Multi-omics single-cell data integration and regulatory inference with graph-linked embedding View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2022-05-02

AUTHORS

Zhi-Jie Cao, Ge Gao

ABSTRACT

Despite the emergence of experimental methods for simultaneous measurement of multiple omics modalities in single cells, most single-cell datasets include only one modality. A major obstacle in integrating omics data from multiple modalities is that different omics layers typically have distinct feature spaces. Here, we propose a computational framework called GLUE (graph-linked unified embedding), which bridges the gap by modeling regulatory interactions across omics layers explicitly. Systematic benchmarking demonstrated that GLUE is more accurate, robust and scalable than state-of-the-art tools for heterogeneous single-cell multi-omics data. We applied GLUE to various challenging tasks, including triple-omics integration, integrative regulatory inference and multi-omics human cell atlas construction over millions of cells, where GLUE was able to correct previous annotations. GLUE features a modular design that can be flexibly extended and enhanced for new analysis tasks. The full package is available online at https://github.com/gao-lab/GLUE. More... »

PAGES

1-9

References to SciGraph publications

  • 2021-02-23. Single-cell multiomics sequencing reveals the functional regulatory landscape of early embryos in NATURE COMMUNICATIONS
  • 2013-09-22. Smart-seq2 for sensitive full-length transcriptome profiling in single cells in NATURE METHODS
  • 2021-08-25. Sfaira accelerates data and model reuse in single cell genomics in GENOME BIOLOGY
  • 2021-05-05. Deep generative model embedding of single-cell RNA-Seq profiles on hyperspheres and hyperbolic spaces in NATURE COMMUNICATIONS
  • 2019-10-10. DC3 is a method for deconvolution and coupled clustering from bulk and single-cell genomics data in NATURE COMMUNICATIONS
  • 2013-05-09. Exploring the three-dimensional organization of genomes: interpreting chromatin interaction data in NATURE REVIEWS GENETICS
  • 2018-03-01. Exponential scaling of single-cell RNA-seq in the past decade in NATURE PROTOCOLS
  • 2021-12-23. Benchmarking atlas-level data integration in single-cell genomics in NATURE METHODS
  • 2019-11-18. Fast, sensitive and accurate integration of single-cell data with Harmony in NATURE METHODS
  • 2021-04-13. Single cell transcriptional and chromatin accessibility profiling redefine cellular heterogeneity in the adult human kidney in NATURE COMMUNICATIONS
  • 2021-10-11. Multiscale and integrative single-cell Hi-C analysis with Higashi in NATURE BIOTECHNOLOGY
  • 2021-05-03. Computational principles and challenges in single-cell data integration in NATURE BIOTECHNOLOGY
  • 2021-10-06. A transcriptomic atlas of mouse cerebellar cortex comprehensively defines cell types in NATURE
  • 2021-04-19. Iterative single-cell multi-omic integration using online learning in NATURE BIOTECHNOLOGY
  • 2018-12-17. A rapid and robust method for single cell chromatin accessibility profiling in NATURE COMMUNICATIONS
  • 2015-11-16. Fixed single-cell transcriptomic characterization of human radial glial diversity in NATURE METHODS
  • 2020-01-16. A benchmark of batch-effect correction methods for single-cell RNA sequencing data in GENOME BIOLOGY
  • 2017-12-11. Integrative single-cell analysis of transcriptional and epigenetic states in the human adult brain in NATURE BIOTECHNOLOGY
  • 2020-07-10. Searching large-scale scRNA-seq databases via unbiased cell embedding with Cell BLAST in NATURE COMMUNICATIONS
  • 2017-10-09. SCENIC: single-cell regulatory network inference and clustering in NATURE METHODS
  • 2018-04-09. Highly scalable generation of DNA methylation profiles in single cells in NATURE BIOTECHNOLOGY
  • 2019-10-14. High-throughput sequencing of the transcriptome and chromatin accessibility in the same cell in NATURE BIOTECHNOLOGY
  • 2021-10-06. A transcriptomic and epigenomic cell atlas of the mouse primary motor cortex in NATURE
  • 2021-04-12. Single-cell CUT&Tag profiles histone modifications and transcription factors in complex tissues in NATURE BIOTECHNOLOGY
  • 2018-11-30. Deep generative modeling for single-cell transcriptomics in NATURE METHODS
  • 2019-09-09. A compendium of promoter-centered long-range chromatin interactions in the human genome in NATURE GENETICS
  • 2018-04-02. Integrating single-cell transcriptomic data across different conditions, technologies, and species in NATURE BIOTECHNOLOGY
  • 2017-01-16. Massively parallel digital transcriptional profiling of single cells in NATURE COMMUNICATIONS
  • 2018-02-22. scNMT-seq enables joint profiling of chromatin accessibility DNA methylation and transcription in single cells in NATURE COMMUNICATIONS
  • 2015-11-25. Efficient Test and Visualization of Multi-Set Intersections in SCIENTIFIC REPORTS
  • 2019-03-25. Transcriptome-scale super-resolved imaging in tissues by RNA seqFISH+ in NATURE
  • 2017-10-12. Genetic effects on gene expression across human tissues in NATURE
  • 2019-01-29. Integrative single-cell analysis in NATURE REVIEWS GENETICS
  • 2019-11-18. Assessment of computational methods for the analysis of single-cell ATAC-seq data in GENOME BIOLOGY
  • 2021-01-04. Multi-domain translation between single-cell imaging and sequencing data using autoencoders in NATURE COMMUNICATIONS
  • 2015-03-11. Disruption of DNA-methylation-dependent long gene repression in Rett syndrome in NATURE
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1038/s41587-022-01284-4

