Deep Feature Selection: Theory and Application to Identify Enhancers and Promoters View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2015

AUTHORS

Yifeng Li , Chih-Yu Chen , Wyeth W. Wasserman

ABSTRACT

Sparse linear models approximate target variable(s) by a sparse linear combination of input variables. The sparseness is realized through a regularization term. Since they are simple, fast, and able to select features, they are widely used in classification and regression. Essentially linear models are shallow feed-forward neural networks which have three limitations: (1) incompatibility to model non-linearity of features, (2) inability to learn high-level features, and (3) unnatural extensions to select features in multi-class case. Deep neural networks are models structured by multiple hidden layers with non-linear activation functions. Compared with linear models, they have two distinctive strengths: the capability to (1) model complex systems with non-linear structures, (2) learn high-level representation of features. Deep learning has been applied in many large and complex systems where deep models significantly outperform shallow ones. However, feature selection at the input level, which is very helpful to understand the nature of a complex system, is still not well-studied. In genome research, the cis-regulatory elements in non-coding DNA sequences play a key role in the expression of genes. Since the activity of regulatory elements involves highly interactive factors, a deep tool is strongly needed to discover informative features. In order to address the above limitations of shallow and deep models for selecting features of a complex system, we propose a deep feature selection model that (1) takes advantages of deep structures to model non-linearity and (2) conveniently selects a subset of features right at the input level for multi-class data. We applied this model to the identification of active enhancers and promoters by integrating multiple sources of genomic information. Results show that our model outperforms elastic net in terms of size of discriminative feature subset and classification accuracy. More... »

