Support vector inductive logic programming outperforms the naive Bayes classifier and inductive logic programming for the classification of bioactive chemical ... View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2007-05

AUTHORS

Edward O. Cannon, Ata Amini, Andreas Bender, Michael J. E. Sternberg, Stephen H. Muggleton, Robert C. Glen, John B. O. Mitchell

ABSTRACT

We investigate the classification performance of circular fingerprints in combination with the Naive Bayes Classifier (MP2D), Inductive Logic Programming (ILP) and Support Vector Inductive Logic Programming (SVILP) on a standard molecular benchmark dataset comprising 11 activity classes and about 102,000 structures. The Naive Bayes Classifier treats features independently while ILP combines structural fragments, and then creates new features with higher predictive power. SVILP is a very recently presented method which adds a support vector machine after common ILP procedures. The performance of the methods is evaluated via a number of statistical measures, namely recall, specificity, precision, F-measure, Matthews Correlation Coefficient, area under the Receiver Operating Characteristic (ROC) curve and enrichment factor (EF). According to the F-measure, which takes both recall and precision into account, SVILP is for seven out of the 11 classes the superior method. The results show that the Bayes Classifier gives the best recall performance for eight of the 11 targets, but has a much lower precision, specificity and F-measure. The SVILP model on the other hand has the highest recall for only three of the 11 classes, but generally far superior specificity and precision. To evaluate the statistical significance of the SVILP superiority, we employ McNemar's test which shows that SVILP performs significantly (p < 5%) better than both other methods for six out of 11 activity classes, while being superior with less significance for three of the remaining classes. While previously the Bayes Classifier was shown to perform very well in molecular classification studies, these results suggest that SVILP is able to extract additional knowledge from the data, thus improving classification results further. More... »

