Question about training models for other motifs in Arabidopsis thaliana

[maxdayu]

Dear m6Anet developers,

Thank you for your great work on m6Anet. I'm trying to train models for other motifs. In the training procedure, the dataprep step selects eight transcripts for training, validation, and testing. In my dataset, however, dataprep only finds a single transcript. How should I label/split it in this case? Is it appropriate to assign it to the training set, or is there a recommended way to handle a single-transcript scenario?

This is the training method.

Here is my data.

Thank you very much in advance for your time and support!

Best regards

[yuukiiwa]

Hi @maxdayu,

m6anet only supports training for multiple transcript entries, so you will have to rename your transcript seq_1240 into different transcript_ids in your eventalign file to split them (e.g. seq_1240_1...seq_1240_n).

Thanks!

Best wishes,
Yuk Kei