EPIMR: Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image Representation
Prediction of enhancer-promoter interactions (EPIs) is key to regulating gene expression and diagnosing genetic diseases. Due to limited resolution, biological experiments perform not as well as expected while precisely identifying specific interactions, giving rise to computational biology approach...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-09-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2024.9020018 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542992283467776 |
|---|---|
| author | Qiaozhen Meng Yinuo Lyu Xiaoqing Peng Junhai Xu Jijun Tang Fei Guo |
| author_facet | Qiaozhen Meng Yinuo Lyu Xiaoqing Peng Junhai Xu Jijun Tang Fei Guo |
| author_sort | Qiaozhen Meng |
| collection | DOAJ |
| description | Prediction of enhancer-promoter interactions (EPIs) is key to regulating gene expression and diagnosing genetic diseases. Due to limited resolution, biological experiments perform not as well as expected while precisely identifying specific interactions, giving rise to computational biology approaches. Many EPI predictors have been developed, but their prediction accuracy still needs to be enhanced. Here, we design a new model named EPIMR to identify enhancer-promoter interactions. First, Hilbert Curve is utilized to represent sequences to images to preserve the position and spatial information. Second, a multi-scale residual neural network (ResNet) is used to learn the distinguishing features of different abstraction levels. Finally, matching heuristics are adopted to concatenate the learned features of enhancers and promoters, which pays attention to their potential interaction information. Experimental results on six cell lines indicate that EPIMR performs better than existing methods, with higher area under the precision-recall curve (AUPR) and area under the receiver operating characteristic (AUROC) results on benchmark and under-sampling datasets. Furthermore, our model is pre-trained on all cell lines, which improves not only the transferability of cross-cell line prediction, but also cell line-specific prediction ability. In conclusion, our method serves as a valuable technical tool for predicting enhancer-promoter interactions, contributing to the understanding of gene transcription mechanisms. Our code and results are available at https://github.com/guofei-tju/EPIMR. |
| format | Article |
| id | doaj-art-0d280fd5822a4394bed6baa6761aba8a |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-0d280fd5822a4394bed6baa6761aba8a2025-02-03T11:53:24ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-09-017366868110.26599/BDMA.2024.9020018EPIMR: Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image RepresentationQiaozhen Meng0Yinuo Lyu1Xiaoqing Peng2Junhai Xu3Jijun Tang4Fei Guo5School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaAeronautical Information Service Center of the Civil Aviation Administration of China (AISC.ATMB.CAAC), Beijing 100015, ChinaCenter for Medical Genetics & Hunan Key Laboratory of Medical Genetics, School of Life Sciences, Central South University, Changsha 410038, ChinaSchool of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518000, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410083, ChinaPrediction of enhancer-promoter interactions (EPIs) is key to regulating gene expression and diagnosing genetic diseases. Due to limited resolution, biological experiments perform not as well as expected while precisely identifying specific interactions, giving rise to computational biology approaches. Many EPI predictors have been developed, but their prediction accuracy still needs to be enhanced. Here, we design a new model named EPIMR to identify enhancer-promoter interactions. First, Hilbert Curve is utilized to represent sequences to images to preserve the position and spatial information. Second, a multi-scale residual neural network (ResNet) is used to learn the distinguishing features of different abstraction levels. Finally, matching heuristics are adopted to concatenate the learned features of enhancers and promoters, which pays attention to their potential interaction information. Experimental results on six cell lines indicate that EPIMR performs better than existing methods, with higher area under the precision-recall curve (AUPR) and area under the receiver operating characteristic (AUROC) results on benchmark and under-sampling datasets. Furthermore, our model is pre-trained on all cell lines, which improves not only the transferability of cross-cell line prediction, but also cell line-specific prediction ability. In conclusion, our method serves as a valuable technical tool for predicting enhancer-promoter interactions, contributing to the understanding of gene transcription mechanisms. Our code and results are available at https://github.com/guofei-tju/EPIMR.https://www.sciopen.com/article/10.26599/BDMA.2024.9020018enhancer-promoter interactionshilbert curvemulti-scale residual neural network (resnet) |
| spellingShingle | Qiaozhen Meng Yinuo Lyu Xiaoqing Peng Junhai Xu Jijun Tang Fei Guo EPIMR: Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image Representation Big Data Mining and Analytics enhancer-promoter interactions hilbert curve multi-scale residual neural network (resnet) |
| title | EPIMR: Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image Representation |
| title_full | EPIMR: Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image Representation |
| title_fullStr | EPIMR: Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image Representation |
| title_full_unstemmed | EPIMR: Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image Representation |
| title_short | EPIMR: Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image Representation |
| title_sort | epimr prediction of enhancer promoter interactions by multi scale resnet on image representation |
| topic | enhancer-promoter interactions hilbert curve multi-scale residual neural network (resnet) |
| url | https://www.sciopen.com/article/10.26599/BDMA.2024.9020018 |
| work_keys_str_mv | AT qiaozhenmeng epimrpredictionofenhancerpromoterinteractionsbymultiscaleresnetonimagerepresentation AT yinuolyu epimrpredictionofenhancerpromoterinteractionsbymultiscaleresnetonimagerepresentation AT xiaoqingpeng epimrpredictionofenhancerpromoterinteractionsbymultiscaleresnetonimagerepresentation AT junhaixu epimrpredictionofenhancerpromoterinteractionsbymultiscaleresnetonimagerepresentation AT jijuntang epimrpredictionofenhancerpromoterinteractionsbymultiscaleresnetonimagerepresentation AT feiguo epimrpredictionofenhancerpromoterinteractionsbymultiscaleresnetonimagerepresentation |