Skip to content
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

Identify novel events with respect to annotation #138

Closed
pablommesas opened this issue Sep 14, 2021 · 3 comments
Closed

Identify novel events with respect to annotation #138

pablommesas opened this issue Sep 14, 2021 · 3 comments

Comments

@pablommesas
Copy link

  • spladder version: v2.4.4
  • Python version: 3.7.3
  • Operating System: Scientific Linux 7.9 (Nitrogen)

Description

Hi Andre,
I recently started using SplAdder.
I was wondering if there is any straightforward way provided by SplAdder to classify as_events into either:

  • Annotated events: present in the annotation (e.g. gtf)
  • Novel events: introduced during the graph augmentation step

Thanks in advance!

@akahles
Copy link
Member

akahles commented Sep 21, 2021

Dear @pablommesas ,

This is on my to-do list since quite a while and it is my plan to make the feature available with the next major release. I will leave this issue open and post here, once this has happened.

Best,

Andre

@akahles
Copy link
Member

akahles commented Jan 5, 2022

Dear @pablommesas ,

This functionality has been added with the latest release. Feedback is welcome. I am closing this for now. Please re-open, if there is an issue.

Best,

Andre

@akahles akahles closed this as completed Jan 5, 2022
@pablommesas
Copy link
Author

Dear Andre,

Thank you for this! I have tested the novel functionality, I think there might be something wrong with the implementation.
Overall there seems to be an exaggerated number of novel events, in my samples I found that ~80% of events were classified as novel.
For 'alt_3prime' events 100% of events were classified as novel which can't be.

Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants