-
Notifications
You must be signed in to change notification settings - Fork 1
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
Unable to establish baseline #2
Comments
Hi, The minimum number of MSI and MSS samples required for model creation is 10: 10 MSI and 10 MSS. You can change this minimum value with the argument For a real dataset, you are encouraged to have more samples to train your model. For the test dataset it is necessary to set this value to 1 because it contains only 2 samples (you can see an example of command line for this dataset on line 41 in This value can also be reduced when you try you first models for your panel. Kind regards |
Hi, The link between your samples names in the BED file and the fastq is retrieved by searching the name from the BED in the fastq basename. In your case, "ILMN01_MSS" does not match with the file "ILMN01.end1.fq.gz". It is necessary to remove "_MSS" from your sample name in the BED file. I cannot provide you a baseline and model file because they depend on your amplicons design. The learning step records amplicons coordinates (from BED) and size distribution (from your reads) for each status. Kind regards |
Hi, Could you provide me the result of the following command: Have a nice day. |
Hi,
I used your test case, the program reported the following error "unsufficient number of samples in model:MSINR21_MSS: 1 samples, MSINR21_MSI: 0 samples"
I am wondering how to establish a baseline? How many samples are needed to establish a baseline? Or can you provide an established baseline for us to use?
Thanks
The text was updated successfully, but these errors were encountered: