A novel machine learning-based approach for the computational functional assessment of pharmacogenomic variants View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2021-08-09

AUTHORS

Maria-Theodora Pandi, Maria Koromina, Iordanis Tsafaridis, Sotirios Patsilinakos, Evangelos Christoforou, Peter J. van der Spek, George P. Patrinos

ABSTRACT

BackgroundThe field of pharmacogenomics focuses on the way a person’s genome affects his or her response to a certain dose of a specified medication. The main aim is to utilize this information to guide and personalize the treatment in a way that maximizes the clinical benefits and minimizes the risks for the patients, thus fulfilling the promises of personalized medicine. Technological advances in genome sequencing, combined with the development of improved computational methods for the efficient analysis of the huge amount of generated data, have allowed the fast and inexpensive sequencing of a patient’s genome, hence rendering its incorporation into clinical routine practice a realistic possibility.MethodsThis study exploited thoroughly characterized in functional level SNVs within genes involved in drug metabolism and transport, to train a classifier that would categorize novel variants according to their expected effect on protein functionality. This categorization is based on the available in silico prediction and/or conservation scores, which are selected with the use of recursive feature elimination process. Toward this end, information regarding 190 pharmacovariants was leveraged, alongside with 4 machine learning algorithms, namely AdaBoost, XGBoost, multinomial logistic regression, and random forest, of which the performance was assessed through 5-fold cross validation.ResultsAll models achieved similar performance toward making informed conclusions, with RF model achieving the highest accuracy (85%, 95% CI: 0.79, 0.90), as well as improved overall performance (precision 85%, sensitivity 84%, specificity 94%) and being used for subsequent analyses. When applied on real world WGS data, the selected RF model identified 2 missense variants, expected to lead to decreased function proteins and 1 to increased. As expected, a greater number of variants were highlighted when the approach was used on NGS data derived from targeted resequencing of coding regions. Specifically, 71 variants (out of 156 with sufficient annotation information) were classified as to “Decreased function,” 41 variants as “No” function proteins, and 1 variant in “Increased function.”ConclusionOverall, the proposed RF-based classification model holds promise to lead to an extremely useful variant prioritization and act as a scoring tool with interesting clinical applications in the fields of pharmacogenomics and personalized medicine. More... »

PAGES

51

References to SciGraph publications

  • 2020-12-02. dbNSFP v4: a comprehensive database of transcript-specific functional predictions and annotations for human nonsynonymous and splice-site SNVs in GENOME MEDICINE
  • 2014-05-20. In silico comparative characterization of pharmacogenomic missense variants in BMC GENOMICS
  • 2018-09-12. An optimized prediction framework to assess the functional impact of pharmacogenetic variants in THE PHARMACOGENOMICS JOURNAL
  • 2002. Modern Applied Statistics with S in NONE
  • 2015-03-05. Standards and guidelines for the interpretation of sequence variants: a joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology in GENETICS IN MEDICINE
  • 2015-07-31. Improving the Sequence Ontology terminology for genomic variant annotation in JOURNAL OF BIOMEDICAL SEMANTICS
  • 2001-10. Random Forests in MACHINE LEARNING
  • 2015-01-19. A method for calculating probabilities of fitness consequences for point mutations across the human genome in NATURE GENETICS
  • 2015-04-21. Clinical Association Between Pharmacogenomics and Adverse Drug Reactions in DRUGS
  • 2015-02-24. Pharmacogenomic information in drug labels: European Medicines Agency perspective in THE PHARMACOGENOMICS JOURNAL
  • 2016-04-21. Rare genetic variants in cellular transporters, metabolic enzymes, and nuclear receptors can be important determinants of interindividual differences in drug response in GENETICS IN MEDICINE
  • 2018-05-25. Integrating rare genetic variants into pharmacogenetic drug response predictions in HUMAN GENOMICS
  • 2017-10-26. Novel copy-number variations in pharmacogenes contribute to interindividual differences in drug pharmacokinetics in GENETICS IN MEDICINE
  • 2021-02-04. Prevalence of pharmacogenomic variants in 100 pharmacogenes among Southeast Asian populations under the collaboration of the Southeast Asian Pharmacogenomics Research Network (SEAPharm) in HUMAN GENOME VARIATION
  • 2016-01-04. A spectral approach integrating functional genomic annotations for coding and noncoding variants in NATURE GENETICS
  • 2015-10-14. Pharmacogenomics in the clinic in NATURE
  • 2017-11-27. Pharmacogenomic Biomarkers for Improved Drug Therapy—Recent Progress and Future Developments in THE AAPS JOURNAL
  • 2016-06-06. The Ensembl Variant Effect Predictor in GENOME BIOLOGY
  • 2010-04. A method and server for predicting damaging missense mutations in NATURE METHODS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1186/s40246-021-00352-1

