Abstract:
:Single-cell RNA-seq (scRNA-seq) is quite prevalent in studying transcriptomes, but it suffers from excessive zeros, some of which are true, but others are false. False zeros, which can be seen as missing data, obstruct the downstream analysis of single-cell RNA-seq data. How to distinguish true zeros from false ones is the key point of this problem. Here, we propose sparsity-penalized stacked denoising autoencoders (scSDAEs) to impute scRNA-seq data. scSDAEs adopt stacked denoising autoencoders with a sparsity penalty, as well as a layer-wise pretraining procedure to improve model fitting. scSDAEs can capture nonlinear relationships among the data and incorporate information about the observed zeros. We tested the imputation efficiency of scSDAEs on recovering the true values of gene expression and helping downstream analysis. First, we show that scSDAE can recover the true values and the sample-sample correlations of bulk sequencing data with simulated noise. Next, we demonstrate that scSDAEs accurately impute RNA mixture dataset with different dilutions, spike-in RNA concentrations affected by technical zeros, and improves the consistency of RNA and protein levels in CITE-seq data. Finally, we show that scSDAEs can help downstream clustering analysis. In this study, we develop a deep learning-based method, scSDAE, to impute single-cell RNA-seq affected by technical zeros. Furthermore, we show that scSDAEs can recover the true values, to some extent, and help downstream analysis.
journal_name
Genes (Basel)journal_title
Genesauthors
Chi W,Deng Mdoi
10.3390/genes11050532subject
Has Abstractpub_date
2020-05-11 00:00:00issue
5issn
2073-4425pii
genes11050532journal_volume
11pub_type
杂志文章相关文献
Genes文献大全abstract::Tetralin (1,2,3,4-tetrahydonaphthalene) is a recalcitrant compound that consists of an aromatic and an alicyclic ring. It is found in crude oils, produced industrially from naphthalene or anthracene, and widely used as an organic solvent. Its toxicity is due to the alteration of biological membranes by its hydrophobic...
journal_title:Genes
pub_type: 杂志文章,评审
doi:10.3390/genes10050339
更新日期:2019-05-06 00:00:00
abstract::Prader⁻Willi syndrome (PWS) is a complex genetic disorder that, besides cognitive impairments, is characterized by hyperphagia, obesity, hypogonadism, and growth impairment. Proprotein convertase subtilisin/kexin type 1 (PCSK1) deficiency, a rare recessive congenital disorder, partially overlaps phenotypically with PW...
journal_title:Genes
pub_type: 杂志文章,评审
doi:10.3390/genes9060288
更新日期:2018-06-07 00:00:00
abstract::Drosophila melanogaster is one of the most extensively used genetic model organisms for studying LTR retrotransposons that are represented by various groups in its genome. However, the phenomenon of molecular domestication of LTR retrotransposons has been insufficiently studied in Drosophila, as well as in other inver...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes11040396
更新日期:2020-04-06 00:00:00
abstract::Fragile X syndrome (FXS) is the most common inherited cause of intellectual disability and autism spectrum disorder, and among those with fragile X syndrome, approximately 1/3rd meet a threshold for an autism spectrum disorder (ASD) diagnosis. Previous functional imaging studies of fragile X syndrome have typically fo...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes10121052
更新日期:2019-12-17 00:00:00
abstract::One of the primary objectives of plant biotechnology is to increase resistance to abiotic stresses, such as salinity. Salinity is a major abiotic stress and increasing crop resistant to salt continues to the present day as a major challenge. Salt stress disturbs cellular environment leading to protein misfolding, affe...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes8080195
更新日期:2017-08-03 00:00:00
abstract::Genomic imprinting in domestic animals contributes to the variance of performance traits. However, research remains to be done on large-scale detection of epigenetic landscape of porcine imprinted loci including the GNAS complex locus. The purpose of this study was to generate porcine parthenogenetic fetuses and compr...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes11010096
更新日期:2020-01-14 00:00:00
abstract::Prader-Willi syndrome (PWS) is a complex multisystemic condition caused by a lack of paternal expression of imprinted genes from the 15q11.2-q13 region. Limited literature exists on the association between molecular classes, growth hormone use, and the prevalence of psychiatric phenotypes in PWS. In this study, we ana...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes11111250
更新日期:2020-10-23 00:00:00
abstract::Long non-coding (lnc) RNAs serve a multitude of functions in cells. NEAT1 RNA is a highly abundant 4 kb lncRNA in nuclei, and coincides with paraspeckles, nuclear domains that control sequestration of paraspeckle proteins. We examined NEAT1 RNA levels and its function in 3T3-L1 cells during differentiation to adipocyt...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes5041050
更新日期:2014-11-27 00:00:00
abstract::Pleurotus tuoliensis (Pt) and P. eryngii var. eryngii (Pe) are important edible mushrooms. The epigenetic and gene expression signatures characterizing major developmental transitions in these two mushrooms remain largely unknown. Here, we report global analyses of DNA methylation and gene expression in both mushrooms...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes10060465
更新日期:2019-06-17 00:00:00
abstract::DNA Helicase B (HELB) is a conserved helicase in higher eukaryotes with roles in the initiation of DNA replication and in the DNA damage and replication stress responses. HELB is a predominately nuclear protein in G1 phase where it is involved in initiation of DNA replication through interactions with DNA topoisomeras...
journal_title:Genes
pub_type: 杂志文章,评审
doi:10.3390/genes11050578
更新日期:2020-05-21 00:00:00
abstract::The Himalayas are one of earth's hotspots of biodiversity. Among its many cryptic and undiscovered organisms, including vertebrates, this complex high-mountain ecosystem is expected to harbour many species with adaptations to life in high altitudes. However, modern evolutionary genomic studies in Himalayan vertebrates...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes10110873
更新日期:2019-10-31 00:00:00
abstract::Aging is a complex multi-layered phenomenon. The study of aging in humans is based on the use of biological material from hard-to-gather tissues and highly specific cohorts. The introduction of cell reprogramming techniques posed promising features for medical practice and basic research. Recently, a growing number of...
journal_title:Genes
pub_type: 杂志文章,评审
doi:10.3390/genes9010039
更新日期:2018-01-16 00:00:00
abstract::Biogerontological research highlighted a complex and dynamic connection between aging, health and longevity, partially determined by genetic factors. Multifunctional proteins with moonlighting features, by integrating different cellular activities in the space and time, may explain part of this complexity. Inositol Po...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes10020125
更新日期:2019-02-08 00:00:00
abstract::Each domestic dog breed is characterized by a strict set of physical and behavioral characteristics by which breed members are judged and rewarded in conformation shows. One defining feature of particular interest is the coat, which is comprised of either a double- or single-layer of hair. The top coat contains coarse...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes10050323
更新日期:2019-04-26 00:00:00
abstract::RNA plays complex roles in normal health and disease and is becoming an important target for therapeutic intervention; accordingly, therapeutic strategies that modulate RNA function have gained great interest over the past decade. Antisense oligonucleotides (AOs) are perhaps the most promising strategy to modulate RNA...
