An Efficient Lightweight Hybrid Model with Attention Mechanism for Enhancer Sequence Recognition
Enhancers are sequences with short motifs that exhibit high positional variability and free scattering properties. Identification of these noncoding DNA fragments and their strength are extremely important because they play a key role in controlling gene regulation on a cellular basis. The identific...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Biomolecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-273X/13/1/70 |
| _version_ | 1797445530942439424 |
|---|---|
| author | Suliman Aladhadh Saleh A. Almatroodi Shabana Habib Abdulatif Alabdulatif Saeed Ullah Khattak Muhammad Islam |
| author_facet | Suliman Aladhadh Saleh A. Almatroodi Shabana Habib Abdulatif Alabdulatif Saeed Ullah Khattak Muhammad Islam |
| author_sort | Suliman Aladhadh |
| collection | DOAJ |
| description | Enhancers are sequences with short motifs that exhibit high positional variability and free scattering properties. Identification of these noncoding DNA fragments and their strength are extremely important because they play a key role in controlling gene regulation on a cellular basis. The identification of enhancers is more complex than that of other factors in the genome because they are freely scattered, and their location varies widely. In recent years, bioinformatics tools have enabled significant improvement in identifying this biological difficulty. Cell line-specific screening is not possible using these existing computational methods based solely on DNA sequences. DNA segment chromatin accessibility may provide useful information about its potential function in regulation, thereby identifying regulatory elements based on its chromatin accessibility. In chromatin, the entanglement structure allows positions far apart in the sequence to encounter each other, regardless of their proximity to the gene to be acted upon. Thus, identifying enhancers and assessing their strength is difficult and time-consuming. The goal of our work was to overcome these limitations by presenting a convolutional neural network (CNN) with attention-gated recurrent units (AttGRU) based on Deep Learning. It used a CNN and one-hot coding to build models, primarily to identify enhancers and secondarily to classify their strength. To test the performance of the proposed model, parallels were drawn between enhancer-CNNAttGRU and existing state-of-the-art methods to enable comparisons. The proposed model performed the best for predicting stage one and stage two enhancer sequences, as well as their strengths, in a cross-species analysis, achieving best accuracy values of 87.39% and 84.46%, respectively. Overall, the results showed that the proposed model provided comparable results to state-of-the-art models, highlighting its usefulness. |
| first_indexed | 2024-03-09T13:27:08Z |
| format | Article |
| id | doaj.art-463bc3956f96451ba7c227d8e0922151 |
| institution | Directory Open Access Journal |
| issn | 2218-273X |
| language | English |
| last_indexed | 2024-03-09T13:27:08Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomolecules |
| spelling | doaj.art-463bc3956f96451ba7c227d8e09221512023-11-30T21:22:18ZengMDPI AGBiomolecules2218-273X2022-12-011317010.3390/biom13010070An Efficient Lightweight Hybrid Model with Attention Mechanism for Enhancer Sequence RecognitionSuliman Aladhadh0Saleh A. Almatroodi1Shabana Habib2Abdulatif Alabdulatif3Saeed Ullah Khattak4Muhammad Islam5Department of Information Technology, College of Computer, Qassim University, Buraydah 51452, Saudi ArabiaDepartment of Medical Laboratories, College of Applied Medical Sciences, Qassim University, Buraydah 51452, Saudi ArabiaDepartment of Information Technology, College of Computer, Qassim University, Buraydah 51452, Saudi ArabiaDepartment of Computer Science, College of Computer, Qassim University, Buraydah 51452, Saudi ArabiaCentre of Biotechnology and Microbiology, University of Peshawar, Peshawar 25120, PakistanDepartment of Electrical Engineering, College of Engineering and Information Technology, Onaizah Colleges, Onaizah 56447, Saudi ArabiaEnhancers are sequences with short motifs that exhibit high positional variability and free scattering properties. Identification of these noncoding DNA fragments and their strength are extremely important because they play a key role in controlling gene regulation on a cellular basis. The identification of enhancers is more complex than that of other factors in the genome because they are freely scattered, and their location varies widely. In recent years, bioinformatics tools have enabled significant improvement in identifying this biological difficulty. Cell line-specific screening is not possible using these existing computational methods based solely on DNA sequences. DNA segment chromatin accessibility may provide useful information about its potential function in regulation, thereby identifying regulatory elements based on its chromatin accessibility. In chromatin, the entanglement structure allows positions far apart in the sequence to encounter each other, regardless of their proximity to the gene to be acted upon. Thus, identifying enhancers and assessing their strength is difficult and time-consuming. The goal of our work was to overcome these limitations by presenting a convolutional neural network (CNN) with attention-gated recurrent units (AttGRU) based on Deep Learning. It used a CNN and one-hot coding to build models, primarily to identify enhancers and secondarily to classify their strength. To test the performance of the proposed model, parallels were drawn between enhancer-CNNAttGRU and existing state-of-the-art methods to enable comparisons. The proposed model performed the best for predicting stage one and stage two enhancer sequences, as well as their strengths, in a cross-species analysis, achieving best accuracy values of 87.39% and 84.46%, respectively. Overall, the results showed that the proposed model provided comparable results to state-of-the-art models, highlighting its usefulness.https://www.mdpi.com/2218-273X/13/1/70deep learningenhancer sequenceconvolution neural networksequential learning modelstemporal attention mechanism |
| spellingShingle | Suliman Aladhadh Saleh A. Almatroodi Shabana Habib Abdulatif Alabdulatif Saeed Ullah Khattak Muhammad Islam An Efficient Lightweight Hybrid Model with Attention Mechanism for Enhancer Sequence Recognition Biomolecules deep learning enhancer sequence convolution neural network sequential learning models temporal attention mechanism |
| title | An Efficient Lightweight Hybrid Model with Attention Mechanism for Enhancer Sequence Recognition |
| title_full | An Efficient Lightweight Hybrid Model with Attention Mechanism for Enhancer Sequence Recognition |
| title_fullStr | An Efficient Lightweight Hybrid Model with Attention Mechanism for Enhancer Sequence Recognition |
| title_full_unstemmed | An Efficient Lightweight Hybrid Model with Attention Mechanism for Enhancer Sequence Recognition |
| title_short | An Efficient Lightweight Hybrid Model with Attention Mechanism for Enhancer Sequence Recognition |
| title_sort | efficient lightweight hybrid model with attention mechanism for enhancer sequence recognition |
| topic | deep learning enhancer sequence convolution neural network sequential learning models temporal attention mechanism |
| url | https://www.mdpi.com/2218-273X/13/1/70 |
| work_keys_str_mv | AT sulimanaladhadh anefficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition AT salehaalmatroodi anefficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition AT shabanahabib anefficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition AT abdulatifalabdulatif anefficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition AT saeedullahkhattak anefficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition AT muhammadislam anefficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition AT sulimanaladhadh efficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition AT salehaalmatroodi efficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition AT shabanahabib efficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition AT abdulatifalabdulatif efficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition AT saeedullahkhattak efficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition AT muhammadislam efficientlightweighthybridmodelwithattentionmechanismforenhancersequencerecognition |