    DOI

    http://dx.doi.org/10.1038/s41587-022-01284-4

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1147541248

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/35501393


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Changping Laboratory, Beijing, China", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "State Key Laboratory of Protein and Plant Gene Research, School of Life Sciences, Biomedical Pioneering Innovative Center (BIOPIC) and Beijing Advanced Innovation Center for Genomics (ICG), Center for Bioinformatics (CBI), Peking University, Beijing, China", 
                "Changping Laboratory, Beijing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Cao", 
            "givenName": "Zhi-Jie", 
            "id": "sg:person.012323105171.88", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012323105171.88"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Changping Laboratory, Beijing, China", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "State Key Laboratory of Protein and Plant Gene Research, School of Life Sciences, Biomedical Pioneering Innovative Center (BIOPIC) and Beijing Advanced Innovation Center for Genomics (ICG), Center for Bioinformatics (CBI), Peking University, Beijing, China", 
                "Changping Laboratory, Beijing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Gao", 
            "givenName": "Ge", 
            "id": "sg:person.01240557564.33", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01240557564.33"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1038/s41592-018-0229-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1110105670", 
              "https://doi.org/10.1038/s41592-018-0229-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41592-021-01336-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1144112334", 
              "https://doi.org/10.1038/s41592-021-01336-8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nbt.4038", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099637572", 
              "https://doi.org/10.1038/nbt.4038"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41587-021-00867-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1137304898", 
              "https://doi.org/10.1038/s41587-021-00867-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/srep16923", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045031591", 
              "https://doi.org/10.1038/srep16923"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/ncomms14049", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019155899", 
              "https://doi.org/10.1038/ncomms14049"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41587-021-00869-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1137142226", 
              "https://doi.org/10.1038/s41587-021-00869-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41587-019-0290-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1121784608", 
              "https://doi.org/10.1038/s41587-019-0290-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13059-019-1850-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1124132420", 
              "https://doi.org/10.1186/s13059-019-1850-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13059-019-1854-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1122683497", 
              "https://doi.org/10.1186/s13059-019-1854-5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature14319", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1015767010", 
              "https://doi.org/10.1038/nature14319"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41467-021-22368-w", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1137166690", 
              "https://doi.org/10.1038/s41467-021-22368-w"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41467-018-03149-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101086624", 
              "https://doi.org/10.1038/s41467-018-03149-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41588-019-0494-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1120926154", 
              "https://doi.org/10.1038/s41588-019-0494-8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41587-021-00895-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1137703351", 
              "https://doi.org/10.1038/s41587-021-00895-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nrg3454", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046147193", 
              "https://doi.org/10.1038/nrg3454"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nmeth.3629", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026517170", 
              "https://doi.org/10.1038/nmeth.3629"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41586-021-03500-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1141642032", 
              "https://doi.org/10.1038/s41586-021-03500-8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nmeth.2639", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1006291172", 
              "https://doi.org/10.1038/nmeth.2639"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nprot.2017.149", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101289316", 
              "https://doi.org/10.1038/nprot.2017.149"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41467-020-17281-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1129128665", 
              "https://doi.org/10.1038/s41467-020-17281-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nbt.4112", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1103188713", 
              "https://doi.org/10.1038/nbt.4112"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41576-019-0093-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1111753598", 
              "https://doi.org/10.1038/s41576-019-0093-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature24277", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092152730", 
              "https://doi.org/10.1038/nature24277"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41592-019-0619-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1122668169", 
              "https://doi.org/10.1038/s41592-019-0619-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41586-019-1049-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1112966762", 
              "https://doi.org/10.1038/s41586-019-1049-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41467-019-12547-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1121615204", 
              "https://doi.org/10.1038/s41467-019-12547-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41586-021-03220-z", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1141642081", 
              "https://doi.org/10.1038/s41586-021-03220-z"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41467-020-20249-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1134293765", 
              "https://doi.org/10.1038/s41467-020-20249-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nbt.4096", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101885942", 
              "https://doi.org/10.1038/nbt.4096"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41467-021-21409-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1135651135", 
              "https://doi.org/10.1038/s41467-021-21409-8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41467-021-22851-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1137745286", 
              "https://doi.org/10.1038/s41467-021-22851-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nmeth.4463", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092132373", 
              "https://doi.org/10.1038/nmeth.4463"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13059-021-02452-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1140643366", 
              "https://doi.org/10.1186/s13059-021-02452-6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41467-018-07771-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1110537170", 
              "https://doi.org/10.1038/s41467-018-07771-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41587-021-01034-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1141783009", 
              "https://doi.org/10.1038/s41587-021-01034-y"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2022-05-02", 
        "datePublishedReg": "2022-05-02", 
        "description": "Despite the emergence of experimental methods for simultaneous measurement of multiple omics modalities in single cells, most single-cell datasets include only one modality. A major obstacle in integrating omics data from multiple modalities is that different omics layers typically have distinct feature spaces. Here, we propose a computational framework called GLUE (graph-linked unified embedding), which bridges the gap by modeling regulatory interactions across omics layers explicitly. Systematic benchmarking demonstrated that GLUE is more accurate, robust and scalable than state-of-the-art tools for heterogeneous single-cell multi-omics data. We applied GLUE to various challenging tasks, including triple-omics integration, integrative regulatory inference and multi-omics human cell atlas construction over millions of cells, where GLUE was able to correct previous annotations. GLUE features a modular design that can be flexibly extended and enhanced for new analysis tasks. The full package is available online at https://github.com/gao-lab/GLUE.", 
        "genre": "article", 
        "id": "sg:pub.10.1038/s41587-022-01284-4", 
        "inLanguage": "en", 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1115214", 
            "issn": [
              "1087-0156", 
              "1546-1696"
            ], 
            "name": "Nature Biotechnology", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }
        ], 
        "keywords": [
          "new analysis tasks", 
          "distinct feature spaces", 
          "single-cell data integration", 
          "different omics layers", 
          "analysis tasks", 
          "data integration", 
          "feature space", 
          "art tools", 
          "challenging task", 
          "multiple modalities", 
          "systematic benchmarking", 
          "modular design", 
          "computational framework", 
          "omics layers", 
          "millions of cells", 
          "previous annotations", 
          "single-cell datasets", 
          "omics data", 
          "task", 
          "regulatory inference", 
          "multi-omics data", 
          "integration", 
          "dataset", 
          "annotation", 
          "inference", 
          "embedding", 
          "omics modalities", 
          "single-cell multi-omics data", 
          "framework", 
          "benchmarking", 
          "major obstacle", 
          "millions", 
          "package", 
          "tool", 
          "data", 
          "full package", 
          "obstacles", 
          "design", 
          "space", 
          "modalities", 
          "method", 
          "construction", 
          "layer", 
          "state", 
          "emergence", 
          "gap", 
          "regulatory interactions", 
          "interaction", 
          "glue", 
          "experimental methods", 
          "measurements", 
          "single cells", 
          "simultaneous measurement", 
          "cells", 
          "human cells"
        ], 
        "name": "Multi-omics single-cell data integration and regulatory inference with graph-linked embedding", 
        "pagination": "1-9", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1147541248"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1038/s41587-022-01284-4"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "35501393"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1038/s41587-022-01284-4", 
          "https://app.dimensions.ai/details/publication/pub.1147541248"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-06-01T22:24", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20220601/entities/gbq_results/article/article_937.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1038/s41587-022-01284-4"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1038/s41587-022-01284-4'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1038/s41587-022-01284-4'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1038/s41587-022-01284-4'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1038/s41587-022-01284-4'


