Chuai et al. |

DeepCRISPR: sgRNA Efficacy

8
12
Omics
    More
Step 1: Upload your data

Upload Source Molecules

Drag your file(s) or upload
  • Your file can be in the following formats:csv
  • This app allows for sequence-only prediction or full-featured prediction. Data for full featured prediction contains epigenetic features and is structured as follows where A represents 1 meaning a signal located and N represents 0 meaning no signal: +------------+------+-------+---------+------+ | target_seq | ctcf | dnase | h3k4me3 | rrbs | +------------+------+-------+---------+------+ | CTT… | AAA… | AAA… | AAA… | NNN… | +------------+------+-------+---------+------+ You must have the exact column headings as above for the app to work. However, they can be in any order. Data for sequence only predictions only requires the “target_seq” column. Note, sequence-only prediction is only available for regression.
or
Don’t have a file?
Use our demo data to run
Use Demo Data
View example data
Step 2: Set Parameters
Both
Step 3: Complete run profile

An efficient and extendable computational model for prediction of CRISPR sgRNA on-target knockout efficacy, facilitating optimized sgRNA with high sensitivity and specificity

Example use case: Epigenetics research

Limitations: Focuses on conventional NGG-based sgRNA design for SpCas9 in humans

Technology: Convolutional neural network-based deep learning network, trained on ~15,000 sgRNAs containing 1071 genes from
four different cell lines (hct116, hek293t, hela, and hl60) with redundancy removed and can generalise well in new cell types for
sgRNA on-target knockout efficacy prediction

Metrics: As reported by Chuai et al.  

Citation:
Chuai, G., Ma, H., Yan, J. et al. DeepCRISPR: optimized CRISPR guide RNA design by deep learning. Genome Biol 19, 80 (2018). https://doi.org/10.1186/s13059-018-1459-4
Released:
Sep-14-2022
Previous Job Parameters
Your previous job parameters will show up here
so you can keep track of your jobs
Results
Parameters