Transformers significantly improve splice site prediction
Abstract Mutations that affect RNA splicing significantly impact human diversity and disease. Here we present a method using transformers, a type of machine learning model, to detect splicing from raw 45,000-nucleotide sequences. We generate embeddings with residual neural networks and apply hard at...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Communications Biology |
| Online Access: | https://doi.org/10.1038/s42003-024-07298-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846112310128541696 |
|---|---|
| author | Benedikt A. Jónsson Gísli H. Halldórsson Steinþór Árdal Sölvi Rögnvaldsson Eyþór Einarsson Patrick Sulem Daníel F. Guðbjartsson Páll Melsted Kári Stefánsson Magnús Ö. Úlfarsson |
| author_facet | Benedikt A. Jónsson Gísli H. Halldórsson Steinþór Árdal Sölvi Rögnvaldsson Eyþór Einarsson Patrick Sulem Daníel F. Guðbjartsson Páll Melsted Kári Stefánsson Magnús Ö. Úlfarsson |
| author_sort | Benedikt A. Jónsson |
| collection | DOAJ |
| description | Abstract Mutations that affect RNA splicing significantly impact human diversity and disease. Here we present a method using transformers, a type of machine learning model, to detect splicing from raw 45,000-nucleotide sequences. We generate embeddings with residual neural networks and apply hard attention to select splice site candidates, enabling efficient training on long sequences. Our method surpasses the leading tool, SpliceAI, in detecting splice sites in GENCODE and ENSEMBL annotations. Using extensive RNA sequencing data from an Icelandic cohort of 17,848 individuals and the Genotype-Tissue Expression (GTEx) project, our method demonstrates superior performance in detecting splice junctions compared to SpliceAI-10k (PR-AUC = 0.834 vs. PR-AUC = 0.820) and is more effective at identifying disease-related splice variants in ClinVar (PR-AUC = 0.997 vs. PR-AUC = 0.996). These advancements hold promise for improving genetic research and clinical diagnostics, potentially leading to better understanding and treatment of splicing-related diseases. |
| format | Article |
| id | doaj-art-edb255f68b4b469996e1fb41ad38a6e0 |
| institution | Kabale University |
| issn | 2399-3642 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Biology |
| spelling | doaj-art-edb255f68b4b469996e1fb41ad38a6e02024-12-22T12:41:54ZengNature PortfolioCommunications Biology2399-36422024-12-01711910.1038/s42003-024-07298-9Transformers significantly improve splice site predictionBenedikt A. Jónsson0Gísli H. Halldórsson1Steinþór Árdal2Sölvi Rögnvaldsson3Eyþór Einarsson4Patrick Sulem5Daníel F. Guðbjartsson6Páll Melsted7Kári Stefánsson8Magnús Ö. Úlfarsson9deCODE Genetics/Amgen Inc.deCODE Genetics/Amgen Inc.deCODE Genetics/Amgen Inc.deCODE Genetics/Amgen Inc.deCODE Genetics/Amgen Inc.deCODE Genetics/Amgen Inc.deCODE Genetics/Amgen Inc.deCODE Genetics/Amgen Inc.deCODE Genetics/Amgen Inc.deCODE Genetics/Amgen Inc.Abstract Mutations that affect RNA splicing significantly impact human diversity and disease. Here we present a method using transformers, a type of machine learning model, to detect splicing from raw 45,000-nucleotide sequences. We generate embeddings with residual neural networks and apply hard attention to select splice site candidates, enabling efficient training on long sequences. Our method surpasses the leading tool, SpliceAI, in detecting splice sites in GENCODE and ENSEMBL annotations. Using extensive RNA sequencing data from an Icelandic cohort of 17,848 individuals and the Genotype-Tissue Expression (GTEx) project, our method demonstrates superior performance in detecting splice junctions compared to SpliceAI-10k (PR-AUC = 0.834 vs. PR-AUC = 0.820) and is more effective at identifying disease-related splice variants in ClinVar (PR-AUC = 0.997 vs. PR-AUC = 0.996). These advancements hold promise for improving genetic research and clinical diagnostics, potentially leading to better understanding and treatment of splicing-related diseases.https://doi.org/10.1038/s42003-024-07298-9 |
| spellingShingle | Benedikt A. Jónsson Gísli H. Halldórsson Steinþór Árdal Sölvi Rögnvaldsson Eyþór Einarsson Patrick Sulem Daníel F. Guðbjartsson Páll Melsted Kári Stefánsson Magnús Ö. Úlfarsson Transformers significantly improve splice site prediction Communications Biology |
| title | Transformers significantly improve splice site prediction |
| title_full | Transformers significantly improve splice site prediction |
| title_fullStr | Transformers significantly improve splice site prediction |
| title_full_unstemmed | Transformers significantly improve splice site prediction |
| title_short | Transformers significantly improve splice site prediction |
| title_sort | transformers significantly improve splice site prediction |
| url | https://doi.org/10.1038/s42003-024-07298-9 |
| work_keys_str_mv | AT benediktajonsson transformerssignificantlyimprovesplicesiteprediction AT gislihhalldorsson transformerssignificantlyimprovesplicesiteprediction AT steinþorardal transformerssignificantlyimprovesplicesiteprediction AT solvirognvaldsson transformerssignificantlyimprovesplicesiteprediction AT eyþoreinarsson transformerssignificantlyimprovesplicesiteprediction AT patricksulem transformerssignificantlyimprovesplicesiteprediction AT danielfguðbjartsson transformerssignificantlyimprovesplicesiteprediction AT pallmelsted transformerssignificantlyimprovesplicesiteprediction AT karistefansson transformerssignificantlyimprovesplicesiteprediction AT magnusoulfarsson transformerssignificantlyimprovesplicesiteprediction |