     

    This table displays all metadata directly associated to this object as RDF triples.

    263 TRIPLES      22 PREDICATES      115 URIs      71 LITERALS      5 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1038/s41587-022-01284-4 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Ne3922291fb9d4d74acb1c04a52b79fda
    4 schema:citation sg:pub.10.1038/nature14319
    5 sg:pub.10.1038/nature24277
    6 sg:pub.10.1038/nbt.4038
    7 sg:pub.10.1038/nbt.4096
    8 sg:pub.10.1038/nbt.4112
    9 sg:pub.10.1038/ncomms14049
    10 sg:pub.10.1038/nmeth.2639
    11 sg:pub.10.1038/nmeth.3629
    12 sg:pub.10.1038/nmeth.4463
    13 sg:pub.10.1038/nprot.2017.149
    14 sg:pub.10.1038/nrg3454
    15 sg:pub.10.1038/s41467-018-03149-4
    16 sg:pub.10.1038/s41467-018-07771-0
    17 sg:pub.10.1038/s41467-019-12547-1
    18 sg:pub.10.1038/s41467-020-17281-7
    19 sg:pub.10.1038/s41467-020-20249-2
    20 sg:pub.10.1038/s41467-021-21409-8
    21 sg:pub.10.1038/s41467-021-22368-w
    22 sg:pub.10.1038/s41467-021-22851-4
    23 sg:pub.10.1038/s41576-019-0093-7
    24 sg:pub.10.1038/s41586-019-1049-y
    25 sg:pub.10.1038/s41586-021-03220-z
    26 sg:pub.10.1038/s41586-021-03500-8
    27 sg:pub.10.1038/s41587-019-0290-0
    28 sg:pub.10.1038/s41587-021-00867-x
    29 sg:pub.10.1038/s41587-021-00869-9
    30 sg:pub.10.1038/s41587-021-00895-7
    31 sg:pub.10.1038/s41587-021-01034-y
    32 sg:pub.10.1038/s41588-019-0494-8
    33 sg:pub.10.1038/s41592-018-0229-2
    34 sg:pub.10.1038/s41592-019-0619-0
    35 sg:pub.10.1038/s41592-021-01336-8
    36 sg:pub.10.1038/srep16923
    37 sg:pub.10.1186/s13059-019-1850-9
    38 sg:pub.10.1186/s13059-019-1854-5
    39 sg:pub.10.1186/s13059-021-02452-6
    40 schema:datePublished 2022-05-02
    41 schema:datePublishedReg 2022-05-02
    42 schema:description Despite the emergence of experimental methods for simultaneous measurement of multiple omics modalities in single cells, most single-cell datasets include only one modality. A major obstacle in integrating omics data from multiple modalities is that different omics layers typically have distinct feature spaces. Here, we propose a computational framework called GLUE (graph-linked unified embedding), which bridges the gap by modeling regulatory interactions across omics layers explicitly. Systematic benchmarking demonstrated that GLUE is more accurate, robust and scalable than state-of-the-art tools for heterogeneous single-cell multi-omics data. We applied GLUE to various challenging tasks, including triple-omics integration, integrative regulatory inference and multi-omics human cell atlas construction over millions of cells, where GLUE was able to correct previous annotations. GLUE features a modular design that can be flexibly extended and enhanced for new analysis tasks. The full package is available online at https://github.com/gao-lab/GLUE.
    43 schema:genre article
    44 schema:inLanguage en
    45 schema:isAccessibleForFree true
    46 schema:isPartOf sg:journal.1115214
    47 schema:keywords analysis tasks
    48 annotation
    49 art tools
    50 benchmarking
    51 cells
    52 challenging task
    53 computational framework
    54 construction
    55 data
    56 data integration
    57 dataset
    58 design
    59 different omics layers
    60 distinct feature spaces
    61 embedding
    62 emergence
    63 experimental methods
    64 feature space
    65 framework
    66 full package
    67 gap
    68 glue
