Fusion of conditional random field and signalp for protein cleavage site prediction

Man Wai Mak; Wei Wang; Sun Yuan Kung

Fusion of conditional random field and signalp for protein cleavage site prediction

Man Wai Mak, Wei Wang, Sun Yuan Kung

The Hong Kong Polytechnic University

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

4 Citations (Scopus)

Abstract

Prediction of protein cleavage sites is an important step in drug design. Recent research has demonstrated that conditional random fields are capable of predicting the cleavage site locations of signal peptides, and their performance is comparable to that of SignalP-a state-of-the-art predictor based on hidden Markov models and neural networks. This paper investigates the degree of complementarity between CRF-based predictors and SignalP and proposes using the complementary properties to fuse the two predictors. It was found that about 40% of the sequences that are incorrectly predicted by SignalP can be correctly predicted by CRF, and that about 30% of the sequences that are incorrectly predicted by CRF can be correctly predicted by SignalP. This suggests that the two predictors complement each other. The paper also shows that the performance of CRF can be further improved by constructing the state features from spatially dispersed amino acids in the training sequences.

Original language	English
Title of host publication	APSIPA ASC 2009 - Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference
Pages	716-721
Number of pages	6
Publication status	Published - 1 Dec 2009
Event	Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference, APSIPA ASC 2009 - Sapporo, Japan Duration: 4 Oct 2009 → 7 Oct 2009

Conference

Conference	Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference, APSIPA ASC 2009
Country/Territory	Japan
City	Sapporo
Period	4/10/09 → 7/10/09

Keywords

Cleavage sites
Conditional random fields
Discriminative models
Protein sequences
Signal peptides

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Electrical and Electronic Engineering
Communication

Cite this

@inproceedings{4ac099a77f854d2887f893a4edfddb2e,

title = "Fusion of conditional random field and signalp for protein cleavage site prediction",

abstract = "Prediction of protein cleavage sites is an important step in drug design. Recent research has demonstrated that conditional random fields are capable of predicting the cleavage site locations of signal peptides, and their performance is comparable to that of SignalP-a state-of-the-art predictor based on hidden Markov models and neural networks. This paper investigates the degree of complementarity between CRF-based predictors and SignalP and proposes using the complementary properties to fuse the two predictors. It was found that about 40% of the sequences that are incorrectly predicted by SignalP can be correctly predicted by CRF, and that about 30% of the sequences that are incorrectly predicted by CRF can be correctly predicted by SignalP. This suggests that the two predictors complement each other. The paper also shows that the performance of CRF can be further improved by constructing the state features from spatially dispersed amino acids in the training sequences.",

keywords = "Cleavage sites, Conditional random fields, Discriminative models, Protein sequences, Signal peptides",

author = "Mak, {Man Wai} and Wei Wang and Kung, {Sun Yuan}",

year = "2009",

month = dec,

day = "1",

language = "English",

pages = "716--721",

booktitle = "APSIPA ASC 2009 - Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference",

note = "Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference, APSIPA ASC 2009 ; Conference date: 04-10-2009 Through 07-10-2009",

}

Mak, MW, Wang, W & Kung, SY 2009, Fusion of conditional random field and signalp for protein cleavage site prediction. in APSIPA ASC 2009 - Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference. pp. 716-721, Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference, APSIPA ASC 2009, Sapporo, Japan, 4/10/09.

Fusion of conditional random field and signalp for protein cleavage site prediction. / Mak, Man Wai; Wang, Wei; Kung, Sun Yuan.
APSIPA ASC 2009 - Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference. 2009. p. 716-721.

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

TY - GEN

T1 - Fusion of conditional random field and signalp for protein cleavage site prediction

AU - Mak, Man Wai

AU - Wang, Wei

AU - Kung, Sun Yuan

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Prediction of protein cleavage sites is an important step in drug design. Recent research has demonstrated that conditional random fields are capable of predicting the cleavage site locations of signal peptides, and their performance is comparable to that of SignalP-a state-of-the-art predictor based on hidden Markov models and neural networks. This paper investigates the degree of complementarity between CRF-based predictors and SignalP and proposes using the complementary properties to fuse the two predictors. It was found that about 40% of the sequences that are incorrectly predicted by SignalP can be correctly predicted by CRF, and that about 30% of the sequences that are incorrectly predicted by CRF can be correctly predicted by SignalP. This suggests that the two predictors complement each other. The paper also shows that the performance of CRF can be further improved by constructing the state features from spatially dispersed amino acids in the training sequences.

AB - Prediction of protein cleavage sites is an important step in drug design. Recent research has demonstrated that conditional random fields are capable of predicting the cleavage site locations of signal peptides, and their performance is comparable to that of SignalP-a state-of-the-art predictor based on hidden Markov models and neural networks. This paper investigates the degree of complementarity between CRF-based predictors and SignalP and proposes using the complementary properties to fuse the two predictors. It was found that about 40% of the sequences that are incorrectly predicted by SignalP can be correctly predicted by CRF, and that about 30% of the sequences that are incorrectly predicted by CRF can be correctly predicted by SignalP. This suggests that the two predictors complement each other. The paper also shows that the performance of CRF can be further improved by constructing the state features from spatially dispersed amino acids in the training sequences.

KW - Cleavage sites

KW - Conditional random fields

KW - Discriminative models

KW - Protein sequences

KW - Signal peptides

UR - http://www.scopus.com/inward/record.url?scp=77950555852&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SP - 716

EP - 721

BT - APSIPA ASC 2009 - Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference

T2 - Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference, APSIPA ASC 2009

Y2 - 4 October 2009 through 7 October 2009

ER -

Fusion of conditional random field and signalp for protein cleavage site prediction

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this