Trained models and training DeepMod

[pepebonet]

Hi! :) Nice method!

I would like to test DeepMod on the ecoli data set from Simpson et al.
I was wondering which one of the trained models you have in the repo would allow me to recover the results presented in the paper.
Would it be either rnn_sinmodC_P100wd21_f7ne1u0_4 or rnn_conmodC_P100wd21_f7ne1u0_4?
Could you highlight the difference between them?

Alternatively, could you give some guidance on how to train DeepMod on any data set.

Thank you in advance,

Pepe

[liuqianhn]

@pepebonet Thank you for being interested in DeepMod. The difference between the two trained models are described below:

rnn_sinmodC_P100wd21_f7ne1u0_4: the model is trained on the two datasets published by Simpson et al. for 5mC prediction
rnn_conmodC_P100wd21_f7ne1u0_4: the model is trained on Simpson's data and also NanoRaw's data for 5mC prediction.

Regarding how to train a new DeepMod model, you need to generate the features and then call the training process. This is not a straightforward process. If possible, we have collaboration projects to help you to train the new model.

[pepebonet]

@liuqianhn Thank you for the information on the different pretrained models.

Hopefully, it will be straightforward to train it for everybody at some point.

Cheers,

Pepe