Skip to content

Question about training dataset files for reproducing DeepCRISPRon #7

Description

@linwenxin121

Hello CRISPRon team,

Thank you for making the CRISPRon code and pretrained models publicly available. I am currently trying to reproduce the DeepCRISPRon model described in your paper:

Enhancing CRISPR-Cas9 gRNA efficiency prediction by data integration and deep learning (Nature Communications, 2021).

I have downloaded the GitHub repository and the provided Luo2020_Kim2019 dataset. However, I noticed that the training script (DeepCRISPRon_train.py) requires input files such as:

validation_set1.csv 
validation_set2.csv
...
validation_set6.csv 

with columns including:

30mer_gRNA
Quant_norm_efficiency
CRISPRoff

I could not find these processed training files in the GitHub repository or the downloaded dataset package.

Could you please let me know whether these training partition files are publicly available somewhere, or if there is a recommended preprocessing pipeline to generate them from the provided datasets?

I would also appreciate any guidance regarding how the Quant_norm_efficiency values and the CRISPRoff feature were generated for the released training data.

Thank you very much for your help and for sharing this valuable resource.

Best regards,

Lin

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions