AZOrange - High performance open source machine learning for QSAR modeling in a graphical programming environment View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2011-12

AUTHORS

Jonna C Stålring, Lars A Carlsson, Pedro Almeida, Scott Boyer

ABSTRACT

BACKGROUND: Machine learning has a vast range of applications. In particular, advanced machine learning methods are routinely and increasingly used in quantitative structure activity relationship (QSAR) modeling. QSAR data sets often encompass tens of thousands of compounds and the size of proprietary, as well as public data sets, is rapidly growing. Hence, there is a demand for computationally efficient machine learning algorithms, easily available to researchers without extensive machine learning knowledge. In granting the scientific principles of transparency and reproducibility, Open Source solutions are increasingly acknowledged by regulatory authorities. Thus, an Open Source state-of-the-art high performance machine learning platform, interfacing multiple, customized machine learning algorithms for both graphical programming and scripting, to be used for large scale development of QSAR models of regulatory quality, is of great value to the QSAR community. RESULTS: This paper describes the implementation of the Open Source machine learning package AZOrange. AZOrange is specially developed to support batch generation of QSAR models in providing the full work flow of QSAR modeling, from descriptor calculation to automated model building, validation and selection. The automated work flow relies upon the customization of the machine learning algorithms and a generalized, automated model hyper-parameter selection process. Several high performance machine learning algorithms are interfaced for efficient data set specific selection of the statistical method, promoting model accuracy. Using the high performance machine learning algorithms of AZOrange does not require programming knowledge as flexible applications can be created, not only at a scripting level, but also in a graphical programming environment. CONCLUSIONS: AZOrange is a step towards meeting the needs for an Open Source high performance machine learning platform, supporting the efficient development of highly accurate QSAR models fulfilling regulatory requirements. More... »

PAGES

28

References to SciGraph publications

  • 2004. Orange: From Experimental Machine Learning to Interactive Data Mining in KNOWLEDGE DISCOVERY IN DATABASES: PKDD 2004
  • 2003-03. Antiherpesvirus drugs: a promising spectrum of new drugs and drug targets in NATURE REVIEWS DRUG DISCOVERY
  • 2001-10. Random Forests in MACHINE LEARNING
  • 2008-12. Cinfony – combining Open Source cheminformatics toolkits behind a common interface in CHEMISTRY CENTRAL JOURNAL
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1186/1758-2946-3-28

    DOI

    http://dx.doi.org/10.1186/1758-2946-3-28

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1004778394

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/21798025


    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/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "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"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "AstraZeneca (Sweden)", 
              "id": "https://www.grid.ac/institutes/grid.418151.8", 
              "name": [
                "Computational Toxicology, Global Safety Assessment, AstraZeneca R&D, Pepparedsleden 1, 431 53, M\u00f6lndal, Sweden"
              ], 
              "type": "Organization"
            }, 
            "familyName": "St\u00e5lring", 
            "givenName": "Jonna C", 
            "id": "sg:person.01256123446.46", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01256123446.46"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "AstraZeneca (Sweden)", 
              "id": "https://www.grid.ac/institutes/grid.418151.8", 
              "name": [
                "Computational Toxicology, Global Safety Assessment, AstraZeneca R&D, Pepparedsleden 1, 431 53, M\u00f6lndal, Sweden"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Carlsson", 
            "givenName": "Lars A", 
            "id": "sg:person.01320336524.68", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01320336524.68"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "EngInMotion Ltd, Avenida Infante D. Henrique, n. 145, 3510-070, Viseu, Portugal"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Almeida", 
            "givenName": "Pedro", 
            "id": "sg:person.01150341743.16", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01150341743.16"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "AstraZeneca (Sweden)", 
              "id": "https://www.grid.ac/institutes/grid.418151.8", 
              "name": [
                "Computational Toxicology, Global Safety Assessment, AstraZeneca R&D, Pepparedsleden 1, 431 53, M\u00f6lndal, Sweden"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Boyer", 
            "givenName": "Scott", 
            "id": "sg:person.01032510371.14", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01032510371.14"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1145/1163641.1163647", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001835647"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3169/itej.61.1602", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019540576"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3169/itej.61.1602", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019540576"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0893-6080(98)00010-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024491244"
            ], 
            "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.10.1038/nrd1032", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027720279", 
              "https://doi.org/10.1038/nrd1032"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nrd1032", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027720279", 
              "https://doi.org/10.1038/nrd1032"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1002/qsar.200610093", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028066543"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1656274.1656278", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028526411"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1021/ci025584y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1033183422"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1021/ci025584y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1033183422"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-30116-5_58", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039779667", 
              "https://doi.org/10.1007/978-3-540-30116-5_58"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/1752-153x-2-24", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040062769", 
              "https://doi.org/10.1186/1752-153x-2-24"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1021/ci600332j", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1055404111"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1021/ci600332j", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1055404111"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1021/jm049254b", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1055948967"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1021/jm049254b", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1055948967"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2174/138620706776055539", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1069174265"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2011-12", 
        "datePublishedReg": "2011-12-01", 
        "description": "BACKGROUND: Machine learning has a vast range of applications. In particular, advanced machine learning methods are routinely and increasingly used in quantitative structure activity relationship (QSAR) modeling. QSAR data sets often encompass tens of thousands of compounds and the size of proprietary, as well as public data sets, is rapidly growing. Hence, there is a demand for computationally efficient machine learning algorithms, easily available to researchers without extensive machine learning knowledge. In granting the scientific principles of transparency and reproducibility, Open Source solutions are increasingly acknowledged by regulatory authorities. Thus, an Open Source state-of-the-art high performance machine learning platform, interfacing multiple, customized machine learning algorithms for both graphical programming and scripting, to be used for large scale development of QSAR models of regulatory quality, is of great value to the QSAR community.\nRESULTS: This paper describes the implementation of the Open Source machine learning package AZOrange. AZOrange is specially developed to support batch generation of QSAR models in providing the full work flow of QSAR modeling, from descriptor calculation to automated model building, validation and selection. The automated work flow relies upon the customization of the machine learning algorithms and a generalized, automated model hyper-parameter selection process. Several high performance machine learning algorithms are interfaced for efficient data set specific selection of the statistical method, promoting model accuracy. Using the high performance machine learning algorithms of AZOrange does not require programming knowledge as flexible applications can be created, not only at a scripting level, but also in a graphical programming environment.\nCONCLUSIONS: AZOrange is a step towards meeting the needs for an Open Source high performance machine learning platform, supporting the efficient development of highly accurate QSAR models fulfilling regulatory requirements.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1186/1758-2946-3-28", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1042252", 
            "issn": [
              "1758-2946"
            ], 
            "name": "Journal of Cheminformatics", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "3"
          }
        ], 
        "name": "AZOrange - High performance open source machine learning for QSAR modeling in a graphical programming environment", 
        "pagination": "28", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "16c4ab40a0f07b7d0f41c575db16c42e41a4307b11b77a8985da9026e0322c99"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "21798025"
            ]
          }, 
          {
            "name": "nlm_unique_id", 
            "type": "PropertyValue", 
            "value": [
              "101516718"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1186/1758-2946-3-28"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1004778394"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1186/1758-2946-3-28", 
          "https://app.dimensions.ai/details/publication/pub.1004778394"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-10T14:09", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8660_00000510.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "http://link.springer.com/10.1186%2F1758-2946-3-28"
      }
    ]
     

    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.10.1186/1758-2946-3-28'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/1758-2946-3-28'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/1758-2946-3-28'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/1758-2946-3-28'


     

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

    134 TRIPLES      21 PREDICATES      42 URIs      21 LITERALS      9 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1186/1758-2946-3-28 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N948c7907cfdb4fd5b7293eef0475efc6
    4 schema:citation sg:pub.10.1007/978-3-540-30116-5_58
    5 sg:pub.10.1023/a:1010933404324
    6 sg:pub.10.1038/nrd1032
    7 sg:pub.10.1186/1752-153x-2-24
    8 https://doi.org/10.1002/qsar.200610093
    9 https://doi.org/10.1016/s0893-6080(98)00010-0
    10 https://doi.org/10.1021/ci025584y
    11 https://doi.org/10.1021/ci600332j
    12 https://doi.org/10.1021/jm049254b
    13 https://doi.org/10.1145/1163641.1163647
    14 https://doi.org/10.1145/1656274.1656278
    15 https://doi.org/10.2174/138620706776055539
    16 https://doi.org/10.3169/itej.61.1602
    17 schema:datePublished 2011-12
    18 schema:datePublishedReg 2011-12-01
    19 schema:description BACKGROUND: Machine learning has a vast range of applications. In particular, advanced machine learning methods are routinely and increasingly used in quantitative structure activity relationship (QSAR) modeling. QSAR data sets often encompass tens of thousands of compounds and the size of proprietary, as well as public data sets, is rapidly growing. Hence, there is a demand for computationally efficient machine learning algorithms, easily available to researchers without extensive machine learning knowledge. In granting the scientific principles of transparency and reproducibility, Open Source solutions are increasingly acknowledged by regulatory authorities. Thus, an Open Source state-of-the-art high performance machine learning platform, interfacing multiple, customized machine learning algorithms for both graphical programming and scripting, to be used for large scale development of QSAR models of regulatory quality, is of great value to the QSAR community. RESULTS: This paper describes the implementation of the Open Source machine learning package AZOrange. AZOrange is specially developed to support batch generation of QSAR models in providing the full work flow of QSAR modeling, from descriptor calculation to automated model building, validation and selection. The automated work flow relies upon the customization of the machine learning algorithms and a generalized, automated model hyper-parameter selection process. Several high performance machine learning algorithms are interfaced for efficient data set specific selection of the statistical method, promoting model accuracy. Using the high performance machine learning algorithms of AZOrange does not require programming knowledge as flexible applications can be created, not only at a scripting level, but also in a graphical programming environment. CONCLUSIONS: AZOrange is a step towards meeting the needs for an Open Source high performance machine learning platform, supporting the efficient development of highly accurate QSAR models fulfilling regulatory requirements.
    20 schema:genre research_article
    21 schema:inLanguage en
    22 schema:isAccessibleForFree true
    23 schema:isPartOf N9ca942ed4a5943619ea3bded84890830
    24 Ncf5e3de8981343edbc9d10628764ebf7
    25 sg:journal.1042252
    26 schema:name AZOrange - High performance open source machine learning for QSAR modeling in a graphical programming environment
    27 schema:pagination 28
    28 schema:productId N4d45572b0a734422bf760b49a4680ea3
    29 N4fcf353cfd4445d09609ca2b264f7a76
    30 N65846a19b7994558b45e08c411c83b4a
    31 N6dce798fdd844848af68930b101f961f
    32 N7dc6778cc3224ec8a96afe7ae3dbb197
    33 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004778394
    34 https://doi.org/10.1186/1758-2946-3-28
    35 schema:sdDatePublished 2019-04-10T14:09
    36 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    37 schema:sdPublisher Nd790e9a217254f57a54a32b6c951ff1b
    38 schema:url http://link.springer.com/10.1186%2F1758-2946-3-28
    39 sgo:license sg:explorer/license/
    40 sgo:sdDataset articles
    41 rdf:type schema:ScholarlyArticle
    42 N2c41925b38b24f68b8f6b6a14d515303 rdf:first sg:person.01320336524.68
    43 rdf:rest Ndf69fded1e8b4feb8a485910e4f67d57
    44 N4d45572b0a734422bf760b49a4680ea3 schema:name readcube_id
    45 schema:value 16c4ab40a0f07b7d0f41c575db16c42e41a4307b11b77a8985da9026e0322c99
    46 rdf:type schema:PropertyValue
    47 N4fcf353cfd4445d09609ca2b264f7a76 schema:name nlm_unique_id
    48 schema:value 101516718
    49 rdf:type schema:PropertyValue
    50 N65846a19b7994558b45e08c411c83b4a schema:name dimensions_id
    51 schema:value pub.1004778394
    52 rdf:type schema:PropertyValue
    53 N6dce798fdd844848af68930b101f961f schema:name pubmed_id
    54 schema:value 21798025
    55 rdf:type schema:PropertyValue
    56 N7dc6778cc3224ec8a96afe7ae3dbb197 schema:name doi
