A Novel Hybrid CNN-SVR for CRISPR/Cas9 Guide RNA Activity Prediction
Problem
Accurately predicting CRISPR/Cas9 guide RNA on-target efficacy is critical for effective genome editing, but existing methods need improvement.
Why it matters
Poor gRNA efficacy prediction limits reliable application of CRISPR/Cas9 editing.
What the AI did
A hybrid system combined merged convolutional neural networks for gRNA feature extraction with support vector regression to predict cleavage efficiency, using a two-step feature optimization strategy.
Results
not stated in source
Impact
Proposed system aims to improve gRNA activity prediction; external validation not stated in source.
Record
| Venue | Frontiers in Genetics |
|---|---|
| Published | 2020 |
| Work type | article |
| Authors | Guishan Zhang, Zhiming Dai, Xianhua Dai |
| Citations | 49 (OpenAlex, at import time) |
| References | 65 |
| Model or method | hybrid CNN-SVR (merged CNNs + support vector regression) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3389/fgene.2019.01303 |
| Open access | gold |
| Keywords | CRISPR/Cas9, guide RNA, CNN, support vector regression, on-target efficacy, prediction |
Importance rating
significant — thousands to millions affected
gRNA efficacy prediction is critical for effective CRISPR/Cas9 application per abstract; genome editing is a foundational, widely used capability, but no scale stated.