iEnhancer-DCSA: identifying enhancers via dual-scale convolution and spatial attention
Abstract Background Due to the dynamic nature of enhancers, identifying enhancers and their strength are major bioinformatics challenges. With the development of deep learning, several models have facilitated enhancers detection in recent years. However, existing studies either neglect different len...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-07-01
|
Series: | BMC Genomics |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12864-023-09468-1 |
_version_ | 1797779070710185984 |
---|---|
author | Wenjun Wang Qingyao Wu Chunshan Li |
author_facet | Wenjun Wang Qingyao Wu Chunshan Li |
author_sort | Wenjun Wang |
collection | DOAJ |
description | Abstract Background Due to the dynamic nature of enhancers, identifying enhancers and their strength are major bioinformatics challenges. With the development of deep learning, several models have facilitated enhancers detection in recent years. However, existing studies either neglect different length motifs information or treat the features at all spatial locations equally. How to effectively use multi-scale motifs information while ignoring irrelevant information is a question worthy of serious consideration. In this paper, we propose an accurate and stable predictor iEnhancer-DCSA, mainly composed of dual-scale fusion and spatial attention, automatically extracting features of different length motifs and selectively focusing on the important features. Results Our experimental results demonstrate that iEnhancer-DCSA is remarkably superior to existing state-of-the-art methods on the test dataset. Especially, the accuracy and MCC of enhancer identification are improved by 3.45% and 9.41%, respectively. Meanwhile, the accuracy and MCC of enhancer classification are improved by 7.65% and 18.1%, respectively. Furthermore, we conduct ablation studies to demonstrate the effectiveness of dual-scale fusion and spatial attention. Conclusions iEnhancer-DCSA will be a valuable computational tool in identifying and classifying enhancers, especially for those not included in the training dataset. |
first_indexed | 2024-03-12T23:25:26Z |
format | Article |
id | doaj.art-a85eda6440b145199f6e61517d1930a4 |
institution | Directory Open Access Journal |
issn | 1471-2164 |
language | English |
last_indexed | 2024-03-12T23:25:26Z |
publishDate | 2023-07-01 |
publisher | BMC |
record_format | Article |
series | BMC Genomics |
spelling | doaj.art-a85eda6440b145199f6e61517d1930a42023-07-16T11:10:27ZengBMCBMC Genomics1471-21642023-07-0124111410.1186/s12864-023-09468-1iEnhancer-DCSA: identifying enhancers via dual-scale convolution and spatial attentionWenjun Wang0Qingyao Wu1Chunshan Li2School of Software Engineering, South China University of TechnologySchool of Software Engineering, South China University of TechnologyDepartment of Computer Science and Technology, Harbin Institute of TechnologyAbstract Background Due to the dynamic nature of enhancers, identifying enhancers and their strength are major bioinformatics challenges. With the development of deep learning, several models have facilitated enhancers detection in recent years. However, existing studies either neglect different length motifs information or treat the features at all spatial locations equally. How to effectively use multi-scale motifs information while ignoring irrelevant information is a question worthy of serious consideration. In this paper, we propose an accurate and stable predictor iEnhancer-DCSA, mainly composed of dual-scale fusion and spatial attention, automatically extracting features of different length motifs and selectively focusing on the important features. Results Our experimental results demonstrate that iEnhancer-DCSA is remarkably superior to existing state-of-the-art methods on the test dataset. Especially, the accuracy and MCC of enhancer identification are improved by 3.45% and 9.41%, respectively. Meanwhile, the accuracy and MCC of enhancer classification are improved by 7.65% and 18.1%, respectively. Furthermore, we conduct ablation studies to demonstrate the effectiveness of dual-scale fusion and spatial attention. Conclusions iEnhancer-DCSA will be a valuable computational tool in identifying and classifying enhancers, especially for those not included in the training dataset.https://doi.org/10.1186/s12864-023-09468-1EnhancersDual-scale convolutionSpatial attentionWord embedding |
spellingShingle | Wenjun Wang Qingyao Wu Chunshan Li iEnhancer-DCSA: identifying enhancers via dual-scale convolution and spatial attention BMC Genomics Enhancers Dual-scale convolution Spatial attention Word embedding |
title | iEnhancer-DCSA: identifying enhancers via dual-scale convolution and spatial attention |
title_full | iEnhancer-DCSA: identifying enhancers via dual-scale convolution and spatial attention |
title_fullStr | iEnhancer-DCSA: identifying enhancers via dual-scale convolution and spatial attention |
title_full_unstemmed | iEnhancer-DCSA: identifying enhancers via dual-scale convolution and spatial attention |
title_short | iEnhancer-DCSA: identifying enhancers via dual-scale convolution and spatial attention |
title_sort | ienhancer dcsa identifying enhancers via dual scale convolution and spatial attention |
topic | Enhancers Dual-scale convolution Spatial attention Word embedding |
url | https://doi.org/10.1186/s12864-023-09468-1 |
work_keys_str_mv | AT wenjunwang ienhancerdcsaidentifyingenhancersviadualscaleconvolutionandspatialattention AT qingyaowu ienhancerdcsaidentifyingenhancersviadualscaleconvolutionandspatialattention AT chunshanli ienhancerdcsaidentifyingenhancersviadualscaleconvolutionandspatialattention |