An ensemble learning approach for modeling the systems biology of drug-induced injury View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2021-01-12

AUTHORS

Joaquim Aguirre-Plans, Janet Piñero, Terezinha Souza, Giulia Callegaro, Steven J. Kunnen, Ferran Sanz, Narcis Fernandez-Fuentes, Laura I. Furlong, Emre Guney, Baldo Oliva

ABSTRACT

BACKGROUND: Drug-induced liver injury (DILI) is an adverse reaction caused by the intake of drugs of common use that produces liver damage. The impact of DILI is estimated to affect around 20 in 100,000 inhabitants worldwide each year. Despite being one of the main causes of liver failure, the pathophysiology and mechanisms of DILI are poorly understood. In the present study, we developed an ensemble learning approach based on different features (CMap gene expression, chemical structures, drug targets) to predict drugs that might cause DILI and gain a better understanding of the mechanisms linked to the adverse reaction. RESULTS: We searched for gene signatures in CMap gene expression data by using two approaches: phenotype-gene associations data from DisGeNET, and a non-parametric test comparing gene expression of DILI-Concern and No-DILI-Concern drugs (as per DILIrank definitions). The average accuracy of the classifiers in both approaches was 69%. We used chemical structures as features, obtaining an accuracy of 65%. The combination of both types of features produced an accuracy around 63%, but improved the independent hold-out test up to 67%. The use of drug-target associations as feature obtained the best accuracy (70%) in the independent hold-out test. CONCLUSIONS: When using CMap gene expression data, searching for a specific gene signature among the landmark genes improves the quality of the classifiers, but it is still limited by the intrinsic noise of the dataset. When using chemical structures as a feature, the structural diversity of the known DILI-causing drugs hampers the prediction, which is a similar problem as for the use of gene expression information. The combination of both features did not improve the quality of the classifiers but increased the robustness as shown on independent hold-out tests. The use of drug-target associations as feature improved the prediction, specially the specificity, and the results were comparable to previous research studies. More... »

PAGES

5

References to SciGraph publications

  • 2019-06-17. Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen in NATURE COMMUNICATIONS
  • 2020-02-13. Predictability of drug-induced liver injury by machine learning in BIOLOGY DIRECT
  • 2018-03-28. Cancer Genome Interpreter annotates the biological and clinical relevance of tumor alterations in GENOME MEDICINE
  • 2004-08. Can the pharmaceutical industry reduce attrition rates? in NATURE REVIEWS DRUG DISCOVERY
  • 2014-06-01. A community effort to assess and improve drug sensitivity prediction algorithms in NATURE BIOTECHNOLOGY
  • 2016-09-17. Predicting drug-induced liver injury in human with Naïve Bayes classifier approach in JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN
  • 2020-01-15. Diverse approaches to predicting drug-induced liver injury using gene-expression profiles in BIOLOGY DIRECT
  • 2017-12-11. Development of Decision Forest Models for Prediction of Drug-Induced Liver Injury in Humans Using A Large Set of FDA-approved Drugs in SCIENTIFIC REPORTS
  • 2018-03-13. Why Drugs Fail in Late Stages of Development: Case Study Analyses from the Last Decade and Recommendations in THE AAPS JOURNAL
  • 2016-10-28. The incidence, presentation, outcomes, risk of mortality and economic data of drug-induced liver injury from a national database in Thailand: a population-base study in BMC GASTROENTEROLOGY
  • 2019-04-11. Applications of machine learning in drug discovery and development in NATURE REVIEWS DRUG DISCOVERY
  • 2007-02-07. Relating protein pharmacology by ligand chemistry in NATURE BIOTECHNOLOGY
  • 2014-01-09. Clinical development success rates for investigational drugs in NATURE BIOTECHNOLOGY
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1186/s13062-020-00288-x