PAGES

205-217

Book

TITLE

Research in Computational Molecular Biology

ISBN

978-3-319-16705-3
978-3-319-16706-0

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-16706-0_20

DOI

http://dx.doi.org/10.1007/978-3-319-16706-0_20

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1037068298


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": "University of British Columbia", 
          "id": "https://www.grid.ac/institutes/grid.17091.3e", 
          "name": [
            "Centre for Molecular Medicine and Therapeutics, University of British Columbia, 950 West 28th Avenue, Vancouver, BC, V5Z 4H4, Canada"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Li", 
        "givenName": "Yifeng", 
        "id": "sg:person.01162244772.96", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01162244772.96"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of British Columbia", 
          "id": "https://www.grid.ac/institutes/grid.17091.3e", 
          "name": [
            "Centre for Molecular Medicine and Therapeutics, University of British Columbia, 950 West 28th Avenue, Vancouver, BC, V5Z 4H4, Canada"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Chen", 
        "givenName": "Chih-Yu", 
        "id": "sg:person.013307242554.22", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013307242554.22"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of British Columbia", 
          "id": "https://www.grid.ac/institutes/grid.17091.3e", 
          "name": [
            "Centre for Molecular Medicine and Therapeutics, University of British Columbia, 950 West 28th Avenue, Vancouver, BC, V5Z 4H4, Canada"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wasserman", 
        "givenName": "Wyeth W.", 
        "id": "sg:person.01164162122.26", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01164162122.26"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1038/nrg3682", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000164192", 
          "https://doi.org/10.1038/nrg3682"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1126/science.1127647", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004607132"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/neco.2006.18.7.1527", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004707137"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0014-5793(97)00387-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004790855"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0168-9525(97)01103-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006171641"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1207/s15516709cog0901_7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006217895"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1207/s15516709cog0901_7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006217895"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1471-2164-11-257", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007794062", 
          "https://doi.org/10.1186/1471-2164-11-257"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1471-2164-12-181", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1008255115", 
          "https://doi.org/10.1186/1471-2164-12-181"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nature12787", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022158752", 
          "https://doi.org/10.1038/nature12787"
        ], 
        "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": "https://doi.org/10.1016/j.neucom.2013.02.012", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024990547"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nrg2905", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026386976", 
          "https://doi.org/10.1038/nrg2905"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nrg2905", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026386976", 
          "https://doi.org/10.1038/nrg2905"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1128/mcb.00987-12", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1029045967"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nature11247", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1029065430", 
          "https://doi.org/10.1038/nature11247"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nature13182", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1029370855", 
          "https://doi.org/10.1038/nature13182"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/ni.2037", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030015954", 
          "https://doi.org/10.1038/ni.2037"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1128/mcb.01529-06", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030878257"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/j.1467-9868.2005.00503.x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043971564"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/ni.2641", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053013874", 
          "https://doi.org/10.1038/ni.2641"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.ygeno.2014.02.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053040014"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/5.726791", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061179979"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2013.50", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061744581"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18637/jss.v033.i01", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1068672496"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18637/jss.v033.i01", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1068672496"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2015", 
    "datePublishedReg": "2015-01-01", 
    "description": "Sparse linear models approximate target variable(s) by a sparse linear combination of input variables. The sparseness is realized through a regularization term. Since they are simple, fast, and able to select features, they are widely used in classification and regression. Essentially linear models are shallow feed-forward neural networks which have three limitations: (1) incompatibility to model non-linearity of features, (2) inability to learn high-level features, and (3) unnatural extensions to select features in multi-class case. Deep neural networks are models structured by multiple hidden layers with non-linear activation functions. Compared with linear models, they have two distinctive strengths: the capability to (1) model complex systems with non-linear structures, (2) learn high-level representation of features. Deep learning has been applied in many large and complex systems where deep models significantly outperform shallow ones. However, feature selection at the input level, which is very helpful to understand the nature of a complex system, is still not well-studied. In genome research, the cis-regulatory elements in non-coding DNA sequences play a key role in the expression of genes. Since the activity of regulatory elements involves highly interactive factors, a deep tool is strongly needed to discover informative features. In order to address the above limitations of shallow and deep models for selecting features of a complex system, we propose a deep feature selection model that (1) takes advantages of deep structures to model non-linearity and (2) conveniently selects a subset of features right at the input level for multi-class data. We applied this model to the identification of active enhancers and promoters by integrating multiple sources of genomic information. Results show that our model outperforms elastic net in terms of size of discriminative feature subset and classification accuracy.", 
    "editor": [
      {
        "familyName": "Przytycka", 
        "givenName": "Teresa M.", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-16706-0_20", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-16705-3", 
        "978-3-319-16706-0"
      ], 
      "name": "Research in Computational Molecular Biology", 
      "type": "Book"
    }, 
    "name": "Deep Feature Selection: Theory and Application to Identify Enhancers and Promoters", 
    "pagination": "205-217", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-16706-0_20"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "b09484c683ed0e61aac084e6e84e93988930f4857b46bf23f330bd9040e6221b"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1037068298"
        ]
      }
    ], 
    "publisher": {
      "location": "Cham", 
      "name": "Springer International Publishing", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-16706-0_20", 
      "https://app.dimensions.ai/details/publication/pub.1037068298"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T17:15", 
    "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_00000266.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/978-3-319-16706-0_20"
  }
]
 

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.10.1007/978-3-319-16706-0_20'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16706-0_20'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16706-0_20'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16706-0_20'


 