    DOI

    http://dx.doi.org/10.1186/s40246-021-00352-1

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1140286979

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/34372920


    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"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Algorithms", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Computational Biology", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Genomics", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Humans", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Inactivation, Metabolic", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Logistic Models", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Machine Learning", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Pharmacogenetics", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Pharmacogenomic Variants", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Precision Medicine", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Whole Genome Sequencing", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Erasmus University Medical Center, Faculty of Medicine and Health Sciences, Department of Pathology, Bioinformatics Unit, Rotterdam, the Netherlands", 
              "id": "http://www.grid.ac/institutes/grid.5645.2", 
              "name": [
                "Erasmus University Medical Center, Faculty of Medicine and Health Sciences, Department of Pathology, Bioinformatics Unit, Rotterdam, the Netherlands"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Pandi", 
            "givenName": "Maria-Theodora", 
            "id": "sg:person.011714573623.28", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011714573623.28"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "The Golden Helix Foundation, London, UK", 
              "id": "http://www.grid.ac/institutes/grid.491002.e", 
              "name": [
                "Laboratory of Pharmacogenomics and Individualized Therapy, Department of Pharmacy, School of Health Sciences, University of Patras, Patras, Greece", 
                "The Golden Helix Foundation, London, UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Koromina", 
            "givenName": "Maria", 
            "id": "sg:person.016427226004.44", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016427226004.44"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Katharsis Technologies Inc., Chicago, USA", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Katharsis Technologies Inc., Chicago, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Tsafaridis", 
            "givenName": "Iordanis", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Konstantopouleion General Hospital, Athens, Greece", 
              "id": "http://www.grid.ac/institutes/grid.414012.2", 
              "name": [
                "Konstantopouleion General Hospital, Athens, Greece"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Patsilinakos", 
            "givenName": "Sotirios", 
            "id": "sg:person.01125061665.86", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01125061665.86"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Katharsis Technologies Inc., Chicago, USA", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Katharsis Technologies Inc., Chicago, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Christoforou", 
            "givenName": "Evangelos", 
            "id": "sg:person.012050456524.29", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012050456524.29"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Erasmus University Medical Center, Faculty of Medicine and Health Sciences, Department of Pathology, Bioinformatics Unit, Rotterdam, the Netherlands", 
              "id": "http://www.grid.ac/institutes/grid.5645.2", 
              "name": [
                "Erasmus University Medical Center, Faculty of Medicine and Health Sciences, Department of Pathology, Bioinformatics Unit, Rotterdam, the Netherlands"
              ], 
              "type": "Organization"
            }, 
            "familyName": "van der Spek", 
            "givenName": "Peter J.", 
            "id": "sg:person.0772646275.55", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0772646275.55"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Pathology, College of Medicine and Health Sciences, United Arab Emirates University, Al-Ain, United Arab Emirates", 
              "id": "http://www.grid.ac/institutes/grid.43519.3a", 
              "name": [
                "Laboratory of Pharmacogenomics and Individualized Therapy, Department of Pharmacy, School of Health Sciences, University of Patras, Patras, Greece", 
                "Zayed Center of Health Sciences, United Arab Emirates University, Al-Ain, United Arab Emirates", 
                "Department of Pathology, College of Medicine and Health Sciences, United Arab Emirates University, Al-Ain, United Arab Emirates"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Patrinos", 
            "givenName": "George P.", 
            "id": "sg:person.0751124105.99", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0751124105.99"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1038/s41439-021-00135-z", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1135110689", 
