You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
The text was updated successfully, but these errors were encountered:
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!
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.
The text was updated successfully, but these errors were encountered: