Using sampling methods to improve binding site predictions

Yi. Sun; M. Robinson; R.G. Adams; R. Te Boekhorst; A.G. Rust; N. Davey

Using sampling methods to improve binding site predictions

Yi. Sun, M. Robinson, R.G. Adams, R. Te Boekhorst, A.G. Rust, N. Davey

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

42 Downloads (Pure)

Abstract

Currently the best algorithms for transcription factor binding site prediction are severely limited in accuracy. In previous work we combine random selection under-sampling into SMOTE over-sampling technique, working with several classification algorithms from machine learning field to integrate binding site predictions. In this paper, we improve the classification result with the aid of Tomek links as an either undersampling or cleaning technique.

Original language	English
Title of host publication	In: Procs of the 14th European Symposium on Artificial Neural Networks, ESANN 2006
Pages	533-538
Publication status	Published - 2006

Access to Document

900846.pdf

Cite this

@inproceedings{6ed8fd635680486f8ea0b30754b65a8b,

title = "Using sampling methods to improve binding site predictions",

abstract = "Currently the best algorithms for transcription factor binding site prediction are severely limited in accuracy. In previous work we combine random selection under-sampling into SMOTE over-sampling technique, working with several classification algorithms from machine learning field to integrate binding site predictions. In this paper, we improve the classification result with the aid of Tomek links as an either undersampling or cleaning technique.",

author = "Yi. Sun and M. Robinson and R.G. Adams and {Te Boekhorst}, R. and A.G. Rust and N. Davey",

year = "2006",

language = "English",

isbn = "2-930307-06-4",

pages = "533--538",

booktitle = "In: Procs of the 14th European Symposium on Artificial Neural Networks, ESANN 2006",

}

TY - GEN

T1 - Using sampling methods to improve binding site predictions

AU - Sun, Yi.

AU - Robinson, M.

AU - Adams, R.G.

AU - Te Boekhorst, R.

AU - Rust, A.G.

AU - Davey, N.

PY - 2006

Y1 - 2006

N2 - Currently the best algorithms for transcription factor binding site prediction are severely limited in accuracy. In previous work we combine random selection under-sampling into SMOTE over-sampling technique, working with several classification algorithms from machine learning field to integrate binding site predictions. In this paper, we improve the classification result with the aid of Tomek links as an either undersampling or cleaning technique.

AB - Currently the best algorithms for transcription factor binding site prediction are severely limited in accuracy. In previous work we combine random selection under-sampling into SMOTE over-sampling technique, working with several classification algorithms from machine learning field to integrate binding site predictions. In this paper, we improve the classification result with the aid of Tomek links as an either undersampling or cleaning technique.

M3 - Conference contribution

SN - 2-930307-06-4

SP - 533

EP - 538

BT - In: Procs of the 14th European Symposium on Artificial Neural Networks, ESANN 2006

ER -

Using sampling methods to improve binding site predictions

Abstract

Access to Document

Fingerprint

Cite this