              "https://doi.org/10.1038/s41439-021-00135-z"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41397-018-0044-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1106911407", 
              "https://doi.org/10.1038/s41397-018-0044-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-0-387-21706-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035613449", 
              "https://doi.org/10.1007/978-0-387-21706-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/tpj.2014.86", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1053682676", 
              "https://doi.org/10.1038/tpj.2014.86"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13059-016-0974-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1005070991", 
              "https://doi.org/10.1186/s13059-016-0974-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s40265-015-0375-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045414825", 
              "https://doi.org/10.1007/s40265-015-0375-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/gim.2016.33", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007577349", 
              "https://doi.org/10.1038/gim.2016.33"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature15817", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042563527", 
              "https://doi.org/10.1038/nature15817"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nmeth0410-248", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007489634", 
              "https://doi.org/10.1038/nmeth0410-248"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13326-015-0030-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1020579100", 
              "https://doi.org/10.1186/s13326-015-0030-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s40246-018-0157-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1104168578", 
              "https://doi.org/10.1186/s40246-018-0157-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/gim.2017.156", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092352374", 
              "https://doi.org/10.1038/gim.2017.156"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1208/s12248-017-0161-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093037536", 
              "https://doi.org/10.1208/s12248-017-0161-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/ng.3196", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1034264039", 
              "https://doi.org/10.1038/ng.3196"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/1471-2164-15-s4-s4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007273796", 
              "https://doi.org/10.1186/1471-2164-15-s4-s4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/gim.2015.30", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022229472", 
              "https://doi.org/10.1038/gim.2015.30"
            ], 
            "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/s13073-020-00803-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1132950485", 
              "https://doi.org/10.1186/s13073-020-00803-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/ng.3477", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1043158715", 
              "https://doi.org/10.1038/ng.3477"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2021-08-09", 
        "datePublishedReg": "2021-08-09", 
        "description": "BackgroundThe field of pharmacogenomics focuses on the way a person\u2019s genome affects his or her response to a certain dose of a specified medication. The main aim is to utilize this information to guide and personalize the treatment in a way that maximizes the clinical benefits and minimizes the risks for the patients, thus fulfilling the promises of personalized medicine. Technological advances in genome sequencing, combined with the development of improved computational methods for the efficient analysis of the huge amount of generated data, have allowed the fast and inexpensive sequencing of a patient\u2019s genome, hence rendering its incorporation into clinical routine practice a realistic possibility.MethodsThis study exploited thoroughly characterized in functional level SNVs within genes involved in drug metabolism and transport, to train a classifier that would categorize novel variants according to their expected effect on protein functionality. This categorization is based on the available in silico prediction and/or conservation scores, which are selected with the use of recursive feature elimination process. Toward this end, information regarding 190 pharmacovariants was leveraged, alongside with 4 machine learning algorithms, namely AdaBoost, XGBoost, multinomial logistic regression, and random forest, of which the performance was assessed through 5-fold cross validation.ResultsAll models achieved similar performance toward making informed conclusions, with RF model achieving the highest accuracy (85%, 95% CI: 0.79, 0.90), as well as improved overall performance (precision 85%, sensitivity 84%, specificity 94%) and being used for subsequent analyses. When applied on real world WGS data, the selected RF model identified 2 missense variants, expected to lead to decreased function proteins and 1 to increased. As expected, a greater number of variants were highlighted when the approach was used on NGS data derived from targeted resequencing of coding regions. Specifically, 71 variants (out of 156 with sufficient annotation information) were classified as to \u201cDecreased function,\u201d 41 variants as \u201cNo\u201d function proteins, and 1 variant in \u201cIncreased function.