Modeling CRISPR-Cas13d on-target and off-target effects using machine learning approaches
Problem
Accurately predicting the on-target efficiency and off-target effects of guide RNAs in the CRISPR-Cas13d RNA editing system.
Why it matters
Reliable guide prediction is needed to make RNA-targeting CRISPR therapies safe and effective.
What the AI did
A deep learning model (DeepCas13) was trained on proliferation-screen data to predict gRNA on-target activity from sequence and secondary structure, and off-target viability effects were systematically modeled.
Results
Outperforms existing methods and predicts efficiency for protein-coding and non-coding RNAs; no numeric accuracy metrics stated in abstract
Impact
Cited 70 times; provides a predictive model for Cas13d guide design, per abstract.
Record
| Venue | Nature Communications |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Xiaolong Cheng, Zexu Li, Ruocheng Shan, Zihan Li, Shengnan Wang, Wenchang Zhao, Han Zhang, Lumen Chao et al. |
| Citations | 70 (OpenAlex, at import time) |
| References | 64 |
| Model or method | DeepCas13 |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41467-023-36316-3 |
| Open access | gold |
| Keywords | CRISPR-Cas13d, deep learning, gRNA design, off-target effects, RNA editing |
Importance rating
significant — thousands to millions affected
Guide prediction is called a major challenge for CRISPR-Cas13d RNA editing; enables safer RNA-targeting CRISPR use, but no disease or population scale stated.