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

Implement scoring #62

Closed
5 tasks done
matq007 opened this issue Mar 1, 2019 · 2 comments
Closed
5 tasks done

Implement scoring #62

matq007 opened this issue Mar 1, 2019 · 2 comments
Labels
help wanted Extra attention is needed

Comments

@matq007
Copy link
Member

matq007 commented Mar 1, 2019

It would be a good idea to implement some sort of scoring function for each tool individually as each tool uses a slightly different approach for fusion detection.

  • STAR-Fusion
  • Ericscript (own score)
  • Fusioncatcher
  • Pizzly
  • Squid

Could clustering be an option here?
This issue is used for discussions and suggestions.

@matq007 matq007 added the help wanted Extra attention is needed label Mar 1, 2019
@apeltzer
Copy link
Member

apeltzer commented Mar 2, 2019

Some weighted voting system maybe? I guess all tools have pretty different benchmarking results, so could be weighted accordingly based on real-world tests...

e.g. benchmark on some datasets and then justify using the ones with highest SE and SP giving them most weight.

@matq007
Copy link
Member Author

matq007 commented Mar 15, 2019

Closing and moving the issue to a new repository where the discussion can continue: Clinical-Genomics/fusion-report#2.
I've implemented a basic scoring function, we will see what will be the feedback.

@matq007 matq007 closed this as completed Mar 15, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
help wanted Extra attention is needed
Projects
None yet
Development

No branches or pull requests

2 participants