\u201dConclusionOverall, the proposed RF-based classification model holds promise to lead to an extremely useful variant prioritization and act as a scoring tool with interesting clinical applications in the fields of pharmacogenomics and personalized medicine.", 
        "genre": "article", 
        "id": "sg:pub.10.1186/s40246-021-00352-1", 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1033252", 
            "issn": [
              "1473-9542", 
              "1479-7364"
            ], 
            "name": "Human Genomics", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "15"
          }
        ], 
        "keywords": [
          "recursive feature elimination process", 
          "novel machine learning-based approach", 
          "machine learning-based approach", 
          "learning-based approach", 
          "feature elimination process", 
          "RF model", 
          "classification model", 
          "huge amount", 
          "random forest", 
          "high accuracy", 
          "efficient analysis", 
          "cross validation", 
          "overall performance", 
          "NGS data", 
          "similar performance", 
          "computational methods", 
          "person's genome", 
          "variant prioritization", 
          "informed conclusions", 
          "AdaBoost", 
          "classifier", 
          "XGBoost", 
          "information", 
          "technological advances", 
          "performance", 
          "interesting clinical applications", 
          "machine", 
          "algorithm", 
          "conservation scores", 
          "personalized medicine", 
          "patient's genome", 
          "functionality", 
          "inexpensive sequencing", 
          "model", 
          "accuracy", 
          "data", 
          "way", 
          "main aim", 
          "categorization", 
          "pharmacogenomic variants", 
          "tool", 
          "applications", 
          "BackgroundThe field", 
          "prioritization", 
          "WGS data", 
          "variants", 
          "validation", 
          "subsequent analysis", 
          "field", 
          "realistic possibility", 
          "prediction", 
          "clinical routine practice", 
          "promise", 
          "advances", 
          "method", 
          "elimination process", 
          "benefits", 
          "novel variants", 
          "number", 
          "process", 
          "use", 
          "end", 
          "field of pharmacogenomics", 
          "function", 
          "amount", 
          "analysis", 
          "development", 
          "forest", 
          "greater number", 
          "logistic regression", 
          "possibility", 
          "clinical application", 
          "multinomial logistic regression", 
          "regression", 
          "silico prediction", 
          "practice", 
          "SNVs", 
          "medicine", 
          "pharmacogenomics", 
          "assessment", 
          "aim", 
          "ResultsAll models", 
          "genome sequencing", 
          "scores", 
          "acts", 
          "region", 
          "routine practice", 
          "study", 
          "protein functionality", 
          "incorporation", 
          "genome", 
          "risk", 
          "approach", 
          "sequencing", 
          "conclusion", 
          "transport", 
          "response", 
          "certain dose", 
          "ConclusionOverall", 
          "function proteins", 
          "effect", 
          "functional assessment", 
          "patients", 
          "missense variants", 
          "medications", 
          "clinical benefit", 
          "treatment", 
          "MethodsThis study", 
          "decreased function", 
          "drug metabolism", 
          "genes", 
          "dose", 
          "protein", 
          "metabolism"
        ], 
        "name": "A novel machine learning-based approach for the computational functional assessment of pharmacogenomic variants", 
        "pagination": "51", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1140286979"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1186/s40246-021-00352-1"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "34372920"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1186/s40246-021-00352-1", 
          "https://app.dimensions.ai/details/publication/pub.1140286979"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-08-04T17:09", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20220804/entities/gbq_results/article/article_876.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1186/s40246-021-00352-1"
      }
    ]
     

