scIGANs: single-cell RNA-seq imputation using generative adversarial networks.

Abstract:

:Single-cell RNA-sequencing (scRNA-seq) enables the characterization of transcriptomic profiles at the single-cell resolution with increasingly high throughput. However, it suffers from many sources of technical noises, including insufficient mRNA molecules that lead to excess false zero values, termed dropouts. Computational approaches have been proposed to recover the biologically meaningful expression by borrowing information from similar cells in the observed dataset. However, these methods suffer from oversmoothing and removal of natural cell-to-cell stochasticity in gene expression. Here, we propose the generative adversarial networks (GANs) for scRNA-seq imputation (scIGANs), which uses generated cells rather than observed cells to avoid these limitations and balances the performance between major and rare cell populations. Evaluations based on a variety of simulated and real scRNA-seq datasets show that scIGANs is effective for dropout imputation and enhances various downstream analysis. ScIGANs is robust to small datasets that have very few genes with low expression and/or cell-to-cell variance. ScIGANs works equally well on datasets from different scRNA-seq protocols and is scalable to datasets with over 100 000 cells. We demonstrated in many ways with compelling evidence that scIGANs is not only an application of GANs in omics data but also represents a competing imputation method for the scRNA-seq data.

journal_name

Nucleic Acids Res

journal_title

Nucleic acids research

authors

Xu Y,Zhang Z,You L,Liu J,Fan Z,Zhou X

doi

10.1093/nar/gkaa506

subject

Has Abstract

pub_date

2020-09-04 00:00:00

pages

e85

issue

15

eissn

0305-1048

issn

1362-4962

pii

5862684

journal_volume

48

pub_type

杂志文章
  • Identification of cis-acting elements in the SUC2 promoter of Saccharomyces cerevisiae required for activation of transcription.

    abstract::We analyzed the effects of site-directed mutations in the SUC2 promoter of Saccharomyces cerevisiae. Analyses were performed in wild-type as well as mig1 and tup1 mutant strains after the promoter mutants were reintroduced into the native SUC2 locus on the left arm of chromosome IX. Mutation of the two GC boxes reveal...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/26.4.1002

    authors: Bu Y,Schmidt MC

    更新日期:1998-02-15 00:00:00

  • INTERSPIA: a web application for exploring the dynamics of protein-protein interactions among multiple species.

    abstract::Proteins perform biological functions through cascading interactions with each other by forming protein complexes. As a result, interactions among proteins, called protein-protein interactions (PPIs) are not completely free from selection constraint during evolution. Therefore, the identification and analysis of PPI c...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gky378

    authors: Kwon D,Lee D,Kim J,Lee J,Sim M,Kim J

    更新日期:2018-07-02 00:00:00

  • ConSurf 2010: calculating evolutionary conservation in sequence and structure of proteins and nucleic acids.

    abstract::It is informative to detect highly conserved positions in proteins and nucleic acid sequence/structure since they are often indicative of structural and/or functional importance. ConSurf (http://consurf.tau.ac.il) and ConSeq (http://conseq.tau.ac.il) are two well-established web servers for calculating the evolutionar...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkq399

    authors: Ashkenazy H,Erez E,Martz E,Pupko T,Ben-Tal N

    更新日期:2010-07-01 00:00:00

  • Overexpression of eIF5 or its protein mimic 5MP perturbs eIF2 function and induces ATF4 translation through delayed re-initiation.

    abstract::ATF4 is a pro-oncogenic transcription factor whose translation is activated by eIF2 phosphorylation through delayed re-initiation involving two uORFs in the mRNA leader. However, in yeast, the effect of eIF2 phosphorylation can be mimicked by eIF5 overexpression, which turns eIF5 into translational inhibitor, thereby ...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkw559

    authors: Kozel C,Thompson B,Hustak S,Moore C,Nakashima A,Singh CR,Reid M,Cox C,Papadopoulos E,Luna RE,Anderson A,Tagami H,Hiraishi H,Slone EA,Yoshino KI,Asano M,Gillaspie S,Nietfeld J,Perchellet JP,Rothenburg S,Masai H,W

    更新日期:2016-10-14 00:00:00

  • Site-directed integration of the cre gene mediated by Cre recombinase using a combination of mutant lox sites.

    abstract::The Cre-lox system is an important tool for genetic manipulation. To promote integrative reactions, two strategies using mutant lox sites have been developed. One is the left element/right element (LE/RE)-mutant strategy and the other is the cassette exchange strategy using heterospecific lox sites such as lox511 or l...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gnf102

    authors: Araki K,Araki M,Yamamura K

    更新日期:2002-10-01 00:00:00

  • DNA catenation maintains structure of human metaphase chromosomes.

    abstract::Mitotic chromosome structure is pivotal to cell division but difficult to observe in fine detail using conventional methods. DNA catenation has been implicated in both sister chromatid cohesion and chromosome condensation, but has never been observed directly. We have used a lab-on-a-chip microfluidic device and fluor...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gks931

    authors: Bauer DL,Marie R,Rasmussen KH,Kristensen A,Mir KU

    更新日期:2012-12-01 00:00:00

  • Targeting alternative splicing by RNAi: from the differential impact on splice variants to triggering artificial pre-mRNA splicing.

    abstract::Alternative splicing generates multiple transcript and protein isoforms from a single gene and controls transcript intracellular localization and stability by coupling to mRNA export and nonsense-mediated mRNA decay (NMD). RNA interference (RNAi) is a potent mechanism to modulate gene expression. However, its interact...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkaa1260

    authors: Fuchs A,Riegler S,Ayatollahi Z,Cavallari N,Giono LE,Nimeth BA,Mutanwad KV,Schweighofer A,Lucyshyn D,Barta A,Petrillo E,Kalyna M

    更新日期:2021-01-25 00:00:00

  • Structural basis for m7G-cap hypermethylation of small nuclear, small nucleolar and telomerase RNA by the dimethyltransferase TGS1.

    abstract::The 5'-cap of spliceosomal small nuclear RNAs, some small nucleolar RNAs and of telomerase RNA was found to be hypermethylated in vivo. The Trimethylguanosine Synthase 1 (TGS1) mediates this conversion of the 7-methylguanosine-cap to the 2,2,7-trimethylguanosine (m(3)G)-cap during maturation of the RNPs. For mammalian...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkp249

    authors: Monecke T,Dickmanns A,Ficner R

    更新日期:2009-07-01 00:00:00

  • Golgi-endosome transport mediated by M6PR facilitates release of antisense oligonucleotides from endosomes.

    abstract::Release of phosphorothioate antisense oligonucleotides (PS-ASOs) from late endosomes (LEs) is a rate-limiting step and a poorly defined process for productive intracellular ASO drug delivery. Here, we examined the role of Golgi-endosome transport, specifically M6PR shuttling mediated by GCC2, in PS-ASO trafficking and...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkz1171

    authors: Liang XH,Sun H,Hsu CW,Nichols JG,Vickers TA,De Hoyos CL,Crooke ST

    更新日期:2020-02-20 00:00:00

  • The Frog Prince: a reconstructed transposon from Rana pipiens with high transpositional activity in vertebrate cells.

    abstract::Members of the Tc1/mariner superfamily of transposable elements isolated from vertebrates are transpositionally inactive due to the accumulation of mutations in their transposase genes. A novel open reading frame-trapping method was used to isolate uninterrupted transposase coding regions from the genome of the frog s...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkg910

    authors: Miskey C,Izsvák Z,Plasterk RH,Ivics Z

    更新日期:2003-12-01 00:00:00

  • PhycoCosm, a comparative algal genomics resource.

    abstract::Algae are a diverse, polyphyletic group of photosynthetic eukaryotes spanning nearly all eukaryotic lineages of life and collectively responsible for ∼50% of photosynthesis on Earth. Sequenced algal genomes, critical to understanding their complex biology, are growing in number and require efficient tools for analysis...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkaa898

    authors: Grigoriev IV,Hayes RD,Calhoun S,Kamel B,Wang A,Ahrendt S,Dusheyko S,Nikitin R,Mondo SJ,Salamov A,Shabalov I,Kuo A

    更新日期:2021-01-08 00:00:00

  • A new method for gene discovery in large-scale microarray data.

    abstract::Microarrays are an effective tool for monitoring genome-wide gene expression levels. In current microarray analyses, the majority of genes on arrays are frequently eliminated for further analysis because the changes in their expression levels (ratios) are considered to be not significant. This strategy risks failure t...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkl058

    authors: Yano K,Imai K,Shimizu A,Hanashita T

    更新日期:2006-03-14 00:00:00

  • A correlation with exon expression approach to identify cis-regulatory elements for tissue-specific alternative splicing.

    abstract::Correlation of motif occurrences with gene expression intensity is an effective strategy for elucidating transcriptional cis-regulatory logic. Here we demonstrate that this approach can also identify cis-regulatory elements for alternative pre-mRNA splicing. Using data from a human exon microarray, we identified 56 ca...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkm485

    authors: Das D,Clark TA,Schweitzer A,Yamamoto M,Marr H,Arribere J,Minovitsky S,Poliakov A,Dubchak I,Blume JE,Conboy JG

    更新日期:2007-01-01 00:00:00

  • Nucleotide excision repair efficiency in quiescent human fibroblasts is modulated by circadian clock.

