Prediction and mechanistic analysis of drug-induced liver injury (DILI) based on chemical structure View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2021-01-18

AUTHORS

Anika Liu, Moritz Walter, Peter Wright, Aleksandra Bartosik, Daniela Dolciami, Abdurrahman Elbasir, Hongbin Yang, Andreas Bender

ABSTRACT

BACKGROUND: Drug-induced liver injury (DILI) is a major safety concern characterized by a complex and diverse pathogenesis. In order to identify DILI early in drug development, a better understanding of the injury and models with better predictivity are urgently needed. One approach in this regard are in silico models which aim at predicting the risk of DILI based on the compound structure. However, these models do not yet show sufficient predictive performance or interpretability to be useful for decision making by themselves, the former partially stemming from the underlying problem of labeling the in vivo DILI risk of compounds in a meaningful way for generating machine learning models. RESULTS: As part of the Critical Assessment of Massive Data Analysis (CAMDA) "CMap Drug Safety Challenge" 2019 ( http://camda2019.bioinf.jku.at ), chemical structure-based models were generated using the binarized DILIrank annotations. Support Vector Machine (SVM) and Random Forest (RF) classifiers showed comparable performance to previously published models with a mean balanced accuracy over models generated using 5-fold LOCO-CV inside a 10-fold training scheme of 0.759 ± 0.027 when predicting an external test set. In the models which used predicted protein targets as compound descriptors, we identified the most information-rich proteins which agreed with the mechanisms of action and toxicity of nonsteroidal anti-inflammatory drugs (NSAIDs), one of the most important drug classes causing DILI, stress response via TP53 and biotransformation. In addition, we identified multiple proteins involved in xenobiotic metabolism which could be novel DILI-related off-targets, such as CLK1 and DYRK2. Moreover, we derived potential structural alerts for DILI with high precision, including furan and hydrazine derivatives; however, all derived alerts were present in approved drugs and were over specific indicating the need to consider quantitative variables such as dose. CONCLUSION: Using chemical structure-based descriptors such as structural fingerprints and predicted protein targets, DILI prediction models were built with a predictive performance comparable to previous literature. In addition, we derived insights on proteins and pathways statistically (and potentially causally) linked to DILI from these models and inferred new structural alerts related to this adverse endpoint. More... »

PAGES

6

References to SciGraph publications

  • 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
  • 2016-04-02. Differential Expression of Adenosine P1 Receptor ADORA1 and ADORA2A Associated with Glioma Development and Tumor-Associated Epilepsy in NEUROCHEMICAL RESEARCH
  • 1994-09. Arachidonic acid metabolism in galactosamine/endotoxin induced acute liver injury in rats in CURRENT MEDICAL SCIENCE
  • 2015-09-30. Overexpression of Aldose Reductase Render Mouse Hepatocytes More Sensitive to Acetaminophen Induced Oxidative Stress and Cell Death in INDIAN JOURNAL OF CLINICAL BIOCHEMISTRY
  • 2020-02-03. SciPy 1.0: fundamental algorithms for scientific computing in Python in NATURE METHODS
  • 2015-02-11. Data-driven identification of structural alerts for mitigating the risk of drug-induced human liver injuries in JOURNAL OF CHEMINFORMATICS
  • 2001-10. Random Forests in MACHINE LEARNING
  • 2015-10-24. Target prediction utilising negative bioactivity data covering large chemical space in JOURNAL OF CHEMINFORMATICS
  • 2016-09-17. Predicting drug-induced liver injury in human with Naïve Bayes classifier approach in JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN
  • 2019-06-27. Prediction of human drug-induced liver injury (DILI) in relation to oral doses and blood concentrations in ARCHIVES OF TOXICOLOGY
  • 1974-11. Morphological and Biochemical Effects of 1,2-Dimethylhydrazine and 1-Methylhydrazine in Rats and Mice in BRITISH JOURNAL OF CANCER
  • 1995-09. Support-vector networks in MACHINE LEARNING
  • 2017-06-05. SCRAMBLE’N’GAMBLE: a tool for fast and facile generation of random data for statistical evaluation of QSAR models in CHEMICAL PAPERS
  • 2018-02-06. Mordred: a molecular descriptor calculator in JOURNAL OF CHEMINFORMATICS
  • 2018-03-03. Dynamic imaging of adaptive stress response pathway activation for prediction of drug induced liver injury in ARCHIVES OF TOXICOLOGY
  • 2015-05-20. Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? in JOURNAL OF CHEMINFORMATICS
  • 2016-12-03. A novel applicability domain technique for mapping predictive reliability across the chemical space of a QSAR: reliability-density neighbourhood in JOURNAL OF CHEMINFORMATICS
  • 2017-01-26. Ror2 signaling regulates Golgi structure and transport through IFT20 for tumor invasiveness in SCIENTIFIC REPORTS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1186/s13062-020-00285-0