    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/s40246-021-00352-1'

    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/s40246-021-00352-1'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s40246-021-00352-1'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s40246-021-00352-1'


     

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

    351 TRIPLES      21 PREDICATES      169 URIs      142 LITERALS      18 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1186/s40246-021-00352-1 schema:about N0474b524a13849c784e0c75c505c01ea
    2 N1778832dbb7c421599850f29016352fd
    3 N21dd4b4f00be4799bc62f0c0d07dc496
    4 N34144793227f4b02a3c87d2cf869ed72
    5 N378c215f0624424d98d293a67265ea2d
    6 N53cd05dc16d04f7f9bce7381a7e01443
    7 N85cb9601c829460ebc05c78c1fdb0160
    8 Nbff66a6bc36b48d188d068ed71a35167
    9 Nc665691f6f284eb9b014cb8c8272e855
    10 Nc690e275dbb74ab3afee33ffe1dc4a34
    11 Nf18a4d319fe848b49cda5bcf3434ac59
    12 anzsrc-for:08
    13 anzsrc-for:0801
    14 schema:author Ne8982af24ff64da29dbf7e5a26dc4057
    15 schema:citation sg:pub.10.1007/978-0-387-21706-2
    16 sg:pub.10.1007/s40265-015-0375-0
    17 sg:pub.10.1023/a:1010933404324
    18 sg:pub.10.1038/gim.2015.30
    19 sg:pub.10.1038/gim.2016.33
    20 sg:pub.10.1038/gim.2017.156
    21 sg:pub.10.1038/nature15817
    22 sg:pub.10.1038/ng.3196
    23 sg:pub.10.1038/ng.3477
    24 sg:pub.10.1038/nmeth0410-248
    25 sg:pub.10.1038/s41397-018-0044-2
    26 sg:pub.10.1038/s41439-021-00135-z
    27 sg:pub.10.1038/tpj.2014.86
    28 sg:pub.10.1186/1471-2164-15-s4-s4
    29 sg:pub.10.1186/s13059-016-0974-4
    30 sg:pub.10.1186/s13073-020-00803-9
    31 sg:pub.10.1186/s13326-015-0030-4
    32 sg:pub.10.1186/s40246-018-0157-3
    33 sg:pub.10.1208/s12248-017-0161-x
    34 schema:datePublished 2021-08-09
    35 schema:datePublishedReg 2021-08-09
    36 schema:description BackgroundThe field of pharmacogenomics focuses on the way a person’s genome affects his or her response to a certain dose of a specified medication. The main aim is to utilize this information to guide and personalize the treatment in a way that maximizes the clinical benefits and minimizes the risks for the patients, thus fulfilling the promises of personalized medicine. Technological advances in genome sequencing, combined with the development of improved computational methods for the efficient analysis of the huge amount of generated data, have allowed the fast and inexpensive sequencing of a patient’s genome, hence rendering its incorporation into clinical routine practice a realistic possibility.MethodsThis study exploited thoroughly characterized in functional level SNVs within genes involved in drug metabolism and transport, to train a classifier that would categorize novel variants according to their expected effect on protein functionality. This categorization is based on the available in silico prediction and/or conservation scores, which are selected with the use of recursive feature elimination process. Toward this end, information regarding 190 pharmacovariants was leveraged, alongside with 4 machine learning algorithms, namely AdaBoost, XGBoost, multinomial logistic regression, and random forest, of which the performance was assessed through 5-fold cross validation.ResultsAll models achieved similar performance toward making informed conclusions, with RF model achieving the highest accuracy (85%, 95% CI: 0.79, 0.90), as well as improved overall performance (precision 85%, sensitivity 84%, specificity 94%) and being used for subsequent analyses. When applied on real world WGS data, the selected RF model identified 2 missense variants, expected to lead to decreased function proteins and 1 to increased. As expected, a greater number of variants were highlighted when the approach was used on NGS data derived from targeted resequencing of coding regions. Specifically, 71 variants (out of 156 with sufficient annotation information) were classified as to “Decreased function,” 41 variants as “No” function proteins, and 1 variant in “Increased function.”ConclusionOverall, the proposed RF-based classification model holds promise to lead to an extremely useful variant prioritization and act as a scoring tool with interesting clinical applications in the fields of pharmacogenomics and personalized medicine.
    37 schema:genre article
    38 schema:isAccessibleForFree true
    39 schema:isPartOf Nf7184e43ea454d0ba7674e49da91a0d3
    40 Nfb20f2f445d64beb90894b4d17e64b13
    41 sg:journal.1033252
    42 schema:keywords AdaBoost
    43 BackgroundThe field
    44 ConclusionOverall
    45 MethodsThis study
    46 NGS data
    47 RF model
    48 ResultsAll models
    49 SNVs
    50 WGS data
