Predicting Protein–Protein Interactions Based on Ensemble Learning-Based Model from Protein Sequence
Protein–protein interactions (PPIs) play an essential role in many biological cellular functions. However, it is still tedious and time-consuming to identify protein–protein interactions through traditional experimental methods. For this reason, it is imperative and necessary to develop a computatio...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Biology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-7737/11/7/995 |
| _version_ | 1797433803499634688 |
|---|---|
| author | Xinke Zhan Mang Xiao Zhuhong You Chenggang Yan Jianxin Guo Liping Wang Yaoqi Sun Bingwan Shang |
| author_facet | Xinke Zhan Mang Xiao Zhuhong You Chenggang Yan Jianxin Guo Liping Wang Yaoqi Sun Bingwan Shang |
| author_sort | Xinke Zhan |
| collection | DOAJ |
| description | Protein–protein interactions (PPIs) play an essential role in many biological cellular functions. However, it is still tedious and time-consuming to identify protein–protein interactions through traditional experimental methods. For this reason, it is imperative and necessary to develop a computational method for predicting PPIs efficiently. This paper explores a novel computational method for detecting PPIs from protein sequence, the approach which mainly adopts the feature extraction method: Locality Preserving Projections (LPP) and classifier: Rotation Forest (RF). Specifically, we first employ the Position Specific Scoring Matrix (PSSM), which can remain evolutionary information of biological for representing protein sequence efficiently. Then, the LPP descriptor is applied to extract feature vectors from PSSM. The feature vectors are fed into the RF to obtain the final results. The proposed method is applied to two datasets: <i>Y</i><i>east</i> and <i>H. pylori</i>, and obtained an average accuracy of 92.81% and 92.56%, respectively. We also compare it with <i>K</i> nearest neighbors (KNN) and support vector machine (SVM) to better evaluate the performance of the proposed method. In summary, all experimental results indicate that the proposed approach is stable and robust for predicting PPIs and promising to be a useful tool for proteomics research. |
| first_indexed | 2024-03-09T10:21:54Z |
| format | Article |
| id | doaj.art-1027508065b84a77b363f3d235feb103 |
| institution | Directory Open Access Journal |
| issn | 2079-7737 |
| language | English |
| last_indexed | 2024-03-09T10:21:54Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biology |
| spelling | doaj.art-1027508065b84a77b363f3d235feb1032023-12-01T21:54:22ZengMDPI AGBiology2079-77372022-06-0111799510.3390/biology11070995Predicting Protein–Protein Interactions Based on Ensemble Learning-Based Model from Protein SequenceXinke Zhan0Mang Xiao1Zhuhong You2Chenggang Yan3Jianxin Guo4Liping Wang5Yaoqi Sun6Bingwan Shang7School of Information Engineering, Xijing University, Xi’an 710123, ChinaSir Run Run Shaw Hospital, Zhejiang University, Hangzhou 310016, ChinaSchool of Computer Science, Northwestern Polytechnical University, Xi’an 710129, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Information Engineering, Xijing University, Xi’an 710123, ChinaSchool of Information Engineering, Xijing University, Xi’an 710123, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Information Engineering, Xijing University, Xi’an 710123, ChinaProtein–protein interactions (PPIs) play an essential role in many biological cellular functions. However, it is still tedious and time-consuming to identify protein–protein interactions through traditional experimental methods. For this reason, it is imperative and necessary to develop a computational method for predicting PPIs efficiently. This paper explores a novel computational method for detecting PPIs from protein sequence, the approach which mainly adopts the feature extraction method: Locality Preserving Projections (LPP) and classifier: Rotation Forest (RF). Specifically, we first employ the Position Specific Scoring Matrix (PSSM), which can remain evolutionary information of biological for representing protein sequence efficiently. Then, the LPP descriptor is applied to extract feature vectors from PSSM. The feature vectors are fed into the RF to obtain the final results. The proposed method is applied to two datasets: <i>Y</i><i>east</i> and <i>H. pylori</i>, and obtained an average accuracy of 92.81% and 92.56%, respectively. We also compare it with <i>K</i> nearest neighbors (KNN) and support vector machine (SVM) to better evaluate the performance of the proposed method. In summary, all experimental results indicate that the proposed approach is stable and robust for predicting PPIs and promising to be a useful tool for proteomics research.https://www.mdpi.com/2079-7737/11/7/995locality preserving projectionsrotation forestPSSMSVMKNN |
| spellingShingle | Xinke Zhan Mang Xiao Zhuhong You Chenggang Yan Jianxin Guo Liping Wang Yaoqi Sun Bingwan Shang Predicting Protein–Protein Interactions Based on Ensemble Learning-Based Model from Protein Sequence Biology locality preserving projections rotation forest PSSM SVM KNN |
| title | Predicting Protein–Protein Interactions Based on Ensemble Learning-Based Model from Protein Sequence |
| title_full | Predicting Protein–Protein Interactions Based on Ensemble Learning-Based Model from Protein Sequence |
| title_fullStr | Predicting Protein–Protein Interactions Based on Ensemble Learning-Based Model from Protein Sequence |
| title_full_unstemmed | Predicting Protein–Protein Interactions Based on Ensemble Learning-Based Model from Protein Sequence |
| title_short | Predicting Protein–Protein Interactions Based on Ensemble Learning-Based Model from Protein Sequence |
| title_sort | predicting protein protein interactions based on ensemble learning based model from protein sequence |
| topic | locality preserving projections rotation forest PSSM SVM KNN |
| url | https://www.mdpi.com/2079-7737/11/7/995 |
| work_keys_str_mv | AT xinkezhan predictingproteinproteininteractionsbasedonensemblelearningbasedmodelfromproteinsequence AT mangxiao predictingproteinproteininteractionsbasedonensemblelearningbasedmodelfromproteinsequence AT zhuhongyou predictingproteinproteininteractionsbasedonensemblelearningbasedmodelfromproteinsequence AT chenggangyan predictingproteinproteininteractionsbasedonensemblelearningbasedmodelfromproteinsequence AT jianxinguo predictingproteinproteininteractionsbasedonensemblelearningbasedmodelfromproteinsequence AT lipingwang predictingproteinproteininteractionsbasedonensemblelearningbasedmodelfromproteinsequence AT yaoqisun predictingproteinproteininteractionsbasedonensemblelearningbasedmodelfromproteinsequence AT bingwanshang predictingproteinproteininteractionsbasedonensemblelearningbasedmodelfromproteinsequence |