    69 human cells
    70 inference
    71 integration
    72 interaction
    73 layer
    74 major obstacle
    75 measurements
    76 method
    77 millions
    78 millions of cells
    79 modalities
    80 modular design
    81 multi-omics data
    82 multiple modalities
    83 new analysis tasks
    84 obstacles
    85 omics data
    86 omics layers
    87 omics modalities
    88 package
    89 previous annotations
    90 regulatory inference
    91 regulatory interactions
    92 simultaneous measurement
    93 single cells
    94 single-cell data integration
    95 single-cell datasets
    96 single-cell multi-omics data
    97 space
    98 state
    99 systematic benchmarking
    100 task
    101 tool
    102 schema:name Multi-omics single-cell data integration and regulatory inference with graph-linked embedding
    103 schema:pagination 1-9
    104 schema:productId N1d088f491b3e4061884f51f8dfd8ab9d
    105 N5440fddbd3f543e98ba141eb0b97fcec
    106 Nd309f45cb6b74bfe9875fbe920a0eb09
    107 schema:sameAs https://app.dimensions.ai/details/publication/pub.1147541248
    108 https://doi.org/10.1038/s41587-022-01284-4
    109 schema:sdDatePublished 2022-06-01T22:24
    110 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    111 schema:sdPublisher Naf56335c1a504545b63cb061e4a8ed7a
    112 schema:url https://doi.org/10.1038/s41587-022-01284-4
    113 sgo:license sg:explorer/license/
    114 sgo:sdDataset articles
    115 rdf:type schema:ScholarlyArticle
    116 N1b5420764a854573993324ec5566436f rdf:first sg:person.01240557564.33
    117 rdf:rest rdf:nil
    118 N1d088f491b3e4061884f51f8dfd8ab9d schema:name doi
    119 schema:value 10.1038/s41587-022-01284-4
    120 rdf:type schema:PropertyValue
    121 N5440fddbd3f543e98ba141eb0b97fcec schema:name pubmed_id
    122 schema:value 35501393
    123 rdf:type schema:PropertyValue
    124 Naf56335c1a504545b63cb061e4a8ed7a schema:name Springer Nature - SN SciGraph project
    125 rdf:type schema:Organization
    126 Nd309f45cb6b74bfe9875fbe920a0eb09 schema:name dimensions_id
    127 schema:value pub.1147541248
    128 rdf:type schema:PropertyValue
    129 Ne3922291fb9d4d74acb1c04a52b79fda rdf:first sg:person.012323105171.88
    130 rdf:rest N1b5420764a854573993324ec5566436f
    131 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    132 schema:name Information and Computing Sciences
    133 rdf:type schema:DefinedTerm
    134 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    135 schema:name Artificial Intelligence and Image Processing
    136 rdf:type schema:DefinedTerm
    137 sg:journal.1115214 schema:issn 1087-0156
    138 1546-1696
    139 schema:name Nature Biotechnology
    140 schema:publisher Springer Nature
    141 rdf:type schema:Periodical
    142 sg:person.012323105171.88 schema:affiliation grid-institutes:None
    143 schema:familyName Cao
    144 schema:givenName Zhi-Jie
    145 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012323105171.88
    146 rdf:type schema:Person
    147 sg:person.01240557564.33 schema:affiliation grid-institutes:None
    148 schema:familyName Gao
    149 schema:givenName Ge
    150 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01240557564.33
    151 rdf:type schema:Person
    152 sg:pub.10.1038/nature14319 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015767010
    153 https://doi.org/10.1038/nature14319
    154 rdf:type schema:CreativeWork
    155 sg:pub.10.1038/nature24277 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092152730
