Methods for improving protein disorder prediction

S. Vucetic, P. Radivojac, Z. Obradovic, C. J. Brown, A. Dunker

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

In this paper we propose several methods for improving prediction of protein disorder. These include attribute construction from protein sequence, choice of classifier and postprocessing. While ensembles of neural networks achieved the higher accuracy, the difference as compared to logistic regression classifiers was smaller then 1%. Bagging of neural networks, where moving averages over windows of length 61 were used for attribute construction, combined with postprocessing by averaging predictions over windows of length 81 resulted in 82.6% accuracy for a larger set of ordered and disordered proteins than used previously. This result was a significant improvement over previous methodology, which gave an accuracy of 70.2%. Moreover, unlike the previous methodology, the modified attribute construction allowed prediction at protein ends.

Original languageEnglish (US)
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages2718-2723
Number of pages6
Volume4
StatePublished - 2001
Externally publishedYes
EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States
Duration: Jul 15 2001Jul 19 2001

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'01)
CountryUnited States
CityWashington, DC
Period7/15/017/19/01

Fingerprint

Proteins
Classifiers
Neural networks
Logistics

ASJC Scopus subject areas

  • Software

Cite this

Vucetic, S., Radivojac, P., Obradovic, Z., Brown, C. J., & Dunker, A. (2001). Methods for improving protein disorder prediction. In Proceedings of the International Joint Conference on Neural Networks (Vol. 4, pp. 2718-2723)

Methods for improving protein disorder prediction. / Vucetic, S.; Radivojac, P.; Obradovic, Z.; Brown, C. J.; Dunker, A.

Proceedings of the International Joint Conference on Neural Networks. Vol. 4 2001. p. 2718-2723.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vucetic, S, Radivojac, P, Obradovic, Z, Brown, CJ & Dunker, A 2001, Methods for improving protein disorder prediction. in Proceedings of the International Joint Conference on Neural Networks. vol. 4, pp. 2718-2723, International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States, 7/15/01.
Vucetic S, Radivojac P, Obradovic Z, Brown CJ, Dunker A. Methods for improving protein disorder prediction. In Proceedings of the International Joint Conference on Neural Networks. Vol. 4. 2001. p. 2718-2723
Vucetic, S. ; Radivojac, P. ; Obradovic, Z. ; Brown, C. J. ; Dunker, A. / Methods for improving protein disorder prediction. Proceedings of the International Joint Conference on Neural Networks. Vol. 4 2001. pp. 2718-2723
@inproceedings{c36d0a45883945ceb747f4c1abe07487,
title = "Methods for improving protein disorder prediction",
abstract = "In this paper we propose several methods for improving prediction of protein disorder. These include attribute construction from protein sequence, choice of classifier and postprocessing. While ensembles of neural networks achieved the higher accuracy, the difference as compared to logistic regression classifiers was smaller then 1{\%}. Bagging of neural networks, where moving averages over windows of length 61 were used for attribute construction, combined with postprocessing by averaging predictions over windows of length 81 resulted in 82.6{\%} accuracy for a larger set of ordered and disordered proteins than used previously. This result was a significant improvement over previous methodology, which gave an accuracy of 70.2{\%}. Moreover, unlike the previous methodology, the modified attribute construction allowed prediction at protein ends.",
author = "S. Vucetic and P. Radivojac and Z. Obradovic and Brown, {C. J.} and A. Dunker",
year = "2001",
language = "English (US)",
volume = "4",
pages = "2718--2723",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - Methods for improving protein disorder prediction

AU - Vucetic, S.

AU - Radivojac, P.

AU - Obradovic, Z.

AU - Brown, C. J.

AU - Dunker, A.

PY - 2001

Y1 - 2001

N2 - In this paper we propose several methods for improving prediction of protein disorder. These include attribute construction from protein sequence, choice of classifier and postprocessing. While ensembles of neural networks achieved the higher accuracy, the difference as compared to logistic regression classifiers was smaller then 1%. Bagging of neural networks, where moving averages over windows of length 61 were used for attribute construction, combined with postprocessing by averaging predictions over windows of length 81 resulted in 82.6% accuracy for a larger set of ordered and disordered proteins than used previously. This result was a significant improvement over previous methodology, which gave an accuracy of 70.2%. Moreover, unlike the previous methodology, the modified attribute construction allowed prediction at protein ends.

AB - In this paper we propose several methods for improving prediction of protein disorder. These include attribute construction from protein sequence, choice of classifier and postprocessing. While ensembles of neural networks achieved the higher accuracy, the difference as compared to logistic regression classifiers was smaller then 1%. Bagging of neural networks, where moving averages over windows of length 61 were used for attribute construction, combined with postprocessing by averaging predictions over windows of length 81 resulted in 82.6% accuracy for a larger set of ordered and disordered proteins than used previously. This result was a significant improvement over previous methodology, which gave an accuracy of 70.2%. Moreover, unlike the previous methodology, the modified attribute construction allowed prediction at protein ends.

UR - http://www.scopus.com/inward/record.url?scp=0034865602&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034865602&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034865602

VL - 4

SP - 2718

EP - 2723

BT - Proceedings of the International Joint Conference on Neural Networks

ER -