Eintrag weiter verarbeiten
Interaction-based feature selection and classification for high-dimensional biological data
Gespeichert in:
Zeitschriftentitel: | Bioinformatics |
---|---|
Personen und Körperschaften: | , , , |
In: | Bioinformatics, 28, 2012, 21, S. 2834-2842 |
Format: | E-Article |
Sprache: | Englisch |
veröffentlicht: |
Oxford University Press (OUP)
|
Schlagwörter: |
author_facet |
Wang, Haitian Lo, Shaw-Hwa Zheng, Tian Hu, Inchi Wang, Haitian Lo, Shaw-Hwa Zheng, Tian Hu, Inchi |
---|---|
author |
Wang, Haitian Lo, Shaw-Hwa Zheng, Tian Hu, Inchi |
spellingShingle |
Wang, Haitian Lo, Shaw-Hwa Zheng, Tian Hu, Inchi Bioinformatics Interaction-based feature selection and classification for high-dimensional biological data Computational Mathematics Computational Theory and Mathematics Computer Science Applications Molecular Biology Biochemistry Statistics and Probability |
author_sort |
wang, haitian |
spelling |
Wang, Haitian Lo, Shaw-Hwa Zheng, Tian Hu, Inchi 1367-4811 1367-4803 Oxford University Press (OUP) Computational Mathematics Computational Theory and Mathematics Computer Science Applications Molecular Biology Biochemistry Statistics and Probability http://dx.doi.org/10.1093/bioinformatics/bts531 <jats:title>Abstract</jats:title> <jats:p>Motivation: Epistasis or gene–gene interaction has gained increasing attention in studies of complex diseases. Its presence as an ubiquitous component of genetic architecture of common human diseases has been contemplated. However, the detection of gene–gene interaction is difficult due to combinatorial explosion.</jats:p> <jats:p>Results: We present a novel feature selection method incorporating variable interaction. Three gene expression datasets are analyzed to illustrate our method, although it can also be applied to other types of high-dimensional data. The quality of variables selected is evaluated in two ways: first by classification error rates, then by functional relevance assessed using biological knowledge. We show that the classification error rates can be significantly reduced by considering interactions. Secondly, a sizable portion of genes identified by our method for breast cancer metastasis overlaps with those reported in gene-to-system breast cancer (G2SBC) database as disease associated and some of them have interesting biological implication. In summary, interaction-based methods may lead to substantial gain in biological insights as well as more accurate prediction.</jats:p> <jats:p>Contact: imichu@ust.hk; slo@stat.columnbia.edu</jats:p> <jats:p>Supplementary information: Supplementary data are available at the Bioinformatics online.</jats:p> Interaction-based feature selection and classification for high-dimensional biological data Bioinformatics |
doi_str_mv |
10.1093/bioinformatics/bts531 |
facet_avail |
Online Free |
finc_class_facet |
Mathematik Informatik Biologie Chemie und Pharmazie |
format |
ElectronicArticle |
fullrecord |
blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTA5My9iaW9pbmZvcm1hdGljcy9idHM1MzE |
id |
ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTA5My9iaW9pbmZvcm1hdGljcy9idHM1MzE |
institution |
DE-D275 DE-Bn3 DE-Brt1 DE-Zwi2 DE-D161 DE-Zi4 DE-Gla1 DE-15 DE-Pl11 DE-Rs1 DE-14 DE-105 DE-Ch1 DE-L229 |
imprint |
Oxford University Press (OUP), 2012 |
imprint_str_mv |
Oxford University Press (OUP), 2012 |
issn |
1367-4811 1367-4803 |
issn_str_mv |
1367-4811 1367-4803 |
language |
English |
mega_collection |
Oxford University Press (OUP) (CrossRef) |
match_str |
wang2012interactionbasedfeatureselectionandclassificationforhighdimensionalbiologicaldata |
publishDateSort |
2012 |
publisher |
Oxford University Press (OUP) |
recordtype |
ai |
record_format |
ai |
series |
Bioinformatics |
source_id |
49 |
title |
Interaction-based feature selection and classification for high-dimensional biological data |
title_unstemmed |
Interaction-based feature selection and classification for high-dimensional biological data |
title_full |
Interaction-based feature selection and classification for high-dimensional biological data |
title_fullStr |
Interaction-based feature selection and classification for high-dimensional biological data |
title_full_unstemmed |
Interaction-based feature selection and classification for high-dimensional biological data |
title_short |
Interaction-based feature selection and classification for high-dimensional biological data |
title_sort |
interaction-based feature selection and classification for high-dimensional biological data |
topic |
Computational Mathematics Computational Theory and Mathematics Computer Science Applications Molecular Biology Biochemistry Statistics and Probability |
url |
http://dx.doi.org/10.1093/bioinformatics/bts531 |
publishDate |
2012 |
physical |
2834-2842 |
description |
<jats:title>Abstract</jats:title>
<jats:p>Motivation: Epistasis or gene–gene interaction has gained increasing attention in studies of complex diseases. Its presence as an ubiquitous component of genetic architecture of common human diseases has been contemplated. However, the detection of gene–gene interaction is difficult due to combinatorial explosion.</jats:p>
<jats:p>Results: We present a novel feature selection method incorporating variable interaction. Three gene expression datasets are analyzed to illustrate our method, although it can also be applied to other types of high-dimensional data. The quality of variables selected is evaluated in two ways: first by classification error rates, then by functional relevance assessed using biological knowledge. We show that the classification error rates can be significantly reduced by considering interactions. Secondly, a sizable portion of genes identified by our method for breast cancer metastasis overlaps with those reported in gene-to-system breast cancer (G2SBC) database as disease associated and some of them have interesting biological implication. In summary, interaction-based methods may lead to substantial gain in biological insights as well as more accurate prediction.</jats:p>
<jats:p>Contact: imichu@ust.hk; slo@stat.columnbia.edu</jats:p>
<jats:p>Supplementary information: Supplementary data are available at the Bioinformatics online.</jats:p> |
container_issue |
21 |
container_start_page |
2834 |
container_title |
Bioinformatics |
container_volume |
28 |
format_de105 |
Article, E-Article |
format_de14 |
Article, E-Article |
format_de15 |
Article, E-Article |
format_de520 |
Article, E-Article |
format_de540 |
Article, E-Article |
format_dech1 |
Article, E-Article |
format_ded117 |
Article, E-Article |
format_degla1 |
E-Article |
format_del152 |
Buch |
format_del189 |
Article, E-Article |
format_dezi4 |
Article |
format_dezwi2 |
Article, E-Article |
format_finc |
Article, E-Article |
format_nrw |
Article, E-Article |
_version_ |
1792346317703348233 |
geogr_code |
not assigned |
last_indexed |
2024-03-01T17:36:38.59Z |
geogr_code_person |
not assigned |
openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=Interaction-based+feature+selection+and+classification+for+high-dimensional+biological+data&rft.date=2012-11-01&genre=article&issn=1367-4803&volume=28&issue=21&spage=2834&epage=2842&pages=2834-2842&jtitle=Bioinformatics&atitle=Interaction-based+feature+selection+and+classification+for+high-dimensional+biological+data&aulast=Hu&aufirst=Inchi&rft_id=info%3Adoi%2F10.1093%2Fbioinformatics%2Fbts531&rft.language%5B0%5D=eng |
SOLR | |
_version_ | 1792346317703348233 |
author | Wang, Haitian, Lo, Shaw-Hwa, Zheng, Tian, Hu, Inchi |
author_facet | Wang, Haitian, Lo, Shaw-Hwa, Zheng, Tian, Hu, Inchi, Wang, Haitian, Lo, Shaw-Hwa, Zheng, Tian, Hu, Inchi |
author_sort | wang, haitian |
container_issue | 21 |
container_start_page | 2834 |
container_title | Bioinformatics |
container_volume | 28 |
description | <jats:title>Abstract</jats:title> <jats:p>Motivation: Epistasis or gene–gene interaction has gained increasing attention in studies of complex diseases. Its presence as an ubiquitous component of genetic architecture of common human diseases has been contemplated. However, the detection of gene–gene interaction is difficult due to combinatorial explosion.</jats:p> <jats:p>Results: We present a novel feature selection method incorporating variable interaction. Three gene expression datasets are analyzed to illustrate our method, although it can also be applied to other types of high-dimensional data. The quality of variables selected is evaluated in two ways: first by classification error rates, then by functional relevance assessed using biological knowledge. We show that the classification error rates can be significantly reduced by considering interactions. Secondly, a sizable portion of genes identified by our method for breast cancer metastasis overlaps with those reported in gene-to-system breast cancer (G2SBC) database as disease associated and some of them have interesting biological implication. In summary, interaction-based methods may lead to substantial gain in biological insights as well as more accurate prediction.</jats:p> <jats:p>Contact: imichu@ust.hk; slo@stat.columnbia.edu</jats:p> <jats:p>Supplementary information: Supplementary data are available at the Bioinformatics online.</jats:p> |
doi_str_mv | 10.1093/bioinformatics/bts531 |
