Genome-wide prediction of cis-regulatory regions using supervised deep learning methods
Abstract Background In the human genome, 98% of DNA sequences are non-protein-coding regions that were previously disregarded as junk DNA. In fact, non-coding regions host a variety of cis-regulatory regions which precisely control the expression of genes. Thus, Identifying active cis-regulatory reg...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2018-05-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12859-018-2187-1 |
| _version_ | 1818129272565399552 |
|---|---|
| author | Yifeng Li Wenqiang Shi Wyeth W. Wasserman |
| author_facet | Yifeng Li Wenqiang Shi Wyeth W. Wasserman |
| author_sort | Yifeng Li |
| collection | DOAJ |
| description | Abstract Background In the human genome, 98% of DNA sequences are non-protein-coding regions that were previously disregarded as junk DNA. In fact, non-coding regions host a variety of cis-regulatory regions which precisely control the expression of genes. Thus, Identifying active cis-regulatory regions in the human genome is critical for understanding gene regulation and assessing the impact of genetic variation on phenotype. The developments of high-throughput sequencing and machine learning technologies make it possible to predict cis-regulatory regions genome wide. Results Based on rich data resources such as the Encyclopedia of DNA Elements (ENCODE) and the Functional Annotation of the Mammalian Genome (FANTOM) projects, we introduce DECRES based on supervised deep learning approaches for the identification of enhancer and promoter regions in the human genome. Due to their ability to discover patterns in large and complex data, the introduction of deep learning methods enables a significant advance in our knowledge of the genomic locations of cis-regulatory regions. Using models for well-characterized cell lines, we identify key experimental features that contribute to the predictive performance. Applying DECRES, we delineate locations of 300,000 candidate enhancers genome wide (6.8% of the genome, of which 40,000 are supported by bidirectional transcription data), and 26,000 candidate promoters (0.6% of the genome). Conclusion The predicted annotations of cis-regulatory regions will provide broad utility for genome interpretation from functional genomics to clinical applications. The DECRES model demonstrates potentials of deep learning technologies when combined with high-throughput sequencing data, and inspires the development of other advanced neural network models for further improvement of genome annotations. |
| first_indexed | 2024-12-11T07:46:31Z |
| format | Article |
| id | doaj.art-cf7888513cf24443b01e82c9177e727d |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-11T07:46:31Z |
| publishDate | 2018-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-cf7888513cf24443b01e82c9177e727d2022-12-22T01:15:27ZengBMCBMC Bioinformatics1471-21052018-05-0119111410.1186/s12859-018-2187-1Genome-wide prediction of cis-regulatory regions using supervised deep learning methodsYifeng Li0Wenqiang Shi1Wyeth W. Wasserman2Centre for Molecular Medicine and Therapeutics, BC Children’s Hospital Research Institute, Department of Medical Genetics, University of British ColumbiaCentre for Molecular Medicine and Therapeutics, BC Children’s Hospital Research Institute, Department of Medical Genetics, University of British ColumbiaCentre for Molecular Medicine and Therapeutics, BC Children’s Hospital Research Institute, Department of Medical Genetics, University of British ColumbiaAbstract Background In the human genome, 98% of DNA sequences are non-protein-coding regions that were previously disregarded as junk DNA. In fact, non-coding regions host a variety of cis-regulatory regions which precisely control the expression of genes. Thus, Identifying active cis-regulatory regions in the human genome is critical for understanding gene regulation and assessing the impact of genetic variation on phenotype. The developments of high-throughput sequencing and machine learning technologies make it possible to predict cis-regulatory regions genome wide. Results Based on rich data resources such as the Encyclopedia of DNA Elements (ENCODE) and the Functional Annotation of the Mammalian Genome (FANTOM) projects, we introduce DECRES based on supervised deep learning approaches for the identification of enhancer and promoter regions in the human genome. Due to their ability to discover patterns in large and complex data, the introduction of deep learning methods enables a significant advance in our knowledge of the genomic locations of cis-regulatory regions. Using models for well-characterized cell lines, we identify key experimental features that contribute to the predictive performance. Applying DECRES, we delineate locations of 300,000 candidate enhancers genome wide (6.8% of the genome, of which 40,000 are supported by bidirectional transcription data), and 26,000 candidate promoters (0.6% of the genome). Conclusion The predicted annotations of cis-regulatory regions will provide broad utility for genome interpretation from functional genomics to clinical applications. The DECRES model demonstrates potentials of deep learning technologies when combined with high-throughput sequencing data, and inspires the development of other advanced neural network models for further improvement of genome annotations.http://link.springer.com/article/10.1186/s12859-018-2187-1cis-regulatory regionEnhancerPromoterDeep learning |
| spellingShingle | Yifeng Li Wenqiang Shi Wyeth W. Wasserman Genome-wide prediction of cis-regulatory regions using supervised deep learning methods BMC Bioinformatics cis-regulatory region Enhancer Promoter Deep learning |
| title | Genome-wide prediction of cis-regulatory regions using supervised deep learning methods |
| title_full | Genome-wide prediction of cis-regulatory regions using supervised deep learning methods |
| title_fullStr | Genome-wide prediction of cis-regulatory regions using supervised deep learning methods |
| title_full_unstemmed | Genome-wide prediction of cis-regulatory regions using supervised deep learning methods |
| title_short | Genome-wide prediction of cis-regulatory regions using supervised deep learning methods |
| title_sort | genome wide prediction of cis regulatory regions using supervised deep learning methods |
| topic | cis-regulatory region Enhancer Promoter Deep learning |
| url | http://link.springer.com/article/10.1186/s12859-018-2187-1 |
| work_keys_str_mv | AT yifengli genomewidepredictionofcisregulatoryregionsusingsuperviseddeeplearningmethods AT wenqiangshi genomewidepredictionofcisregulatoryregionsusingsuperviseddeeplearningmethods AT wyethwwasserman genomewidepredictionofcisregulatoryregionsusingsuperviseddeeplearningmethods |