    DOI

    http://dx.doi.org/10.1186/s13062-020-00288-x

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1134522513

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/33435983


    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/2008/11", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Medical and Health Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1115", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Pharmacology and Pharmaceutical Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Chemical and Drug Induced Liver Injury", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Drug-Related Side Effects and Adverse Reactions", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Humans", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Machine Learning", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Models, Biological", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Pharmaceutical Preparations", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Systems Biology", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Aguirre-Plans", 
            "givenName": "Joaquim", 
            "id": "sg:person.012655774713.44", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012655774713.44"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Pi\u00f1ero", 
            "givenName": "Janet", 
            "id": "sg:person.01164723305.52", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01164723305.52"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Toxicogenomics, Maastricht University, Maastricht, The Netherlands", 
              "id": "http://www.grid.ac/institutes/grid.5012.6", 
              "name": [
                "Department of Toxicogenomics, Maastricht University, Maastricht, The Netherlands"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Souza", 
            "givenName": "Terezinha", 
            "id": "sg:person.0666301633.19", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0666301633.19"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Leiden Academic Centre for Drug Research, Leiden University, Leiden, The Netherlands", 
              "id": "http://www.grid.ac/institutes/grid.5132.5", 
              "name": [
                "Leiden Academic Centre for Drug Research, Leiden University, Leiden, The Netherlands"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Callegaro", 
            "givenName": "Giulia", 
            "id": "sg:person.01032527011.42", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01032527011.42"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Leiden Academic Centre for Drug Research, Leiden University, Leiden, The Netherlands", 
              "id": "http://www.grid.ac/institutes/grid.5132.5", 
              "name": [
                "Leiden Academic Centre for Drug Research, Leiden University, Leiden, The Netherlands"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kunnen", 
            "givenName": "Steven J.", 
            "id": "sg:person.01033136227.47", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01033136227.47"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Sanz", 
            "givenName": "Ferran", 
            "id": "sg:person.01027577033.13", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01027577033.13"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Institute of Biological, Environmental and Rural Sciences, Aberystwyth University, Aberystwyth, UK", 
              "id": "http://www.grid.ac/institutes/grid.8186.7", 
              "name": [
                "Department of Biosciences, U Science Tech, Universitat de Vic-Universitat Central de Catalunya, Vic, Spain", 
                "Institute of Biological, Environmental and Rural Sciences, Aberystwyth University, Aberystwyth, UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Fernandez-Fuentes", 
            "givenName": "Narcis", 
            "id": "sg:person.01225527767.67", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01225527767.67"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Furlong", 
            "givenName": "Laura I.", 
            "id": "sg:person.01230201477.14", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01230201477.14"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Guney", 
            "givenName": "Emre", 
            "id": "sg:person.01152440137.81", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01152440137.81"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Oliva", 
            "givenName": "Baldo", 
            "id": "sg:person.016300135377.79", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016300135377.79"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1038/nbt1284", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045526065", 
              "https://doi.org/10.1038/nbt1284"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13062-019-0257-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1124106105", 
              "https://doi.org/10.1186/s13062-019-0257-6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13062-020-0259-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1124861608", 
              "https://doi.org/10.1186/s13062-020-0259-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nrd1470", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041019353", 
              "https://doi.org/10.1038/nrd1470"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41573-019-0024-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1113378385", 
              "https://doi.org/10.1038/s41573-019-0024-5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s12876-016-0550-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031455513", 
              "https://doi.org/10.1186/s12876-016-0550-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41598-017-17701-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099597131", 
              "https://doi.org/10.1038/s41598-017-17701-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41467-019-09799-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1117288715", 
              "https://doi.org/10.1038/s41467-019-09799-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13073-018-0531-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101822517", 
              "https://doi.org/10.1186/s13073-018-0531-8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10822-016-9972-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035406834", 
