FusionAI: Predicting fusion breakpoint from DNA sequence with deep learning
Summary: Identifying the molecular mechanisms related to genomic breakage is an important goal of cancer mechanism studies. Among diverse locations of structural variants, fusion genes, which have the breakpoints in the gene bodies and are typically identified from the split reads of RNA-seq data, c...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-10-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004221011329 |
| id |
doaj-8667acc01132414a96cb70642377db16 |
|---|---|
| record_format |
Article |
| spelling |
doaj-8667acc01132414a96cb70642377db162021-10-07T04:26:35ZengElsevieriScience2589-00422021-10-012410103164FusionAI: Predicting fusion breakpoint from DNA sequence with deep learningPora Kim0Hua Tan1Jiajia Liu2Mengyuan Yang3Xiaobo Zhou4School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USA; Corresponding authorSchool of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USASchool of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USA; College of Electronic and Information Engineering, Tongji University, Shanghai, Shanghai 201804, ChinaSchool of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USA; School of Life Sciences and Technology, Tongji University, Shanghai 200092, ChinaSchool of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USA; McGovern Medical School, The University of Texas Health Science Center at Houston, Houston, TX 77030, USA; School of Dentistry, The University of Texas Health Science Center at Houston, Houston, TX 77030, USA; Corresponding authorSummary: Identifying the molecular mechanisms related to genomic breakage is an important goal of cancer mechanism studies. Among diverse locations of structural variants, fusion genes, which have the breakpoints in the gene bodies and are typically identified from the split reads of RNA-seq data, can provide a highlighted structural variant resource for studying the genomic breakages with expression and potential pathogenic impacts. In this study, we developed FusionAI, which utilizes deep learning to predict gene fusion breakpoints based on DNA sequence and let us identify fusion breakage code and genomic context. FusionAI leverages the known fusion breakpoints to provide a prediction model of the fusion genes from the primary genomic sequences via deep learning, thereby helping researchers a more accurate selection of fusion genes and better understand genomic breakage.http://www.sciencedirect.com/science/article/pii/S2589004221011329geneticsgenomicscomputational bioinformaticsartificial intelligence applications |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Pora Kim Hua Tan Jiajia Liu Mengyuan Yang Xiaobo Zhou |
| spellingShingle |
Pora Kim Hua Tan Jiajia Liu Mengyuan Yang Xiaobo Zhou FusionAI: Predicting fusion breakpoint from DNA sequence with deep learning iScience genetics genomics computational bioinformatics artificial intelligence applications |
| author_facet |
Pora Kim Hua Tan Jiajia Liu Mengyuan Yang Xiaobo Zhou |
| author_sort |
Pora Kim |
| title |
FusionAI: Predicting fusion breakpoint from DNA sequence with deep learning |
| title_short |
FusionAI: Predicting fusion breakpoint from DNA sequence with deep learning |
| title_full |
FusionAI: Predicting fusion breakpoint from DNA sequence with deep learning |
| title_fullStr |
FusionAI: Predicting fusion breakpoint from DNA sequence with deep learning |
| title_full_unstemmed |
FusionAI: Predicting fusion breakpoint from DNA sequence with deep learning |
| title_sort |
fusionai: predicting fusion breakpoint from dna sequence with deep learning |
| publisher |
Elsevier |
| series |
iScience |
| issn |
2589-0042 |
| publishDate |
2021-10-01 |
| description |
Summary: Identifying the molecular mechanisms related to genomic breakage is an important goal of cancer mechanism studies. Among diverse locations of structural variants, fusion genes, which have the breakpoints in the gene bodies and are typically identified from the split reads of RNA-seq data, can provide a highlighted structural variant resource for studying the genomic breakages with expression and potential pathogenic impacts. In this study, we developed FusionAI, which utilizes deep learning to predict gene fusion breakpoints based on DNA sequence and let us identify fusion breakage code and genomic context. FusionAI leverages the known fusion breakpoints to provide a prediction model of the fusion genes from the primary genomic sequences via deep learning, thereby helping researchers a more accurate selection of fusion genes and better understand genomic breakage. |
| topic |
genetics genomics computational bioinformatics artificial intelligence applications |
| url |
http://www.sciencedirect.com/science/article/pii/S2589004221011329 |
| work_keys_str_mv |
AT porakim fusionaipredictingfusionbreakpointfromdnasequencewithdeeplearning AT huatan fusionaipredictingfusionbreakpointfromdnasequencewithdeeplearning AT jiajialiu fusionaipredictingfusionbreakpointfromdnasequencewithdeeplearning AT mengyuanyang fusionaipredictingfusionbreakpointfromdnasequencewithdeeplearning AT xiaobozhou fusionaipredictingfusionbreakpointfromdnasequencewithdeeplearning |
| _version_ |
1716839908600971264 |