    DOI

    http://dx.doi.org/10.1186/s13062-020-00285-0

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1134679269

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/33461600


    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": "Computer Simulation", 
            "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"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK", 
              "id": "http://www.grid.ac/institutes/grid.5335.0", 
              "name": [
                "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Liu", 
            "givenName": "Anika", 
            "id": "sg:person.013707411067.25", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013707411067.25"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK", 
              "id": "http://www.grid.ac/institutes/grid.5335.0", 
              "name": [
                "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Walter", 
            "givenName": "Moritz", 
            "id": "sg:person.014504771467.30", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014504771467.30"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK", 
              "id": "http://www.grid.ac/institutes/grid.5335.0", 
              "name": [
                "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Wright", 
            "givenName": "Peter", 
            "id": "sg:person.015302352067.18", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015302352067.18"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK", 
              "id": "http://www.grid.ac/institutes/grid.5335.0", 
              "name": [
                "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Bartosik", 
            "givenName": "Aleksandra", 
            "id": "sg:person.016077732467.71", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016077732467.71"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Pharmaceutical Sciences, University of Perugia, Via del Liceo 1, 06123 Perugia, Italy", 
              "id": "http://www.grid.ac/institutes/grid.9027.c", 
              "name": [
                "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK", 
                "Department of Pharmaceutical Sciences, University of Perugia, Via del Liceo 1, 06123 Perugia, Italy"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Dolciami", 
            "givenName": "Daniela", 
            "id": "sg:person.01016162114.96", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01016162114.96"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "ICT Department, College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar", 
              "id": "http://www.grid.ac/institutes/grid.452146.0", 
              "name": [
                "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK", 
                "ICT Department, College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Elbasir", 
            "givenName": "Abdurrahman", 
            "id": "sg:person.015316311243.73", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015316311243.73"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK", 
              "id": "http://www.grid.ac/institutes/grid.5335.0", 
              "name": [
                "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Yang", 
            "givenName": "Hongbin", 
            "id": "sg:person.010176102767.24", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010176102767.24"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK", 
              "id": "http://www.grid.ac/institutes/grid.5335.0", 
              "name": [
                "Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Bender", 
            "givenName": "Andreas", 
            "id": "sg:person.0626547717.06", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0626547717.06"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1038/s41592-019-0686-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1124547608", 
              "https://doi.org/10.1038/s41592-019-0686-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41598-016-0028-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1079403223", 
              "https://doi.org/10.1038/s41598-016-0028-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1010933404324", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024739340", 
              "https://doi.org/10.1023/a:1010933404324"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13321-016-0182-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1011404086", 