journal_title:Genes
pub_type: 杂志文章,评审
doi:10.3390/genes8020051
更新日期:2017-01-26 00:00:00
abstract::Brycon is an important group of Neotropical fish and the principal genus of the family Bryconidae, with 44 valid species that are found in some Central American rivers and practically all the major hydrographic basins of South America. These fish are medium to large in size, migratory, omnivorous, important seed dispe...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes10090639
更新日期:2019-08-23 00:00:00
abstract::Testis cords are the embryonic precursors of the seminiferous tubules. Development of testis cords is a key event during embryonic testicular morphogenesis and is regulated by multiple signaling molecules produced by Sertoli cells. However, the exact nature and the cascade of molecular events underlying testis cord de...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes10120974
更新日期:2019-11-26 00:00:00
abstract::Epigenetic modifications are a mechanism conveying environmental information to subsequent generations via parental germ lines. Research on epigenetic responses to environmental changes in wild mammals has been widely neglected, as well as studies that compare responses to changes in different environmental factors. H...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes10010004
更新日期:2018-12-21 00:00:00
abstract::Cancer stem cells (CSCs), having both self-renewal and tumorigenic capacity, utilize an energy metabolism system different from that of non-CSCs. Lipid droplets (LDs) are organelles that store neutral lipids, including triacylglycerol. Previous studies demonstrated that LDs are formed and store lipids as an energy sou...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes12010099
更新日期:2021-01-14 00:00:00
abstract::Listeria monocytogenes is a major human foodborne pathogen that is prevalent in the natural environment and has a high case fatality rate. Whole genome sequencing (WGS) analysis has emerged as a valuable methodology for the classification of L. monocytogenes isolates and the identification of virulence islands that ma...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes9030171
更新日期:2018-03-20 00:00:00
abstract::Y-chromosomal (Y-DNA) haplogroups are more widely used in population genetics than in genetic epidemiology, although associations between Y-DNA haplogroups and several traits, including cardiometabolic traits, have been reported. In apparently homogeneous populations defined by principal component analyses, there is s...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes9010045
更新日期:2018-01-22 00:00:00
abstract::The increasing availability of large-scale time series data allows the inference of microbial community dynamics by association network analysis. However, correlation-based association network analyses are noninformative of causal, mediating and time-dependent relationships between microbial community functional facto...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes10030216
更新日期:2019-03-14 00:00:00
abstract::Continuous cultures assure the invariability of environmental conditions and the metabolic state of cultured microorganisms, whereas batch-cultured cells undergo constant changes in nutrients availability. For that reason, continuous culture is sometimes employed in the whole transcriptome, whole proteome, or whole me...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes11121419
更新日期:2020-11-27 00:00:00
abstract::We employed Illumina 450 K Infinium microarrays to profile DNA methylation (DNAm) in neuronal nuclei separated by fluorescence-activated sorting from the postmortem orbitofrontal cortex (OFC) of heroin users who died from heroin overdose (N = 37), suicide completers (N = 22) with no evidence of heroin use and from con...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes8060152
更新日期:2017-05-30 00:00:00
abstract::Background: Congenital disorder of glycosylation (CDG) is a severe morphogenic and metabolic disorder that affects all of the systems of organs and is caused by a mutation of the gene PMM2, having a mortality rate of 20% during the first months of life. Results: Here we report the outcome of an in vitro fertilisation ...
journal_title:Genes
pub_type:
doi:10.3390/genes11060697
更新日期:2020-06-25 00:00:00
abstract::microRNA (miRNA) activity and regulation are of increasing interest as new therapeutic targets. Traditional approaches to assess miRNA levels in cells rely on RNA sequencing or quantitative PCR. While useful, these approaches are based on RNA extraction and cannot be applied in real-time to observe miRNA activity with...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes9060305
更新日期:2018-06-19 00:00:00
abstract::Protein sequence, structure, and function are inherently linked through evolution and population genetics. Our knowledge of protein structure comes from solved structures in the Protein Data Bank (PDB), our knowledge of sequence through sequences found in the NCBI sequence databases (http://www.ncbi.nlm.nih.gov/), and...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes2040748
更新日期:2011-10-28 00:00:00
abstract::Winged bean (Psophocarpus tetragonolobus) is an herbaceous multipurpose legume grown in hot and humid countries as a pulse, vegetable (leaves and pods), or root tuber crop depending on local consumption preferences. In addition to its different nutrient-rich edible parts which could contribute to food and nutritional ...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes8030100
更新日期:2017-03-09 00:00:00
abstract::Changes of telomere length with age were assessed in diploid and triploid rainbow trout (Oncorhynchus mykiss) females in the cross-sectional study using Q-FISH technique. Triploid trout as sterile do not invest an energy in gametogenesis and continue to grow, whereas fertile diploid individuals suffer from declines in...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes11070786
更新日期:2020-07-13 00:00:00
abstract::Cisplatin is a chemotherapeutic agent widely used for multiple indications. Unfortunately, in a substantial set of patients treated with cisplatin, dose-limiting acute kidney injury (AKI) occurs. Here, we assessed the association of 3 catechol-O-methyltransferase (COMT) single nucleotide polymorphisms (SNPs) with incr...
journal_title:Genes
pub_type: 杂志文章
doi:10.3390/genes11040358
更新日期:2020-03-27 00:00:00