Predicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target library screens
Base editors enable precise genetic alterations but vary in efficiency at different loci. Here the authors analyse ABEs and CBEs at over 28,000 integrated sequences to train BE-DICT, a machine learning model capable of predicting base editing outcomes.
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-08-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-021-25375-z |
id |
doaj-c9632ae8e3554eb0a6f6c3e3694e3ef8 |
---|---|
record_format |
Article |
spelling |
doaj-c9632ae8e3554eb0a6f6c3e3694e3ef82021-08-29T11:38:19ZengNature Publishing GroupNature Communications2041-17232021-08-011211910.1038/s41467-021-25375-zPredicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target library screensKim F. Marquart0Ahmed Allam1Sharan Janjuha2Anna Sintsova3Lukas Villiger4Nina Frey5Michael Krauthammer6Gerald Schwank7Institute of Molecular Health Sciences, ETH ZurichDepartment of Quantitative Biomedicine, University of ZurichDepartment of Pharmacology and Toxicology, University of ZurichDepartment of Quantitative Biomedicine, University of ZurichDepartment of Pharmacology and Toxicology, University of ZurichInstitute of Molecular Health Sciences, ETH ZurichDepartment of Quantitative Biomedicine, University of ZurichDepartment of Pharmacology and Toxicology, University of ZurichBase editors enable precise genetic alterations but vary in efficiency at different loci. Here the authors analyse ABEs and CBEs at over 28,000 integrated sequences to train BE-DICT, a machine learning model capable of predicting base editing outcomes.https://doi.org/10.1038/s41467-021-25375-z |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Kim F. Marquart Ahmed Allam Sharan Janjuha Anna Sintsova Lukas Villiger Nina Frey Michael Krauthammer Gerald Schwank |
spellingShingle |
Kim F. Marquart Ahmed Allam Sharan Janjuha Anna Sintsova Lukas Villiger Nina Frey Michael Krauthammer Gerald Schwank Predicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target library screens Nature Communications |
author_facet |
Kim F. Marquart Ahmed Allam Sharan Janjuha Anna Sintsova Lukas Villiger Nina Frey Michael Krauthammer Gerald Schwank |
author_sort |
Kim F. Marquart |
title |
Predicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target library screens |
title_short |
Predicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target library screens |
title_full |
Predicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target library screens |
title_fullStr |
Predicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target library screens |
title_full_unstemmed |
Predicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target library screens |
title_sort |
predicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target library screens |
publisher |
Nature Publishing Group |
series |
Nature Communications |
issn |
2041-1723 |
publishDate |
2021-08-01 |
description |
Base editors enable precise genetic alterations but vary in efficiency at different loci. Here the authors analyse ABEs and CBEs at over 28,000 integrated sequences to train BE-DICT, a machine learning model capable of predicting base editing outcomes. |
url |
https://doi.org/10.1038/s41467-021-25375-z |
work_keys_str_mv |
AT kimfmarquart predictingbaseeditingoutcomeswithanattentionbaseddeeplearningalgorithmtrainedonhighthroughputtargetlibraryscreens AT ahmedallam predictingbaseeditingoutcomeswithanattentionbaseddeeplearningalgorithmtrainedonhighthroughputtargetlibraryscreens AT sharanjanjuha predictingbaseeditingoutcomeswithanattentionbaseddeeplearningalgorithmtrainedonhighthroughputtargetlibraryscreens AT annasintsova predictingbaseeditingoutcomeswithanattentionbaseddeeplearningalgorithmtrainedonhighthroughputtargetlibraryscreens AT lukasvilliger predictingbaseeditingoutcomeswithanattentionbaseddeeplearningalgorithmtrainedonhighthroughputtargetlibraryscreens AT ninafrey predictingbaseeditingoutcomeswithanattentionbaseddeeplearningalgorithmtrainedonhighthroughputtargetlibraryscreens AT michaelkrauthammer predictingbaseeditingoutcomeswithanattentionbaseddeeplearningalgorithmtrainedonhighthroughputtargetlibraryscreens AT geraldschwank predictingbaseeditingoutcomeswithanattentionbaseddeeplearningalgorithmtrainedonhighthroughputtargetlibraryscreens |
_version_ |
1721186631066583040 |