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

Rank-Scoring for predictions #192

Open
b-schubert opened this issue Apr 28, 2017 · 3 comments
Open

Rank-Scoring for predictions #192

b-schubert opened this issue Apr 28, 2017 · 3 comments

Comments

@b-schubert
Copy link
Contributor

Transformation of prediction score to its rank based on empirically approximated scoring distribution using random peptides of natural proteins

@b-schubert b-schubert added this to the Release 2.0 milestone Apr 28, 2017
@monikasekelja
Copy link

Hi,

Thank you for the great software! Regarding the rank values - is there a simple way of changing the code to obtain the rank values in stead of affinity scores from NetMHCpan and NetMHCIIpan? I see that both programs write the rank values in the output result file...

@b-schubert
Copy link
Contributor Author

Hi @monikasekelja

Thanks!

Regarding the rank scores:

Each of the external prediction methods under Fred2.EpitopePrediction.External implement a method called parse_external_resultwhich reads usually the excel output of NetMHC. It should be fairly simple to adjust the code so that it returns the rank scores by just shifting the hard coded index of the IC50-values to the rank-scores.

If you need help, let me know.

@monikasekelja
Copy link

I changed the ic_pos to 6 and it worked! Thanks!

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

No branches or pull requests

2 participants