The Effect of Relational Background Knowledge on Learning of Protein Three-Dimensional Fold Signatures View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2001-04

AUTHORS

Marcel Turcotte, Stephen H. Muggleton, Michael J.E. Sternberg

ABSTRACT

As a form of Machine Learning the study of Inductive Logic Programming (ILP) is motivated by a central belief: relational description languages are better (in terms of accuracy and understandability) than propositional ones for certain real-world applications. This claim is investigated here for a particular application in structural molecular biology, that of constructing readable descriptions of the major protein folds. To the authors' knowledge Machine Learning has not previously been applied systematically to this task. In this application, the domain expert (third author) identified a natural divide between essentially propositional features and more structurally-oriented relational ones. The following null hypotheses are tested: 1) for a given ILP system (Progol) provision of relational background knowledge does not increase predictive accuracy, 2) a good propositional learning system (C5.0) without relational background knowledge will outperform Progol with relational background knowledge, 3) relational background knowledge does not produce improved explanatory insight. Null hypotheses 1) and 2) are both refuted on cross-validation results carried out over 20 of the most populated protein folds. Hypothesis 3 is refuted by demonstration of various insightful rules discovered only in the relationally-oriented learned rules. More... »

PAGES

81-95

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1023/a:1007672817406

DOI

http://dx.doi.org/10.1023/a:1007672817406

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1015313414


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": "Cancer Research UK", 
          "id": "https://www.grid.ac/institutes/grid.11485.39", 
          "name": [
            "Biomolecular Modelling Laboratory, Imperial Cancer Research Fund, P.O. Box 123, WC2A 3PX, London, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Turcotte", 
        "givenName": "Marcel", 
        "id": "sg:person.01010146661.37", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01010146661.37"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of York", 
          "id": "https://www.grid.ac/institutes/grid.5685.e", 
          "name": [
            "Department of Computer Science, University of York, YO1 5DD, Heslington, York, 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": "Cancer Research UK", 
          "id": "https://www.grid.ac/institutes/grid.11485.39", 
          "name": [
            "Biomolecular Modelling Laboratory, Imperial Cancer Research Fund, P.O. Box 123, WC2A 3PX, 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"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/0743-1066(94)90035-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002893202"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1073/pnas.93.1.438", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005032985"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0076-6879(96)66039-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006906574"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1006/jmbi.2000.3741", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1013672263"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-49292-5_3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015463517", 
          "https://doi.org/10.1007/3-540-49292-5_3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-49292-5_3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015463517", 
          "https://doi.org/10.1007/3-540-49292-5_3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0022-2836(87)90521-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016752148"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1098/rstb.1994.0075", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1023258494"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/pro.5560050204", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025936435"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/pro.5560050204", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025936435"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1073/pnas.37.4.205", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028791339"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(95)00122-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1029374130"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0969-2126(00)00018-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037226762"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/372631a0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041521574", 
          "https://doi.org/10.1038/372631a0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0022-2836(86)90409-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042330641"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1007460424845", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049786310", 
          "https://doi.org/10.1023/a:1007460424845"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3540635149_56", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050437600", 
          "https://doi.org/10.1007/3540635149_56"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1073/pnas.89.23.11322", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052642229"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1021/ja00766a060", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1055746093"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/protein/5.7.647", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1059980792"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2001-04", 
    "datePublishedReg": "2001-04-01", 
    "description": "As a form of Machine Learning the study of Inductive Logic Programming (ILP) is motivated by a central belief: relational description languages are better (in terms of accuracy and understandability) than propositional ones for certain real-world applications. This claim is investigated here for a particular application in structural molecular biology, that of constructing readable descriptions of the major protein folds. To the authors' knowledge Machine Learning has not previously been applied systematically to this task. In this application, the domain expert (third author) identified a natural divide between essentially propositional features and more structurally-oriented relational ones. The following null hypotheses are tested: 1) for a given ILP system (Progol) provision of relational background knowledge does not increase predictive accuracy, 2) a good propositional learning system (C5.0) without relational background knowledge will outperform Progol with relational background knowledge, 3) relational background knowledge does not produce improved explanatory insight. Null hypotheses 1) and 2) are both refuted on cross-validation results carried out over 20 of the most populated protein folds. Hypothesis 3 is refuted by demonstration of various insightful rules discovered only in the relationally-oriented learned rules.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1023/a:1007672817406", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1125588", 
        "issn": [
          "0885-6125", 
          "1573-0565"
        ], 
        "name": "Machine Learning", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1-2", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "43"
      }
    ], 
    "name": "The Effect of Relational Background Knowledge on Learning of Protein Three-Dimensional Fold Signatures", 
    "pagination": "81-95", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "48f61c8b970fd0fccc7641876c5786dd12547a9c9d2b2c11f80ed789d06673ce"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1023/a:1007672817406"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1015313414"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1023/a:1007672817406", 
      "https://app.dimensions.ai/details/publication/pub.1015313414"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-10T19:06", 
    "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_8678_00000499.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1023/A:1007672817406"
  }
]
 

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.10.1023/a:1007672817406'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1023/a:1007672817406'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1023/a:1007672817406'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1023/a:1007672817406'


 

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

136 TRIPLES      21 PREDICATES      45 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1023/a:1007672817406 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nd449e09cc31945c483643baeed60a386
4 schema:citation sg:pub.10.1007/3-540-49292-5_3
5 sg:pub.10.1007/3540635149_56
6 sg:pub.10.1023/a:1007460424845
7 sg:pub.10.1038/372631a0
8 https://doi.org/10.1002/pro.5560050204
9 https://doi.org/10.1006/jmbi.2000.3741
10 https://doi.org/10.1016/0004-3702(95)00122-0
11 https://doi.org/10.1016/0022-2836(86)90409-2
12 https://doi.org/10.1016/0022-2836(87)90521-3
13 https://doi.org/10.1016/0743-1066(94)90035-3
14 https://doi.org/10.1016/s0076-6879(96)66039-x
15 https://doi.org/10.1016/s0969-2126(00)00018-6
16 https://doi.org/10.1021/ja00766a060
17 https://doi.org/10.1073/pnas.37.4.205
18 https://doi.org/10.1073/pnas.89.23.11322
19 https://doi.org/10.1073/pnas.93.1.438
20 https://doi.org/10.1093/protein/5.7.647
21 https://doi.org/10.1098/rstb.1994.0075
22 schema:datePublished 2001-04
23 schema:datePublishedReg 2001-04-01
24 schema:description As a form of Machine Learning the study of Inductive Logic Programming (ILP) is motivated by a central belief: relational description languages are better (in terms of accuracy and understandability) than propositional ones for certain real-world applications. This claim is investigated here for a particular application in structural molecular biology, that of constructing readable descriptions of the major protein folds. To the authors' knowledge Machine Learning has not previously been applied systematically to this task. In this application, the domain expert (third author) identified a natural divide between essentially propositional features and more structurally-oriented relational ones. The following null hypotheses are tested: 1) for a given ILP system (Progol) provision of relational background knowledge does not increase predictive accuracy, 2) a good propositional learning system (C5.0) without relational background knowledge will outperform Progol with relational background knowledge, 3) relational background knowledge does not produce improved explanatory insight. Null hypotheses 1) and 2) are both refuted on cross-validation results carried out over 20 of the most populated protein folds. Hypothesis 3 is refuted by demonstration of various insightful rules discovered only in the relationally-oriented learned rules.
25 schema:genre research_article
26 schema:inLanguage en
27 schema:isAccessibleForFree true
28 schema:isPartOf N3daed82085c14fe49e3266054d247a20
29 Nac362ed332de4694b25a37cca2d4d999
30 sg:journal.1125588
31 schema:name The Effect of Relational Background Knowledge on Learning of Protein Three-Dimensional Fold Signatures
32 schema:pagination 81-95
33 schema:productId N5903a579ce594521bb32d86d29b576f4
34 N5d05c417da6d4230b3f2e981777c57d2
35 Nd2ae123820ae49fe98ebf808b6083c47
36 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015313414
37 https://doi.org/10.1023/a:1007672817406
38 schema:sdDatePublished 2019-04-10T19:06
39 schema:sdLicense https://scigraph.springernature.com/explorer/license/
40 schema:sdPublisher Neb97dfc32baa412f90ff344e8533cb92
41 schema:url http://link.springer.com/10.1023/A:1007672817406
42 sgo:license sg:explorer/license/
43 sgo:sdDataset articles
44 rdf:type schema:ScholarlyArticle
45 N3daed82085c14fe49e3266054d247a20 schema:issueNumber 1-2
46 rdf:type schema:PublicationIssue
47 N5903a579ce594521bb32d86d29b576f4 schema:name readcube_id
48 schema:value 48f61c8b970fd0fccc7641876c5786dd12547a9c9d2b2c11f80ed789d06673ce
49 rdf:type schema:PropertyValue
50 N5d05c417da6d4230b3f2e981777c57d2 schema:name doi
51 schema:value 10.1023/a:1007672817406
52 rdf:type schema:PropertyValue
53 N6aa3d116f9ae492b9951c02b9a3a59b7 rdf:first sg:person.01125137176.85
54 rdf:rest Naa76d106467347428358524745301194
55 Naa76d106467347428358524745301194 rdf:first sg:person.0611736450.97
56 rdf:rest rdf:nil
57 Nac362ed332de4694b25a37cca2d4d999 schema:volumeNumber 43
58 rdf:type schema:PublicationVolume
59 Nd2ae123820ae49fe98ebf808b6083c47 schema:name dimensions_id
60 schema:value pub.1015313414
61 rdf:type schema:PropertyValue