PAGES

269-280

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s10822-007-9113-3

DOI

http://dx.doi.org/10.1007/s10822-007-9113-3

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1039032784

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/17387437


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/2008/0906", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Electrical and Electronic Engineering", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/09", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Engineering", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Bayes Theorem", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Computational Biology", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Confidence Intervals", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Drug Design", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Pharmaceutical Preparations", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Software", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Cambridge", 
          "id": "https://www.grid.ac/institutes/grid.5335.0", 
          "name": [
            "Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, CB2 1EW, Cambridge, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Cannon", 
        "givenName": "Edward O.", 
        "id": "sg:person.01260015477.47", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01260015477.47"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Imperial College London", 
          "id": "https://www.grid.ac/institutes/grid.7445.2", 
          "name": [
            "Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, CB2 1EW, Cambridge, UK", 
            "Structural Bioinformatics, Division of Molecular Biosciences, Faculty of Natural Sciences, Imperial College, SW7 2AZ, London, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Amini", 
        "givenName": "Ata", 
        "id": "sg:person.0705207625.92", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0705207625.92"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Novartis (United States)", 
          "id": "https://www.grid.ac/institutes/grid.418424.f", 
          "name": [
            "Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, CB2 1EW, Cambridge, UK", 
            "Novartis Institutes for Biomedical Research, Lead Discovery Informatics, 250 Mass Ave., 3C463, 02139, Cambridge, MA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bender", 
        "givenName": "Andreas", 
        "id": "sg:person.0626547717.06", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0626547717.06"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Imperial College London", 
          "id": "https://www.grid.ac/institutes/grid.7445.2", 
          "name": [
            "Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, CB2 1EW, Cambridge, UK", 
            "Structural Bioinformatics, Division of Molecular Biosciences, Faculty of Natural Sciences, Imperial College, SW7 2AZ, London, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Sternberg", 
        "givenName": "Michael J. E.", 
        "id": "sg:person.0611736450.97", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0611736450.97"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Imperial College London", 
          "id": "https://www.grid.ac/institutes/grid.7445.2", 
          "name": [
            "Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, CB2 1EW, Cambridge, UK", 
            "Structural Bioinformatics, Division of Molecular Biosciences, Faculty of Natural Sciences, Imperial College, SW7 2AZ, London, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Muggleton", 
        "givenName": "Stephen H.", 
        "id": "sg:person.01125137176.85", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01125137176.85"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Cambridge", 
          "id": "https://www.grid.ac/institutes/grid.5335.0", 
          "name": [
            "Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, CB2 1EW, Cambridge, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Glen", 
        "givenName": "Robert C.", 
        "id": "sg:person.0771416255.12", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0771416255.12"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Cambridge", 
          "id": "https://www.grid.ac/institutes/grid.5335.0", 
          "name": [
            "Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, CB2 1EW, Cambridge, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Mitchell", 
        "givenName": "John B. O.", 
        "id": "sg:person.012546177342.29", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012546177342.29"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1023/a:1008793325522", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000994139", 
          "https://doi.org/10.1023/a:1008793325522"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1073/pnas.93.1.438", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005032985"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf03037227", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005084660", 
          "https://doi.org/10.1007/bf03037227"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf03037227", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005084660", 
          "https://doi.org/10.1007/bf03037227"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1039/b409813g", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006251754"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci050400b", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016591305"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci050400b", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016591305"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10822-006-9058-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018680399", 
          "https://doi.org/10.1007/s10822-006-9058-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10822-006-9058-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018680399", 
          "https://doi.org/10.1007/s10822-006-9058-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-33486-6_5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020273737", 
          "https://doi.org/10.1007/3-540-33486-6_5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s1574-1400(06)02009-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1029671395"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1039/b409865j", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033295658"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00125944", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044330051", 
          "https://doi.org/10.1007/bf00125944"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00125944", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044330051", 
          "https://doi.org/10.1007/bf00125944"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf02295996", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048367524", 
          "https://doi.org/10.1007/bf02295996"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-36266-1_10", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049142297", 
          "https://doi.org/10.1007/978-3-540-36266-1_10"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-36266-1_10", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049142297", 
          "https://doi.org/10.1007/978-3-540-36266-1_10"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-36468-4_4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050157372", 
          "https://doi.org/10.1007/3-540-36468-4_4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-36468-4_4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050157372", 
          "https://doi.org/10.1007/3-540-36468-4_4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1073/pnas.89.23.11322", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052642229"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-44797-0_5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052668465", 
          "https://doi.org/10.1007/3-540-44797-0_5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci00021a011", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055400276"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci034207y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055401707"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci034207y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055401707"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci034231b", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055401726"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci034231b", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055401726"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci0498719", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055401927"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci0498719", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055401927"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci049875d", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055401930"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci049875d", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055401930"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci0500177", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055401993"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci0500177", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055401993"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci0504418", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055402225"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci0504418", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055402225"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci0601160", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055402332"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ci0601160", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055402332"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/jm960290n", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055957654"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/jm960290n", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055957654"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2174/0929867013371923", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1069159743"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2174/1381612013397843", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1069164551"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1077199051", 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1103209493", 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2007-05", 
    "datePublishedReg": "2007-05-01", 
    "description": "We investigate the classification performance of circular fingerprints in combination with the Naive Bayes Classifier (MP2D), Inductive Logic Programming (ILP) and Support Vector Inductive Logic Programming (SVILP) on a standard molecular benchmark dataset comprising 11 activity classes and about 102,000 structures. The Naive Bayes Classifier treats features independently while ILP combines structural fragments, and then creates new features with higher predictive power. SVILP is a very recently presented method which adds a support vector machine after common ILP procedures. The performance of the methods is evaluated via a number of statistical measures, namely recall, specificity, precision, F-measure, Matthews Correlation Coefficient, area under the Receiver Operating Characteristic (ROC) curve and enrichment factor (EF). According to the F-measure, which takes both recall and precision into account, SVILP is for seven out of the 11 classes the superior method. The results show that the Bayes Classifier gives the best recall performance for eight of the 11 targets, but has a much lower precision, specificity and F-measure. The SVILP model on the other hand has the highest recall for only three of the 11 classes, but generally far superior specificity and precision. To evaluate the statistical significance of the SVILP superiority, we employ McNemar's test which shows that SVILP performs significantly (p < 5%) better than both other methods for six out of 11 activity classes, while being superior with less significance for three of the remaining classes. While previously the Bayes Classifier was shown to perform very well in molecular classification studies, these results suggest that SVILP is able to extract additional knowledge from the data, thus improving classification results further.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s10822-007-9113-3", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1105375", 
        "issn": [
          "0928-2866", 
          "1573-9023"
        ], 
        "name": "Journal of Computer-Aided Molecular Design", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "5", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "21"
      }
    ], 
    "name": "Support vector inductive logic programming outperforms the naive Bayes classifier and inductive logic programming for the classification of bioactive chemical compounds", 
    "pagination": "269-280", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s10822-007-9113-3"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "b9ee7b311e8646c62bb5e4f6b0b636cdd49dc5d7dfdfb23f41518f1264549200"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1039032784"
        ]
      }, 
      {
        "name": "nlm_unique_id", 
        "type": "PropertyValue", 
        "value": [
          "8710425"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "17387437"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s10822-007-9113-3", 
      "https://app.dimensions.ai/details/publication/pub.1039032784"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-15T09:17", 
    "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/v90/0000000376_0000000376/records_56173_00000001.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1007/s10822-007-9113-3"
  }
]
 

