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

Prevent spliced in-frame stop codons and allow spliced start codons #7

Open
3 tasks
MarioStanke opened this issue Oct 14, 2024 · 0 comments
Open
3 tasks

Comments

@MarioStanke
Copy link
Contributor

MarioStanke commented Oct 14, 2024

  • Extend the (n=15 states) architecture to allow the prevention of spliced stop codons.
    • Ask Mario to for a solution architecture from an exam question on genome analysis.
    • Share the parameters for the embedding emissions, so that no new parameters need to be learned and a choice between the two architectures can be made at inference time.
  • Extend the architecture for spliced start codons, Agt ... ag GT or ATgt... ag G. This probably can be used with benefit only after RNA-Seq integration has been implemented.
  • A simpler and faster model is chosen at first during inference. If spliced stop codons occur. The region or tile can be reannotated with the slower model that enforces structures without spliced stop codons.
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

1 participant