DeepVISP: Deep Learning for Virus Site Integration Prediction and Motif Discovery
Abstract Approximately 15% of human cancers are estimated to be attributed to viruses. Virus sequences can be integrated into the host genome, leading to genomic instability and carcinogenesis. Here, a new deep convolutional neural network (CNN) model is developed with attention architecture, namely...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-05-01
|
Series: | Advanced Science |
Subjects: | |
Online Access: | https://doi.org/10.1002/advs.202004958 |
id |
doaj-c930b648def6469c974ac77b3075eed6 |
---|---|
record_format |
Article |
spelling |
doaj-c930b648def6469c974ac77b3075eed62021-05-05T07:56:42ZengWileyAdvanced Science2198-38442021-05-0189n/an/a10.1002/advs.202004958DeepVISP: Deep Learning for Virus Site Integration Prediction and Motif DiscoveryHaodong Xu0Peilin Jia1Zhongming Zhao2Center for Precision Health School of Biomedical Informatics The University of Texas Health Science Center at Houston (UTHealth) Houston TX 77030 USACenter for Precision Health School of Biomedical Informatics The University of Texas Health Science Center at Houston (UTHealth) Houston TX 77030 USACenter for Precision Health School of Biomedical Informatics The University of Texas Health Science Center at Houston (UTHealth) Houston TX 77030 USAAbstract Approximately 15% of human cancers are estimated to be attributed to viruses. Virus sequences can be integrated into the host genome, leading to genomic instability and carcinogenesis. Here, a new deep convolutional neural network (CNN) model is developed with attention architecture, namely DeepVISP, for accurately predicting oncogenic virus integration sites (VISs) in the human genome. Using the curated benchmark integration data of three viruses, hepatitis B virus (HBV), human herpesvirus (HPV), and Epstein‐Barr virus (EBV), DeepVISP achieves high accuracy and robust performance for all three viruses through automatically learning informative features and essential genomic positions only from the DNA sequences. In comparison, DeepVISP outperforms conventional machine learning methods by 8.43–34.33% measured by area under curve (AUC) value enhancement in three viruses. Moreover, DeepVISP can decode cis‐regulatory factors that are potentially involved in virus integration and tumorigenesis, such as HOXB7, IKZF1, and LHX6. These findings are supported by multiple lines of evidence in literature. The clustering analysis of the informative motifs reveales that the representative k‐mers in clusters could help guide virus recognition of the host genes. A user‐friendly web server is developed for predicting putative oncogenic VISs in the human genome using DeepVISP.https://doi.org/10.1002/advs.202004958cancerdeep learningEBVHBVHPVviruses |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Haodong Xu Peilin Jia Zhongming Zhao |
spellingShingle |
Haodong Xu Peilin Jia Zhongming Zhao DeepVISP: Deep Learning for Virus Site Integration Prediction and Motif Discovery Advanced Science cancer deep learning EBV HBV HPV viruses |
author_facet |
Haodong Xu Peilin Jia Zhongming Zhao |
author_sort |
Haodong Xu |
title |
DeepVISP: Deep Learning for Virus Site Integration Prediction and Motif Discovery |
title_short |
DeepVISP: Deep Learning for Virus Site Integration Prediction and Motif Discovery |
title_full |
DeepVISP: Deep Learning for Virus Site Integration Prediction and Motif Discovery |
title_fullStr |
DeepVISP: Deep Learning for Virus Site Integration Prediction and Motif Discovery |
title_full_unstemmed |
DeepVISP: Deep Learning for Virus Site Integration Prediction and Motif Discovery |
title_sort |
deepvisp: deep learning for virus site integration prediction and motif discovery |
publisher |
Wiley |
series |
Advanced Science |
issn |
2198-3844 |
publishDate |
2021-05-01 |
description |
Abstract Approximately 15% of human cancers are estimated to be attributed to viruses. Virus sequences can be integrated into the host genome, leading to genomic instability and carcinogenesis. Here, a new deep convolutional neural network (CNN) model is developed with attention architecture, namely DeepVISP, for accurately predicting oncogenic virus integration sites (VISs) in the human genome. Using the curated benchmark integration data of three viruses, hepatitis B virus (HBV), human herpesvirus (HPV), and Epstein‐Barr virus (EBV), DeepVISP achieves high accuracy and robust performance for all three viruses through automatically learning informative features and essential genomic positions only from the DNA sequences. In comparison, DeepVISP outperforms conventional machine learning methods by 8.43–34.33% measured by area under curve (AUC) value enhancement in three viruses. Moreover, DeepVISP can decode cis‐regulatory factors that are potentially involved in virus integration and tumorigenesis, such as HOXB7, IKZF1, and LHX6. These findings are supported by multiple lines of evidence in literature. The clustering analysis of the informative motifs reveales that the representative k‐mers in clusters could help guide virus recognition of the host genes. A user‐friendly web server is developed for predicting putative oncogenic VISs in the human genome using DeepVISP. |
topic |
cancer deep learning EBV HBV HPV viruses |
url |
https://doi.org/10.1002/advs.202004958 |
work_keys_str_mv |
AT haodongxu deepvispdeeplearningforvirussiteintegrationpredictionandmotifdiscovery AT peilinjia deepvispdeeplearningforvirussiteintegrationpredictionandmotifdiscovery AT zhongmingzhao deepvispdeeplearningforvirussiteintegrationpredictionandmotifdiscovery |
_version_ |
1721467805305405440 |