    51 XGBoost
    52 accuracy
    53 acts
    54 advances
    55 aim
    56 algorithm
    57 amount
    58 analysis
    59 applications
    60 approach
    61 assessment
    62 benefits
    63 categorization
    64 certain dose
    65 classification model
    66 classifier
    67 clinical application
    68 clinical benefit
    69 clinical routine practice
    70 computational methods
    71 conclusion
    72 conservation scores
    73 cross validation
    74 data
    75 decreased function
    76 development
    77 dose
    78 drug metabolism
    79 effect
    80 efficient analysis
    81 elimination process
    82 end
    83 feature elimination process
    84 field
    85 field of pharmacogenomics
    86 forest
    87 function
    88 function proteins
    89 functional assessment
    90 functionality
    91 genes
    92 genome
    93 genome sequencing
    94 greater number
    95 high accuracy
    96 huge amount
    97 incorporation
    98 inexpensive sequencing
    99 information
    100 informed conclusions
    101 interesting clinical applications
    102 learning-based approach
    103 logistic regression
    104 machine
    105 machine learning-based approach
    106 main aim
    107 medications
    108 medicine
    109 metabolism
    110 method
    111 missense variants
    112 model
    113 multinomial logistic regression
    114 novel machine learning-based approach
    115 novel variants
    116 number
    117 overall performance
    118 patient's genome
    119 patients
    120 performance
    121 person's genome
    122 personalized medicine
    123 pharmacogenomic variants
    124 pharmacogenomics
    125 possibility
    126 practice
    127 prediction
    128 prioritization
    129 process
    130 promise
    131 protein
    132 protein functionality
    133 random forest
    134 realistic possibility
    135 recursive feature elimination process
    136 region
    137 regression
    138 response
    139 risk
    140 routine practice
    141 scores
    142 sequencing
    143 silico prediction
    144 similar performance
    145 study
    146 subsequent analysis
    147 technological advances
    148 tool
    149 transport
    150 treatment
    151 use
    152 validation
    153 variant prioritization
    154 variants
    155 way
    156 schema:name A novel machine learning-based approach for the computational functional assessment of pharmacogenomic variants
    157 schema:pagination 51
    158 schema:productId N15faf37a780446f8872267c41ed4fd41
    159 Nd7f4af509d824ccd96a0e196c9e78d09
    160 Neeabf77caf494f66b4f421020be232af
    161 schema:sameAs https://app.dimensions.ai/details/publication/pub.1140286979
    162 https://doi.org/10.1186/s40246-021-00352-1
    163 schema:sdDatePublished 2022-08-04T17:09
    164 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    165 schema:sdPublisher N3cfe8a7342b44251b54d9754bb44e684
    166 schema:url https://doi.org/10.1186/s40246-021-00352-1
    167 sgo:license sg:explorer/license/
    168 sgo:sdDataset articles
    169 rdf:type schema:ScholarlyArticle
    170 N0474b524a13849c784e0c75c505c01ea schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    171 schema:name Precision Medicine
    172 rdf:type schema:DefinedTerm
    173 N15faf37a780446f8872267c41ed4fd41 schema:name dimensions_id
    174 schema:value pub.1140286979
    175 rdf:type schema:PropertyValue
    176 N1778832dbb7c421599850f29016352fd schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    177 schema:name Computational Biology
    178 rdf:type schema:DefinedTerm
    179 N21dd4b4f00be4799bc62f0c0d07dc496 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    180 schema:name Logistic Models
    181 rdf:type schema:DefinedTerm
    182 N34144793227f4b02a3c87d2cf869ed72 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    183 schema:name Genomics
    184 rdf:type schema:DefinedTerm
    185 N378c215f0624424d98d293a67265ea2d schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    186 schema:name Pharmacogenetics
    187 rdf:type schema:DefinedTerm
    188 N37a7ab9a9e2e4d8f8a34b8bacbec920b rdf:first sg:person.0772646275.55
    189 rdf:rest Na0dab13f00b9494dae06f25303ddd1ac
    190 N3a74f0a6a82a45089d904da2a09fc753 rdf:first sg:person.016427226004.44
    191 rdf:rest Nfeccee3aadc345fd84b395f3e3284b8a
    192 N3cfe8a7342b44251b54d9754bb44e684 schema:name Springer Nature - SN SciGraph project
    193 rdf:type schema:Organization
    194 N53cd05dc16d04f7f9bce7381a7e01443 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    195 schema:name Algorithms
    196 rdf:type schema:DefinedTerm
    197 N6dd12f2093c14e0e85177aeed9e0e06a rdf:first sg:person.012050456524.29
    198 rdf:rest N37a7ab9a9e2e4d8f8a34b8bacbec920b
    199 N85cb9601c829460ebc05c78c1fdb0160 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    200 schema:name Inactivation, Metabolic
    201 rdf:type schema:DefinedTerm
    202 N8dc886367d7e42c6aa6577402b3ea92f schema:affiliation grid-institutes:None
    203 schema:familyName Tsafaridis
    204 schema:givenName Iordanis
    205 rdf:type schema:Person
    206 Na0dab13f00b9494dae06f25303ddd1ac rdf:first sg:person.0751124105.99
    207 rdf:rest rdf:nil
    208 Nbff66a6bc36b48d188d068ed71a35167 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    209 schema:name Machine Learning
    210 rdf:type schema:DefinedTerm
    211 Nc665691f6f284eb9b014cb8c8272e855 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    212 schema:name Whole Genome Sequencing
    213 rdf:type schema:DefinedTerm
    214 Nc690e275dbb74ab3afee33ffe1dc4a34 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    215 schema:name Humans
    216 rdf:type schema:DefinedTerm
    217 Nd7f4af509d824ccd96a0e196c9e78d09 schema:name pubmed_id
    218 schema:value 34372920
    219 rdf:type schema:PropertyValue
    220 Ne193e768ab4d4878a34981051b2cbce5 rdf:first sg:person.01125061665.86
    221 rdf:rest N6dd12f2093c14e0e85177aeed9e0e06a
    222 Ne8982af24ff64da29dbf7e5a26dc4057 rdf:first sg:person.011714573623.28
    223 rdf:rest N3a74f0a6a82a45089d904da2a09fc753
    224 Neeabf77caf494f66b4f421020be232af schema:name doi
    225 schema:value 10.1186/s40246-021-00352-1
    226 rdf:type schema:PropertyValue
    227 Nf18a4d319fe848b49cda5bcf3434ac59 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    228 schema:name Pharmacogenomic Variants
    229 rdf:type schema:DefinedTerm
    230 Nf7184e43ea454d0ba7674e49da91a0d3 schema:issueNumber 1
    231 rdf:type schema:PublicationIssue
    232 Nfb20f2f445d64beb90894b4d17e64b13 schema:volumeNumber 15
    233 rdf:type schema:PublicationVolume
    234 Nfeccee3aadc345fd84b395f3e3284b8a rdf:first N8dc886367d7e42c6aa6577402b3ea92f
    235 rdf:rest Ne193e768ab4d4878a34981051b2cbce5
    236 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    237 schema:name Information and Computing Sciences
    238 rdf:type schema:DefinedTerm
    239 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    240 schema:name Artificial Intelligence and Image Processing
    241 rdf:type schema:DefinedTerm
    242 sg:journal.1033252 schema:issn 1473-9542
    243 1479-7364
    244 schema:name Human Genomics
    245 schema:publisher Springer Nature
    246 rdf:type schema:Periodical
    247 sg:person.01125061665.86 schema:affiliation grid-institutes:grid.414012.2
    248 schema:familyName Patsilinakos
    249 schema:givenName Sotirios
    250 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01125061665.86
    251 rdf:type schema:Person
    252 sg:person.011714573623.28 schema:affiliation grid-institutes:grid.5645.2
    253 schema:familyName Pandi
    254 schema:givenName Maria-Theodora
    255 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011714573623.28
    256 rdf:type schema:Person
    257 sg:person.012050456524.29 schema:affiliation grid-institutes:None
    258 schema:familyName Christoforou
    259 schema:givenName Evangelos
    260 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012050456524.29
    261 rdf:type schema:Person
    262 sg:person.016427226004.44 schema:affiliation grid-institutes:grid.491002.e
    263 schema:familyName Koromina
    264 schema:givenName Maria
    265 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016427226004.44
    266 rdf:type schema:Person
    267 sg:person.0751124105.99 schema:affiliation grid-institutes:grid.43519.3a
    268 schema:familyName Patrinos
    269 schema:givenName George P.
    270 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0751124105.99
    271 rdf:type schema:Person
    272 sg:person.0772646275.55 schema:affiliation grid-institutes:grid.5645.2
    273 schema:familyName van der Spek
    274 schema:givenName Peter J.
    275 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0772646275.55
    276 rdf:type schema:Person
    277 sg:pub.10.1007/978-0-387-21706-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035613449
    278 https://doi.org/10.1007/978-0-387-21706-2
    279 rdf:type schema:CreativeWork
    280 sg:pub.10.1007/s40265-015-0375-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045414825
    281 https://doi.org/10.1007/s40265-015-0375-0
    282 rdf:type schema:CreativeWork
    283 sg:pub.10.1023/a:1010933404324 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024739340
    284 https://doi.org/10.1023/a:1010933404324
    285 rdf:type schema:CreativeWork
    286 sg:pub.10.1038/gim.2015.30 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022229472