              "https://doi.org/10.1007/s10822-016-9972-6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nbt.2877", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045563208", 
              "https://doi.org/10.1038/nbt.2877"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1208/s12248-018-0204-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101526622", 
              "https://doi.org/10.1208/s12248-018-0204-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nbt.2786", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013732820", 
              "https://doi.org/10.1038/nbt.2786"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2021-01-12", 
        "datePublishedReg": "2021-01-12", 
        "description": "BACKGROUND: Drug-induced liver injury (DILI) is an adverse reaction caused by the intake of drugs of common use that produces liver damage. The impact of DILI is estimated to affect around 20 in 100,000 inhabitants worldwide each year. Despite being one of the main causes of liver failure, the pathophysiology and mechanisms of DILI are poorly understood. In the present study, we developed an ensemble learning approach based on different features (CMap gene expression, chemical structures, drug targets) to predict drugs that might cause DILI and gain a better understanding of the mechanisms linked to the adverse reaction.\nRESULTS: We searched for gene signatures in CMap gene expression data by using two approaches: phenotype-gene associations data from DisGeNET, and a non-parametric test comparing gene expression of DILI-Concern and No-DILI-Concern drugs (as per DILIrank definitions). The average accuracy of the classifiers in both approaches was 69%. We used chemical structures as features, obtaining an accuracy of 65%. The combination of both types of features produced an accuracy around 63%, but improved the independent hold-out test up to 67%. The use of drug-target associations as feature obtained the best accuracy (70%) in the independent hold-out test.\nCONCLUSIONS: When using CMap gene expression data, searching for a specific gene signature among the landmark genes improves the quality of the classifiers, but it is still limited by the intrinsic noise of the dataset. When using chemical structures as a feature, the structural diversity of the known DILI-causing drugs hampers the prediction, which is a similar problem as for the use of gene expression information. The combination of both features did not improve the quality of the classifiers but increased the robustness as shown on independent hold-out tests. The use of drug-target associations as feature improved the prediction, specially the specificity, and the results were comparable to previous research studies.", 
        "genre": "article", 
        "id": "sg:pub.10.1186/s13062-020-00288-x", 
        "inLanguage": "en", 
        "isAccessibleForFree": true, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.4274042", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": [
          {
            "id": "sg:journal.1036001", 
            "issn": [
              "1745-6150"
            ], 
            "name": "Biology Direct", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "16"
          }
        ], 
        "keywords": [
          "drug-induced liver injury", 
          "adverse reactions", 
          "mechanisms of DILI", 
          "gene signature", 
          "drug-induced injury", 
          "intake of drugs", 
          "specific gene signatures", 
          "liver failure", 
          "liver injury", 
          "liver damage", 
          "DILI concern", 
          "drugs", 
          "injury", 
          "non-parametric tests", 
          "present study", 
          "independent hold", 
          "main cause", 
          "association", 
          "gene expression", 
          "pathophysiology", 
          "intake", 
          "test", 
          "research studies", 
          "study", 
          "cause", 
          "expression data", 
          "gene expression data", 
          "use", 
          "drug-target associations", 
          "common use", 
          "better understanding", 
          "association data", 
          "failure", 
          "DisGeNET", 
          "expression", 
          "years", 
          "mechanism", 
          "data", 
          "specificity", 
          "damage", 
          "combination", 
          "features", 
          "quality", 
          "genes", 
          "previous research studies", 
          "gene expression information", 
          "chemical structure", 
          "reaction", 
          "biology", 
          "inhabitants", 
          "types", 
          "impact", 
          "approach", 
          "hampers", 
          "results", 
          "understanding", 
          "signatures", 
          "expression information", 
          "information", 
          "accuracy", 
          "different features", 
          "systems biology", 
          "hold", 
          "landmark genes", 
          "average accuracy", 
          "prediction", 
          "problem", 
          "good accuracy", 
          "structural diversity", 
          "similar problems", 
          "diversity", 
          "classifier", 
          "structure", 
          "dataset", 
          "intrinsic noise", 
          "types of features", 
          "ensemble learning approach", 
          "learning approach", 
          "noise", 
          "robustness", 
          "impact of DILI", 
          "CMap gene expression data", 
          "phenotype-gene associations data", 
          "DILI-Concern drugs", 
          "independent hold-out test", 
          "hold-out test", 
          "DILI-causing drugs hampers", 
          "drugs hampers"
        ], 
        "name": "An ensemble learning approach for modeling the systems biology of drug-induced injury", 
        "pagination": "5", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1134522513"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1186/s13062-020-00288-x"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "33435983"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1186/s13062-020-00288-x", 
          "https://app.dimensions.ai/details/publication/pub.1134522513"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-01-01T19:02", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/article/article_892.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1186/s13062-020-00288-x"
      }
    ]
     

    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.10.1186/s13062-020-00288-x'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s13062-020-00288-x'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s13062-020-00288-x'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s13062-020-00288-x'


     

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

    304 TRIPLES      22 PREDICATES      134 URIs      113 LITERALS      14 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1186/s13062-020-00288-x schema:about N1a6c1bc794b34f70a86295c203d9b478
    2 N4e30ab5e862b438a91890c6ec4d8488f
    3 N50d287bcf8ed4c8a8fbfd80601593d2f
    4 N6c70c9810e1a493889186b0c4cd89d47
    5 N7a28b551c7a744f588695d2560e9e0da
    6 N8acb8856072e4c6097d269c45d0235e8
    7 Nde4fa046cb18424aa7c80d32b9b35992
    8 anzsrc-for:11
    9 anzsrc-for:1115
    10 schema:author Na8e6c897460547148c36e017ef9f3357
    11 schema:citation sg:pub.10.1007/s10822-016-9972-6
    12 sg:pub.10.1038/nbt.2786
    13 sg:pub.10.1038/nbt.2877
    14 sg:pub.10.1038/nbt1284
    15 sg:pub.10.1038/nrd1470
    16 sg:pub.10.1038/s41467-019-09799-2
    17 sg:pub.10.1038/s41573-019-0024-5
    18 sg:pub.10.1038/s41598-017-17701-7
    19 sg:pub.10.1186/s12876-016-0550-0
    20 sg:pub.10.1186/s13062-019-0257-6
    21 sg:pub.10.1186/s13062-020-0259-4
    22 sg:pub.10.1186/s13073-018-0531-8
    23 sg:pub.10.1208/s12248-018-0204-y
    24 schema:datePublished 2021-01-12
    25 schema:datePublishedReg 2021-01-12
    26 schema:description BACKGROUND: Drug-induced liver injury (DILI) is an adverse reaction caused by the intake of drugs of common use that produces liver damage. The impact of DILI is estimated to affect around 20 in 100,000 inhabitants worldwide each year. Despite being one of the main causes of liver failure, the pathophysiology and mechanisms of DILI are poorly understood. In the present study, we developed an ensemble learning approach based on different features (CMap gene expression, chemical structures, drug targets) to predict drugs that might cause DILI and gain a better understanding of the mechanisms linked to the adverse reaction. RESULTS: We searched for gene signatures in CMap gene expression data by using two approaches: phenotype-gene associations data from DisGeNET, and a non-parametric test comparing gene expression of DILI-Concern and No-DILI-Concern drugs (as per DILIrank definitions). The average accuracy of the classifiers in both approaches was 69%. We used chemical structures as features, obtaining an accuracy of 65%. The combination of both types of features produced an accuracy around 63%, but improved the independent hold-out test up to 67%. The use of drug-target associations as feature obtained the best accuracy (70%) in the independent hold-out test. CONCLUSIONS: When using CMap gene expression data, searching for a specific gene signature among the landmark genes improves the quality of the classifiers, but it is still limited by the intrinsic noise of the dataset. When using chemical structures as a feature, the structural diversity of the known DILI-causing drugs hampers the prediction, which is a similar problem as for the use of gene expression information. The combination of both features did not improve the quality of the classifiers but increased the robustness as shown on independent hold-out tests. The use of drug-target associations as feature improved the prediction, specially the specificity, and the results were comparable to previous research studies.
    27 schema:genre article
    28 schema:inLanguage en
    29 schema:isAccessibleForFree true
    30 schema:isPartOf N601e8a2595e045b0bbcefb30add9ab9c
    31 N98f6e6cd147446a499e30a39121b73a3
    32 sg:journal.1036001
    33 schema:keywords CMap gene expression data
    34 DILI concern
    35 DILI-Concern drugs
    36 DILI-causing drugs hampers
    37 DisGeNET
    38 accuracy
    39 adverse reactions
    40 approach
    41 association
    42 association data
    43 average accuracy
    44 better understanding
    45 biology
    46 cause
    47 chemical structure
    48 classifier
    49 combination
    50 common use
    51 damage
    52 data
    53 dataset
    54 different features
    55 diversity
    56 drug-induced injury
    57 drug-induced liver injury
    58 drug-target associations
    59 drugs
    60 drugs hampers
    61 ensemble learning approach
    62 expression
    63 expression data
    64 expression information
    65 failure
    66 features
    67 gene expression
    68 gene expression data
    69 gene expression information
    70 gene signature
    71 genes
    72 good accuracy
    73 hampers
    74 hold
    75 hold-out test
    76 impact
    77 impact of DILI
    78 independent hold
    79 independent hold-out test
    80 information
    81 inhabitants
    82 injury
    83 intake
    84 intake of drugs
    85 intrinsic noise
    86 landmark genes
    87 learning approach
    88 liver damage
    89 liver failure
    90 liver injury
    91 main cause
    92 mechanism
    93 mechanisms of DILI
    94 noise
    95 non-parametric tests
    96 pathophysiology
    97 phenotype-gene associations data
    98 prediction
    99 present study
    100 previous research studies
    101 problem
    102 quality
    103 reaction
    104 research studies
    105 results
    106 robustness
    107 signatures
    108 similar problems
    109 specific gene signatures
    110 specificity
    111 structural diversity
    112 structure
    113 study
    114 systems biology
    115 test
    116 types
    117 types of features
    118 understanding
    119 use
    120 years
    121 schema:name An ensemble learning approach for modeling the systems biology of drug-induced injury
    122 schema:pagination 5
    123 schema:productId N4d3eff6f57464a7b9984887f66da4cdf
    124 N683180ddf78840c78aef36e499f5ae35
    125 N7a396c2a8d9f4a2fa37d70c17b013617
    126 schema:sameAs https://app.dimensions.ai/details/publication/pub.1134522513
    127 https://doi.org/10.1186/s13062-020-00288-x
    128 schema:sdDatePublished 2022-01-01T19:02
    129 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    130 schema:sdPublisher N21b0de08e51e42c6977e22bb657cae1c
    131 schema:url https://doi.org/10.1186/s13062-020-00288-x
    132 sgo:license sg:explorer/license/
    133 sgo:sdDataset articles
    134 rdf:type schema:ScholarlyArticle
    135 N03679ef85fbc4324a4dee5063b5a7871 rdf:first sg:person.01225527767.67
    136 rdf:rest Na0b8b9bc2358410eb9fad3455765e21b
    137 N1a6c1bc794b34f70a86295c203d9b478 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    138 schema:name Humans
    139 rdf:type schema:DefinedTerm
    140 N21b0de08e51e42c6977e22bb657cae1c schema:name Springer Nature - SN SciGraph project
    141 rdf:type schema:Organization
    142 N4ac99ef2b5804d71aafea0214d705bdc rdf:first sg:person.016300135377.79
    143 rdf:rest rdf:nil
    144 N4d3eff6f57464a7b9984887f66da4cdf schema:name dimensions_id
    145 schema:value pub.1134522513
    146 rdf:type schema:PropertyValue
    147 N4e30ab5e862b438a91890c6ec4d8488f schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    148 schema:name Drug-Related Side Effects and Adverse Reactions
    149 rdf:type schema:DefinedTerm
    150 N50d287bcf8ed4c8a8fbfd80601593d2f schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    151 schema:name Machine Learning
    152 rdf:type schema:DefinedTerm
    153 N601e8a2595e045b0bbcefb30add9ab9c schema:volumeNumber 16
    154 rdf:type schema:PublicationVolume
    155 N6638ebcd0b114c9fa6c5a7fa228d23bc rdf:first sg:person.01032527011.42
    156 rdf:rest Ne7c9bce3674948f4806ee0ec5889643a
    157 N683180ddf78840c78aef36e499f5ae35 schema:name doi
    158 schema:value 10.1186/s13062-020-00288-x
    159 rdf:type schema:PropertyValue
    160 N6c70c9810e1a493889186b0c4cd89d47 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    161 schema:name Chemical and Drug Induced Liver Injury
    162 rdf:type schema:DefinedTerm
    163 N7804fdce0077441ab603297992e11b6c rdf:first sg:person.01027577033.13
    164 rdf:rest N03679ef85fbc4324a4dee5063b5a7871
    165 N7a28b551c7a744f588695d2560e9e0da schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    166 schema:name Models, Biological
