Related Experiment Video
Updated: Feb 2, 2026
CRISPR/Cas9 Ribonucleoprotein-mediated Precise Gene Editing by Tube Electroporation
Published on: June 20, 2019
Off-target predictions in CRISPR-Cas9 gene editing using deep learning
1Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong SAR.
Motivation:
The prediction of off-target mutations in CRISPR-Cas9 is a hot topic due to its relevance to gene editing research. Existing prediction methods have been developed; however, most of them just calculated scores based on mismatches to the guide sequence in CRISPR-Cas9. Therefore, the existing prediction methods are unable to scale and improve their performance with the rapid expansion of experimental data in CRISPR-Cas9. Moreover, the existing methods still cannot satisfy enough precision in off-target predictions for gene editing at the clinical level.
Results:
To address it, we design and implement two algorithms using deep neural networks to predict off-target mutations in CRISPR-Cas9 gene editing (i.e. deep convolutional neural network and deep feedforward neural network). The models were trained and tested on the recently released off-target dataset, CRISPOR dataset, for performance benchmark. Another off-target dataset identified by GUIDE-seq was adopted for additional evaluation. We demonstrate that convolutional neural network achieves the best performance on CRISPOR dataset, yielding an average classification area under the ROC curve (AUC) of 97.2% under stratified 5-fold cross-validation. Interestingly, the deep feedforward neural network can also be competitive at the average AUC of 97.0% under the same setting. We compare the two deep neural network models with the state-of-the-art off-target prediction methods (i.e. CFD, MIT, CROP-IT, and CCTop) and three traditional machine learning models (i.e. random forest, gradient boosting trees, and logistic regression) on both datasets in terms of AUC values, demonstrating the competitive edges of the proposed algorithms. Additional analyses are conducted to investigate the underlying reasons from different perspectives.
Availability And Implementation:
The example code are available at https://github.com/MichaelLinn/off_target_prediction. The related datasets are available at https://github.com/MichaelLinn/off_target_prediction/tree/master/data.
Insights
New deep learning models accurately predict CRISPR-Cas9 gene editing off-target mutations. These advanced algorithms offer improved precision for clinical gene editing applications.
Area of Science:
- Genomics
- Bioinformatics
- Molecular Biology
Background:
- CRISPR-Cas9 gene editing requires accurate prediction of off-target mutations for safety and efficacy.
- Existing prediction methods based on sequence mismatches have limitations in scalability and precision for clinical applications.
Purpose of the Study:
- To develop and evaluate deep neural network algorithms for predicting CRISPR-Cas9 off-target mutations.
- To compare the performance of deep learning models against existing methods and traditional machine learning approaches.
Main Methods:
- Implementation of two deep neural network models: deep convolutional neural network (CNN) and deep feedforward neural network (FFNN).
- Training and testing on the CRISPOR dataset and additional evaluation using the GUIDE-seq dataset.
- Comparison of AUC values with state-of-the-art methods (CFD, MIT, CROP-IT, CCTop) and traditional ML models.
Main Results:
- Deep CNN achieved the highest performance with an average AUC of 97.2% on the CRISPOR dataset.
- Deep FFNN demonstrated competitive performance with an average AUC of 97.0% under similar conditions.
- Both deep learning models showed superior performance compared to existing prediction methods and traditional machine learning models.
Conclusions:
- Deep neural networks, particularly CNNs, offer a significant advancement in predicting CRISPR-Cas9 off-target mutations.
- The developed algorithms provide enhanced precision necessary for safe and effective clinical gene editing.
- The study provides open-source code and datasets for further research and development.
Related Concept Videos
01:28CRISPR/Cas9 Genome Editing
01:59CRISPR
02:53CRISPR and crRNAs
The CRISPR-Cas system stores a copy of foreign DNA in the host genome and uses it to identify the foreign DNA upon reinfection. CRISPR-Cas has three different...
02:23RNA Editing
02:27Predicting Molecular Geometry
01:03Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.