Predicting enhancer-promoter interaction based on epigenomic signals
Introduction: The physical interactions between enhancers and promoters are often involved in gene transcriptional regulation. High tissue-specific enhancer-promoter interactions (EPIs) are responsible for the differential expression of genes. Experimental methods are time-consuming and labor-intens...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Genetics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fgene.2023.1133775/full |
| _version_ | 1797828798243143680 |
|---|---|
| author | Leqiong Zheng Leqiong Zheng Leqiong Zheng Li Liu Wen Zhu Wen Zhu Yijie Ding Fangxiang Wu |
| author_facet | Leqiong Zheng Leqiong Zheng Leqiong Zheng Li Liu Wen Zhu Wen Zhu Yijie Ding Fangxiang Wu |
| author_sort | Leqiong Zheng |
| collection | DOAJ |
| description | Introduction: The physical interactions between enhancers and promoters are often involved in gene transcriptional regulation. High tissue-specific enhancer-promoter interactions (EPIs) are responsible for the differential expression of genes. Experimental methods are time-consuming and labor-intensive in measuring EPIs. An alternative approach, machine learning, has been widely used to predict EPIs. However, most existing machine learning methods require a large number of functional genomic and epigenomic features as input, which limits the application to different cell lines.Methods: In this paper, we developed a random forest model, HARD (H3K27ac, ATAC-seq, RAD21, and Distance), to predict EPI using only four types of features.Results: Independent tests on a benchmark dataset showed that HARD outperforms other models with the fewest features.Discussion: Our results revealed that chromatin accessibility and the binding of cohesin are important for cell-line-specific EPIs. Furthermore, we trained the HARD model in the GM12878 cell line and performed testing in the HeLa cell line. The cross-cell-lines prediction also performs well, suggesting it has the potential to be applied to other cell lines. |
| first_indexed | 2024-04-09T13:10:11Z |
| format | Article |
| id | doaj.art-5fda1721957641a88757f258bc4dfff5 |
| institution | Directory Open Access Journal |
| issn | 1664-8021 |
| language | English |
| last_indexed | 2024-04-09T13:10:11Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Genetics |
| spelling | doaj.art-5fda1721957641a88757f258bc4dfff52023-05-12T08:26:03ZengFrontiers Media S.A.Frontiers in Genetics1664-80212023-04-011410.3389/fgene.2023.11337751133775Predicting enhancer-promoter interaction based on epigenomic signalsLeqiong Zheng0Leqiong Zheng1Leqiong Zheng2Li Liu3Wen Zhu4Wen Zhu5Yijie Ding6Fangxiang Wu7School of Mathematics and Statistics, Hainan Normal University, Haikou, ChinaYangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou, ChinaKey Laboratory of Computational Science and Application of Hainan Province, Haikou, ChinaYangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou, ChinaSchool of Mathematics and Statistics, Hainan Normal University, Haikou, ChinaKey Laboratory of Computational Science and Application of Hainan Province, Haikou, ChinaKey Laboratory of Computational Science and Application of Hainan Province, Haikou, ChinaSchool of Mathematics and Statistics, Hainan Normal University, Haikou, ChinaIntroduction: The physical interactions between enhancers and promoters are often involved in gene transcriptional regulation. High tissue-specific enhancer-promoter interactions (EPIs) are responsible for the differential expression of genes. Experimental methods are time-consuming and labor-intensive in measuring EPIs. An alternative approach, machine learning, has been widely used to predict EPIs. However, most existing machine learning methods require a large number of functional genomic and epigenomic features as input, which limits the application to different cell lines.Methods: In this paper, we developed a random forest model, HARD (H3K27ac, ATAC-seq, RAD21, and Distance), to predict EPI using only four types of features.Results: Independent tests on a benchmark dataset showed that HARD outperforms other models with the fewest features.Discussion: Our results revealed that chromatin accessibility and the binding of cohesin are important for cell-line-specific EPIs. Furthermore, we trained the HARD model in the GM12878 cell line and performed testing in the HeLa cell line. The cross-cell-lines prediction also performs well, suggesting it has the potential to be applied to other cell lines.https://www.frontiersin.org/articles/10.3389/fgene.2023.1133775/fullenhancer-promoter interactionmachine learningChIA-PETrandom forestepigenomic signals |
| spellingShingle | Leqiong Zheng Leqiong Zheng Leqiong Zheng Li Liu Wen Zhu Wen Zhu Yijie Ding Fangxiang Wu Predicting enhancer-promoter interaction based on epigenomic signals Frontiers in Genetics enhancer-promoter interaction machine learning ChIA-PET random forest epigenomic signals |
| title | Predicting enhancer-promoter interaction based on epigenomic signals |
| title_full | Predicting enhancer-promoter interaction based on epigenomic signals |
| title_fullStr | Predicting enhancer-promoter interaction based on epigenomic signals |
| title_full_unstemmed | Predicting enhancer-promoter interaction based on epigenomic signals |
| title_short | Predicting enhancer-promoter interaction based on epigenomic signals |
| title_sort | predicting enhancer promoter interaction based on epigenomic signals |
| topic | enhancer-promoter interaction machine learning ChIA-PET random forest epigenomic signals |
| url | https://www.frontiersin.org/articles/10.3389/fgene.2023.1133775/full |
| work_keys_str_mv | AT leqiongzheng predictingenhancerpromoterinteractionbasedonepigenomicsignals AT leqiongzheng predictingenhancerpromoterinteractionbasedonepigenomicsignals AT leqiongzheng predictingenhancerpromoterinteractionbasedonepigenomicsignals AT liliu predictingenhancerpromoterinteractionbasedonepigenomicsignals AT wenzhu predictingenhancerpromoterinteractionbasedonepigenomicsignals AT wenzhu predictingenhancerpromoterinteractionbasedonepigenomicsignals AT yijieding predictingenhancerpromoterinteractionbasedonepigenomicsignals AT fangxiangwu predictingenhancerpromoterinteractionbasedonepigenomicsignals |