Sensitivity analysis of boosting PSI-BLAST with case study on subcellular localization

F. Mai; Man Wai Mak; Y. S. Hung; S. Y. Kung

doi:10.1109/MLSP.2007.4414279

Sensitivity analysis of boosting PSI-BLAST with case study on subcellular localization

F. Mai, Man Wai Mak, Y. S. Hung, S. Y. Kung

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

This paper studies the sensitivity of PSI-BLAST with respect to the 'h' parameter. Observing that the standard PSI-BLAST is sensitive to parameter 'h' in the high-value region, we propose a new technique, called Boosting PSI-BLAST, to reduce the sensitivity, By constraining 'h' to a small value first so as to reduce the chance of early corruption and then relaxing it gradually to increase divergence, the boosting PSI-BLAST not only can reduce the sensitivity to h-value, but also may strike a good balance between corruption and divergence in profiles. Tests on Reinhardt and Hubbard's eukaryotic protein dataset verify that our method is better in reducing the sensitivity of profile alignment scores to h-value than the standard PSI-BLAST.

Original language	English
Title of host publication	Machine Learning for Signal Processing 17 - Proceedings of the 2007 IEEE Signal Processing Society Workshop, MLSP
Pages	39-44
Number of pages	6
DOIs	https://doi.org/10.1109/MLSP.2007.4414279
Publication status	Published - 1 Dec 2007
Event	17th IEEE International Workshop on Machine Learning for Signal Processing, MLSP-2007 - Thessaloniki, Greece Duration: 27 Aug 2007 → 29 Aug 2007

Conference

Conference	17th IEEE International Workshop on Machine Learning for Signal Processing, MLSP-2007
Country/Territory	Greece
City	Thessaloniki
Period	27/08/07 → 29/08/07

ASJC Scopus subject areas

General Computer Science
Signal Processing

More information

10.1109/MLSP.2007.4414279

Cite this

@inproceedings{e56f67b0a0824e3f8cf38c2d76499001,

title = "Sensitivity analysis of boosting PSI-BLAST with case study on subcellular localization",

abstract = "This paper studies the sensitivity of PSI-BLAST with respect to the 'h' parameter. Observing that the standard PSI-BLAST is sensitive to parameter 'h' in the high-value region, we propose a new technique, called Boosting PSI-BLAST, to reduce the sensitivity, By constraining 'h' to a small value first so as to reduce the chance of early corruption and then relaxing it gradually to increase divergence, the boosting PSI-BLAST not only can reduce the sensitivity to h-value, but also may strike a good balance between corruption and divergence in profiles. Tests on Reinhardt and Hubbard's eukaryotic protein dataset verify that our method is better in reducing the sensitivity of profile alignment scores to h-value than the standard PSI-BLAST.",

author = "F. Mai and Mak, {Man Wai} and Hung, {Y. S.} and Kung, {S. Y.}",

year = "2007",

month = dec,

day = "1",

doi = "10.1109/MLSP.2007.4414279",

language = "English",

isbn = "1424415667",

pages = "39--44",

booktitle = "Machine Learning for Signal Processing 17 - Proceedings of the 2007 IEEE Signal Processing Society Workshop, MLSP",

note = "17th IEEE International Workshop on Machine Learning for Signal Processing, MLSP-2007 ; Conference date: 27-08-2007 Through 29-08-2007",

}

Mai, F, Mak, MW, Hung, YS & Kung, SY 2007, Sensitivity analysis of boosting PSI-BLAST with case study on subcellular localization. in Machine Learning for Signal Processing 17 - Proceedings of the 2007 IEEE Signal Processing Society Workshop, MLSP., 4414279, pp. 39-44, 17th IEEE International Workshop on Machine Learning for Signal Processing, MLSP-2007, Thessaloniki, Greece, 27/08/07. https://doi.org/10.1109/MLSP.2007.4414279

Sensitivity analysis of boosting PSI-BLAST with case study on subcellular localization. / Mai, F.; Mak, Man Wai; Hung, Y. S. et al.
Machine Learning for Signal Processing 17 - Proceedings of the 2007 IEEE Signal Processing Society Workshop, MLSP. 2007. p. 39-44 4414279.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Sensitivity analysis of boosting PSI-BLAST with case study on subcellular localization

AU - Mai, F.

AU - Mak, Man Wai

AU - Hung, Y. S.

AU - Kung, S. Y.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - This paper studies the sensitivity of PSI-BLAST with respect to the 'h' parameter. Observing that the standard PSI-BLAST is sensitive to parameter 'h' in the high-value region, we propose a new technique, called Boosting PSI-BLAST, to reduce the sensitivity, By constraining 'h' to a small value first so as to reduce the chance of early corruption and then relaxing it gradually to increase divergence, the boosting PSI-BLAST not only can reduce the sensitivity to h-value, but also may strike a good balance between corruption and divergence in profiles. Tests on Reinhardt and Hubbard's eukaryotic protein dataset verify that our method is better in reducing the sensitivity of profile alignment scores to h-value than the standard PSI-BLAST.

AB - This paper studies the sensitivity of PSI-BLAST with respect to the 'h' parameter. Observing that the standard PSI-BLAST is sensitive to parameter 'h' in the high-value region, we propose a new technique, called Boosting PSI-BLAST, to reduce the sensitivity, By constraining 'h' to a small value first so as to reduce the chance of early corruption and then relaxing it gradually to increase divergence, the boosting PSI-BLAST not only can reduce the sensitivity to h-value, but also may strike a good balance between corruption and divergence in profiles. Tests on Reinhardt and Hubbard's eukaryotic protein dataset verify that our method is better in reducing the sensitivity of profile alignment scores to h-value than the standard PSI-BLAST.

UR - http://www.scopus.com/inward/record.url?scp=48149087990&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2007.4414279

DO - 10.1109/MLSP.2007.4414279

M3 - Conference article published in proceeding or book

SN - 1424415667

SN - 9781424415663

SP - 39

EP - 44

BT - Machine Learning for Signal Processing 17 - Proceedings of the 2007 IEEE Signal Processing Society Workshop, MLSP

T2 - 17th IEEE International Workshop on Machine Learning for Signal Processing, MLSP-2007

Y2 - 27 August 2007 through 29 August 2007

ER -

Sensitivity analysis of boosting PSI-BLAST with case study on subcellular localization

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this