    abstract::The efficiency of Nucleotide Excision Repair (NER)process is crucial for maintaining genomic integrity because in many organisms, including humans, it represents the only system able to repair a wide range of DNA damage. The aim of the work was to investigate whether the efficiency of the repair of photoproducts induc...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkv081

    authors: Bee L,Marini S,Pontarin G,Ferraro P,Costa R,Albrecht U,Celotti L

    更新日期:2015-02-27 00:00:00

  • Temperature mediated variation of DNA secondary structure in (A.T) clusters; evidence by use of the oligopeptide netropsin as a structural probe.

    abstract::The titration viscometric investigation of the multi-mode interaction of netropsin (Nt) with (A.T) clusters of NaDNA12 and NH4DNA10 has been extended to different temperatures. The position of two boundaries on the r-scale (r= [Nt]bound/[DNA-P]) with increasing temperature steadily (rI/II) or more abruptly (rO/I) shif...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/9.10.2335

    authors: Reinert KE,Geller D,Stutter E

    更新日期:1981-05-25 00:00:00

  • RNAMST: efficient and flexible approach for identifying RNA structural homologs.

    abstract::RNA molecules fold into characteristic secondary structures for their diverse functional activities such as post-translational regulation of gene expression. Searching homologs of a pre-defined RNA structural motif, which may be a known functional element or a putative RNA structural motif, can provide useful informat...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkl231

    authors: Chang TH,Huang HD,Chuang TN,Shien DM,Horng JT

    更新日期:2006-07-01 00:00:00

  • Two self-splicing group I introns in the ribonucleotide reductase large subunit gene of Staphylococcus aureus phage Twort.

    abstract::We have recently described three group I introns inserted into a single gene, orf142, of the staphylococcal bacteriophage Twort and suggested the presence of at least two additional self-splicing introns in this phage genome. Here we report that two previously uncharacterized introns, 429 and 1087 nt in length, interr...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/30.9.1935

    authors: Landthaler M,Begley U,Lau NC,Shub DA

    更新日期:2002-05-01 00:00:00

  • Genome sequence comparison of Col and Ler lines reveals the dynamic nature of Arabidopsis chromosomes.

    abstract::Large differences in plant genome sizes are mainly due to numerous events of insertions or deletions (indels). The balance between these events determines the evolutionary direction of genome changes. To address the question of what phenomena trigger these alterations, we compared the genomic sequences of two Arabidop...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkp183

    authors: Ziolkowski PA,Koczyk G,Galganski L,Sadowski J

    更新日期:2009-06-01 00:00:00

  • Identification and characterisation of PmaCI an endonuclease of novel specificity from Pseudomonas maltophila.

    abstract::We report the use of MonoQ FPLC (Fast Protein Liquid Chromatography) for the rapid purification of a novel Type II restriction endonuclease PmaCI, from Pseudomonas maltophila, which recognises the sequence 5'-CAC decreases GTG-3'. The resulting enzyme is free of other nucleases to a level suitable for its characterisa...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/14.3.1293

    authors: Walker JN,Dean PD,Saunders JR

    更新日期:1986-02-11 00:00:00

  • Methyl transferases induced during chemical adaptation of M. luteus.

    abstract::Three peaks of methyltransferase activity specific for MNNG alkylated DNA have been identified from extracts of chemically adapted M. luteus. They are designated as TI to TIII in order to their elution from a Sephadex G-75 column. The first one of these peaks has been purified to homogeneity. TI, is an inducible, unus...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/15.22.9471

    authors: Riazuddin S,Athar A,Sohail A

    更新日期:1987-11-25 00:00:00

  • A long stringent sequence signal for programmed chromosome breakage in Tetrahymena thermophila.

    abstract::Programmed chromosome breakage occurs at 50-200 specific sites in the genome of Tetrahymena thermo-phila during somatic nuclear (macronuclear) differentiation. Previous studies have identified a 15 bp sequence, the Cbs (for chromosome breakage sequence), that is necessary and sufficient to specify these sites. In this...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/28.4.895

    authors: Fan Q,Yao MC

    更新日期:2000-02-15 00:00:00

  • Frequent oligonucleotide motifs in genomes of three streptococci.

    abstract::Complete genomes of three closely related Gram-positive bacteria Streptococcus pyogenes, Streptococcus pneumoniae and Lactococcus lactis are analyzed for abundances of short DNA sequence motifs (frequent words). The character and extent of frequent words are strikingly different among these genomes. The frequent words...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkf534

    authors: Mrázek J,Gaynon LH,Karlin S

    更新日期:2002-10-01 00:00:00

  • Intracellular receptor-type transcription factor, LasR, contains a highly conserved amphipathic region which precedes the putative helix-turn-helix DNA binding motif.

