EPIsHilbert: Prediction of Enhancer-Promoter Interactions via Hilbert Curve Encoding and Transfer Learning
Enhancer-promoter interactions (EPIs) play a significant role in the regulation of gene transcription. However, enhancers may not necessarily interact with the closest promoters, but with distant promoters via chromatin looping. Considering the spatial position relationship between enhancers and the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Genes |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4425/12/9/1385 |
| _version_ | 1797519149036994560 |
|---|---|
| author | Mingyang Zhang Yujia Hu Min Zhu |
| author_facet | Mingyang Zhang Yujia Hu Min Zhu |
| author_sort | Mingyang Zhang |
| collection | DOAJ |
| description | Enhancer-promoter interactions (EPIs) play a significant role in the regulation of gene transcription. However, enhancers may not necessarily interact with the closest promoters, but with distant promoters via chromatin looping. Considering the spatial position relationship between enhancers and their target promoters is important for predicting EPIs. Most existing methods only consider sequence information regardless of spatial information. On the other hand, recent computational methods lack generalization capability across different cell line datasets. In this paper, we propose EPIsHilbert, which uses Hilbert curve encoding and two transfer learning approaches. Hilbert curve encoding can preserve the spatial position information between enhancers and promoters. Additionally, we use visualization techniques to explore important sequence fragments that have a high impact on EPIs and the spatial relationships between them. Transfer learning can improve prediction performance across cell lines. In order to further prove the effectiveness of transfer learning, we analyze the sequence coincidence of different cell lines. Experimental results demonstrate that EPIsHilbert is a state-of-the-art model that is superior to most of the existing methods both in specific cell lines and cross cell lines. |
| first_indexed | 2024-03-10T07:38:59Z |
| format | Article |
| id | doaj.art-bc75d49ac38a44438595f6f31ad66001 |
| institution | Directory Open Access Journal |
| issn | 2073-4425 |
| language | English |
| last_indexed | 2024-03-10T07:38:59Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Genes |
| spelling | doaj.art-bc75d49ac38a44438595f6f31ad660012023-11-22T13:14:16ZengMDPI AGGenes2073-44252021-09-01129138510.3390/genes12091385EPIsHilbert: Prediction of Enhancer-Promoter Interactions via Hilbert Curve Encoding and Transfer LearningMingyang Zhang0Yujia Hu1Min Zhu2Department of Computer Science, Sichuan University, Chengdu 610065, ChinaDepartment of Computer Science, Sichuan University, Chengdu 610065, ChinaDepartment of Computer Science, Sichuan University, Chengdu 610065, ChinaEnhancer-promoter interactions (EPIs) play a significant role in the regulation of gene transcription. However, enhancers may not necessarily interact with the closest promoters, but with distant promoters via chromatin looping. Considering the spatial position relationship between enhancers and their target promoters is important for predicting EPIs. Most existing methods only consider sequence information regardless of spatial information. On the other hand, recent computational methods lack generalization capability across different cell line datasets. In this paper, we propose EPIsHilbert, which uses Hilbert curve encoding and two transfer learning approaches. Hilbert curve encoding can preserve the spatial position information between enhancers and promoters. Additionally, we use visualization techniques to explore important sequence fragments that have a high impact on EPIs and the spatial relationships between them. Transfer learning can improve prediction performance across cell lines. In order to further prove the effectiveness of transfer learning, we analyze the sequence coincidence of different cell lines. Experimental results demonstrate that EPIsHilbert is a state-of-the-art model that is superior to most of the existing methods both in specific cell lines and cross cell lines.https://www.mdpi.com/2073-4425/12/9/1385Hilbert curveenhancer-promoter interactionstransfer learning |
| spellingShingle | Mingyang Zhang Yujia Hu Min Zhu EPIsHilbert: Prediction of Enhancer-Promoter Interactions via Hilbert Curve Encoding and Transfer Learning Genes Hilbert curve enhancer-promoter interactions transfer learning |
| title | EPIsHilbert: Prediction of Enhancer-Promoter Interactions via Hilbert Curve Encoding and Transfer Learning |
| title_full | EPIsHilbert: Prediction of Enhancer-Promoter Interactions via Hilbert Curve Encoding and Transfer Learning |
| title_fullStr | EPIsHilbert: Prediction of Enhancer-Promoter Interactions via Hilbert Curve Encoding and Transfer Learning |
| title_full_unstemmed | EPIsHilbert: Prediction of Enhancer-Promoter Interactions via Hilbert Curve Encoding and Transfer Learning |
| title_short | EPIsHilbert: Prediction of Enhancer-Promoter Interactions via Hilbert Curve Encoding and Transfer Learning |
| title_sort | epishilbert prediction of enhancer promoter interactions via hilbert curve encoding and transfer learning |
| topic | Hilbert curve enhancer-promoter interactions transfer learning |
| url | https://www.mdpi.com/2073-4425/12/9/1385 |
| work_keys_str_mv | AT mingyangzhang epishilbertpredictionofenhancerpromoterinteractionsviahilbertcurveencodingandtransferlearning AT yujiahu epishilbertpredictionofenhancerpromoterinteractionsviahilbertcurveencodingandtransferlearning AT minzhu epishilbertpredictionofenhancerpromoterinteractionsviahilbertcurveencodingandtransferlearning |