AIVariant: a deep learning-based somatic variant detector for highly contaminated tumor samples
Abstract The detection of somatic DNA variants in tumor samples with low tumor purity or sequencing depth remains a daunting challenge despite numerous attempts to address this problem. In this study, we constructed a substantially extended set of actual positive variants originating from a wide ran...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Publishing Group
2023-08-01
|
| Series: | Experimental and Molecular Medicine |
| Online Access: | https://doi.org/10.1038/s12276-023-01049-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572035466788864 |
|---|---|
| author | Hyeonseong Jeon Junhak Ahn Byunggook Na Soona Hong Lee Sael Sun Kim Sungroh Yoon Daehyun Baek |
| author_facet | Hyeonseong Jeon Junhak Ahn Byunggook Na Soona Hong Lee Sael Sun Kim Sungroh Yoon Daehyun Baek |
| author_sort | Hyeonseong Jeon |
| collection | DOAJ |
| description | Abstract The detection of somatic DNA variants in tumor samples with low tumor purity or sequencing depth remains a daunting challenge despite numerous attempts to address this problem. In this study, we constructed a substantially extended set of actual positive variants originating from a wide range of tumor purities and sequencing depths, as well as actual negative variants derived from sequencer-specific sequencing errors. A deep learning model named AIVariant, trained on this extended dataset, outperforms previously reported methods when tested under various tumor purities and sequencing depths, especially low tumor purity and sequencing depth. |
| format | Article |
| id | doaj-art-dd14fe5a9ca84370b1063435e5491f1e |
| institution | Kabale University |
| issn | 2092-6413 |
| language | English |
| publishDate | 2023-08-01 |
| publisher | Nature Publishing Group |
| record_format | Article |
| series | Experimental and Molecular Medicine |
| spelling | doaj-art-dd14fe5a9ca84370b1063435e5491f1e2025-02-02T12:10:22ZengNature Publishing GroupExperimental and Molecular Medicine2092-64132023-08-015581734174210.1038/s12276-023-01049-2AIVariant: a deep learning-based somatic variant detector for highly contaminated tumor samplesHyeonseong Jeon0Junhak Ahn1Byunggook Na2Soona Hong3Lee Sael4Sun Kim5Sungroh Yoon6Daehyun Baek7Interdisciplinary Program in Bioinformatics, Seoul National UniversityGenome4me Inc.Department of Electrical and Computer Engineering, Seoul National UniversityAIGENDRUG Co., Ltd.Department of Software and Computer Engineering, Ajou UniversityDepartment of Computer Science and Engineering, Seoul National UniversityDepartment of Electrical and Computer Engineering, Seoul National UniversityInterdisciplinary Program in Bioinformatics, Seoul National UniversityAbstract The detection of somatic DNA variants in tumor samples with low tumor purity or sequencing depth remains a daunting challenge despite numerous attempts to address this problem. In this study, we constructed a substantially extended set of actual positive variants originating from a wide range of tumor purities and sequencing depths, as well as actual negative variants derived from sequencer-specific sequencing errors. A deep learning model named AIVariant, trained on this extended dataset, outperforms previously reported methods when tested under various tumor purities and sequencing depths, especially low tumor purity and sequencing depth.https://doi.org/10.1038/s12276-023-01049-2 |
| spellingShingle | Hyeonseong Jeon Junhak Ahn Byunggook Na Soona Hong Lee Sael Sun Kim Sungroh Yoon Daehyun Baek AIVariant: a deep learning-based somatic variant detector for highly contaminated tumor samples Experimental and Molecular Medicine |
| title | AIVariant: a deep learning-based somatic variant detector for highly contaminated tumor samples |
| title_full | AIVariant: a deep learning-based somatic variant detector for highly contaminated tumor samples |
| title_fullStr | AIVariant: a deep learning-based somatic variant detector for highly contaminated tumor samples |
| title_full_unstemmed | AIVariant: a deep learning-based somatic variant detector for highly contaminated tumor samples |
| title_short | AIVariant: a deep learning-based somatic variant detector for highly contaminated tumor samples |
| title_sort | aivariant a deep learning based somatic variant detector for highly contaminated tumor samples |
| url | https://doi.org/10.1038/s12276-023-01049-2 |
| work_keys_str_mv | AT hyeonseongjeon aivariantadeeplearningbasedsomaticvariantdetectorforhighlycontaminatedtumorsamples AT junhakahn aivariantadeeplearningbasedsomaticvariantdetectorforhighlycontaminatedtumorsamples AT byunggookna aivariantadeeplearningbasedsomaticvariantdetectorforhighlycontaminatedtumorsamples AT soonahong aivariantadeeplearningbasedsomaticvariantdetectorforhighlycontaminatedtumorsamples AT leesael aivariantadeeplearningbasedsomaticvariantdetectorforhighlycontaminatedtumorsamples AT sunkim aivariantadeeplearningbasedsomaticvariantdetectorforhighlycontaminatedtumorsamples AT sungrohyoon aivariantadeeplearningbasedsomaticvariantdetectorforhighlycontaminatedtumorsamples AT daehyunbaek aivariantadeeplearningbasedsomaticvariantdetectorforhighlycontaminatedtumorsamples |