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.10.1007/s10822-007-9113-3'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s10822-007-9113-3'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s10822-007-9113-3'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s10822-007-9113-3'


 

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

234 TRIPLES      21 PREDICATES      63 URIs      27 LITERALS      15 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s10822-007-9113-3 schema:about N0592fbaf794946ac9b8cc873600416ee
2 N0c067f3b39b44e38a2321f0a9c9da049
3 N4cf78b710eb54dae80a1ee1a7e79e44c
4 Nac0f99b7c32447d4ab4f90599458cf40
5 Nadd28dddd1c24c6e8a154ef940aa2011
6 Nde231f56170949f988fc3d6a890a94b2
7 anzsrc-for:09
8 anzsrc-for:0906
9 schema:author N43bd70db0d4b4dc8b1fcaf7da285b85c
10 schema:citation sg:pub.10.1007/3-540-33486-6_5
11 sg:pub.10.1007/3-540-36468-4_4
12 sg:pub.10.1007/3-540-44797-0_5
13 sg:pub.10.1007/978-3-540-36266-1_10
14 sg:pub.10.1007/bf00125944
15 sg:pub.10.1007/bf02295996
16 sg:pub.10.1007/bf03037227
17 sg:pub.10.1007/s10822-006-9058-y
18 sg:pub.10.1023/a:1008793325522
19 https://app.dimensions.ai/details/publication/pub.1077199051
20 https://app.dimensions.ai/details/publication/pub.1103209493
21 https://doi.org/10.1016/s1574-1400(06)02009-3
22 https://doi.org/10.1021/ci00021a011
23 https://doi.org/10.1021/ci034207y
24 https://doi.org/10.1021/ci034231b
25 https://doi.org/10.1021/ci0498719
26 https://doi.org/10.1021/ci049875d
27 https://doi.org/10.1021/ci0500177
28 https://doi.org/10.1021/ci050400b
29 https://doi.org/10.1021/ci0504418
30 https://doi.org/10.1021/ci0601160
31 https://doi.org/10.1021/jm960290n
32 https://doi.org/10.1039/b409813g
33 https://doi.org/10.1039/b409865j
34 https://doi.org/10.1073/pnas.89.23.11322
35 https://doi.org/10.1073/pnas.93.1.438
36 https://doi.org/10.2174/0929867013371923
37 https://doi.org/10.2174/1381612013397843
38 schema:datePublished 2007-05
39 schema:datePublishedReg 2007-05-01
40 schema:description We investigate the classification performance of circular fingerprints in combination with the Naive Bayes Classifier (MP2D), Inductive Logic Programming (ILP) and Support Vector Inductive Logic Programming (SVILP) on a standard molecular benchmark dataset comprising 11 activity classes and about 102,000 structures. The Naive Bayes Classifier treats features independently while ILP combines structural fragments, and then creates new features with higher predictive power. SVILP is a very recently presented method which adds a support vector machine after common ILP procedures. The performance of the methods is evaluated via a number of statistical measures, namely recall, specificity, precision, F-measure, Matthews Correlation Coefficient, area under the Receiver Operating Characteristic (ROC) curve and enrichment factor (EF). According to the F-measure, which takes both recall and precision into account, SVILP is for seven out of the 11 classes the superior method. The results show that the Bayes Classifier gives the best recall performance for eight of the 11 targets, but has a much lower precision, specificity and F-measure. The SVILP model on the other hand has the highest recall for only three of the 11 classes, but generally far superior specificity and precision. To evaluate the statistical significance of the SVILP superiority, we employ McNemar's test which shows that SVILP performs significantly (p < 5%) better than both other methods for six out of 11 activity classes, while being superior with less significance for three of the remaining classes. While previously the Bayes Classifier was shown to perform very well in molecular classification studies, these results suggest that SVILP is able to extract additional knowledge from the data, thus improving classification results further.
41 schema:genre research_article
42 schema:inLanguage en
43 schema:isAccessibleForFree false
44 schema:isPartOf N323f5078feb64ca9985fb8ddd9c4f5e3
45 Nccf2e4fd9a484b1bb1896c77d9067028
46 sg:journal.1105375
47 schema:name Support vector inductive logic programming outperforms the naive Bayes classifier and inductive logic programming for the classification of bioactive chemical compounds
48 schema:pagination 269-280
49 schema:productId N0a5399fcdb334f1fb53894fed1d94f24
50 N20a4471244264cdd81c989c34031998d
51 Naa286a91d7e54099984f19b7645c2b5b
52 Ncca94204d0d249bbb0f9754fa728f07d
53 Ndd81051e2c48411f83a35b1e0884f108
54 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039032784
55 https://doi.org/10.1007/s10822-007-9113-3
56 schema:sdDatePublished 2019-04-15T09:17
57 schema:sdLicense https://scigraph.springernature.com/explorer/license/
58 schema:sdPublisher Nb15f45f2541a4787abd46eb7e0d7257b
59 schema:url http://link.springer.com/10.1007/s10822-007-9113-3
60 sgo:license sg:explorer/license/
61 sgo:sdDataset articles
62 rdf:type schema:ScholarlyArticle
63 N0592fbaf794946ac9b8cc873600416ee schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