    156 https://doi.org/10.1038/nature24277
    157 rdf:type schema:CreativeWork
    158 sg:pub.10.1038/nbt.4038 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099637572
    159 https://doi.org/10.1038/nbt.4038
    160 rdf:type schema:CreativeWork
    161 sg:pub.10.1038/nbt.4096 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101885942
    162 https://doi.org/10.1038/nbt.4096
    163 rdf:type schema:CreativeWork
    164 sg:pub.10.1038/nbt.4112 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103188713
    165 https://doi.org/10.1038/nbt.4112
    166 rdf:type schema:CreativeWork
    167 sg:pub.10.1038/ncomms14049 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019155899
    168 https://doi.org/10.1038/ncomms14049
    169 rdf:type schema:CreativeWork
    170 sg:pub.10.1038/nmeth.2639 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006291172
    171 https://doi.org/10.1038/nmeth.2639
    172 rdf:type schema:CreativeWork
    173 sg:pub.10.1038/nmeth.3629 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026517170
    174 https://doi.org/10.1038/nmeth.3629
    175 rdf:type schema:CreativeWork
    176 sg:pub.10.1038/nmeth.4463 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092132373
    177 https://doi.org/10.1038/nmeth.4463
    178 rdf:type schema:CreativeWork
    179 sg:pub.10.1038/nprot.2017.149 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101289316
    180 https://doi.org/10.1038/nprot.2017.149
    181 rdf:type schema:CreativeWork
    182 sg:pub.10.1038/nrg3454 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046147193
    183 https://doi.org/10.1038/nrg3454
    184 rdf:type schema:CreativeWork
    185 sg:pub.10.1038/s41467-018-03149-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101086624
    186 https://doi.org/10.1038/s41467-018-03149-4
    187 rdf:type schema:CreativeWork
    188 sg:pub.10.1038/s41467-018-07771-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1110537170
    189 https://doi.org/10.1038/s41467-018-07771-0
    190 rdf:type schema:CreativeWork
    191 sg:pub.10.1038/s41467-019-12547-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1121615204
    192 https://doi.org/10.1038/s41467-019-12547-1
    193 rdf:type schema:CreativeWork
    194 sg:pub.10.1038/s41467-020-17281-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1129128665
    195 https://doi.org/10.1038/s41467-020-17281-7
    196 rdf:type schema:CreativeWork
    197 sg:pub.10.1038/s41467-020-20249-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1134293765
    198 https://doi.org/10.1038/s41467-020-20249-2
    199 rdf:type schema:CreativeWork
    200 sg:pub.10.1038/s41467-021-21409-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1135651135
    201 https://doi.org/10.1038/s41467-021-21409-8
    202 rdf:type schema:CreativeWork
    203 sg:pub.10.1038/s41467-021-22368-w schema:sameAs https://app.dimensions.ai/details/publication/pub.1137166690
    204 https://doi.org/10.1038/s41467-021-22368-w
    205 rdf:type schema:CreativeWork
    206 sg:pub.10.1038/s41467-021-22851-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1137745286
    207 https://doi.org/10.1038/s41467-021-22851-4
    208 rdf:type schema:CreativeWork
    209 sg:pub.10.1038/s41576-019-0093-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111753598
    210 https://doi.org/10.1038/s41576-019-0093-7
    211 rdf:type schema:CreativeWork
