Antônio Camargo

Yes, I think that's useful. Good idea. I've considered representing storing the `TaxDb` data in graphs before, but gave up on the idea to avoid adding another requirement (`networkx`). But...

Thanks for your suggestion! TaxonKit is super useful. I use it combined with `taxopy` all the time.

Hi @morriso1 Thanks for your effort! I'm very interested in a PR :)

You can filter those using the `topology` column of the summary file. If you want to process only the punitively complete genomes, you'd need to filter fragments before running geNomad....

Yes. That makes sense. RNAsamba just takes the longest CDS in the transcript. Trnadecodrr will give you good results

This could be because RNAsamba is good in identifying truncated transcripts, which might not appear if you require complete ORFs in transdecodor. Another option is that transdecodor is applying a...

Thanks, @alexweisberg! I agree with you that making geNomad able to parse the outputs of bakta/prokka would be very useful. Unfortunately, geNomad requires some information that is present in the...

Thanks for the report @amaque! You're right, this is a problem caused by using `h5py >= 3.0`. To fix this, just downgrade `h5py` to `2.10.0` or lower. I'll fix this...

RNAsamba stores all the sequences in memory to train a model. So, if your computer doesn't have enough memory, there's nothing you can do to use all the sequences for...

Hi @DOieGYuan Can you check which version of TensorFlow and Keras you have installed?