64 schema:name Confidence Intervals
65 rdf:type schema:DefinedTerm
66 N08caa54746d44a13a5566a8940b9db87 rdf:first sg:person.01125137176.85
67 rdf:rest Nd84e2faa97d448fda3bffdd1a2e5ac6b
68 N0a5399fcdb334f1fb53894fed1d94f24 schema:name readcube_id
69 schema:value b9ee7b311e8646c62bb5e4f6b0b636cdd49dc5d7dfdfb23f41518f1264549200
70 rdf:type schema:PropertyValue
71 N0c067f3b39b44e38a2321f0a9c9da049 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
72 schema:name Computational Biology
73 rdf:type schema:DefinedTerm
74 N20a4471244264cdd81c989c34031998d schema:name nlm_unique_id
75 schema:value 8710425
76 rdf:type schema:PropertyValue
77 N323f5078feb64ca9985fb8ddd9c4f5e3 schema:issueNumber 5
78 rdf:type schema:PublicationIssue
79 N43bd70db0d4b4dc8b1fcaf7da285b85c rdf:first sg:person.01260015477.47
80 rdf:rest N6c5e850b13c64158995e6d126b499a68
81 N4cf78b710eb54dae80a1ee1a7e79e44c schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
82 schema:name Bayes Theorem
83 rdf:type schema:DefinedTerm
84 N5a4147642dc846b58123176dffd5ffd1 rdf:first sg:person.012546177342.29
85 rdf:rest rdf:nil
86 N6c5e850b13c64158995e6d126b499a68 rdf:first sg:person.0705207625.92
87 rdf:rest N719f3eabf5c5449fb7d198e670c2431e
88 N719f3eabf5c5449fb7d198e670c2431e rdf:first sg:person.0626547717.06
89 rdf:rest Nc0fa5113133447d584575b1c232085dc
90 Naa286a91d7e54099984f19b7645c2b5b schema:name doi
91 schema:value 10.1007/s10822-007-9113-3
92 rdf:type schema:PropertyValue
93 Nac0f99b7c32447d4ab4f90599458cf40 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
94 schema:name Pharmaceutical Preparations
95 rdf:type schema:DefinedTerm
96 Nadd28dddd1c24c6e8a154ef940aa2011 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
97 schema:name Drug Design
98 rdf:type schema:DefinedTerm
99 Nb15f45f2541a4787abd46eb7e0d7257b schema:name Springer Nature - SN SciGraph project
100 rdf:type schema:Organization
101 Nc0fa5113133447d584575b1c232085dc rdf:first sg:person.0611736450.97
102 rdf:rest N08caa54746d44a13a5566a8940b9db87
103 Ncca94204d0d249bbb0f9754fa728f07d schema:name dimensions_id
104 schema:value pub.1039032784
105 rdf:type schema:PropertyValue
106 Nccf2e4fd9a484b1bb1896c77d9067028 schema:volumeNumber 21
107 rdf:type schema:PublicationVolume
108 Nd84e2faa97d448fda3bffdd1a2e5ac6b rdf:first sg:person.0771416255.12
109 rdf:rest N5a4147642dc846b58123176dffd5ffd1
110 Ndd81051e2c48411f83a35b1e0884f108 schema:name pubmed_id
111 schema:value 17387437
112 rdf:type schema:PropertyValue
113 Nde231f56170949f988fc3d6a890a94b2 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
114 schema:name Software
115 rdf:type schema:DefinedTerm
116 anzsrc-for:09 schema:inDefinedTermSet anzsrc-for:
117 schema:name Engineering
118 rdf:type schema:DefinedTerm
119 anzsrc-for:0906 schema:inDefinedTermSet anzsrc-for:
120 schema:name Electrical and Electronic Engineering
121 rdf:type schema:DefinedTerm
122 sg:journal.1105375 schema:issn 0928-2866
123 1573-9023
124 schema:name Journal of Computer-Aided Molecular Design
125 rdf:type schema:Periodical
126 sg:person.01125137176.85 schema:affiliation https://www.grid.ac/institutes/grid.7445.2
127 schema:familyName Muggleton
128 schema:givenName Stephen H.
129 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01125137176.85
130 rdf:type schema:Person
131 sg:person.012546177342.29 schema:affiliation https://www.grid.ac/institutes/grid.5335.0
132 schema:familyName Mitchell
133 schema:givenName John B. O.
134 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012546177342.29
135 rdf:type schema:Person
136 sg:person.01260015477.47 schema:affiliation https://www.grid.ac/institutes/grid.5335.0
137 schema:familyName Cannon
138 schema:givenName Edward O.
139 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01260015477.47
140 rdf:type schema:Person
141 sg:person.0611736450.97 schema:affiliation https://www.grid.ac/institutes/grid.7445.2
142 schema:familyName Sternberg
143 schema:givenName Michael J. E.
144 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0611736450.97
145 rdf:type schema:Person
146 sg:person.0626547717.06 schema:affiliation https://www.grid.ac/institutes/grid.418424.f
147 schema:familyName Bender
148 schema:givenName Andreas
149 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0626547717.06
150 rdf:type schema:Person
151 sg:person.0705207625.92 schema:affiliation https://www.grid.ac/institutes/grid.7445.2
152 schema:familyName Amini
153 schema:givenName Ata
154 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0705207625.92
155 rdf:type schema:Person
156 sg:person.0771416255.12 schema:affiliation https://www.grid.ac/institutes/grid.5335.0
157 schema:familyName Glen
158 schema:givenName Robert C.
159 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0771416255.12
160 rdf:type schema:Person
161 sg:pub.10.1007/3-540-33486-6_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020273737
162 https://doi.org/10.1007/3-540-33486-6_5
163 rdf:type schema:CreativeWork
