A Gram-Negative Bacterial Secreted Protein Types Prediction Method Based on PSI-BLAST Profile

Prediction of secreted protein types based solely on sequence data remains to be a challenging problem. In this study, we extract the long-range correlation information and linear correlation information from position-specific score matrix (PSSM). A total of 6800 features are extracted at 17 differe...

Full description

Bibliographic Details
Main Authors: Shuyan Ding, Shengli Zhang
Format: Article
Language:English
Published: Hindawi Limited 2016-01-01
Series:BioMed Research International
Online Access:http://dx.doi.org/10.1155/2016/3206741
id doaj-bec447d0f1a34e36b7314939f513f092
record_format Article
spelling doaj-bec447d0f1a34e36b7314939f513f0922020-11-25T00:44:58ZengHindawi LimitedBioMed Research International2314-61332314-61412016-01-01201610.1155/2016/32067413206741A Gram-Negative Bacterial Secreted Protein Types Prediction Method Based on PSI-BLAST ProfileShuyan Ding0Shengli Zhang1Department of Sciences, Dalian Nationalities University, Dalian 116600, ChinaSchool of Mathematics and Statistics, Xidian University, Xi’an 710071, ChinaPrediction of secreted protein types based solely on sequence data remains to be a challenging problem. In this study, we extract the long-range correlation information and linear correlation information from position-specific score matrix (PSSM). A total of 6800 features are extracted at 17 different gaps; then, 309 features are selected by a filter feature selection method based on the training set. To verify the performance of our method, jackknife and independent dataset tests are performed on the test set and the reported overall accuracies are 93.60% and 100%, respectively. Comparison of our results with the existing method shows that our method provides the favorable performance for secreted protein type prediction.http://dx.doi.org/10.1155/2016/3206741
collection DOAJ
language English
format Article
sources DOAJ
author Shuyan Ding
Shengli Zhang
spellingShingle Shuyan Ding
Shengli Zhang
A Gram-Negative Bacterial Secreted Protein Types Prediction Method Based on PSI-BLAST Profile
BioMed Research International
author_facet Shuyan Ding
Shengli Zhang
author_sort Shuyan Ding
title A Gram-Negative Bacterial Secreted Protein Types Prediction Method Based on PSI-BLAST Profile
title_short A Gram-Negative Bacterial Secreted Protein Types Prediction Method Based on PSI-BLAST Profile
title_full A Gram-Negative Bacterial Secreted Protein Types Prediction Method Based on PSI-BLAST Profile
title_fullStr A Gram-Negative Bacterial Secreted Protein Types Prediction Method Based on PSI-BLAST Profile
title_full_unstemmed A Gram-Negative Bacterial Secreted Protein Types Prediction Method Based on PSI-BLAST Profile
title_sort gram-negative bacterial secreted protein types prediction method based on psi-blast profile
publisher Hindawi Limited
series BioMed Research International
issn 2314-6133
2314-6141
publishDate 2016-01-01
description Prediction of secreted protein types based solely on sequence data remains to be a challenging problem. In this study, we extract the long-range correlation information and linear correlation information from position-specific score matrix (PSSM). A total of 6800 features are extracted at 17 different gaps; then, 309 features are selected by a filter feature selection method based on the training set. To verify the performance of our method, jackknife and independent dataset tests are performed on the test set and the reported overall accuracies are 93.60% and 100%, respectively. Comparison of our results with the existing method shows that our method provides the favorable performance for secreted protein type prediction.
url http://dx.doi.org/10.1155/2016/3206741
work_keys_str_mv AT shuyanding agramnegativebacterialsecretedproteintypespredictionmethodbasedonpsiblastprofile
AT shenglizhang agramnegativebacterialsecretedproteintypespredictionmethodbasedonpsiblastprofile
AT shuyanding gramnegativebacterialsecretedproteintypespredictionmethodbasedonpsiblastprofile
AT shenglizhang gramnegativebacterialsecretedproteintypespredictionmethodbasedonpsiblastprofile
_version_ 1725272176284663808