INSnet: a method for detecting insertions based on deep learning network
Abstract Background Many studies have shown that structural variations (SVs) strongly impact human disease. As a common type of SV, insertions are usually associated with genetic diseases. Therefore, accurately detecting insertions is of great significance. Although many methods for detecting insert...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-03-01
|
Series: | BMC Bioinformatics |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12859-023-05216-0 |
_version_ | 1797863374709587968 |
---|---|
author | Runtian Gao Junwei Luo Hongyu Ding Haixia Zhai |
author_facet | Runtian Gao Junwei Luo Hongyu Ding Haixia Zhai |
author_sort | Runtian Gao |
collection | DOAJ |
description | Abstract Background Many studies have shown that structural variations (SVs) strongly impact human disease. As a common type of SV, insertions are usually associated with genetic diseases. Therefore, accurately detecting insertions is of great significance. Although many methods for detecting insertions have been proposed, these methods often generate some errors and miss some variants. Hence, accurately detecting insertions remains a challenging task. Results In this paper, we propose a method named INSnet to detect insertions using a deep learning network. First, INSnet divides the reference genome into continuous sub-regions and takes five features for each locus through alignments between long reads and the reference genome. Next, INSnet uses a depthwise separable convolutional network. The convolution operation extracts informative features through spatial information and channel information. INSnet uses two attention mechanisms, the convolutional block attention module (CBAM) and efficient channel attention (ECA) to extract key alignment features in each sub-region. In order to capture the relationship between adjacent subregions, INSnet uses a gated recurrent unit (GRU) network to further extract more important SV signatures. After predicting whether a sub-region contains an insertion through the previous steps, INSnet determines the precise site and length of the insertion. The source code is available from GitHub at https://github.com/eioyuou/INSnet . Conclusion Experimental results show that INSnet can achieve better performance than other methods in terms of F1 score on real datasets. |
first_indexed | 2024-04-09T22:34:35Z |
format | Article |
id | doaj.art-0b73e36495964f33bb388eb0e31c2440 |
institution | Directory Open Access Journal |
issn | 1471-2105 |
language | English |
last_indexed | 2024-04-09T22:34:35Z |
publishDate | 2023-03-01 |
publisher | BMC |
record_format | Article |
series | BMC Bioinformatics |
spelling | doaj.art-0b73e36495964f33bb388eb0e31c24402023-03-22T12:33:02ZengBMCBMC Bioinformatics1471-21052023-03-0124111510.1186/s12859-023-05216-0INSnet: a method for detecting insertions based on deep learning networkRuntian Gao0Junwei Luo1Hongyu Ding2Haixia Zhai3School of Software, Henan Polytechnic UniversitySchool of Software, Henan Polytechnic UniversitySchool of Software, Henan Polytechnic UniversitySchool of Software, Henan Polytechnic UniversityAbstract Background Many studies have shown that structural variations (SVs) strongly impact human disease. As a common type of SV, insertions are usually associated with genetic diseases. Therefore, accurately detecting insertions is of great significance. Although many methods for detecting insertions have been proposed, these methods often generate some errors and miss some variants. Hence, accurately detecting insertions remains a challenging task. Results In this paper, we propose a method named INSnet to detect insertions using a deep learning network. First, INSnet divides the reference genome into continuous sub-regions and takes five features for each locus through alignments between long reads and the reference genome. Next, INSnet uses a depthwise separable convolutional network. The convolution operation extracts informative features through spatial information and channel information. INSnet uses two attention mechanisms, the convolutional block attention module (CBAM) and efficient channel attention (ECA) to extract key alignment features in each sub-region. In order to capture the relationship between adjacent subregions, INSnet uses a gated recurrent unit (GRU) network to further extract more important SV signatures. After predicting whether a sub-region contains an insertion through the previous steps, INSnet determines the precise site and length of the insertion. The source code is available from GitHub at https://github.com/eioyuou/INSnet . Conclusion Experimental results show that INSnet can achieve better performance than other methods in terms of F1 score on real datasets.https://doi.org/10.1186/s12859-023-05216-0Structural variationInsertionDeep learningDepthwise separable convolutional networkGated recurrent unit |
spellingShingle | Runtian Gao Junwei Luo Hongyu Ding Haixia Zhai INSnet: a method for detecting insertions based on deep learning network BMC Bioinformatics Structural variation Insertion Deep learning Depthwise separable convolutional network Gated recurrent unit |
title | INSnet: a method for detecting insertions based on deep learning network |
title_full | INSnet: a method for detecting insertions based on deep learning network |
title_fullStr | INSnet: a method for detecting insertions based on deep learning network |
title_full_unstemmed | INSnet: a method for detecting insertions based on deep learning network |
title_short | INSnet: a method for detecting insertions based on deep learning network |
title_sort | insnet a method for detecting insertions based on deep learning network |
topic | Structural variation Insertion Deep learning Depthwise separable convolutional network Gated recurrent unit |
url | https://doi.org/10.1186/s12859-023-05216-0 |
work_keys_str_mv | AT runtiangao insnetamethodfordetectinginsertionsbasedondeeplearningnetwork AT junweiluo insnetamethodfordetectinginsertionsbasedondeeplearningnetwork AT hongyuding insnetamethodfordetectinginsertionsbasedondeeplearningnetwork AT haixiazhai insnetamethodfordetectinginsertionsbasedondeeplearningnetwork |