Protein long disordered region prediction based on profile-level disorder propensities and position-specific scoring matrixes

Bin Liu; Lei Lin; Xiaolong Wang; Xuan Wang; Yi Shen

doi:10.1109/BIBM.2009.15

Protein long disordered region prediction based on profile-level disorder propensities and position-specific scoring matrixes

Bin Liu^*, Lei Lin, Xiaolong Wang, Xuan Wang, Yi Shen

^*Corresponding author for this work

Harbin Institute of Technology

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

4 Citations (Scopus)

Abstract

Identification of long disordered regions in protein sequence is important for understanding protein function. In this work, a class of novel propensities at profile level is presented, namely, the order profile disorder propensities, which use the evolutionary information of profile for protein long disorder prediction. These propensities, combined with position-specific scoring matrixes, are inputted to the Logistic Regression (LR) for the prediction of protein long disordered regions. In 5-fold cross-validation test, our method can achieve an area of 97.5% under the ROC cure. Testing on a blind-test set, our method is significantly more accurate than several existing disorder predictors.

Original language	English
Title of host publication	2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009
Pages	66-69
Number of pages	4
DOIs	https://doi.org/10.1109/BIBM.2009.15
Publication status	Published - 2009
Externally published	Yes
Event	2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009 - Washington, D.C., United States Duration: 1 Nov 2009 → 4 Nov 2009

Publication series

Name	2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009

Conference

Conference	2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009
Country/Territory	United States
City	Washington, D.C.
Period	1/11/09 → 4/11/09

Access to Document

10.1109/BIBM.2009.15

Cite this

Liu, B., Lin, L., Wang, X., Wang, X., & Shen, Y. (2009). Protein long disordered region prediction based on profile-level disorder propensities and position-specific scoring matrixes. In 2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009 (pp. 66-69). Article 5341863 (2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009). https://doi.org/10.1109/BIBM.2009.15

@inproceedings{1561c102064641a9b4b097bc836b8138,

title = "Protein long disordered region prediction based on profile-level disorder propensities and position-specific scoring matrixes",

abstract = "Identification of long disordered regions in protein sequence is important for understanding protein function. In this work, a class of novel propensities at profile level is presented, namely, the order profile disorder propensities, which use the evolutionary information of profile for protein long disorder prediction. These propensities, combined with position-specific scoring matrixes, are inputted to the Logistic Regression (LR) for the prediction of protein long disordered regions. In 5-fold cross-validation test, our method can achieve an area of 97.5% under the ROC cure. Testing on a blind-test set, our method is significantly more accurate than several existing disorder predictors.",

author = "Bin Liu and Lei Lin and Xiaolong Wang and Xuan Wang and Yi Shen",

year = "2009",

doi = "10.1109/BIBM.2009.15",

language = "English",

isbn = "9780769538853",

series = "2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009",

pages = "66--69",

booktitle = "2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009",

note = "2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009 ; Conference date: 01-11-2009 Through 04-11-2009",

}

Liu, B, Lin, L, Wang, X, Wang, X & Shen, Y 2009, Protein long disordered region prediction based on profile-level disorder propensities and position-specific scoring matrixes. in 2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009., 5341863, 2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009, pp. 66-69, 2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009, Washington, D.C., United States, 1/11/09. https://doi.org/10.1109/BIBM.2009.15

Protein long disordered region prediction based on profile-level disorder propensities and position-specific scoring matrixes. / Liu, Bin; Lin, Lei; Wang, Xiaolong et al.
2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009. 2009. p. 66-69 5341863 (2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009).

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

TY - GEN

T1 - Protein long disordered region prediction based on profile-level disorder propensities and position-specific scoring matrixes

AU - Liu, Bin

AU - Lin, Lei

AU - Wang, Xiaolong

AU - Wang, Xuan

AU - Shen, Yi

PY - 2009

Y1 - 2009

N2 - Identification of long disordered regions in protein sequence is important for understanding protein function. In this work, a class of novel propensities at profile level is presented, namely, the order profile disorder propensities, which use the evolutionary information of profile for protein long disorder prediction. These propensities, combined with position-specific scoring matrixes, are inputted to the Logistic Regression (LR) for the prediction of protein long disordered regions. In 5-fold cross-validation test, our method can achieve an area of 97.5% under the ROC cure. Testing on a blind-test set, our method is significantly more accurate than several existing disorder predictors.

AB - Identification of long disordered regions in protein sequence is important for understanding protein function. In this work, a class of novel propensities at profile level is presented, namely, the order profile disorder propensities, which use the evolutionary information of profile for protein long disorder prediction. These propensities, combined with position-specific scoring matrixes, are inputted to the Logistic Regression (LR) for the prediction of protein long disordered regions. In 5-fold cross-validation test, our method can achieve an area of 97.5% under the ROC cure. Testing on a blind-test set, our method is significantly more accurate than several existing disorder predictors.

UR - http://www.scopus.com/inward/record.url?scp=74549143798&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2009.15

DO - 10.1109/BIBM.2009.15

M3 - Conference contribution

AN - SCOPUS:74549143798

SN - 9780769538853

T3 - 2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009

SP - 66

EP - 69

BT - 2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009

T2 - 2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009

Y2 - 1 November 2009 through 4 November 2009

ER -

Liu B, Lin L, Wang X, Wang X, Shen Y. Protein long disordered region prediction based on profile-level disorder propensities and position-specific scoring matrixes. In 2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009. 2009. p. 66-69. 5341863. (2009 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2009). doi: 10.1109/BIBM.2009.15

Protein long disordered region prediction based on profile-level disorder propensities and position-specific scoring matrixes

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this