    212 sg:pub.10.1038/s41586-019-1049-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1112966762
    213 https://doi.org/10.1038/s41586-019-1049-y
    214 rdf:type schema:CreativeWork
    215 sg:pub.10.1038/s41586-021-03220-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1141642081
    216 https://doi.org/10.1038/s41586-021-03220-z
    217 rdf:type schema:CreativeWork
    218 sg:pub.10.1038/s41586-021-03500-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1141642032
    219 https://doi.org/10.1038/s41586-021-03500-8
    220 rdf:type schema:CreativeWork
    221 sg:pub.10.1038/s41587-019-0290-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1121784608
    222 https://doi.org/10.1038/s41587-019-0290-0
    223 rdf:type schema:CreativeWork
    224 sg:pub.10.1038/s41587-021-00867-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1137304898
    225 https://doi.org/10.1038/s41587-021-00867-x
    226 rdf:type schema:CreativeWork
    227 sg:pub.10.1038/s41587-021-00869-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1137142226
    228 https://doi.org/10.1038/s41587-021-00869-9
    229 rdf:type schema:CreativeWork
    230 sg:pub.10.1038/s41587-021-00895-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1137703351
    231 https://doi.org/10.1038/s41587-021-00895-7
    232 rdf:type schema:CreativeWork
    233 sg:pub.10.1038/s41587-021-01034-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1141783009
    234 https://doi.org/10.1038/s41587-021-01034-y
    235 rdf:type schema:CreativeWork
    236 sg:pub.10.1038/s41588-019-0494-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1120926154
    237 https://doi.org/10.1038/s41588-019-0494-8
    238 rdf:type schema:CreativeWork
    239 sg:pub.10.1038/s41592-018-0229-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1110105670
    240 https://doi.org/10.1038/s41592-018-0229-2
    241 rdf:type schema:CreativeWork
    242 sg:pub.10.1038/s41592-019-0619-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1122668169
    243 https://doi.org/10.1038/s41592-019-0619-0
    244 rdf:type schema:CreativeWork
    245 sg:pub.10.1038/s41592-021-01336-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1144112334
    246 https://doi.org/10.1038/s41592-021-01336-8
    247 rdf:type schema:CreativeWork
    248 sg:pub.10.1038/srep16923 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045031591
    249 https://doi.org/10.1038/srep16923
    250 rdf:type schema:CreativeWork
    251 sg:pub.10.1186/s13059-019-1850-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1124132420
    252 https://doi.org/10.1186/s13059-019-1850-9
    253 rdf:type schema:CreativeWork
    254 sg:pub.10.1186/s13059-019-1854-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1122683497
    255 https://doi.org/10.1186/s13059-019-1854-5
    256 rdf:type schema:CreativeWork
    257 sg:pub.10.1186/s13059-021-02452-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1140643366
    258 https://doi.org/10.1186/s13059-021-02452-6
    259 rdf:type schema:CreativeWork
    260 grid-institutes:None schema:alternateName Changping Laboratory, Beijing, China
    261 schema:name Changping Laboratory, Beijing, China
    262 State Key Laboratory of Protein and Plant Gene Research, School of Life Sciences, Biomedical Pioneering Innovative Center (BIOPIC) and Beijing Advanced Innovation Center for Genomics (ICG), Center for Bioinformatics (CBI), Peking University, Beijing, China
    263 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...