-
Notifications
You must be signed in to change notification settings - Fork 2
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Training data from HG002, HG003 and HG004 #26
Comments
Hi, please see the following code for reproducing the training CpG labels: Process individual datasets for each genome:
Get common sites among six technologies and split into training, testing and validation
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi,
Thanks for the impressive work of DeepMod2. I am trying to generate the training/valid/test data following your criteria as described in your paper, but I can not get the same number as in Supplementary Table 4. Take HG002 for instance, I downloaded 12 files by LAB01 of the six WGBS methods (TrueSeq, MethylSeq, SPLAT, TrueMethIBS, TrueMethyIOX, and EMSeq) from EpiQC.
GSM5649436_TruSeq_HG002_LAB01_REP02.bedGraph.gz GSM5649437_TruSeq_HG002_LAB01_REP01.bedGraph.gz GSM5649458_SPLAT_HG002_LAB01_REP02.bedGraph.gz GSM5649459_SPLAT_HG002_LAB01_REP01.bedGraph.gz GSM5649479_MethylSeq_HG002_LAB01_REP02.bedGraph.gz GSM5649480_MethylSeq_HG002_LAB01_REP01.bedGraph.gz GSM5649518_EMSeq_HG002_LAB01_REP02.bedGraph.gz GSM5649520_EMSeq_HG002_LAB01_REP01.bedGraph.gz GSM5649543_TrueMethylOX_HG002_LAB01_REP02.bedGraph.gz GSM5649545_TrueMethylOX_HG002_LAB01_REP01.bedGraph.gz GSM5649565_TrueMethylBS_HG002_LAB01_REP02.bedGraph.gz GSM5649567_TrueMethylBS_HG002_LAB01_REP01.bedGraph.gz
I processed these files following the description in your paper:
Our Train: meth 4,212,407, unmeth: 2,169,575
Your Paper Train: meth 5,332,746, unmeth: 2,490,174
Our Valid: meth 134,316, unmeth: 58,293
Your Paper Valid: meth 179,954, unmeth: 65,730
Could you help me to reproduce the training data split as in Supplmentary Table 4 with more detailed information or kindly sharing your script to generate the data?
Thank you very much!
The text was updated successfully, but these errors were encountered: