Links to Exploration step
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Selection bias in gene extraction on the basis of microarray gene-expression data</title><author><name sortKey="Ambroise, Christophe" sort="Ambroise, Christophe" uniqKey="Ambroise C" first="Christophe" last="Ambroise">Christophe Ambroise</name><affiliation><nlm:aff wicri:cut="; and" id="N0x8ba7258.0xa0b5150">Laboratoire Heudiasyc, Unité Mixte de Recherche/Centre National de la Recherche Scientifique 6599, 60200 Compiègne, France</nlm:aff></affiliation></author><author><name sortKey="Mclachlan, Geoffrey J" sort="Mclachlan, Geoffrey J" uniqKey="Mclachlan G" first="Geoffrey J." last="Mclachlan">Geoffrey J. Mclachlan</name><affiliation><nlm:aff id="N0x8ba7258.0xa0b5150">Department of Mathematics, University of Queensland, Brisbane 4072, Australia</nlm:aff></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PMC</idno><idno type="pmid">11983868</idno><idno type="pmc">124442</idno><idno type="url">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC124442</idno><idno type="RBID">PMC:124442</idno><idno type="doi">10.1073/pnas.102102699</idno><date when="2002">2002</date><idno type="wicri:Area/Pmc/Corpus">000A26</idno><idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Corpus" wicri:corpus="PMC">000A26</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a" type="main">Selection bias in gene extraction on the basis of microarray gene-expression data</title><author><name sortKey="Ambroise, Christophe" sort="Ambroise, Christophe" uniqKey="Ambroise C" first="Christophe" last="Ambroise">Christophe Ambroise</name><affiliation><nlm:aff wicri:cut="; and" id="N0x8ba7258.0xa0b5150">Laboratoire Heudiasyc, Unité Mixte de Recherche/Centre National de la Recherche Scientifique 6599, 60200 Compiègne, France</nlm:aff></affiliation></author><author><name sortKey="Mclachlan, Geoffrey J" sort="Mclachlan, Geoffrey J" uniqKey="Mclachlan G" first="Geoffrey J." last="Mclachlan">Geoffrey J. Mclachlan</name><affiliation><nlm:aff id="N0x8ba7258.0xa0b5150">Department of Mathematics, University of Queensland, Brisbane 4072, Australia</nlm:aff></affiliation></author></analytic><series><title level="j">Proceedings of the National Academy of Sciences of the United States of America</title><idno type="ISSN">0027-8424</idno><idno type="eISSN">1091-6490</idno><imprint><date when="2002">2002</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en"><p>In the context of cancer diagnosis and treatment, we consider the problem of constructing an accurate prediction rule on the basis of a relatively small number of tumor tissue samples of known type containing the expression data on very many (possibly thousands) genes. Recently, results have been presented in the literature suggesting that it is possible to construct a prediction rule from only a few genes such that it has a negligible prediction error rate. However, in these results the test error or the leave-one-out cross-validated error is calculated without allowance for the selection bias. There is no allowance because the rule is either tested on tissue samples that were used in the first instance to select the genes being used in the rule or because the cross-validation of the rule is not external to the selection process; that is, gene selection is not performed in training the rule at each stage of the cross-validation process. We describe how in practice the selection bias can be assessed and corrected for by either performing a cross-validation or applying the bootstrap external to the selection process. We recommend using 10-fold rather than leave-one-out cross-validation, and concerning the bootstrap, we suggest using the so-called .632+ bootstrap error estimate designed to handle overfitted prediction rules. Using two published data sets, we demonstrate that when correction is made for the selection bias, the cross-validated error is no longer zero for a subset of only a few genes.</p></div></front></TEI><pmc article-type="research-article"><pmc-comment>The publisher of this article does not allow downloading of the full text in XML form.</pmc-comment>
<front><journal-meta><journal-id journal-id-type="nlm-ta">Proc Natl Acad Sci U S A</journal-id><journal-id journal-id-type="publisher-id">PNAS</journal-id><journal-title>Proceedings of the National Academy of Sciences of the United States of America</journal-title><issn pub-type="ppub">0027-8424</issn><issn pub-type="epub">1091-6490</issn><publisher><publisher-name>The National Academy of Sciences</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="pmid">11983868</article-id><article-id pub-id-type="pmc">124442</article-id><article-id pub-id-type="publisher-id">102102699</article-id><article-id pub-id-type="publisher-id">1026</article-id><article-id pub-id-type="doi">10.1073/pnas.102102699</article-id><article-categories><subj-group subj-group-type="heading"><subject>Physical Sciences</subject><subj-group><subject>Statistics</subject></subj-group></subj-group></article-categories><title-group><article-title>Selection bias in gene extraction on the basis of microarray gene-expression data</article-title></title-group><contrib-group><contrib contrib-type="author"><name><surname>Ambroise</surname><given-names>Christophe</given-names></name><xref ref-type="aff" rid="N0x8ba7258.0xa0b5150">†</xref></contrib><contrib contrib-type="author"><name><surname>McLachlan</surname><given-names>Geoffrey J.</given-names></name><xref ref-type="aff" rid="N0x8ba7258.0xa0b5150">‡</xref><xref ref-type="author-notes" rid="FN153">§</xref></contrib></contrib-group><aff id="N0x8ba7258.0xa0b5150"><label>†</label>Laboratoire Heudiasyc, Unité Mixte de Recherche/Centre National de la Recherche Scientifique 6599, 60200 Compiègne, France; and<label>‡</label>Department of Mathematics, University of Queensland, Brisbane 4072, Australia</aff><author-notes><fn id="FN153"><label>§</label><p>To whom reprint requests should be addressed. E-mail: <email>gjm@maths.uq.edu.au</email>.</p></fn><fn><p>Edited by Stephen E. Fienberg, Carnegie Mellon University, Pittsburgh, PA, and approved March 21, 2002</p></fn></author-notes><pub-date pub-type="ppub"><day>14</day><month>5</month><year>2002</year></pub-date><pub-date pub-type="epub"><day>30</day><month>4</month><year>2002</year></pub-date><volume>99</volume><issue>10</issue><fpage>6562</fpage><lpage>6566</lpage><history><date date-type="received"><day>20</day><month>2</month><year>2002</year></date></history><copyright-statement>Copyright © 2002, The National Academy of Sciences</copyright-statement><copyright-year>2002</copyright-year><abstract><p>In the context of cancer diagnosis and treatment, we consider the problem of constructing an accurate prediction rule on the basis of a relatively small number of tumor tissue samples of known type containing the expression data on very many (possibly thousands) genes. Recently, results have been presented in the literature suggesting that it is possible to construct a prediction rule from only a few genes such that it has a negligible prediction error rate. However, in these results the test error or the leave-one-out cross-validated error is calculated without allowance for the selection bias. There is no allowance because the rule is either tested on tissue samples that were used in the first instance to select the genes being used in the rule or because the cross-validation of the rule is not external to the selection process; that is, gene selection is not performed in training the rule at each stage of the cross-validation process. We describe how in practice the selection bias can be assessed and corrected for by either performing a cross-validation or applying the bootstrap external to the selection process. We recommend using 10-fold rather than leave-one-out cross-validation, and concerning the bootstrap, we suggest using the so-called .632+ bootstrap error estimate designed to handle overfitted prediction rules. Using two published data sets, we demonstrate that when correction is made for the selection bias, the cross-validated error is no longer zero for a subset of only a few genes.</p></abstract></article-meta></front></pmc></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Asie/explor/AustralieFrV1/Data/Pmc/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000A269 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Pmc/Corpus/biblio.hfd -nk 000A269 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Asie
|area= AustralieFrV1
|flux= Pmc
|étape= Corpus
|type= RBID
|clé=
|texte=
}}
| This area was generated with Dilib version V0.6.33. |  |