Prediction of Protein–Protein Interactions with Clustered Amino Acids and Weighted Sparse Representation
With the completion of the Human Genome Project, bioscience has entered into the era of the genome and proteome. Therefore, protein–protein interactions (PPIs) research is becoming more and more important. Life activities and the protein–protein interactions are inseparable, such as DNA synthesis, g...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2015-05-01
|
Series: | International Journal of Molecular Sciences |
Subjects: | |
Online Access: | http://www.mdpi.com/1422-0067/16/5/10855 |
id |
doaj-bb91a7a3fe5943b6b50f483d5ffc1cc8 |
---|---|
record_format |
Article |
spelling |
doaj-bb91a7a3fe5943b6b50f483d5ffc1cc82020-11-25T02:32:25ZengMDPI AGInternational Journal of Molecular Sciences1422-00672015-05-01165108551086910.3390/ijms160510855ijms160510855Prediction of Protein–Protein Interactions with Clustered Amino Acids and Weighted Sparse RepresentationQiaoying Huang0Zhuhong You1Xiaofeng Zhang2Yong Zhou3Shenzhen Graduate School, Harbin Institute of Technology, HIT Campus of University Town of Shenzhen, Shenzhen 518055, ChinaSchool of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, ChinaShenzhen Graduate School, Harbin Institute of Technology, HIT Campus of University Town of Shenzhen, Shenzhen 518055, ChinaSchool of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, ChinaWith the completion of the Human Genome Project, bioscience has entered into the era of the genome and proteome. Therefore, protein–protein interactions (PPIs) research is becoming more and more important. Life activities and the protein–protein interactions are inseparable, such as DNA synthesis, gene transcription activation, protein translation, etc. Though many methods based on biological experiments and machine learning have been proposed, they all spent a long time to learn and obtained an imprecise accuracy. How to efficiently and accurately predict PPIs is still a big challenge. To take up such a challenge, we developed a new predictor by incorporating the reduced amino acid alphabet (RAAA) information into the general form of pseudo-amino acid composition (PseAAC) and with the weighted sparse representation-based classification (WSRC). The remarkable advantages of introducing the reduced amino acid alphabet is being able to avoid the notorious dimensionality disaster or overfitting problem in statistical prediction. Additionally, experiments have proven that our method achieved good performance in both a low- and high-dimensional feature space. Among all of the experiments performed on the PPIs data of Saccharomyces cerevisiae, the best one achieved 90.91% accuracy, 94.17% sensitivity, 87.22% precision and a 83.43% Matthews correlation coefficient (MCC) value. In order to evaluate the prediction ability of our method, extensive experiments are performed to compare with the state-of-the-art technique, support vector machine (SVM). The achieved results show that the proposed approach is very promising for predicting PPIs, and it can be a helpful supplement for PPIs prediction.http://www.mdpi.com/1422-0067/16/5/10855reduced amino acid alphabetweighted sparse representation-based classificationprotein–protein interactions |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Qiaoying Huang Zhuhong You Xiaofeng Zhang Yong Zhou |
spellingShingle |
Qiaoying Huang Zhuhong You Xiaofeng Zhang Yong Zhou Prediction of Protein–Protein Interactions with Clustered Amino Acids and Weighted Sparse Representation International Journal of Molecular Sciences reduced amino acid alphabet weighted sparse representation-based classification protein–protein interactions |
author_facet |
Qiaoying Huang Zhuhong You Xiaofeng Zhang Yong Zhou |
author_sort |
Qiaoying Huang |
title |
Prediction of Protein–Protein Interactions with Clustered Amino Acids and Weighted Sparse Representation |
title_short |
Prediction of Protein–Protein Interactions with Clustered Amino Acids and Weighted Sparse Representation |
title_full |
Prediction of Protein–Protein Interactions with Clustered Amino Acids and Weighted Sparse Representation |
title_fullStr |
Prediction of Protein–Protein Interactions with Clustered Amino Acids and Weighted Sparse Representation |
title_full_unstemmed |
Prediction of Protein–Protein Interactions with Clustered Amino Acids and Weighted Sparse Representation |
title_sort |
prediction of protein–protein interactions with clustered amino acids and weighted sparse representation |
publisher |
MDPI AG |
series |
International Journal of Molecular Sciences |
issn |
1422-0067 |
publishDate |
2015-05-01 |
description |
With the completion of the Human Genome Project, bioscience has entered into the era of the genome and proteome. Therefore, protein–protein interactions (PPIs) research is becoming more and more important. Life activities and the protein–protein interactions are inseparable, such as DNA synthesis, gene transcription activation, protein translation, etc. Though many methods based on biological experiments and machine learning have been proposed, they all spent a long time to learn and obtained an imprecise accuracy. How to efficiently and accurately predict PPIs is still a big challenge. To take up such a challenge, we developed a new predictor by incorporating the reduced amino acid alphabet (RAAA) information into the general form of pseudo-amino acid composition (PseAAC) and with the weighted sparse representation-based classification (WSRC). The remarkable advantages of introducing the reduced amino acid alphabet is being able to avoid the notorious dimensionality disaster or overfitting problem in statistical prediction. Additionally, experiments have proven that our method achieved good performance in both a low- and high-dimensional feature space. Among all of the experiments performed on the PPIs data of Saccharomyces cerevisiae, the best one achieved 90.91% accuracy, 94.17% sensitivity, 87.22% precision and a 83.43% Matthews correlation coefficient (MCC) value. In order to evaluate the prediction ability of our method, extensive experiments are performed to compare with the state-of-the-art technique, support vector machine (SVM). The achieved results show that the proposed approach is very promising for predicting PPIs, and it can be a helpful supplement for PPIs prediction. |
topic |
reduced amino acid alphabet weighted sparse representation-based classification protein–protein interactions |
url |
http://www.mdpi.com/1422-0067/16/5/10855 |
work_keys_str_mv |
AT qiaoyinghuang predictionofproteinproteininteractionswithclusteredaminoacidsandweightedsparserepresentation AT zhuhongyou predictionofproteinproteininteractionswithclusteredaminoacidsandweightedsparserepresentation AT xiaofengzhang predictionofproteinproteininteractionswithclusteredaminoacidsandweightedsparserepresentation AT yongzhou predictionofproteinproteininteractionswithclusteredaminoacidsandweightedsparserepresentation |
_version_ |
1724819310216478720 |