    abstract::We have cloned and sequenced the lasR gene, which is involved in the transcriptional activation of several pathogenic factors, from Pseudomonas aeruginosa IFO3455 and PA103. These clones were predicted to be an open reading frame of 239 amino acids as reported for the PAO1 strain. There is only a single base change re...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/22.18.3706

    authors: Fukushima J,Ishiwata T,Kurata M,You Z,Okuda K

    更新日期:1994-09-11 00:00:00

  • The N-terminus of Prp1 (Prp6/U5-102 K) is essential for spliceosome activation in vivo.

    abstract::The spliceosomal protein Prp1 (Prp6/U5-102 K) is necessary for the integrity of pre-catalytic spliceosomal complexes. We have identified a novel regulatory function for Prp1. Expression of mutations in the N-terminus of Prp1 leads to the accumulation of pre-catalytic spliceosomal complexes containing the five snRNAs U...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkp1155

    authors: Lützelberger M,Bottner CA,Schwelnus W,Zock-Emmenthal S,Razanau A,Käufer NF

    更新日期:2010-03-01 00:00:00

  • An improved procedure for derivatization of controlled-pore glass beads for solid-phase oligonucleotide synthesis.

    abstract::A simplified and economical method for the attachment of 2'-deoxyribo, ribo and arabinonucleosides onto long-chain alkylamidopropanoic acid controlled-pore glass (LCAAP-CPG, P-3) is described. In this procedure, 5'-O-tritylated nucleosides are coupled directly to LCAAP-CPG in excellent yields using 1-(3-dimethylaminop...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/18.13.3813

    authors: Damha MJ,Giannaris PA,Zabarylo SV

    更新日期:1990-07-11 00:00:00

  • IntAct--open source resource for molecular interaction data.

    abstract::IntAct is an open source database and software suite for modeling, storing and analyzing molecular interaction data. The data available in the database originates entirely from published literature and is manually annotated by expert biologists to a high level of detail, including experimental methods, conditions and ...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkl958

    authors: Kerrien S,Alam-Faruque Y,Aranda B,Bancarz I,Bridge A,Derow C,Dimmer E,Feuermann M,Friedrichsen A,Huntley R,Kohler C,Khadake J,Leroy C,Liban A,Lieftink C,Montecchi-Palazzi L,Orchard S,Risse J,Robbe K,Roechert B,Tho

    更新日期:2007-01-01 00:00:00

  • The Reactome pathway knowledgebase.

    abstract::Reactome (http://www.reactome.org) is a manually curated open-source open-data resource of human pathways and reactions. The current version 46 describes 7088 human proteins (34% of the predicted human proteome), participating in 6744 reactions based on data extracted from 15 107 research publications with PubMed link...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkt1102

    authors: Croft D,Mundo AF,Haw R,Milacic M,Weiser J,Wu G,Caudy M,Garapati P,Gillespie M,Kamdar MR,Jassal B,Jupe S,Matthews L,May B,Palatnik S,Rothfels K,Shamovsky V,Song H,Williams M,Birney E,Hermjakob H,Stein L,D'Eusta

    更新日期:2014-01-01 00:00:00

  • Gramene 2018: unifying comparative genomics and pathway resources for plant research.

    abstract::Gramene (http://www.gramene.org) is a knowledgebase for comparative functional analysis in major crops and model plant species. The current release, #54, includes over 1.7 million genes from 44 reference genomes, most of which were organized into 62,367 gene families through orthologous and paralogous gene classificat...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkx1111

    authors: Tello-Ruiz MK,Naithani S,Stein JC,Gupta P,Campbell M,Olson A,Wei S,Preece J,Geniza MJ,Jiao Y,Lee YK,Wang B,Mulvaney J,Chougule K,Elser J,Al-Bader N,Kumari S,Thomason J,Kumar V,Bolser DM,Naamati G,Tapanari E,Fo

    更新日期:2018-01-04 00:00:00

  • TeloTool: a new tool for telomere length measurement from terminal restriction fragment analysis with improved probe intensity correction.

    abstract::Telomeres comprise the protective caps of natural chromosome ends and function in the suppression of DNA damage signaling and cellular senescence. Therefore, techniques used to determine telomere length are important in a number of studies, ranging from those investigating telomeric structure to effects on human disea...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/gkt1315

    authors: Göhring J,Fulcher N,Jacak J,Riha K

    更新日期:2014-02-01 00:00:00

  • Transcripts within the replication origin, oriC, of Escherichia coli.

    abstract::Transcription start and termination sites were mapped in the E. coli replication origin, oriC. Outward transcription from within oriC (promoters Pori-r and Pori-l) was found to start in vivo at position 178 for Pori-l and at positions 294 and 304 for Pori-r, respectively. These transcripts were terminated after 100-15...

    journal_title:Nucleic acids research

    pub_type: 杂志文章

    doi:10.1093/nar/15.6.2479

    authors: Schauzu MA,Kücherer C,Kölling R,Messer W,Lother H

    更新日期:1987-03-25 00:00:00