Projection-Based Neighborhood Non-Negative Matrix Factorization for lncRNA-Protein Interaction Prediction
Many long ncRNAs (lncRNA) make their effort by interacting with the corresponding RNA-binding proteins, and identifying the interactions between lncRNAs and proteins is important to understand the functions of lncRNA. Compared with the time-consuming and laborious experimental methods, more and more...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-11-01
|
| Series: | Frontiers in Genetics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fgene.2019.01148/full |
| _version_ | 1819277019562639360 |
|---|---|
| author | Yingjun Ma Yingjun Ma Tingting He Tingting He Xingpeng Jiang Xingpeng Jiang |
| author_facet | Yingjun Ma Yingjun Ma Tingting He Tingting He Xingpeng Jiang Xingpeng Jiang |
| author_sort | Yingjun Ma |
| collection | DOAJ |
| description | Many long ncRNAs (lncRNA) make their effort by interacting with the corresponding RNA-binding proteins, and identifying the interactions between lncRNAs and proteins is important to understand the functions of lncRNA. Compared with the time-consuming and laborious experimental methods, more and more computational models are proposed to predict lncRNA-protein interactions. However, few models can effectively utilize the biological network topology of lncRNA (protein) and combine its sequence structure features, and most models cannot effectively predict new proteins (lncRNA) that do not interact with any lncRNA (proteins). In this study, we proposed a projection-based neighborhood non-negative matrix decomposition model (PMKDN) to predict potential lncRNA-protein interactions by integrating multiple biological features of lncRNAs (proteins). First, according to lncRNA (protein) sequences and lncRNA expression profile data, we extracted multiple features of lncRNA (protein). Second, based on protein GO ontology annotation, lncRNA sequences, lncRNA(protein) feature information, and modified lncRNA-protein interaction network, we calculated multiple similarities of lncRNA (protein), and fused them to obtain a more accurate lncRNA(protein) similarity network. Finally, combining the similarity and various feature information of lncRNA (protein), as well as the modified interaction network, we proposed a projection-based neighborhood non-negative matrix decomposition algorithm to predict the potential lncRNA-protein interactions. On two benchmark datasets, PMKDN showed better performance than other state-of-the-art methods for the prediction of new lncRNA-protein interactions, new lncRNAs, and new proteins. Case study further indicates that PMKDN can be used as an effective tool for lncRNA-protein interaction prediction. |
| first_indexed | 2024-12-23T23:49:27Z |
| format | Article |
| id | doaj.art-6bcf00a1b7fa4b5dafab4be72170dc9b |
| institution | Directory Open Access Journal |
| issn | 1664-8021 |
| language | English |
| last_indexed | 2024-12-23T23:49:27Z |
| publishDate | 2019-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Genetics |
| spelling | doaj.art-6bcf00a1b7fa4b5dafab4be72170dc9b2022-12-21T17:25:26ZengFrontiers Media S.A.Frontiers in Genetics1664-80212019-11-011010.3389/fgene.2019.01148490530Projection-Based Neighborhood Non-Negative Matrix Factorization for lncRNA-Protein Interaction PredictionYingjun Ma0Yingjun Ma1Tingting He2Tingting He3Xingpeng Jiang4Xingpeng Jiang5School of Mathematics & Statistics, Central China Normal University, Wuhan, ChinaHubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, ChinaHubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, ChinaSchool of Computer, Central China Normal University, Wuhan, ChinaHubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, ChinaSchool of Computer, Central China Normal University, Wuhan, ChinaMany long ncRNAs (lncRNA) make their effort by interacting with the corresponding RNA-binding proteins, and identifying the interactions between lncRNAs and proteins is important to understand the functions of lncRNA. Compared with the time-consuming and laborious experimental methods, more and more computational models are proposed to predict lncRNA-protein interactions. However, few models can effectively utilize the biological network topology of lncRNA (protein) and combine its sequence structure features, and most models cannot effectively predict new proteins (lncRNA) that do not interact with any lncRNA (proteins). In this study, we proposed a projection-based neighborhood non-negative matrix decomposition model (PMKDN) to predict potential lncRNA-protein interactions by integrating multiple biological features of lncRNAs (proteins). First, according to lncRNA (protein) sequences and lncRNA expression profile data, we extracted multiple features of lncRNA (protein). Second, based on protein GO ontology annotation, lncRNA sequences, lncRNA(protein) feature information, and modified lncRNA-protein interaction network, we calculated multiple similarities of lncRNA (protein), and fused them to obtain a more accurate lncRNA(protein) similarity network. Finally, combining the similarity and various feature information of lncRNA (protein), as well as the modified interaction network, we proposed a projection-based neighborhood non-negative matrix decomposition algorithm to predict the potential lncRNA-protein interactions. On two benchmark datasets, PMKDN showed better performance than other state-of-the-art methods for the prediction of new lncRNA-protein interactions, new lncRNAs, and new proteins. Case study further indicates that PMKDN can be used as an effective tool for lncRNA-protein interaction prediction.https://www.frontiersin.org/article/10.3389/fgene.2019.01148/fulllncRNA-protein interactionfeature projectionneighborhood completiongraph non-negative matrix factorizationkernel neighborhood similarity |
| spellingShingle | Yingjun Ma Yingjun Ma Tingting He Tingting He Xingpeng Jiang Xingpeng Jiang Projection-Based Neighborhood Non-Negative Matrix Factorization for lncRNA-Protein Interaction Prediction Frontiers in Genetics lncRNA-protein interaction feature projection neighborhood completion graph non-negative matrix factorization kernel neighborhood similarity |
| title | Projection-Based Neighborhood Non-Negative Matrix Factorization for lncRNA-Protein Interaction Prediction |
| title_full | Projection-Based Neighborhood Non-Negative Matrix Factorization for lncRNA-Protein Interaction Prediction |
| title_fullStr | Projection-Based Neighborhood Non-Negative Matrix Factorization for lncRNA-Protein Interaction Prediction |
| title_full_unstemmed | Projection-Based Neighborhood Non-Negative Matrix Factorization for lncRNA-Protein Interaction Prediction |
| title_short | Projection-Based Neighborhood Non-Negative Matrix Factorization for lncRNA-Protein Interaction Prediction |
| title_sort | projection based neighborhood non negative matrix factorization for lncrna protein interaction prediction |
| topic | lncRNA-protein interaction feature projection neighborhood completion graph non-negative matrix factorization kernel neighborhood similarity |
| url | https://www.frontiersin.org/article/10.3389/fgene.2019.01148/full |
| work_keys_str_mv | AT yingjunma projectionbasedneighborhoodnonnegativematrixfactorizationforlncrnaproteininteractionprediction AT yingjunma projectionbasedneighborhoodnonnegativematrixfactorizationforlncrnaproteininteractionprediction AT tingtinghe projectionbasedneighborhoodnonnegativematrixfactorizationforlncrnaproteininteractionprediction AT tingtinghe projectionbasedneighborhoodnonnegativematrixfactorizationforlncrnaproteininteractionprediction AT xingpengjiang projectionbasedneighborhoodnonnegativematrixfactorizationforlncrnaproteininteractionprediction AT xingpengjiang projectionbasedneighborhoodnonnegativematrixfactorizationforlncrnaproteininteractionprediction |