Using randomised vectors in transcription factor binding site predictions

Faisal I Rezwan; Yi Sun; Neil Davey; Rod Adams; Alistair G. Rust; Mark Robinson

doi:10.1109/ICMLA.2010.82

Using randomised vectors in transcription factor binding site predictions

Faisal I Rezwan, Yi Sun, Neil Davey, Rod Adams, Alistair G. Rust, Mark Robinson

Research output: Contribution to conference › Paper › peer-review

Abstract

Finding the location of binding sites in DNA is a difficult problem. Although the location of some binding sites have been experimentally identified, other parts of the genome may or may not contain binding sites. This poses problems with negative data in a trainable classifier. Here we show that using randomized negative data gives a large boost in classifier performance when compared to the original labeled data.

Original language	English
Pages	523-527
Number of pages	5
DOIs	https://doi.org/10.1109/ICMLA.2010.82
Publication status	Published - 12 Dec 2010
Externally published	Yes
Event	9th IEEE International Conference on Machine Learning and Applications (ICMLA) 2010 - Washington DC, United States of America Duration: 12 Dec 2010 → 14 Dec 2010

Conference

Conference	9th IEEE International Conference on Machine Learning and Applications (ICMLA) 2010
Abbreviated title	ICMLA 2010
Country/Territory	United States of America
City	Washington DC
Period	12 Dec 2010 → 14 Dec 2010

Keywords

Binding site
Classification
Genes
Support
Vector machines

Access to Document

10.1109/ICMLA.2010.82

Permanent link

Persistent link

Cite this

@conference{665eb7c80a7e47cca4f14197d9204af5,

title = "Using randomised vectors in transcription factor binding site predictions",

abstract = "Finding the location of binding sites in DNA is a difficult problem. Although the location of some binding sites have been experimentally identified, other parts of the genome may or may not contain binding sites. This poses problems with negative data in a trainable classifier. Here we show that using randomized negative data gives a large boost in classifier performance when compared to the original labeled data.",

keywords = "Binding site, Classification, Genes, Support, Vector machines",

author = "Rezwan, {Faisal I} and Yi Sun and Neil Davey and Rod Adams and Rust, {Alistair G.} and Mark Robinson",

year = "2010",

month = dec,

day = "12",

doi = "10.1109/ICMLA.2010.82",

language = "English",

pages = "523--527",

note = "9th IEEE International Conference on Machine Learning and Applications (ICMLA) 2010, ICMLA 2010 ; Conference date: 12-12-2010 Through 14-12-2010",

}

TY - CONF

T1 - Using randomised vectors in transcription factor binding site predictions

AU - Rezwan, Faisal I

AU - Sun, Yi

AU - Davey, Neil

AU - Adams, Rod

AU - Rust, Alistair G.

AU - Robinson, Mark

PY - 2010/12/12

Y1 - 2010/12/12

N2 - Finding the location of binding sites in DNA is a difficult problem. Although the location of some binding sites have been experimentally identified, other parts of the genome may or may not contain binding sites. This poses problems with negative data in a trainable classifier. Here we show that using randomized negative data gives a large boost in classifier performance when compared to the original labeled data.

AB - Finding the location of binding sites in DNA is a difficult problem. Although the location of some binding sites have been experimentally identified, other parts of the genome may or may not contain binding sites. This poses problems with negative data in a trainable classifier. Here we show that using randomized negative data gives a large boost in classifier performance when compared to the original labeled data.

KW - Binding site

KW - Classification

KW - Genes

KW - Support

KW - Vector machines

UR - http://www.scopus.com/inward/record.url?scp=79952431294&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2010.82

DO - 10.1109/ICMLA.2010.82

M3 - Paper

SP - 523

EP - 527

T2 - 9th IEEE International Conference on Machine Learning and Applications (ICMLA) 2010

Y2 - 12 December 2010 through 14 December 2010

ER -

Using randomised vectors in transcription factor binding site predictions

Abstract

Conference

Keywords

Access to Document

Permanent link

Other files and links

Fingerprint

Cite this