              "https://doi.org/10.1186/s13321-016-0182-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11064-016-1893-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031818433", 
              "https://doi.org/10.1007/s11064-016-1893-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11696-017-0215-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1085869820", 
              "https://doi.org/10.1007/s11696-017-0215-7"
            ], 
            "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.10.1007/s12291-015-0517-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014527125", 
              "https://doi.org/10.1007/s12291-015-0517-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00204-018-2178-z", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101322873", 
              "https://doi.org/10.1007/s00204-018-2178-z"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf02886800", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022490450", 
              "https://doi.org/10.1007/bf02886800"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00994018", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1025150743", 
              "https://doi.org/10.1007/bf00994018"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/bjc.1974.217", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009186769", 
              "https://doi.org/10.1038/bjc.1974.217"
            ], 
            "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.10.1007/s00204-019-02492-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1117608090", 
              "https://doi.org/10.1007/s00204-019-02492-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13321-015-0098-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038668816", 
              "https://doi.org/10.1186/s13321-015-0098-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13321-018-0258-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100856074", 
              "https://doi.org/10.1186/s13321-018-0258-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13321-015-0069-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013829144", 
              "https://doi.org/10.1186/s13321-015-0069-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13321-015-0053-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1002837276", 
              "https://doi.org/10.1186/s13321-015-0053-y"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2021-01-18", 
        "datePublishedReg": "2021-01-18", 
        "description": "BACKGROUND: Drug-induced liver injury (DILI) is a major safety concern characterized by a complex and diverse pathogenesis. In order to identify DILI early in drug development, a better understanding of the injury and models with better predictivity are urgently needed. One approach in this regard are in silico models which aim at predicting the risk of DILI based on the compound structure. However, these models do not yet show sufficient predictive performance or interpretability to be useful for decision making by themselves, the former partially stemming from the underlying problem of labeling the in vivo DILI risk of compounds in a meaningful way for generating machine learning models.\nRESULTS: As part of the Critical Assessment of Massive Data Analysis (CAMDA) \"CMap Drug Safety Challenge\" 2019 ( http://camda2019.bioinf.jku.at ), chemical structure-based models were generated using the binarized DILIrank annotations. Support Vector Machine (SVM) and Random Forest (RF) classifiers showed comparable performance to previously published models with a mean balanced accuracy over models generated using 5-fold LOCO-CV inside a 10-fold training scheme of 0.759\u2009\u00b1\u20090.027 when predicting an external test set. In the models which used predicted protein targets as compound descriptors, we identified the most information-rich proteins which agreed with the mechanisms of action and toxicity of nonsteroidal anti-inflammatory drugs (NSAIDs), one of the most important drug classes causing DILI, stress response via TP53 and biotransformation. In addition, we identified multiple proteins involved in xenobiotic metabolism which could be novel DILI-related off-targets, such as CLK1 and DYRK2. Moreover, we derived potential structural alerts for DILI with high precision, including furan and hydrazine derivatives; however, all derived alerts were present in approved drugs and were over specific indicating the need to consider quantitative variables such as dose.\nCONCLUSION: Using chemical structure-based descriptors such as structural fingerprints and predicted protein targets, DILI prediction models were built with a predictive performance comparable to previous literature. In addition, we derived insights on proteins and pathways statistically (and potentially causally) linked to DILI from these models and inferred new structural alerts related to this adverse endpoint.", 