    167 rdf:type schema:DefinedTerm
    168 N7a396c2a8d9f4a2fa37d70c17b013617 schema:name pubmed_id
    169 schema:value 33435983
    170 rdf:type schema:PropertyValue
    171 N8acb8856072e4c6097d269c45d0235e8 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    172 schema:name Pharmaceutical Preparations
    173 rdf:type schema:DefinedTerm
    174 N98f6e6cd147446a499e30a39121b73a3 schema:issueNumber 1
    175 rdf:type schema:PublicationIssue
    176 Na0b8b9bc2358410eb9fad3455765e21b rdf:first sg:person.01230201477.14
    177 rdf:rest Nca4290b4922a4379b733f10d8ce2ec9a
    178 Na8e6c897460547148c36e017ef9f3357 rdf:first sg:person.012655774713.44
    179 rdf:rest Nab5948ddc63b4de685b47c84e29a5501
    180 Nab5948ddc63b4de685b47c84e29a5501 rdf:first sg:person.01164723305.52
    181 rdf:rest Ne39195fb442c4d03803cf474c9d6a466
    182 Nca4290b4922a4379b733f10d8ce2ec9a rdf:first sg:person.01152440137.81
    183 rdf:rest N4ac99ef2b5804d71aafea0214d705bdc
    184 Nde4fa046cb18424aa7c80d32b9b35992 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    185 schema:name Systems Biology
    186 rdf:type schema:DefinedTerm
    187 Ne39195fb442c4d03803cf474c9d6a466 rdf:first sg:person.0666301633.19
    188 rdf:rest N6638ebcd0b114c9fa6c5a7fa228d23bc
    189 Ne7c9bce3674948f4806ee0ec5889643a rdf:first sg:person.01033136227.47
    190 rdf:rest N7804fdce0077441ab603297992e11b6c
    191 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
    192 schema:name Medical and Health Sciences
    193 rdf:type schema:DefinedTerm
    194 anzsrc-for:1115 schema:inDefinedTermSet anzsrc-for:
    195 schema:name Pharmacology and Pharmaceutical Sciences
    196 rdf:type schema:DefinedTerm
    197 sg:grant.4274042 http://pending.schema.org/fundedItem sg:pub.10.1186/s13062-020-00288-x
    198 rdf:type schema:MonetaryGrant
    199 sg:journal.1036001 schema:issn 1745-6150
    200 schema:name Biology Direct
    201 schema:publisher Springer Nature
    202 rdf:type schema:Periodical
    203 sg:person.01027577033.13 schema:affiliation grid-institutes:None
    204 schema:familyName Sanz
    205 schema:givenName Ferran
    206 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01027577033.13
    207 rdf:type schema:Person
    208 sg:person.01032527011.42 schema:affiliation grid-institutes:grid.5132.5
    209 schema:familyName Callegaro
    210 schema:givenName Giulia
    211 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01032527011.42
    212 rdf:type schema:Person
    213 sg:person.01033136227.47 schema:affiliation grid-institutes:grid.5132.5
    214 schema:familyName Kunnen
    215 schema:givenName Steven J.
    216 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01033136227.47
    217 rdf:type schema:Person
    218 sg:person.01152440137.81 schema:affiliation grid-institutes:None
    219 schema:familyName Guney
    220 schema:givenName Emre
    221 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01152440137.81
    222 rdf:type schema:Person
    223 sg:person.01164723305.52 schema:affiliation grid-institutes:None
    224 schema:familyName Piñero
    225 schema:givenName Janet
    226 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01164723305.52
    227 rdf:type schema:Person
    228 sg:person.01225527767.67 schema:affiliation grid-institutes:grid.8186.7
    229 schema:familyName Fernandez-Fuentes
    230 schema:givenName Narcis
    231 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01225527767.67
    232 rdf:type schema:Person
    233 sg:person.01230201477.14 schema:affiliation grid-institutes:None
    234 schema:familyName Furlong
    235 schema:givenName Laura I.
    236 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01230201477.14
    237 rdf:type schema:Person
    238 sg:person.012655774713.44 schema:affiliation grid-institutes:None
    239 schema:familyName Aguirre-Plans
    240 schema:givenName Joaquim
    241 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012655774713.44
    242 rdf:type schema:Person
    243 sg:person.016300135377.79 schema:affiliation grid-institutes:None
    244 schema:familyName Oliva
