Yunhee Jeong

Hello @guanghaoli, thank you very much for your interest and sorry for my late reply. I am not working at DKFZ anymore, so it was a bit hard to find...

Hello @guanghaoli Glad to hear that my suggestion slightly improved your situation. How many steps did you use for training? I have a feeling that the entire training process may...

Hello @guanghaoli Glad to hear that you got better results! :) Please feel free to reach out to me by opening an issue when you have any further questions/problems. Kind...

Hello @Yijun-Tian Thank you very much for your interest in MethylBERT. It seems like there's only one sequence read found overlapping with given DMRs in your BAM file. This is...

Hello, @Yijun-Tian. MethylBERT does not have any further filtering steps in the algorithm. However, it does select only reads fully-overlapping with DMRs. Therefore, there's a possibility that the length of...

Dear @LiJingqi7 Thank you for your interest in MethylBERT. Although it's written as optional in the tutorial, in your case, you need pure tumour and normal samples for fine-tuning. It'd...

Hello @LiJingqi7 Sorry for my late reply. This sounds weird to me. Can you share more information about your fine-tuned model?: - train, valid accuracy - approximated number of reads...