62 Nd449e09cc31945c483643baeed60a386 rdf:first sg:person.01010146661.37
63 rdf:rest N6aa3d116f9ae492b9951c02b9a3a59b7
64 Neb97dfc32baa412f90ff344e8533cb92 schema:name Springer Nature - SN SciGraph project
65 rdf:type schema:Organization
66 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
67 schema:name Information and Computing Sciences
68 rdf:type schema:DefinedTerm
69 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
70 schema:name Artificial Intelligence and Image Processing
71 rdf:type schema:DefinedTerm
72 sg:journal.1125588 schema:issn 0885-6125
73 1573-0565
74 schema:name Machine Learning
75 rdf:type schema:Periodical
76 sg:person.01010146661.37 schema:affiliation https://www.grid.ac/institutes/grid.11485.39
77 schema:familyName Turcotte
78 schema:givenName Marcel
79 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01010146661.37
80 rdf:type schema:Person
81 sg:person.01125137176.85 schema:affiliation https://www.grid.ac/institutes/grid.5685.e
82 schema:familyName Muggleton
83 schema:givenName Stephen H.
84 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01125137176.85
85 rdf:type schema:Person
86 sg:person.0611736450.97 schema:affiliation https://www.grid.ac/institutes/grid.11485.39
87 schema:familyName Sternberg
88 schema:givenName Michael J.E.
89 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0611736450.97
90 rdf:type schema:Person
91 sg:pub.10.1007/3-540-49292-5_3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015463517
92 https://doi.org/10.1007/3-540-49292-5_3
93 rdf:type schema:CreativeWork
94 sg:pub.10.1007/3540635149_56 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050437600
95 https://doi.org/10.1007/3540635149_56
96 rdf:type schema:CreativeWork
97 sg:pub.10.1023/a:1007460424845 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049786310
98 https://doi.org/10.1023/a:1007460424845
99 rdf:type schema:CreativeWork
100 sg:pub.10.1038/372631a0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041521574
101 https://doi.org/10.1038/372631a0
102 rdf:type schema:CreativeWork
103 https://doi.org/10.1002/pro.5560050204 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025936435
104 rdf:type schema:CreativeWork
105 https://doi.org/10.1006/jmbi.2000.3741 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013672263
106 rdf:type schema:CreativeWork
107 https://doi.org/10.1016/0004-3702(95)00122-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029374130
108 rdf:type schema:CreativeWork
109 https://doi.org/10.1016/0022-2836(86)90409-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042330641
110 rdf:type schema:CreativeWork
111 https://doi.org/10.1016/0022-2836(87)90521-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016752148
112 rdf:type schema:CreativeWork
113 https://doi.org/10.1016/0743-1066(94)90035-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002893202
114 rdf:type schema:CreativeWork
115 https://doi.org/10.1016/s0076-6879(96)66039-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1006906574
116 rdf:type schema:CreativeWork
117 https://doi.org/10.1016/s0969-2126(00)00018-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037226762
118 rdf:type schema:CreativeWork
119 https://doi.org/10.1021/ja00766a060 schema:sameAs https://app.dimensions.ai/details/publication/pub.1055746093
120 rdf:type schema:CreativeWork
121 https://doi.org/10.1073/pnas.37.4.205 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028791339
122 rdf:type schema:CreativeWork
123 https://doi.org/10.1073/pnas.89.23.11322 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052642229
124 rdf:type schema:CreativeWork
125 https://doi.org/10.1073/pnas.93.1.438 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005032985
126 rdf:type schema:CreativeWork
127 https://doi.org/10.1093/protein/5.7.647 schema:sameAs https://app.dimensions.ai/details/publication/pub.1059980792
128 rdf:type schema:CreativeWork
129 https://doi.org/10.1098/rstb.1994.0075 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023258494
130 rdf:type schema:CreativeWork
131 https://www.grid.ac/institutes/grid.11485.39 schema:alternateName Cancer Research UK
132 schema:name Biomolecular Modelling Laboratory, Imperial Cancer Research Fund, P.O. Box 123, WC2A 3PX, London, UK
133 rdf:type schema:Organization
134 https://www.grid.ac/institutes/grid.5685.e schema:alternateName University of York
135 schema:name Department of Computer Science, University of York, YO1 5DD, Heslington, York, UK
136 rdf:type schema:Organization
 




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


...