Back to Search
Start Over
Enhancing breakpoint resolution with deep segmentation model: A general refinement method for read-depth based structural variant callers
- Source :
- PLoS Computational Biology, Vol 17, Iss 10, p e1009186 (2021), PLoS Computational Biology
- Publication Year :
- 2021
- Publisher :
- Public Library of Science (PLoS), 2021.
-
Abstract
- Read-depths (RDs) are frequently used in identifying structural variants (SVs) from sequencing data. For existing RD-based SV callers, it is difficult for them to determine breakpoints in single-nucleotide resolution due to the noisiness of RD data and the bin-based calculation. In this paper, we propose to use the deep segmentation model UNet to learn base-wise RD patterns surrounding breakpoints of known SVs. We integrate model predictions with an RD-based SV caller to enhance breakpoints in single-nucleotide resolution. We show that UNet can be trained with a small amount of data and can be applied both in-sample and cross-sample. An enhancement pipeline named RDBKE significantly increases the number of SVs with more precise breakpoints on simulated and real data. The source code of RDBKE is freely available at https://github.com/yaozhong/deepIntraSV.<br />Author summary In this paper, we used the deep segmentation model UNet to alleviate the bin size limitation of RD-based SV callers. UNet was initially proposed for image data. Here, we demonstrated that the UNet model could also be applied for one-dimensional genomic data. We formalized the breakpoint prediction as a segmentation task and inferred breakpoints in single-nucleotide resolution from predicted label marks. Through a set of experiments on both simulated and real WGS data, we demonstrated that the UNet model could be trained with a small amount of data, and an enhancement pipeline called RDBKE significantly increased the number of SVs with more precise breakpoints.
- Subjects :
- Computer and Information Sciences
Source code
Neural Networks
QH301-705.5
Computer science
Single Nucleotide Polymorphisms
Pipeline (computing)
media_common.quotation_subject
Sequencing data
Read depth
Research and Analysis Methods
computer.software_genre
Machine Learning
Cellular and Molecular Neuroscience
Deep Learning
Cancer Genomics
Genomic Medicine
Artificial Intelligence
Computational Techniques
Basic Cancer Research
Medicine and Health Sciences
Genetics
Humans
Segmentation
Biology (General)
Molecular Biology
Ecology, Evolution, Behavior and Systematics
media_common
Models, Genetic
Whole Genome Sequencing
Ecology
Genome, Human
Simulation and Modeling
Breakpoint
Computational Pipelines
Biology and Life Sciences
Cancers and Neoplasms
Structural variant
Genomics
Resolution (logic)
Oncology
Computational Theory and Mathematics
Modeling and Simulation
Genomic Structural Variation
Data mining
computer
Research Article
Neuroscience
Subjects
Details
- ISSN :
- 15537358
- Volume :
- 17
- Database :
- OpenAIRE
- Journal :
- PLOS Computational Biology
- Accession number :
- edsair.doi.dedup.....9959176e1eab6d3272909284ec3125f5