        "genre": "article", 
        "id": "sg:pub.10.1186/s13062-020-00285-0", 
        "inLanguage": "en", 
        "isAccessibleForFree": true, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.7158532", 
            "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", 
          "nonsteroidal anti-inflammatory drugs", 
          "liver injury", 
          "risk of DILI", 
          "anti-inflammatory drugs", 
          "important drug class", 
          "mechanism of action", 
          "diverse pathogenesis", 
          "DILI risk", 
          "drug classes", 
          "adverse endpoints", 
          "major safety concern", 
          "injury", 
          "drug development", 
          "xenobiotic metabolism", 
          "safety concerns", 
          "drugs", 
          "quantitative variables", 
          "risk", 
          "predictive performance", 
          "structural alerts", 
          "potential structural alerts", 
          "protein targets", 
          "pathogenesis", 
          "stress response", 
          "dose", 
          "protein", 
          "endpoint", 
          "TP53", 
          "target", 
          "mechanistic analysis", 
          "alerts", 
          "toxicity", 
          "metabolism", 
          "silico models", 
          "good predictivity", 
          "multiple proteins", 
          "better understanding", 
          "new structural alerts", 
          "pathway", 
          "response", 
          "assessment", 
          "DYRK2", 
          "addition", 
          "data analysis", 
          "action", 
          "biotransformation", 
          "loco", 
          "analysis", 
          "predictivity", 
          "regard", 
          "mechanism", 
          "previous literature", 
          "need", 
          "concern", 
          "sufficient predictive performance", 
          "hydrazine derivatives", 
          "prediction model", 
          "literature", 
          "development", 
          "model", 
          "variables", 
          "understanding", 
          "random forest classifier", 
          "compounds", 
          "meaningful way", 
          "machine learning models", 
          "part", 
          "critical assessment", 
          "chemical structure", 
          "decisions", 
          "insights", 
          "derivatives", 
          "forest classifier", 
          "training scheme", 
          "cv", 
          "test set", 
          "approach", 
          "external test set", 
          "class", 
          "CLK1", 
          "compound structure", 
          "accuracy", 
          "order", 
          "problem", 
          "performance", 
          "interpretability", 
          "way", 
          "prediction", 
          "fingerprints", 
          "precision", 
          "structure", 
          "descriptors", 
          "comparable performance", 
          "learning model", 
          "furan", 
          "vector machine", 
          "structural fingerprints", 
          "set", 
          "structure-based descriptors", 
          "classifier", 
          "annotation", 
          "machine", 
          "high precision", 
          "massive data analysis", 
          "compound descriptors", 
          "structure-based model", 
          "scheme", 
          "vivo DILI risk", 
          "chemical structure-based models", 
          "binarized DILIrank annotations", 
          "DILIrank annotations", 
          "most information-rich proteins", 
          "information-rich proteins", 
          "chemical structure-based descriptors", 
          "DILI prediction models"
        ], 
        "name": "Prediction and mechanistic analysis of drug-induced liver injury (DILI) based on chemical structure", 
        "pagination": "6", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1134679269"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1186/s13062-020-00285-0"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "33461600"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1186/s13062-020-00285-0", 
          "https://app.dimensions.ai/details/publication/pub.1134679269"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-01-01T18:57", 
        "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_883.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1186/s13062-020-00285-0"
      }
    ]
     

