Back to Search
Start Over
Predicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target library screens
- Source :
- Nature Communications, Vol 12, Iss 1, Pp 1-9 (2021), Nature Communications, Nature Communications, 12 (1)
- Publication Year :
- 2021
- Publisher :
- Nature Portfolio, 2021.
-
Abstract
- Base editors are chimeric ribonucleoprotein complexes consisting of a DNA-targeting CRISPR-Cas module and a single-stranded DNA deaminase. They enable transition of C•G into T•A base pairs and vice versa on genomic DNA. While base editors have great potential as genome editing tools for basic research and gene therapy, their application has been hampered by a broad variation in editing efficiencies on different genomic loci. Here we perform an extensive analysis of adenine- and cytosine base editors on a library of 28,294 lentivirally integrated genetic sequences and establish BE-DICT, an attention-based deep learning algorithm capable of predicting base editing outcomes with high accuracy. BE-DICT is a versatile tool that in principle can be trained on any novel base editor variant, facilitating the application of base editing for research and therapy.<br />Nature Communications, 12 (1)<br />ISSN:2041-1723
- Subjects :
- CRISPR-Cas9 genome editing
Computer science
Base pair
Science
10050 Institute of Pharmacology and Toxicology
General Physics and Astronomy
610 Medicine & health
1600 General Chemistry
Genomics
Article
General Biochemistry, Genetics and Molecular Biology
Deep Learning
Genome editing
1300 General Biochemistry, Genetics and Molecular Biology
Basic research
Machine learning
Humans
Data mining
Base Pairing
Throughput (business)
Gene Library
Gene Editing
Genome
Multidisciplinary
business.industry
Deep learning
High-Throughput Nucleotide Sequencing
General Chemistry
Base (topology)
3100 General Physics and Astronomy
genomic DNA
570 Life sciences
biology
Artificial intelligence
business
11493 Department of Quantitative Biomedicine
Algorithm
Algorithms
Subjects
Details
- Language :
- English
- ISSN :
- 20411723
- Volume :
- 12
- Issue :
- 1
- Database :
- OpenAIRE
- Journal :
- Nature Communications
- Accession number :
- edsair.doi.dedup.....95aa804166a272f8f2463b99035f04b9