facet_avail | Online, Free |
finc_class_facet | Mathematik, Informatik, Biologie, Chemie und Pharmazie |
format | ElectronicArticle |
format_de105 | Article, E-Article |
format_de14 | Article, E-Article |
format_de15 | Article, E-Article |
format_de520 | Article, E-Article |
format_de540 | Article, E-Article |
format_dech1 | Article, E-Article |
format_ded117 | Article, E-Article |
format_degla1 | E-Article |
format_del152 | Buch |
format_del189 | Article, E-Article |
format_dezi4 | Article |
format_dezwi2 | Article, E-Article |
format_finc | Article, E-Article |
format_nrw | Article, E-Article |
geogr_code | not assigned |
geogr_code_person | not assigned |
id | ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTA5My9iaW9pbmZvcm1hdGljcy9idHM1MzE |
imprint | Oxford University Press (OUP), 2012 |
imprint_str_mv | Oxford University Press (OUP), 2012 |
institution | DE-D275, DE-Bn3, DE-Brt1, DE-Zwi2, DE-D161, DE-Zi4, DE-Gla1, DE-15, DE-Pl11, DE-Rs1, DE-14, DE-105, DE-Ch1, DE-L229 |
issn | 1367-4811, 1367-4803 |
issn_str_mv | 1367-4811, 1367-4803 |
language | English |
last_indexed | 2024-03-01T17:36:38.59Z |
match_str | wang2012interactionbasedfeatureselectionandclassificationforhighdimensionalbiologicaldata |
mega_collection | Oxford University Press (OUP) (CrossRef) |
physical | 2834-2842 |
publishDate | 2012 |
publishDateSort | 2012 |
publisher | Oxford University Press (OUP) |
record_format | ai |
recordtype | ai |
series | Bioinformatics |
source_id | 49 |
spelling | Wang, Haitian Lo, Shaw-Hwa Zheng, Tian Hu, Inchi 1367-4811 1367-4803 Oxford University Press (OUP) Computational Mathematics Computational Theory and Mathematics Computer Science Applications Molecular Biology Biochemistry Statistics and Probability http://dx.doi.org/10.1093/bioinformatics/bts531 <jats:title>Abstract</jats:title> <jats:p>Motivation: Epistasis or gene–gene interaction has gained increasing attention in studies of complex diseases. Its presence as an ubiquitous component of genetic architecture of common human diseases has been contemplated. However, the detection of gene–gene interaction is difficult due to combinatorial explosion.</jats:p> <jats:p>Results: We present a novel feature selection method incorporating variable interaction. Three gene expression datasets are analyzed to illustrate our method, although it can also be applied to other types of high-dimensional data. The quality of variables selected is evaluated in two ways: first by classification error rates, then by functional relevance assessed using biological knowledge. We show that the classification error rates can be significantly reduced by considering interactions. Secondly, a sizable portion of genes identified by our method for breast cancer metastasis overlaps with those reported in gene-to-system breast cancer (G2SBC) database as disease associated and some of them have interesting biological implication. In summary, interaction-based methods may lead to substantial gain in biological insights as well as more accurate prediction.</jats:p> <jats:p>Contact: imichu@ust.hk; slo@stat.columnbia.edu</jats:p> <jats:p>Supplementary information: Supplementary data are available at the Bioinformatics online.</jats:p> Interaction-based feature selection and classification for high-dimensional biological data Bioinformatics |
spellingShingle | Wang, Haitian, Lo, Shaw-Hwa, Zheng, Tian, Hu, Inchi, Bioinformatics, Interaction-based feature selection and classification for high-dimensional biological data, Computational Mathematics, Computational Theory and Mathematics, Computer Science Applications, Molecular Biology, Biochemistry, Statistics and Probability |
title | Interaction-based feature selection and classification for high-dimensional biological data |
title_full | Interaction-based feature selection and classification for high-dimensional biological data |
title_fullStr | Interaction-based feature selection and classification for high-dimensional biological data |
title_full_unstemmed | Interaction-based feature selection and classification for high-dimensional biological data |
title_short | Interaction-based feature selection and classification for high-dimensional biological data |
title_sort | interaction-based feature selection and classification for high-dimensional biological data |
title_unstemmed | Interaction-based feature selection and classification for high-dimensional biological data |
topic | Computational Mathematics, Computational Theory and Mathematics, Computer Science Applications, Molecular Biology, Biochemistry, Statistics and Probability |
url | http://dx.doi.org/10.1093/bioinformatics/bts531 |