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

Get the value of random forest support for each chromosome arm. #27

Open
nmc-ei opened this issue Oct 23, 2024 · 1 comment
Open

Get the value of random forest support for each chromosome arm. #27

nmc-ei opened this issue Oct 23, 2024 · 1 comment

Comments

@nmc-ei
Copy link

nmc-ei commented Oct 23, 2024

Dear Honzee,

Is it possible to get the random forest support values for each chromosome arm in txt format instead of png format?
I am analyzing many samples and it is painstaking to manually check each image one by one.

Thank you.

@honzee
Copy link
Owner

honzee commented Oct 23, 2024

Hey,

thanks for using the tool and the question.

The way the support values for the random forest predictions work is that if more then 85% of the trees agree, it is classified as high confidence and low confidence if less then 85%.

This is reflected 1. in the output figure and 2. in the output table, where the low confidence calls are marked by "?". This you can of course extract.

One of the findings we had during the development of the package was, that it is almost always useful to check the images by hand, and the goal of the confidence score is to enable easier focus on those, CNV's where the tools is not sure. That said, I understand that if you are dealing with hundreds/thousands samples, this can be very tedious.

Currently, there is no way for the user to define the threshold or extract the confidence values for each chromosome. If you were interested you can definitely submit a pull request with such an update. I would fully support you in that and we can try to figure out the best way together.

Alternatively, I can look into this myself, but this would not be immediate.

Let me know if this helps you and how I can further support you!

Best,
Jan

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