CRSIPR-A-I: A webtool for the efficacy prediction of CRISPR activation and interference
Zheng, X.; Cui, J.; Wang, Y.; Zhang, J.; Wang, C.
Show abstract
AO_SCPLOWBSTRACTC_SCPLOWCRISPR-based gene activation (CRISPRa) or interference (CRISPRi) are powerful and easy-to-use approaches to modify the transcription of endogenous genes in eukaryotes. Successful CRISPRa/i requires sgRNA binding and alteration of local chromatin structure, hence largely depends on the original epigenetic status of the target. Consequently, the efficacy of the CRISPRa/i varies in a wide range when applied to target different gene loci, while a reliable prediction tool is unavailable. To address this problem, we integrated published single cell RNA-Seq data involved CRISPRa/i and epigenomic profiles from K562 cells, identified the significant epigenetic features contributing to CRISPRa/i efficacy by ranking the weight of each feature. We further established a mathematic model and built a user-friendly webtool to predict the CRISPRa/i efficacy of customer-designed sgRNA in different cells. Moreover, we experimentally validated our model by employing CROP-Seq assays. Our work provides both the epigenetic insights into CRISPRa/i and an effective tool for the users.
Matching journals
The top 10 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- A systematic evaluation of data processing and problem formulation of CRISPR off-target site prediction 94%
- DISMIR: a deep learning-based cancer-detection method by integrating DNA sequence and methylation information of individual cell-free DNA reads 93%
- Accurate Identification of Extrachromosomal Circular DNA from Long-read Sequences. 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.