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

158 TRIPLES      23 PREDICATES      50 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-16706-0_20 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N13296073ee6c4d60b330906d1e97f355
4 schema:citation sg:pub.10.1023/a:1010933404324
5 sg:pub.10.1038/nature11247
6 sg:pub.10.1038/nature12787
7 sg:pub.10.1038/nature13182
8 sg:pub.10.1038/ni.2037
9 sg:pub.10.1038/ni.2641
10 sg:pub.10.1038/nrg2905
11 sg:pub.10.1038/nrg3682
12 sg:pub.10.1186/1471-2164-11-257
13 sg:pub.10.1186/1471-2164-12-181
14 https://doi.org/10.1016/j.neucom.2013.02.012
15 https://doi.org/10.1016/j.ygeno.2014.02.002
16 https://doi.org/10.1016/s0014-5793(97)00387-6
17 https://doi.org/10.1016/s0168-9525(97)01103-7
18 https://doi.org/10.1109/5.726791
19 https://doi.org/10.1109/tpami.2013.50
20 https://doi.org/10.1111/j.1467-9868.2005.00503.x
21 https://doi.org/10.1126/science.1127647
22 https://doi.org/10.1128/mcb.00987-12
23 https://doi.org/10.1128/mcb.01529-06
24 https://doi.org/10.1162/neco.2006.18.7.1527
25 https://doi.org/10.1207/s15516709cog0901_7
26 https://doi.org/10.18637/jss.v033.i01
27 schema:datePublished 2015
28 schema:datePublishedReg 2015-01-01
29 schema:description Sparse linear models approximate target variable(s) by a sparse linear combination of input variables. The sparseness is realized through a regularization term. Since they are simple, fast, and able to select features, they are widely used in classification and regression. Essentially linear models are shallow feed-forward neural networks which have three limitations: (1) incompatibility to model non-linearity of features, (2) inability to learn high-level features, and (3) unnatural extensions to select features in multi-class case. Deep neural networks are models structured by multiple hidden layers with non-linear activation functions. Compared with linear models, they have two distinctive strengths: the capability to (1) model complex systems with non-linear structures, (2) learn high-level representation of features. Deep learning has been applied in many large and complex systems where deep models significantly outperform shallow ones. However, feature selection at the input level, which is very helpful to understand the nature of a complex system, is still not well-studied. In genome research, the cis-regulatory elements in non-coding DNA sequences play a key role in the expression of genes. Since the activity of regulatory elements involves highly interactive factors, a deep tool is strongly needed to discover informative features. In order to address the above limitations of shallow and deep models for selecting features of a complex system, we propose a deep feature selection model that (1) takes advantages of deep structures to model non-linearity and (2) conveniently selects a subset of features right at the input level for multi-class data. We applied this model to the identification of active enhancers and promoters by integrating multiple sources of genomic information. Results show that our model outperforms elastic net in terms of size of discriminative feature subset and classification accuracy.
30 schema:editor Nf6b623855a584d33b6acdfc3455b06dd
31 schema:genre chapter
32 schema:inLanguage en
33 schema:isAccessibleForFree false
34 schema:isPartOf Nde165422cf6b4fd0a12882246b5cabbe
35 schema:name Deep Feature Selection: Theory and Application to Identify Enhancers and Promoters
36 schema:pagination 205-217
37 schema:productId N57314a42ec5e4945abb57bf19e53c500
38 N653ea963973c405fa8b030a076856f3b
39 N9aa0187002514db5a6458a1ebc203ebb
40 schema:publisher Nd56e118711e34e08b7bd2e9346f09937
41 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037068298
42 https://doi.org/10.1007/978-3-319-16706-0_20
43 schema:sdDatePublished 2019-04-15T17:15
44 schema:sdLicense https://scigraph.springernature.com/explorer/license/
45 schema:sdPublisher N94e6d36d42f84bcda9cae5df810079b4
46 schema:url http://link.springer.com/10.1007/978-3-319-16706-0_20
47 sgo:license sg:explorer/license/
48 sgo:sdDataset chapters
49 rdf:type schema:Chapter
50 N13296073ee6c4d60b330906d1e97f355 rdf:first sg:person.01162244772.96
51 rdf:rest N59436ea896fe4b2a947489804d93a8ed
52 N2d159bd1d43340cc88bc1ae049d3cad6 rdf:first sg:person.01164162122.26
53 rdf:rest rdf:nil
54 N57314a42ec5e4945abb57bf19e53c500 schema:name dimensions_id
55 schema:value pub.1037068298
56 rdf:type schema:PropertyValue
57 N59436ea896fe4b2a947489804d93a8ed rdf:first sg:person.013307242554.22
58 rdf:rest N2d159bd1d43340cc88bc1ae049d3cad6
59 N653ea963973c405fa8b030a076856f3b schema:name doi
60 schema:value 10.1007/978-3-319-16706-0_20
61 rdf:type schema:PropertyValue
62 N737e744faffa41a8a286b7f89dbfb387 schema:familyName Przytycka
63 schema:givenName Teresa M.
64 rdf:type schema:Person
65 N94e6d36d42f84bcda9cae5df810079b4 schema:name Springer Nature - SN SciGraph project
66 rdf:type schema:Organization
67 N9aa0187002514db5a6458a1ebc203ebb schema:name readcube_id
68 schema:value b09484c683ed0e61aac084e6e84e93988930f4857b46bf23f330bd9040e6221b
69 rdf:type schema:PropertyValue
70 Nd56e118711e34e08b7bd2e9346f09937 schema:location Cham
71 schema:name Springer International Publishing
