PEPRF : Identification of Essential Proteins by Integrating Topological Features of PPI Network and Sequence-based Features via Random Forest
(2021) In Current Bioinformatics 16(9). p.1161-1168- Abstract
Background: Essential proteins play an important role in the process of life, which can be identified by experimental methods and computational approaches. Experimental approaches to identify essential proteins are of high accuracy but with the limitation of time and resource-consuming. Objective: Herein, we present a computational model (PEPRF) to identify essential proteins based on machine learning. Methods: Different features of proteins were extracted. Topological features of Protein-Protein Interaction (PPI) network-based are extracted. Based on the protein sequence, graph theory-based features, in-formation-based features, composition and physichemical features, etc., were extracted. Finally, 282 features are constructed. In... (More)
Background: Essential proteins play an important role in the process of life, which can be identified by experimental methods and computational approaches. Experimental approaches to identify essential proteins are of high accuracy but with the limitation of time and resource-consuming. Objective: Herein, we present a computational model (PEPRF) to identify essential proteins based on machine learning. Methods: Different features of proteins were extracted. Topological features of Protein-Protein Interaction (PPI) network-based are extracted. Based on the protein sequence, graph theory-based features, in-formation-based features, composition and physichemical features, etc., were extracted. Finally, 282 features are constructed. In order to select the features that contributed most to the identification, Re-liefF-based feature selection method was adopted to measure the weights of these features. Results: As a result, 212 features were curated to train random forest classifiers. Finally, PEPRF get the AUC of 0.71 and an accuracy of 0.742. Conclusion: Our results show that PEPRF may be applied as an efficient tool to identify essential pro-teins.
(Less)
- author
- Wu, Chuanyan ; Lin, Bentao ; Shi, Kai ; Zhang, Qingju ; Gao, Rui ; Yu, Zhiguo ; De Marinis, Yang LU ; Zhang, Yusen and Liu, Zhi Ping
- organization
- publishing date
- 2021-11-01
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Feature extraction, Graph energy, PEPRF, Random forest classi-fier, ReliefF-based feature selection, Rma Essential protein prediction
- in
- Current Bioinformatics
- volume
- 16
- issue
- 9
- pages
- 8 pages
- publisher
- Bentham Science Publishers
- external identifiers
-
- scopus:85122849381
- ISSN
- 1574-8936
- DOI
- 10.2174/1574893616666210617162258
- language
- English
- LU publication?
- yes
- id
- 0f8f3e1d-d942-4104-9866-83b4a625fc99
- date added to LUP
- 2022-02-18 10:47:38
- date last changed
- 2024-05-07 01:49:26
@article{0f8f3e1d-d942-4104-9866-83b4a625fc99,
abstract = {{<p>Background: Essential proteins play an important role in the process of life, which can be identified by experimental methods and computational approaches. Experimental approaches to identify essential proteins are of high accuracy but with the limitation of time and resource-consuming. Objective: Herein, we present a computational model (PEPRF) to identify essential proteins based on machine learning. Methods: Different features of proteins were extracted. Topological features of Protein-Protein Interaction (PPI) network-based are extracted. Based on the protein sequence, graph theory-based features, in-formation-based features, composition and physichemical features, etc., were extracted. Finally, 282 features are constructed. In order to select the features that contributed most to the identification, Re-liefF-based feature selection method was adopted to measure the weights of these features. Results: As a result, 212 features were curated to train random forest classifiers. Finally, PEPRF get the AUC of 0.71 and an accuracy of 0.742. Conclusion: Our results show that PEPRF may be applied as an efficient tool to identify essential pro-teins.</p>}},
author = {{Wu, Chuanyan and Lin, Bentao and Shi, Kai and Zhang, Qingju and Gao, Rui and Yu, Zhiguo and De Marinis, Yang and Zhang, Yusen and Liu, Zhi Ping}},
issn = {{1574-8936}},
keywords = {{Feature extraction; Graph energy; PEPRF; Random forest classi-fier; ReliefF-based feature selection; Rma Essential protein prediction}},
language = {{eng}},
month = {{11}},
number = {{9}},
pages = {{1161--1168}},
publisher = {{Bentham Science Publishers}},
series = {{Current Bioinformatics}},
title = {{PEPRF : Identification of Essential Proteins by Integrating Topological Features of PPI Network and Sequence-based Features via Random Forest}},
url = {{http://dx.doi.org/10.2174/1574893616666210617162258}},
doi = {{10.2174/1574893616666210617162258}},
volume = {{16}},
year = {{2021}},
}