of unique and transposable genetic elements. Although at the transcriptome level, a relatively higher contribution from transposable elements derived RNA has been reported. This is further highlighted with evidence from pervasive transcription. Of the total RNA, noncod...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章

    doi:10.1093/bfgp/elaa026

    authors: Chattopadhyay P,Srinivasa Vasudevan J,Pandey R

    更新日期:2021-01-25 00:00:00

  • Catching RNAs on chromatin using hybridization capture methods.

    abstract::The growing appreciation of the importance of long noncoding RNAs (lncRNAs), together with the awareness that some of these RNAs are associated with chromatin, has inspired the development of methods to detect their sites of interaction on a genome-wide scale at high resolution. Hybridization capture methods combine a...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elx038

    authors: Machyna M,Simon MD

    更新日期:2018-03-01 00:00:00

  • Long noncoding RNAs in regulation of human breast cancer.

    abstract::Less than 2% of the human genome DNA is composed of protein-coding genes, although the majority of the human genome is transcribed, indicating the transcripts mostly are noncoding RNAs. Those noncoding RNAs with length between 200 nt and 200 kb are categorized as long noncoding RNA (lncRNA). Around 30 000 lncRNAs have...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elv049

    authors: Wang G,Liu C,Deng S,Zhao Q,Li T,Qiao S,Shen L,Zhang Y,Lü J,Meng L,Liang C,Yu Z

    更新日期:2016-05-01 00:00:00

  • Gene set enrichment; a problem of pathways.

    abstract::Gene Set Enrichment (GSE) is a computational technique which determines whether a priori defined set of genes show statistically significant differential expression between two phenotypes. Currently, the gene sets used for GSE are derived from annotation or pathway databases, which often contain computationally based ...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章

    doi:10.1093/bfgp/elq021

    authors: Davies MN,Meaburn EL,Schalkwyk LC

    更新日期:2010-12-01 00:00:00

  • Using population isolates in genetic association studies.

    abstract::The use of genetically isolated populations can empower next-generation association studies. In this review, we discuss the advantages of this approach and review study design and analytical considerations of genetic association studies focusing on isolates. We cite successful examples of using population isolates in ...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elu022

    authors: Hatzikotoulas K,Gilly A,Zeggini E

    更新日期:2014-09-01 00:00:00

  • Spec-seq: determining protein-DNA-binding specificity by sequencing.

    abstract::The specificity of protein-DNA interactions can be determined directly by sequencing the bound and unbound fractions in a standard binding reaction. The procedure is easy and inexpensive, and the accuracy can be high for thousands of sequences assayed in parallel. From the measurements, simple models of specificity, s...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elu043

    authors: Stormo GD,Zuo Z,Chang YK

    更新日期:2015-01-01 00:00:00

  • Epigenetic memory in the context of nuclear reprogramming and cancer.

    abstract::Epigenetic memory represents a natural mechanism whereby the identity of a cell is maintained through successive cell cycles, allowing the specification and maintenance of differentiation during development and in adult cells. Cancer is a loss or reversal of the stable differentiated state of adult cells and may be me...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elt011

    authors: Halley-Stott RP,Gurdon JB

    更新日期:2013-05-01 00:00:00

  • Heart genetics in a small package, exploiting the condensed genome of Ciona intestinalis.

    abstract::Defects in the initial establishment of cardiogenic cell fate are likely to contribute to pervasive human congenital cardiac abnormalities. However, the molecular underpinnings of nascent cardiac fate induction have proven difficult to decipher. In this review we explore the participation of extracellular, cellular an...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elt034

    authors: Cota CD,Segade F,Davidson B

    更新日期:2014-01-01 00:00:00

  • Next-generation sequencing for understanding and accelerating crop domestication.

    abstract::Next generation Sequencing (NGS) provides a powerful tool for discovery of domestication genes in crop plants and their wild relatives. The accelerated domestication of new plant species as crops may be facilitated by this knowledge. Re-sequencing of domesticated genotypes can identify regions of low diversity associa...

    journal_title:Briefings in functional genomics

    pub_type: 杂志文章,评审

    doi:10.1093/bfgp/elr032

    authors: Henry RJ

    更新日期:2012-01-01 00:00:00