    287 https://doi.org/10.1038/gim.2015.30
    288 rdf:type schema:CreativeWork
    289 sg:pub.10.1038/gim.2016.33 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007577349
    290 https://doi.org/10.1038/gim.2016.33
    291 rdf:type schema:CreativeWork
    292 sg:pub.10.1038/gim.2017.156 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092352374
    293 https://doi.org/10.1038/gim.2017.156
    294 rdf:type schema:CreativeWork
    295 sg:pub.10.1038/nature15817 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042563527
    296 https://doi.org/10.1038/nature15817
    297 rdf:type schema:CreativeWork
    298 sg:pub.10.1038/ng.3196 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034264039
    299 https://doi.org/10.1038/ng.3196
    300 rdf:type schema:CreativeWork
    301 sg:pub.10.1038/ng.3477 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043158715
    302 https://doi.org/10.1038/ng.3477
    303 rdf:type schema:CreativeWork
    304 sg:pub.10.1038/nmeth0410-248 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007489634
    305 https://doi.org/10.1038/nmeth0410-248
    306 rdf:type schema:CreativeWork
    307 sg:pub.10.1038/s41397-018-0044-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1106911407
    308 https://doi.org/10.1038/s41397-018-0044-2
    309 rdf:type schema:CreativeWork
    310 sg:pub.10.1038/s41439-021-00135-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1135110689
    311 https://doi.org/10.1038/s41439-021-00135-z
    312 rdf:type schema:CreativeWork
    313 sg:pub.10.1038/tpj.2014.86 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053682676
    314 https://doi.org/10.1038/tpj.2014.86
    315 rdf:type schema:CreativeWork
    316 sg:pub.10.1186/1471-2164-15-s4-s4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007273796
    317 https://doi.org/10.1186/1471-2164-15-s4-s4
    318 rdf:type schema:CreativeWork
    319 sg:pub.10.1186/s13059-016-0974-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005070991
    320 https://doi.org/10.1186/s13059-016-0974-4
    321 rdf:type schema:CreativeWork
    322 sg:pub.10.1186/s13073-020-00803-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1132950485
    323 https://doi.org/10.1186/s13073-020-00803-9
    324 rdf:type schema:CreativeWork
    325 sg:pub.10.1186/s13326-015-0030-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020579100
    326 https://doi.org/10.1186/s13326-015-0030-4
    327 rdf:type schema:CreativeWork
    328 sg:pub.10.1186/s40246-018-0157-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1104168578
    329 https://doi.org/10.1186/s40246-018-0157-3
    330 rdf:type schema:CreativeWork
    331 sg:pub.10.1208/s12248-017-0161-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1093037536
    332 https://doi.org/10.1208/s12248-017-0161-x
    333 rdf:type schema:CreativeWork
    334 grid-institutes:None schema:alternateName Katharsis Technologies Inc., Chicago, USA
    335 schema:name Katharsis Technologies Inc., Chicago, USA
    336 rdf:type schema:Organization
    337 grid-institutes:grid.414012.2 schema:alternateName Konstantopouleion General Hospital, Athens, Greece
    338 schema:name Konstantopouleion General Hospital, Athens, Greece
    339 rdf:type schema:Organization
    340 grid-institutes:grid.43519.3a schema:alternateName Department of Pathology, College of Medicine and Health Sciences, United Arab Emirates University, Al-Ain, United Arab Emirates
    341 schema:name Department of Pathology, College of Medicine and Health Sciences, United Arab Emirates University, Al-Ain, United Arab Emirates
    342 Laboratory of Pharmacogenomics and Individualized Therapy, Department of Pharmacy, School of Health Sciences, University of Patras, Patras, Greece
    343 Zayed Center of Health Sciences, United Arab Emirates University, Al-Ain, United Arab Emirates
    344 rdf:type schema:Organization
    345 grid-institutes:grid.491002.e schema:alternateName The Golden Helix Foundation, London, UK
    346 schema:name Laboratory of Pharmacogenomics and Individualized Therapy, Department of Pharmacy, School of Health Sciences, University of Patras, Patras, Greece
    347 The Golden Helix Foundation, London, UK
    348 rdf:type schema:Organization
    349 grid-institutes:grid.5645.2 schema:alternateName Erasmus University Medical Center, Faculty of Medicine and Health Sciences, Department of Pathology, Bioinformatics Unit, Rotterdam, the Netherlands
    350 schema:name Erasmus University Medical Center, Faculty of Medicine and Health Sciences, Department of Pathology, Bioinformatics Unit, Rotterdam, the Netherlands
    351 rdf:type schema:Organization
     




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


    ...