search

GoekeLab / m6anet

Detection of m6A from direct RNA-Seq data
https://m6anet.readthedocs.io/
MIT License
104 stars 19 forks source link

Question about Fig1d in the paper #99

Closed thadasps closed 1 year ago

thadasps commented 1 year ago

Hi, I was wondering about the 5 model of epinano that you use to generate the ROC curve. Can you explain the different of Epinano1, 2, 3?.

And I try to generate the ROC curve that I download the m6a sites dataset of m6ACE-seq that provided by xPore but I don't know I must use the start or end position to compare with m6A sites from m6Anet. Can you help or point me about this?

image

chrishendra93 commented 1 year ago

hi @thadasps , These are just different models that EpiNano provide in their earlier version. For generating ROC curve, you should use the end position, but take care that you map the genomic position correctly (the reference annotations I have mentioned in issue #96 and you map the chromosome to the ucsc one (If I'm not mistaken the m6Ace chromosome uses ucsc annotation)