About the training dataset

[JappyPing]

Hi,

Thanks for your excellent work.

I am interested in how to generate training and testing datasets. From the description (see below, copied from the paper), I didn't find the approaches for dataset generation from the sequencing read sets. Could you please tell me where I can find the steps to generate the datasets or give me brief instructions here?

These high-throughput experiments resulted in four independent data sets of ABE- and CBE-directed target conversion efficiencies and edited sequence outcomes at integrated sequences: HT_ABE_Train, HT_ABE_Test, HT_CBE_Train and HT_CBE_Test (Supplementary Tables 1 and 2). We also generated data sets, named Endo_ABE_HEK293T and Endo_CBE_HEK293T (Supplementary Tables 1 and 3).

Thanks so much for your help.

Best,

Jappy