An Iterative Method for Identifying Essential Proteins Based on Non-Negative Matrix Factorization
In recent years, with the development of high-throughput technologies, lots of computational methods for predicting essential proteins based on protein-protein interaction (PPI) networks and biological information of proteins have been proposed successively. However, due to the incompleteness of PPI...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9301292/ |
| _version_ | 1828112023070703616 |
|---|---|
| author | Jin Liu Xiangyi Wang Zhiping Chen Yihong Tan Xueyong Li Zhen Zhang Lei Wang |
| author_facet | Jin Liu Xiangyi Wang Zhiping Chen Yihong Tan Xueyong Li Zhen Zhang Lei Wang |
| author_sort | Jin Liu |
| collection | DOAJ |
| description | In recent years, with the development of high-throughput technologies, lots of computational methods for predicting essential proteins based on protein-protein interaction (PPI) networks and biological information of proteins have been proposed successively. However, due to the incompleteness of PPI networks, the prediction accuracy achieved by these methods is still unsatisfactory, and it remains to be a challenging work to design effective computational models to identify essential proteins. In this manuscript, a novel Prediction Model based on the Non-negative Matrix Factorization (PMNMF for abbreviation) is proposed. In PMNMF, an original PPI network will be constructed first based on PPIs downloaded from any given benchmark database. And then, based on topological features of protein nodes, the original PPI network will be further converted to a weighted PPI network. Moreover, in order to overcome the incompleteness of PPI networks, the NMF (Non-negative Matrix Factorization) method will be implemented on the weighted PPI network to obtain a transition probability matrix. And then, by integrating biological information including the gene expression information, homologous information and subcellular localization information of proteins, a unique initial score will be calculated and assigned to each protein node in the weighed PPI network, based on which, an improved Page-Rank algorithm will be designed to infer potential essential proteins. Finally, in order to evaluate the performance of PMNMF, it will be compared with 14 state-of-the-art prediction models, and experimental results show that PMNMF can achieve the best identification accuracy. |
| first_indexed | 2024-04-11T11:44:10Z |
| format | Article |
| id | doaj.art-2a3c3cd99ffa4259a5972df21ea17ac7 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T11:44:10Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2a3c3cd99ffa4259a5972df21ea17ac72022-12-22T04:25:42ZengIEEEIEEE Access2169-35362020-01-01822668522669610.1109/ACCESS.2020.30462549301292An Iterative Method for Identifying Essential Proteins Based on Non-Negative Matrix FactorizationJin Liu0https://orcid.org/0000-0002-5768-3442Xiangyi Wang1https://orcid.org/0000-0001-8634-3917Zhiping Chen2https://orcid.org/0000-0003-4759-3774Yihong Tan3https://orcid.org/0000-0001-7619-8090Xueyong Li4https://orcid.org/0000-0002-9105-1764Zhen Zhang5https://orcid.org/0000-0001-9629-9614Lei Wang6https://orcid.org/0000-0002-5065-8447College of Computer Engineering and Applied Mathematics, Changsha University, Changsha, ChinaCollege of Computer Engineering and Applied Mathematics, Changsha University, Changsha, ChinaCollege of Computer Engineering and Applied Mathematics, Changsha University, Changsha, ChinaCollege of Computer Engineering and Applied Mathematics, Changsha University, Changsha, ChinaCollege of Computer Engineering and Applied Mathematics, Changsha University, Changsha, ChinaCollege of Computer Engineering and Applied Mathematics, Changsha University, Changsha, ChinaCollege of Computer Engineering and Applied Mathematics, Changsha University, Changsha, ChinaIn recent years, with the development of high-throughput technologies, lots of computational methods for predicting essential proteins based on protein-protein interaction (PPI) networks and biological information of proteins have been proposed successively. However, due to the incompleteness of PPI networks, the prediction accuracy achieved by these methods is still unsatisfactory, and it remains to be a challenging work to design effective computational models to identify essential proteins. In this manuscript, a novel Prediction Model based on the Non-negative Matrix Factorization (PMNMF for abbreviation) is proposed. In PMNMF, an original PPI network will be constructed first based on PPIs downloaded from any given benchmark database. And then, based on topological features of protein nodes, the original PPI network will be further converted to a weighted PPI network. Moreover, in order to overcome the incompleteness of PPI networks, the NMF (Non-negative Matrix Factorization) method will be implemented on the weighted PPI network to obtain a transition probability matrix. And then, by integrating biological information including the gene expression information, homologous information and subcellular localization information of proteins, a unique initial score will be calculated and assigned to each protein node in the weighed PPI network, based on which, an improved Page-Rank algorithm will be designed to infer potential essential proteins. Finally, in order to evaluate the performance of PMNMF, it will be compared with 14 state-of-the-art prediction models, and experimental results show that PMNMF can achieve the best identification accuracy.https://ieeexplore.ieee.org/document/9301292/Essential protein predictioniteration methodnon-negative matrix factorization |
| spellingShingle | Jin Liu Xiangyi Wang Zhiping Chen Yihong Tan Xueyong Li Zhen Zhang Lei Wang An Iterative Method for Identifying Essential Proteins Based on Non-Negative Matrix Factorization IEEE Access Essential protein prediction iteration method non-negative matrix factorization |
| title | An Iterative Method for Identifying Essential Proteins Based on Non-Negative Matrix Factorization |
| title_full | An Iterative Method for Identifying Essential Proteins Based on Non-Negative Matrix Factorization |
| title_fullStr | An Iterative Method for Identifying Essential Proteins Based on Non-Negative Matrix Factorization |
| title_full_unstemmed | An Iterative Method for Identifying Essential Proteins Based on Non-Negative Matrix Factorization |
| title_short | An Iterative Method for Identifying Essential Proteins Based on Non-Negative Matrix Factorization |
| title_sort | iterative method for identifying essential proteins based on non negative matrix factorization |
| topic | Essential protein prediction iteration method non-negative matrix factorization |
| url | https://ieeexplore.ieee.org/document/9301292/ |
| work_keys_str_mv | AT jinliu aniterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT xiangyiwang aniterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT zhipingchen aniterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT yihongtan aniterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT xueyongli aniterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT zhenzhang aniterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT leiwang aniterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT jinliu iterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT xiangyiwang iterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT zhipingchen iterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT yihongtan iterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT xueyongli iterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT zhenzhang iterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization AT leiwang iterativemethodforidentifyingessentialproteinsbasedonnonnegativematrixfactorization |