An explainable artificial intelligence approach for decoding the enhancer histone modifications code and identification of novel enhancers in Drosophila
Abstract Background Enhancers are non-coding regions of the genome that control the activity of target genes. Recent efforts to identify active enhancers experimentally and in silico have proven effective. While these tools can predict the locations of enhancers with a high degree of accuracy, the m...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
BMC
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/a7e2a4715eaa4363961c78e7ada16cf1 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:a7e2a4715eaa4363961c78e7ada16cf1 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:a7e2a4715eaa4363961c78e7ada16cf12021-11-14T12:42:49ZAn explainable artificial intelligence approach for decoding the enhancer histone modifications code and identification of novel enhancers in Drosophila10.1186/s13059-021-02532-71474-760Xhttps://doaj.org/article/a7e2a4715eaa4363961c78e7ada16cf12021-11-01T00:00:00Zhttps://doi.org/10.1186/s13059-021-02532-7https://doaj.org/toc/1474-760XAbstract Background Enhancers are non-coding regions of the genome that control the activity of target genes. Recent efforts to identify active enhancers experimentally and in silico have proven effective. While these tools can predict the locations of enhancers with a high degree of accuracy, the mechanisms underpinning the activity of enhancers are often unclear. Results Using machine learning (ML) and a rule-based explainable artificial intelligence (XAI) model, we demonstrate that we can predict the location of known enhancers in Drosophila with a high degree of accuracy. Most importantly, we use the rules of the XAI model to provide insight into the underlying combinatorial histone modifications code of enhancers. In addition, we identified a large set of putative enhancers that display the same epigenetic signature as enhancers identified experimentally. These putative enhancers are enriched in nascent transcription, divergent transcription and have 3D contacts with promoters of transcribed genes. However, they display only intermediary enrichment of mediator and cohesin complexes compared to previously characterised active enhancers. We also found that 10–15% of the predicted enhancers display similar characteristics to super enhancers observed in other species. Conclusions Here, we applied an explainable AI model to predict enhancers with high accuracy. Most importantly, we identified that different combinations of epigenetic marks characterise different groups of enhancers. Finally, we discovered a large set of putative enhancers which display similar characteristics with previously characterised active enhancers.Jareth C. WolfeLiudmila A. MikheevaHani HagrasNicolae Radu ZabetBMCarticleEnhancersHistone modificationsExplainable Artificial IntelligenceGene regulationDrosophilaBiology (General)QH301-705.5GeneticsQH426-470ENGenome Biology, Vol 22, Iss 1, Pp 1-23 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Enhancers Histone modifications Explainable Artificial Intelligence Gene regulation Drosophila Biology (General) QH301-705.5 Genetics QH426-470 |
spellingShingle |
Enhancers Histone modifications Explainable Artificial Intelligence Gene regulation Drosophila Biology (General) QH301-705.5 Genetics QH426-470 Jareth C. Wolfe Liudmila A. Mikheeva Hani Hagras Nicolae Radu Zabet An explainable artificial intelligence approach for decoding the enhancer histone modifications code and identification of novel enhancers in Drosophila |
description |
Abstract Background Enhancers are non-coding regions of the genome that control the activity of target genes. Recent efforts to identify active enhancers experimentally and in silico have proven effective. While these tools can predict the locations of enhancers with a high degree of accuracy, the mechanisms underpinning the activity of enhancers are often unclear. Results Using machine learning (ML) and a rule-based explainable artificial intelligence (XAI) model, we demonstrate that we can predict the location of known enhancers in Drosophila with a high degree of accuracy. Most importantly, we use the rules of the XAI model to provide insight into the underlying combinatorial histone modifications code of enhancers. In addition, we identified a large set of putative enhancers that display the same epigenetic signature as enhancers identified experimentally. These putative enhancers are enriched in nascent transcription, divergent transcription and have 3D contacts with promoters of transcribed genes. However, they display only intermediary enrichment of mediator and cohesin complexes compared to previously characterised active enhancers. We also found that 10–15% of the predicted enhancers display similar characteristics to super enhancers observed in other species. Conclusions Here, we applied an explainable AI model to predict enhancers with high accuracy. Most importantly, we identified that different combinations of epigenetic marks characterise different groups of enhancers. Finally, we discovered a large set of putative enhancers which display similar characteristics with previously characterised active enhancers. |
format |
article |
author |
Jareth C. Wolfe Liudmila A. Mikheeva Hani Hagras Nicolae Radu Zabet |
author_facet |
Jareth C. Wolfe Liudmila A. Mikheeva Hani Hagras Nicolae Radu Zabet |
author_sort |
Jareth C. Wolfe |
title |
An explainable artificial intelligence approach for decoding the enhancer histone modifications code and identification of novel enhancers in Drosophila |
title_short |
An explainable artificial intelligence approach for decoding the enhancer histone modifications code and identification of novel enhancers in Drosophila |
title_full |
An explainable artificial intelligence approach for decoding the enhancer histone modifications code and identification of novel enhancers in Drosophila |
title_fullStr |
An explainable artificial intelligence approach for decoding the enhancer histone modifications code and identification of novel enhancers in Drosophila |
title_full_unstemmed |
An explainable artificial intelligence approach for decoding the enhancer histone modifications code and identification of novel enhancers in Drosophila |
title_sort |
explainable artificial intelligence approach for decoding the enhancer histone modifications code and identification of novel enhancers in drosophila |
publisher |
BMC |
publishDate |
2021 |
url |
https://doaj.org/article/a7e2a4715eaa4363961c78e7ada16cf1 |
work_keys_str_mv |
AT jarethcwolfe anexplainableartificialintelligenceapproachfordecodingtheenhancerhistonemodificationscodeandidentificationofnovelenhancersindrosophila AT liudmilaamikheeva anexplainableartificialintelligenceapproachfordecodingtheenhancerhistonemodificationscodeandidentificationofnovelenhancersindrosophila AT hanihagras anexplainableartificialintelligenceapproachfordecodingtheenhancerhistonemodificationscodeandidentificationofnovelenhancersindrosophila AT nicolaeraduzabet anexplainableartificialintelligenceapproachfordecodingtheenhancerhistonemodificationscodeandidentificationofnovelenhancersindrosophila AT jarethcwolfe explainableartificialintelligenceapproachfordecodingtheenhancerhistonemodificationscodeandidentificationofnovelenhancersindrosophila AT liudmilaamikheeva explainableartificialintelligenceapproachfordecodingtheenhancerhistonemodificationscodeandidentificationofnovelenhancersindrosophila AT hanihagras explainableartificialintelligenceapproachfordecodingtheenhancerhistonemodificationscodeandidentificationofnovelenhancersindrosophila AT nicolaeraduzabet explainableartificialintelligenceapproachfordecodingtheenhancerhistonemodificationscodeandidentificationofnovelenhancersindrosophila |
_version_ |
1718429066421338112 |