Ontology type: schema:ScholarlyArticle Open Access: True
2021-08-09
AUTHORSMaria-Theodora Pandi, Maria Koromina, Iordanis Tsafaridis, Sotirios Patsilinakos, Evangelos Christoforou, Peter J. van der Spek, George P. Patrinos
ABSTRACTBackgroundThe 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... »
PAGES51
http://scigraph.springernature.com/pub.10.1186/s40246-021-00352-1
DOIhttp://dx.doi.org/10.1186/s40246-021-00352-1
DIMENSIONShttps://app.dimensions.ai/details/publication/pub.1140286979
PUBMEDhttps://www.ncbi.nlm.nih.gov/pubmed/34372920
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
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