164 sg:pub.10.1007/3-540-36468-4_4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050157372
165 https://doi.org/10.1007/3-540-36468-4_4
166 rdf:type schema:CreativeWork
167 sg:pub.10.1007/3-540-44797-0_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052668465
168 https://doi.org/10.1007/3-540-44797-0_5
169 rdf:type schema:CreativeWork
170 sg:pub.10.1007/978-3-540-36266-1_10 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049142297
171 https://doi.org/10.1007/978-3-540-36266-1_10
172 rdf:type schema:CreativeWork
173 sg:pub.10.1007/bf00125944 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044330051
174 https://doi.org/10.1007/bf00125944
175 rdf:type schema:CreativeWork
176 sg:pub.10.1007/bf02295996 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048367524
177 https://doi.org/10.1007/bf02295996
178 rdf:type schema:CreativeWork
179 sg:pub.10.1007/bf03037227 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005084660
180 https://doi.org/10.1007/bf03037227
181 rdf:type schema:CreativeWork
182 sg:pub.10.1007/s10822-006-9058-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1018680399
183 https://doi.org/10.1007/s10822-006-9058-y
184 rdf:type schema:CreativeWork
185 sg:pub.10.1023/a:1008793325522 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000994139
186 https://doi.org/10.1023/a:1008793325522
187 rdf:type schema:CreativeWork
188 https://app.dimensions.ai/details/publication/pub.1077199051 schema:CreativeWork
189 https://app.dimensions.ai/details/publication/pub.1103209493 schema:CreativeWork
190 https://doi.org/10.1016/s1574-1400(06)02009-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029671395
191 rdf:type schema:CreativeWork
192 https://doi.org/10.1021/ci00021a011 schema:sameAs https://app.dimensions.ai/details/publication/pub.1055400276
193 rdf:type schema:CreativeWork
194 https://doi.org/10.1021/ci034207y schema:sameAs https://app.dimensions.ai/details/publication/pub.1055401707
195 rdf:type schema:CreativeWork
196 https://doi.org/10.1021/ci034231b schema:sameAs https://app.dimensions.ai/details/publication/pub.1055401726
197 rdf:type schema:CreativeWork
198 https://doi.org/10.1021/ci0498719 schema:sameAs https://app.dimensions.ai/details/publication/pub.1055401927
199 rdf:type schema:CreativeWork
200 https://doi.org/10.1021/ci049875d schema:sameAs https://app.dimensions.ai/details/publication/pub.1055401930
201 rdf:type schema:CreativeWork
202 https://doi.org/10.1021/ci0500177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1055401993
203 rdf:type schema:CreativeWork
204 https://doi.org/10.1021/ci050400b schema:sameAs https://app.dimensions.ai/details/publication/pub.1016591305
205 rdf:type schema:CreativeWork
206 https://doi.org/10.1021/ci0504418 schema:sameAs https://app.dimensions.ai/details/publication/pub.1055402225
207 rdf:type schema:CreativeWork
208 https://doi.org/10.1021/ci0601160 schema:sameAs https://app.dimensions.ai/details/publication/pub.1055402332
209 rdf:type schema:CreativeWork
210 https://doi.org/10.1021/jm960290n schema:sameAs https://app.dimensions.ai/details/publication/pub.1055957654
211 rdf:type schema:CreativeWork
212 https://doi.org/10.1039/b409813g schema:sameAs https://app.dimensions.ai/details/publication/pub.1006251754
213 rdf:type schema:CreativeWork
214 https://doi.org/10.1039/b409865j schema:sameAs https://app.dimensions.ai/details/publication/pub.1033295658
215 rdf:type schema:CreativeWork
216 https://doi.org/10.1073/pnas.89.23.11322 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052642229
217 rdf:type schema:CreativeWork
218 https://doi.org/10.1073/pnas.93.1.438 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005032985
219 rdf:type schema:CreativeWork
220 https://doi.org/10.2174/0929867013371923 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069159743
221 rdf:type schema:CreativeWork
222 https://doi.org/10.2174/1381612013397843 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069164551
223 rdf:type schema:CreativeWork
224 https://www.grid.ac/institutes/grid.418424.f schema:alternateName Novartis (United States)
225 schema:name Novartis Institutes for Biomedical Research, Lead Discovery Informatics, 250 Mass Ave., 3C463, 02139, Cambridge, MA, USA
226 Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, CB2 1EW, Cambridge, UK
227 rdf:type schema:Organization
228 https://www.grid.ac/institutes/grid.5335.0 schema:alternateName University of Cambridge
229 schema:name Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, CB2 1EW, Cambridge, UK
230 rdf:type schema:Organization
231 https://www.grid.ac/institutes/grid.7445.2 schema:alternateName Imperial College London
232 schema:name Structural Bioinformatics, Division of Molecular Biosciences, Faculty of Natural Sciences, Imperial College, SW7 2AZ, London, UK
233 Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, CB2 1EW, Cambridge, UK
234 rdf:type schema:Organization
 




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


...