kathyxchen

Thank you for posting this! This is on our roadmap and we are hoping to be able to look into it in the near future. (Unfortunately, Selene is not currently...

Thanks for posting this issue - it will be good to figure out why CPU doesn't seem to reproduce GPU in your case... what version of Selene are you using?...

Hi Ryan, Sorry for the late response! Yes I think that's an appropriate way to add it for now - do you have some working code for this already you...

Thanks so much for this PR @rfriedman22 ! Is there an example you can add to `config_examples` or just a code snippet you could leave here for us to add...

Thanks @jeffhsu3! Yes, it seems like there's a bug in `online_samplers` that should be fixed. I'll look into that - we've got a couple of PRs to resolve right now...

@jeffhsu3 I've been looking into this a bit recently and I was wondering if you could give me more information about your use case? i.e. what was the configuration file...

It might be a difference in os / shell you are using - can you try removing ``` set -o errexit set -o pipefail set -o nounset ``` in any...

You should run it using ``` sh 1_sequence_prediction.sh /home/amit/Desktop/lingo1/regions/gain.HS.TEs.bed hg19 /home/amit/Desktop/lingo1/regions/TE_predict ``` I would strongly recommend you run this on a GPU node if you have access to one though....

Hi @jianglch sorry for the late response - it should work with sequences shorter than 4096 bp, ideally you will pad the outside of these sequences with 'N's so that...

Sorry for the very late follow-up, no need to reverse DNA sequences as the model by default passes in both the input sequence and the reverse complement, and averages these...