    245 schema:givenName Baldo
    246 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016300135377.79
    247 rdf:type schema:Person
    248 sg:person.0666301633.19 schema:affiliation grid-institutes:grid.5012.6
    249 schema:familyName Souza
    250 schema:givenName Terezinha
    251 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0666301633.19
    252 rdf:type schema:Person
    253 sg:pub.10.1007/s10822-016-9972-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035406834
    254 https://doi.org/10.1007/s10822-016-9972-6
    255 rdf:type schema:CreativeWork
    256 sg:pub.10.1038/nbt.2786 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013732820
    257 https://doi.org/10.1038/nbt.2786
    258 rdf:type schema:CreativeWork
    259 sg:pub.10.1038/nbt.2877 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045563208
    260 https://doi.org/10.1038/nbt.2877
    261 rdf:type schema:CreativeWork
    262 sg:pub.10.1038/nbt1284 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045526065
    263 https://doi.org/10.1038/nbt1284
    264 rdf:type schema:CreativeWork
    265 sg:pub.10.1038/nrd1470 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041019353
    266 https://doi.org/10.1038/nrd1470
    267 rdf:type schema:CreativeWork
    268 sg:pub.10.1038/s41467-019-09799-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1117288715
    269 https://doi.org/10.1038/s41467-019-09799-2
    270 rdf:type schema:CreativeWork
    271 sg:pub.10.1038/s41573-019-0024-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1113378385
    272 https://doi.org/10.1038/s41573-019-0024-5
    273 rdf:type schema:CreativeWork
    274 sg:pub.10.1038/s41598-017-17701-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099597131
    275 https://doi.org/10.1038/s41598-017-17701-7
    276 rdf:type schema:CreativeWork
    277 sg:pub.10.1186/s12876-016-0550-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031455513
    278 https://doi.org/10.1186/s12876-016-0550-0
    279 rdf:type schema:CreativeWork
    280 sg:pub.10.1186/s13062-019-0257-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1124106105
    281 https://doi.org/10.1186/s13062-019-0257-6
    282 rdf:type schema:CreativeWork
    283 sg:pub.10.1186/s13062-020-0259-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1124861608
    284 https://doi.org/10.1186/s13062-020-0259-4
    285 rdf:type schema:CreativeWork
    286 sg:pub.10.1186/s13073-018-0531-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101822517
    287 https://doi.org/10.1186/s13073-018-0531-8
    288 rdf:type schema:CreativeWork
    289 sg:pub.10.1208/s12248-018-0204-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1101526622
    290 https://doi.org/10.1208/s12248-018-0204-y
    291 rdf:type schema:CreativeWork
    292 grid-institutes:None schema:alternateName Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain
    293 schema:name Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), DCEXS, Pompeu Fabra University (UPF), Barcelona, Spain
    294 rdf:type schema:Organization
    295 grid-institutes:grid.5012.6 schema:alternateName Department of Toxicogenomics, Maastricht University, Maastricht, The Netherlands
    296 schema:name Department of Toxicogenomics, Maastricht University, Maastricht, The Netherlands
    297 rdf:type schema:Organization
    298 grid-institutes:grid.5132.5 schema:alternateName Leiden Academic Centre for Drug Research, Leiden University, Leiden, The Netherlands
    299 schema:name Leiden Academic Centre for Drug Research, Leiden University, Leiden, The Netherlands
    300 rdf:type schema:Organization
    301 grid-institutes:grid.8186.7 schema:alternateName Institute of Biological, Environmental and Rural Sciences, Aberystwyth University, Aberystwyth, UK
    302 schema:name Department of Biosciences, U Science Tech, Universitat de Vic-Universitat Central de Catalunya, Vic, Spain
    303 Institute of Biological, Environmental and Rural Sciences, Aberystwyth University, Aberystwyth, UK
    304 rdf:type schema:Organization
     




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


    ...