Predicting CRISPR/Cas9 Repair Outcomes by Attention-Based Deep Learning Framework
As a simple and programmable nuclease-based genome editing tool, the CRISPR/Cas9 system has been widely used in target-gene repair and gene-expression regulation. The DNA mutation generated by CRISPR/Cas9-mediated double-strand breaks determines its biological and phenotypic effects. Experiments hav...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Cells |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4409/11/11/1847 |
| _version_ | 1797493682937528320 |
|---|---|
| author | Xiuqin Liu Shuya Wang Dongmei Ai |
| author_facet | Xiuqin Liu Shuya Wang Dongmei Ai |
| author_sort | Xiuqin Liu |
| collection | DOAJ |
| description | As a simple and programmable nuclease-based genome editing tool, the CRISPR/Cas9 system has been widely used in target-gene repair and gene-expression regulation. The DNA mutation generated by CRISPR/Cas9-mediated double-strand breaks determines its biological and phenotypic effects. Experiments have demonstrated that CRISPR/Cas9-generated cellular-repair outcomes depend on local sequence features. Therefore, the repair outcomes after DNA break can be predicted by sequences near the cleavage sites. However, existing prediction methods rely on manually constructed features or insufficiently detailed prediction labels. They cannot satisfy clinical-level-prediction accuracy, which limit the performance of these models to existing knowledge about CRISPR/Cas9 editing. We predict 557 repair labels of DNA, covering the vast majority of Cas9-generated mutational outcomes, and build a deep learning model called Apindel, to predict CRISPR/Cas9 editing outcomes. Apindel, automatically, trains the sequence features of DNA with the GloVe model, introduces location information through Positional Encoding (PE), and embeds the trained-word vector matrixes into a deep learning model, containing BiLSTM and the Attention mechanism. Apindel has better performance and more detailed prediction categories than the most advanced DNA-mutation-predicting models. It, also, reveals that nucleotides at different positions relative to the cleavage sites have different influences on CRISPR/Cas9 editing outcomes. |
| first_indexed | 2024-03-10T01:23:33Z |
| format | Article |
| id | doaj.art-0bc33f2a294b48e1b517a7e8c9a781b7 |
| institution | Directory Open Access Journal |
| issn | 2073-4409 |
| language | English |
| last_indexed | 2024-03-10T01:23:33Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cells |
| spelling | doaj.art-0bc33f2a294b48e1b517a7e8c9a781b72023-11-23T13:53:45ZengMDPI AGCells2073-44092022-06-011111184710.3390/cells11111847Predicting CRISPR/Cas9 Repair Outcomes by Attention-Based Deep Learning FrameworkXiuqin Liu0Shuya Wang1Dongmei Ai2School of Mathematics and Physics, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Mathematics and Physics, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Mathematics and Physics, University of Science and Technology Beijing, Beijing 100083, ChinaAs a simple and programmable nuclease-based genome editing tool, the CRISPR/Cas9 system has been widely used in target-gene repair and gene-expression regulation. The DNA mutation generated by CRISPR/Cas9-mediated double-strand breaks determines its biological and phenotypic effects. Experiments have demonstrated that CRISPR/Cas9-generated cellular-repair outcomes depend on local sequence features. Therefore, the repair outcomes after DNA break can be predicted by sequences near the cleavage sites. However, existing prediction methods rely on manually constructed features or insufficiently detailed prediction labels. They cannot satisfy clinical-level-prediction accuracy, which limit the performance of these models to existing knowledge about CRISPR/Cas9 editing. We predict 557 repair labels of DNA, covering the vast majority of Cas9-generated mutational outcomes, and build a deep learning model called Apindel, to predict CRISPR/Cas9 editing outcomes. Apindel, automatically, trains the sequence features of DNA with the GloVe model, introduces location information through Positional Encoding (PE), and embeds the trained-word vector matrixes into a deep learning model, containing BiLSTM and the Attention mechanism. Apindel has better performance and more detailed prediction categories than the most advanced DNA-mutation-predicting models. It, also, reveals that nucleotides at different positions relative to the cleavage sites have different influences on CRISPR/Cas9 editing outcomes.https://www.mdpi.com/2073-4409/11/11/1847DNA repairdeep learningpositional encodingattention mechanism |
| spellingShingle | Xiuqin Liu Shuya Wang Dongmei Ai Predicting CRISPR/Cas9 Repair Outcomes by Attention-Based Deep Learning Framework Cells DNA repair deep learning positional encoding attention mechanism |
| title | Predicting CRISPR/Cas9 Repair Outcomes by Attention-Based Deep Learning Framework |
| title_full | Predicting CRISPR/Cas9 Repair Outcomes by Attention-Based Deep Learning Framework |
| title_fullStr | Predicting CRISPR/Cas9 Repair Outcomes by Attention-Based Deep Learning Framework |
| title_full_unstemmed | Predicting CRISPR/Cas9 Repair Outcomes by Attention-Based Deep Learning Framework |
| title_short | Predicting CRISPR/Cas9 Repair Outcomes by Attention-Based Deep Learning Framework |
| title_sort | predicting crispr cas9 repair outcomes by attention based deep learning framework |
| topic | DNA repair deep learning positional encoding attention mechanism |
| url | https://www.mdpi.com/2073-4409/11/11/1847 |
| work_keys_str_mv | AT xiuqinliu predictingcrisprcas9repairoutcomesbyattentionbaseddeeplearningframework AT shuyawang predictingcrisprcas9repairoutcomesbyattentionbaseddeeplearningframework AT dongmeiai predictingcrisprcas9repairoutcomesbyattentionbaseddeeplearningframework |