    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/s13062-020-00285-0'

    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/s13062-020-00285-0'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s13062-020-00285-0'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s13062-020-00285-0'


     

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

    328 TRIPLES      22 PREDICATES      165 URIs      139 LITERALS      12 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1186/s13062-020-00285-0 schema:about N069c2aa9513342369adb0f795a898f9b
    2 N7092f28e0d7e401597a76b5f6337eb2f
    3 N9d13d52adc844137b5466cfd77d4f2e2
    4 N9dc115d91f50458ea0d0b96530e57648
    5 Ncf67bce8320f4c428501131b02ada442
    6 anzsrc-for:11
    7 anzsrc-for:1115
    8 schema:author Nc168b44cba114b40ac8a9aabf199b95b
    9 schema:citation sg:pub.10.1007/bf00994018
    10 sg:pub.10.1007/bf02886800
    11 sg:pub.10.1007/s00204-018-2178-z
    12 sg:pub.10.1007/s00204-019-02492-9
    13 sg:pub.10.1007/s10822-016-9972-6
    14 sg:pub.10.1007/s11064-016-1893-1
    15 sg:pub.10.1007/s11696-017-0215-7
    16 sg:pub.10.1007/s12291-015-0517-x
    17 sg:pub.10.1023/a:1010933404324
    18 sg:pub.10.1038/bjc.1974.217
    19 sg:pub.10.1038/s41592-019-0686-2
    20 sg:pub.10.1038/s41598-016-0028-x
    21 sg:pub.10.1038/s41598-017-17701-7
    22 sg:pub.10.1186/s13321-015-0053-y
    23 sg:pub.10.1186/s13321-015-0069-3
    24 sg:pub.10.1186/s13321-015-0098-y
    25 sg:pub.10.1186/s13321-016-0182-y
    26 sg:pub.10.1186/s13321-018-0258-y
    27 schema:datePublished 2021-01-18
    28 schema:datePublishedReg 2021-01-18
    29 schema:description BACKGROUND: Drug-induced liver injury (DILI) is a major safety concern characterized by a complex and diverse pathogenesis. In order to identify DILI early in drug development, a better understanding of the injury and models with better predictivity are urgently needed. One approach in this regard are in silico models which aim at predicting the risk of DILI based on the compound structure. However, these models do not yet show sufficient predictive performance or interpretability to be useful for decision making by themselves, the former partially stemming from the underlying problem of labeling the in vivo DILI risk of compounds in a meaningful way for generating machine learning models. RESULTS: As part of the Critical Assessment of Massive Data Analysis (CAMDA) "CMap Drug Safety Challenge" 2019 ( http://camda2019.bioinf.jku.at ), chemical structure-based models were generated using the binarized DILIrank annotations. Support Vector Machine (SVM) and Random Forest (RF) classifiers showed comparable performance to previously published models with a mean balanced accuracy over models generated using 5-fold LOCO-CV inside a 10-fold training scheme of 0.759 ± 0.027 when predicting an external test set. In the models which used predicted protein targets as compound descriptors, we identified the most information-rich proteins which agreed with the mechanisms of action and toxicity of nonsteroidal anti-inflammatory drugs (NSAIDs), one of the most important drug classes causing DILI, stress response via TP53 and biotransformation. In addition, we identified multiple proteins involved in xenobiotic metabolism which could be novel DILI-related off-targets, such as CLK1 and DYRK2. Moreover, we derived potential structural alerts for DILI with high precision, including furan and hydrazine derivatives; however, all derived alerts were present in approved drugs and were over specific indicating the need to consider quantitative variables such as dose. CONCLUSION: Using chemical structure-based descriptors such as structural fingerprints and predicted protein targets, DILI prediction models were built with a predictive performance comparable to previous literature. In addition, we derived insights on proteins and pathways statistically (and potentially causally) linked to DILI from these models and inferred new structural alerts related to this adverse endpoint.
    30 schema:genre article
    31 schema:inLanguage en
    32 schema:isAccessibleForFree true
    33 schema:isPartOf N3028d38125a442d2980574d7a57ecfad
    34 N83e7cebe760043fab520288742aa9d27
    35 sg:journal.1036001
    36 schema:keywords CLK1
    37 DILI prediction models