72 rdf:type schema:Organisation
73 Nde165422cf6b4fd0a12882246b5cabbe schema:isbn 978-3-319-16705-3
74 978-3-319-16706-0
75 schema:name Research in Computational Molecular Biology
76 rdf:type schema:Book
77 Nf6b623855a584d33b6acdfc3455b06dd rdf:first N737e744faffa41a8a286b7f89dbfb387
78 rdf:rest rdf:nil
79 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
80 schema:name Information and Computing Sciences
81 rdf:type schema:DefinedTerm
82 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
83 schema:name Artificial Intelligence and Image Processing
84 rdf:type schema:DefinedTerm
85 sg:person.01162244772.96 schema:affiliation https://www.grid.ac/institutes/grid.17091.3e
86 schema:familyName Li
87 schema:givenName Yifeng
88 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01162244772.96
89 rdf:type schema:Person
90 sg:person.01164162122.26 schema:affiliation https://www.grid.ac/institutes/grid.17091.3e
91 schema:familyName Wasserman
92 schema:givenName Wyeth W.
93 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01164162122.26
94 rdf:type schema:Person
95 sg:person.013307242554.22 schema:affiliation https://www.grid.ac/institutes/grid.17091.3e
96 schema:familyName Chen
97 schema:givenName Chih-Yu
98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013307242554.22
99 rdf:type schema:Person
100 sg:pub.10.1023/a:1010933404324 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024739340
101 https://doi.org/10.1023/a:1010933404324
102 rdf:type schema:CreativeWork
103 sg:pub.10.1038/nature11247 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029065430
104 https://doi.org/10.1038/nature11247
105 rdf:type schema:CreativeWork
106 sg:pub.10.1038/nature12787 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022158752
107 https://doi.org/10.1038/nature12787
108 rdf:type schema:CreativeWork
109 sg:pub.10.1038/nature13182 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029370855
110 https://doi.org/10.1038/nature13182
111 rdf:type schema:CreativeWork
112 sg:pub.10.1038/ni.2037 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030015954
113 https://doi.org/10.1038/ni.2037
114 rdf:type schema:CreativeWork
115 sg:pub.10.1038/ni.2641 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053013874
116 https://doi.org/10.1038/ni.2641
117 rdf:type schema:CreativeWork
118 sg:pub.10.1038/nrg2905 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026386976
119 https://doi.org/10.1038/nrg2905
120 rdf:type schema:CreativeWork
121 sg:pub.10.1038/nrg3682 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000164192
122 https://doi.org/10.1038/nrg3682
123 rdf:type schema:CreativeWork
124 sg:pub.10.1186/1471-2164-11-257 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007794062
125 https://doi.org/10.1186/1471-2164-11-257
126 rdf:type schema:CreativeWork
127 sg:pub.10.1186/1471-2164-12-181 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008255115
128 https://doi.org/10.1186/1471-2164-12-181
129 rdf:type schema:CreativeWork
130 https://doi.org/10.1016/j.neucom.2013.02.012 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024990547
131 rdf:type schema:CreativeWork
132 https://doi.org/10.1016/j.ygeno.2014.02.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053040014
133 rdf:type schema:CreativeWork
134 https://doi.org/10.1016/s0014-5793(97)00387-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004790855
135 rdf:type schema:CreativeWork
136 https://doi.org/10.1016/s0168-9525(97)01103-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006171641
137 rdf:type schema:CreativeWork
138 https://doi.org/10.1109/5.726791 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061179979
139 rdf:type schema:CreativeWork
140 https://doi.org/10.1109/tpami.2013.50 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744581
141 rdf:type schema:CreativeWork
142 https://doi.org/10.1111/j.1467-9868.2005.00503.x schema:sameAs https://app.dimensions.ai/details/publication/pub.1043971564
143 rdf:type schema:CreativeWork
144 https://doi.org/10.1126/science.1127647 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004607132
145 rdf:type schema:CreativeWork
146 https://doi.org/10.1128/mcb.00987-12 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029045967
147 rdf:type schema:CreativeWork
148 https://doi.org/10.1128/mcb.01529-06 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030878257
149 rdf:type schema:CreativeWork
150 https://doi.org/10.1162/neco.2006.18.7.1527 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004707137
151 rdf:type schema:CreativeWork
152 https://doi.org/10.1207/s15516709cog0901_7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006217895
153 rdf:type schema:CreativeWork
154 https://doi.org/10.18637/jss.v033.i01 schema:sameAs https://app.dimensions.ai/details/publication/pub.1068672496
155 rdf:type schema:CreativeWork
156 https://www.grid.ac/institutes/grid.17091.3e schema:alternateName University of British Columbia
157 schema:name Centre for Molecular Medicine and Therapeutics, University of British Columbia, 950 West 28th Avenue, Vancouver, BC, V5Z 4H4, Canada
158 rdf:type schema:Organization
 




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


...