Unlocking HDR-mediated nucleotide editing by identifying high-efficiency target sites using machine learning
Problem
Precise single-nucleotide editing via HDR is inefficient, hampering validation of genomic disease associations.
Why it matters
Efficient nucleotide editing is needed to confirm which genetic variants cause disease.
What the AI did
A machine learning model analyzed a novel mouse dataset to identify efficiency-governing factors, finding ssODN sequence composition is key, and predicted high-efficiency target sites; findings were built into the CUNE tool.
Results
Model improves HDR efficiency by 83% compared to traditionally chosen targets
Impact
The CUNE tool enables selection of higher-efficiency target sites for nucleotide editing experiments.
Record
| Venue | Scientific Reports |
|---|---|
| Published | 2019 |
| Work type | article |
| Authors | Aidan R. O’Brien, Laurence O. W. Wilson, Gaétan Burgio, Denis C. Bauer |
| Citations | 48 (OpenAlex, at import time) |
| References | 53 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41598-019-39142-0 |
| Open access | gold |
| Keywords | CRISPR, HDR, machine learning, nucleotide editing, ssODN, CUNE |
Importance rating
significant — thousands to millions affected
Validating genomic disease associations via nucleotide editing is broadly important to genetic disease research; 83% HDR efficiency gain is a real but methodological advance with no stated beneficiary scale.