    57 schema:value 10.1186/1758-2946-3-28
    58 rdf:type schema:PropertyValue
    59 N948c7907cfdb4fd5b7293eef0475efc6 rdf:first sg:person.01256123446.46
    60 rdf:rest N2c41925b38b24f68b8f6b6a14d515303
    61 N9839ab872c1f4c9abcf6bef6f50ad31e schema:name EngInMotion Ltd, Avenida Infante D. Henrique, n. 145, 3510-070, Viseu, Portugal
    62 rdf:type schema:Organization
    63 N9ca942ed4a5943619ea3bded84890830 schema:issueNumber 1
    64 rdf:type schema:PublicationIssue
    65 Nc9f8fc1bcd1e4d1f860b8a74ae9af45a rdf:first sg:person.01032510371.14
    66 rdf:rest rdf:nil
    67 Ncf5e3de8981343edbc9d10628764ebf7 schema:volumeNumber 3
    68 rdf:type schema:PublicationVolume
    69 Nd790e9a217254f57a54a32b6c951ff1b schema:name Springer Nature - SN SciGraph project
    70 rdf:type schema:Organization
    71 Ndf69fded1e8b4feb8a485910e4f67d57 rdf:first sg:person.01150341743.16
    72 rdf:rest Nc9f8fc1bcd1e4d1f860b8a74ae9af45a
    73 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    74 schema:name Information and Computing Sciences
    75 rdf:type schema:DefinedTerm
    76 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    77 schema:name Artificial Intelligence and Image Processing
    78 rdf:type schema:DefinedTerm
    79 sg:journal.1042252 schema:issn 1758-2946
    80 schema:name Journal of Cheminformatics
    81 rdf:type schema:Periodical
    82 sg:person.01032510371.14 schema:affiliation https://www.grid.ac/institutes/grid.418151.8
    83 schema:familyName Boyer
    84 schema:givenName Scott
    85 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01032510371.14
    86 rdf:type schema:Person
    87 sg:person.01150341743.16 schema:affiliation N9839ab872c1f4c9abcf6bef6f50ad31e
    88 schema:familyName Almeida
    89 schema:givenName Pedro
    90 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01150341743.16
    91 rdf:type schema:Person
    92 sg:person.01256123446.46 schema:affiliation https://www.grid.ac/institutes/grid.418151.8
    93 schema:familyName Stålring
    94 schema:givenName Jonna C
    95 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01256123446.46
    96 rdf:type schema:Person
    97 sg:person.01320336524.68 schema:affiliation https://www.grid.ac/institutes/grid.418151.8
    98 schema:familyName Carlsson
    99 schema:givenName Lars A
    100 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01320336524.68
    101 rdf:type schema:Person
    102 sg:pub.10.1007/978-3-540-30116-5_58 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039779667
    103 https://doi.org/10.1007/978-3-540-30116-5_58
    104 rdf:type schema:CreativeWork
    105 sg:pub.10.1023/a:1010933404324 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024739340
    106 https://doi.org/10.1023/a:1010933404324
    107 rdf:type schema:CreativeWork
    108 sg:pub.10.1038/nrd1032 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027720279
    109 https://doi.org/10.1038/nrd1032
    110 rdf:type schema:CreativeWork
    111 sg:pub.10.1186/1752-153x-2-24 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040062769
    112 https://doi.org/10.1186/1752-153x-2-24
    113 rdf:type schema:CreativeWork
    114 https://doi.org/10.1002/qsar.200610093 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028066543
    115 rdf:type schema:CreativeWork
    116 https://doi.org/10.1016/s0893-6080(98)00010-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024491244
    117 rdf:type schema:CreativeWork
    118 https://doi.org/10.1021/ci025584y schema:sameAs https://app.dimensions.ai/details/publication/pub.1033183422
    119 rdf:type schema:CreativeWork
    120 https://doi.org/10.1021/ci600332j schema:sameAs https://app.dimensions.ai/details/publication/pub.1055404111
    121 rdf:type schema:CreativeWork
    122 https://doi.org/10.1021/jm049254b schema:sameAs https://app.dimensions.ai/details/publication/pub.1055948967
    123 rdf:type schema:CreativeWork
    124 https://doi.org/10.1145/1163641.1163647 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001835647
    125 rdf:type schema:CreativeWork
    126 https://doi.org/10.1145/1656274.1656278 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028526411
    127 rdf:type schema:CreativeWork
    128 https://doi.org/10.2174/138620706776055539 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069174265
    129 rdf:type schema:CreativeWork
    130 https://doi.org/10.3169/itej.61.1602 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019540576
    131 rdf:type schema:CreativeWork
    132 https://www.grid.ac/institutes/grid.418151.8 schema:alternateName AstraZeneca (Sweden)
    133 schema:name Computational Toxicology, Global Safety Assessment, AstraZeneca R&D, Pepparedsleden 1, 431 53, Mölndal, Sweden
    134 rdf:type schema:Organization
     




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


    ...