    38 DILI risk
    39 DILIrank annotations
    40 DYRK2
    41 TP53
    42 accuracy
    43 action
    44 addition
    45 adverse endpoints
    46 alerts
    47 analysis
    48 annotation
    49 anti-inflammatory drugs
    50 approach
    51 assessment
    52 better understanding
    53 binarized DILIrank annotations
    54 biotransformation
    55 chemical structure
    56 chemical structure-based descriptors
    57 chemical structure-based models
    58 class
    59 classifier
    60 comparable performance
    61 compound descriptors
    62 compound structure
    63 compounds
    64 concern
    65 critical assessment
    66 cv
    67 data analysis
    68 decisions
    69 derivatives
    70 descriptors
    71 development
    72 diverse pathogenesis
    73 dose
    74 drug classes
    75 drug development
    76 drug-induced liver injury
    77 drugs
    78 endpoint
    79 external test set
    80 fingerprints
    81 forest classifier
    82 furan
    83 good predictivity
    84 high precision
    85 hydrazine derivatives
    86 important drug class
    87 information-rich proteins
    88 injury
    89 insights
    90 interpretability
    91 learning model
    92 literature
    93 liver injury
    94 loco
    95 machine
    96 machine learning models
    97 major safety concern
    98 massive data analysis
    99 meaningful way
    100 mechanism
    101 mechanism of action
    102 mechanistic analysis
    103 metabolism
    104 model
    105 most information-rich proteins
    106 multiple proteins
    107 need
    108 new structural alerts
    109 nonsteroidal anti-inflammatory drugs
    110 order
    111 part
    112 pathogenesis
    113 pathway
    114 performance
    115 potential structural alerts
    116 precision
    117 prediction
    118 prediction model
    119 predictive performance
    120 predictivity
    121 previous literature
    122 problem
    123 protein
    124 protein targets
    125 quantitative variables
    126 random forest classifier
    127 regard
    128 response
    129 risk
    130 risk of DILI
    131 safety concerns
    132 scheme
    133 set
    134 silico models
    135 stress response
    136 structural alerts
    137 structural fingerprints
    138 structure
    139 structure-based descriptors
    140 structure-based model
    141 sufficient predictive performance
    142 target
    143 test set
    144 toxicity
    145 training scheme
    146 understanding
    147 variables
    148 vector machine
    149 vivo DILI risk
    150 way
    151 xenobiotic metabolism
    152 schema:name Prediction and mechanistic analysis of drug-induced liver injury (DILI) based on chemical structure
    153 schema:pagination 6
    154 schema:productId N334ca1fb453a414d82f2414bed7e6679
    155 Na4d25fcac0254a399ca95808adec0b4a
    156 Nffce79bf68f24ec8b7bf07b1428d2ebf
    157 schema:sameAs https://app.dimensions.ai/details/publication/pub.1134679269
    158 https://doi.org/10.1186/s13062-020-00285-0
    159 schema:sdDatePublished 2022-01-01T18:57
    160 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    161 schema:sdPublisher N8b4150569aff4b3eb3d5ce552664457d
    162 schema:url https://doi.org/10.1186/s13062-020-00285-0
    163 sgo:license sg:explorer/license/
    164 sgo:sdDataset articles
    165 rdf:type schema:ScholarlyArticle
    166 N069c2aa9513342369adb0f795a898f9b schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    167 schema:name Chemical and Drug Induced Liver Injury
    168 rdf:type schema:DefinedTerm
    169 N3028d38125a442d2980574d7a57ecfad schema:issueNumber 1
    170 rdf:type schema:PublicationIssue
    171 N319a07ace74f4603995043d343825509 rdf:first sg:person.010176102767.24
    172 rdf:rest N597af7fd34084d4f86c40d1a3df422b9
    173 N334ca1fb453a414d82f2414bed7e6679 schema:name doi
    174 schema:value 10.1186/s13062-020-00285-0
    175 rdf:type schema:PropertyValue
    176 N597af7fd34084d4f86c40d1a3df422b9 rdf:first sg:person.0626547717.06
    177 rdf:rest rdf:nil
    178 N7092f28e0d7e401597a76b5f6337eb2f schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    179 schema:name Models, Biological
    180 rdf:type schema:DefinedTerm
    181 N7d847f23f9df4092a208d2d220ae30c2 rdf:first sg:person.014504771467.30
    182 rdf:rest N9ed4e8e8e11e4a858df4ec4ad2e50800
    183 N83e7cebe760043fab520288742aa9d27 schema:volumeNumber 16
    184 rdf:type schema:PublicationVolume
    185 N8b4150569aff4b3eb3d5ce552664457d schema:name Springer Nature - SN SciGraph project
    186 rdf:type schema:Organization
    187 N9d13d52adc844137b5466cfd77d4f2e2 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    188 schema:name Humans
    189 rdf:type schema:DefinedTerm
    190 N9d336cbe32304c4da36807012d112980 rdf:first sg:person.015316311243.73
    191 rdf:rest N319a07ace74f4603995043d343825509
    192 N9dc115d91f50458ea0d0b96530e57648 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    193 schema:name Machine Learning
    194 rdf:type schema:DefinedTerm
    195 N9ed4e8e8e11e4a858df4ec4ad2e50800 rdf:first sg:person.015302352067.18
    196 rdf:rest Na1bc5aaf334a4aed87012189aa068a2b
    197 Na1bc5aaf334a4aed87012189aa068a2b rdf:first sg:person.016077732467.71
    198 rdf:rest Ne8369957b34e461cabfec9a30ead3f1b
    199 Na4d25fcac0254a399ca95808adec0b4a schema:name dimensions_id
    200 schema:value pub.1134679269
    201 rdf:type schema:PropertyValue
    202 Nc168b44cba114b40ac8a9aabf199b95b rdf:first sg:person.013707411067.25
    203 rdf:rest N7d847f23f9df4092a208d2d220ae30c2
    204 Ncf67bce8320f4c428501131b02ada442 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    205 schema:name Computer Simulation
    206 rdf:type schema:DefinedTerm
    207 Ne8369957b34e461cabfec9a30ead3f1b rdf:first sg:person.01016162114.96
    208 rdf:rest N9d336cbe32304c4da36807012d112980
    209 Nffce79bf68f24ec8b7bf07b1428d2ebf schema:name pubmed_id
    210 schema:value 33461600
    211 rdf:type schema:PropertyValue
    212 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
    213 schema:name Medical and Health Sciences
    214 rdf:type schema:DefinedTerm
    215 anzsrc-for:1115 schema:inDefinedTermSet anzsrc-for:
    216 schema:name Pharmacology and Pharmaceutical Sciences
    217 rdf:type schema:DefinedTerm
    218 sg:grant.7158532 http://pending.schema.org/fundedItem sg:pub.10.1186/s13062-020-00285-0
    219 rdf:type schema:MonetaryGrant
    220 sg:journal.1036001 schema:issn 1745-6150
    221 schema:name Biology Direct
    222 schema:publisher Springer Nature
    223 rdf:type schema:Periodical
    224 sg:person.01016162114.96 schema:affiliation grid-institutes:grid.9027.c
    225 schema:familyName Dolciami
    226 schema:givenName Daniela
    227 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01016162114.96
    228 rdf:type schema:Person
    229 sg:person.010176102767.24 schema:affiliation grid-institutes:grid.5335.0
    230 schema:familyName Yang
    231 schema:givenName Hongbin
    232 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010176102767.24
    233 rdf:type schema:Person
    234 sg:person.013707411067.25 schema:affiliation grid-institutes:grid.5335.0
    235 schema:familyName Liu
    236 schema:givenName Anika
    237 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013707411067.25
    238 rdf:type schema:Person
    239 sg:person.014504771467.30 schema:affiliation grid-institutes:grid.5335.0
    240 schema:familyName Walter
    241 schema:givenName Moritz
    242 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014504771467.30
    243 rdf:type schema:Person
    244 sg:person.015302352067.18 schema:affiliation grid-institutes:grid.5335.0
    245 schema:familyName Wright
    246 schema:givenName Peter
    247 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015302352067.18
    248 rdf:type schema:Person
    249 sg:person.015316311243.73 schema:affiliation grid-institutes:grid.452146.0
    250 schema:familyName Elbasir
    251 schema:givenName Abdurrahman
    252 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015316311243.73
    253 rdf:type schema:Person
    254 sg:person.016077732467.71 schema:affiliation grid-institutes:grid.5335.0
    255 schema:familyName Bartosik
    256 schema:givenName Aleksandra
    257 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016077732467.71
    258 rdf:type schema:Person
    259 sg:person.0626547717.06 schema:affiliation grid-institutes:grid.5335.0
    260 schema:familyName Bender
    261 schema:givenName Andreas
    262 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0626547717.06
    263 rdf:type schema:Person
    264 sg:pub.10.1007/bf00994018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025150743
    265 https://doi.org/10.1007/bf00994018
    266 rdf:type schema:CreativeWork
    267 sg:pub.10.1007/bf02886800 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022490450
    268 https://doi.org/10.1007/bf02886800
    269 rdf:type schema:CreativeWork
    270 sg:pub.10.1007/s00204-018-2178-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1101322873
    271 https://doi.org/10.1007/s00204-018-2178-z
    272 rdf:type schema:CreativeWork
    273 sg:pub.10.1007/s00204-019-02492-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1117608090
    274 https://doi.org/10.1007/s00204-019-02492-9
    275 rdf:type schema:CreativeWork
    276 sg:pub.10.1007/s10822-016-9972-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035406834
    277 https://doi.org/10.1007/s10822-016-9972-6
    278 rdf:type schema:CreativeWork
    279 sg:pub.10.1007/s11064-016-1893-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031818433
    280 https://doi.org/10.1007/s11064-016-1893-1
    281 rdf:type schema:CreativeWork
    282 sg:pub.10.1007/s11696-017-0215-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085869820
    283 https://doi.org/10.1007/s11696-017-0215-7
    284 rdf:type schema:CreativeWork
    285 sg:pub.10.1007/s12291-015-0517-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1014527125
    286 https://doi.org/10.1007/s12291-015-0517-x
    287 rdf:type schema:CreativeWork
    288 sg:pub.10.1023/a:1010933404324 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024739340
    289 https://doi.org/10.1023/a:1010933404324
    290 rdf:type schema:CreativeWork
    291 sg:pub.10.1038/bjc.1974.217 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009186769
    292 https://doi.org/10.1038/bjc.1974.217
    293 rdf:type schema:CreativeWork
    294 sg:pub.10.1038/s41592-019-0686-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1124547608
    295 https://doi.org/10.1038/s41592-019-0686-2
    296 rdf:type schema:CreativeWork
    297 sg:pub.10.1038/s41598-016-0028-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1079403223
    298 https://doi.org/10.1038/s41598-016-0028-x
    299 rdf:type schema:CreativeWork
    300 sg:pub.10.1038/s41598-017-17701-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099597131
    301 https://doi.org/10.1038/s41598-017-17701-7
    302 rdf:type schema:CreativeWork
    303 sg:pub.10.1186/s13321-015-0053-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1002837276
    304 https://doi.org/10.1186/s13321-015-0053-y
    305 rdf:type schema:CreativeWork
    306 sg:pub.10.1186/s13321-015-0069-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013829144
    307 https://doi.org/10.1186/s13321-015-0069-3
    308 rdf:type schema:CreativeWork
    309 sg:pub.10.1186/s13321-015-0098-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1038668816
    310 https://doi.org/10.1186/s13321-015-0098-y
    311 rdf:type schema:CreativeWork
    312 sg:pub.10.1186/s13321-016-0182-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1011404086
    313 https://doi.org/10.1186/s13321-016-0182-y
    314 rdf:type schema:CreativeWork
    315 sg:pub.10.1186/s13321-018-0258-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1100856074
    316 https://doi.org/10.1186/s13321-018-0258-y
    317 rdf:type schema:CreativeWork
    318 grid-institutes:grid.452146.0 schema:alternateName ICT Department, College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar
    319 schema:name Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK
    320 ICT Department, College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar
    321 rdf:type schema:Organization
    322 grid-institutes:grid.5335.0 schema:alternateName Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK
    323 schema:name Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK
    324 rdf:type schema:Organization
    325 grid-institutes:grid.9027.c schema:alternateName Department of Pharmaceutical Sciences, University of Perugia, Via del Liceo 1, 06123 Perugia, Italy
    326 schema:name Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW UK
    327 Department of Pharmaceutical Sciences, University of Perugia, Via del Liceo 1, 06123 Perugia, Italy
    328 rdf:type schema:Organization
     




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


    ...