Michael Hall

If you are wanting to do the same type of filtering as with Albacore + Porechop (i.e only keep reads where both programs agree) you will have to run deepbinner...

Looking at the code, it needs to be a single file. Being able to point at multiple reads files would be super handy though. This would save having to concatenate...

I am also seeing a similar issue trying to build an index for the lastest human reference ``` > graphmap align -I -t 12 -r GRCh38_full_analysis_set_plus_decoy_hla.fa [07:23:42 BuildIndexes] Loading reference...

If like me, you stumble upon this issue for unit test purposes, [mocking](https://docs.python.org/3/library/unittest.mock.html#unittest.mock.patch) the `Variant` is a good way to do this. ```py from unittest.mock import patch from cyvcf2 import...

I am having the same issue. The workaround of dropping the `.gz` extension is a hack and it would be nice if the library seamlessly supported `.bcf.gz`

Hmmm it seems that the link to the bitbucket repo doesn't work now.... To try and summarise the proposed options for how this would be implemented: a) Have nested directives...

Some questions about your proposal: - the `image` function would need to be implemented correct? I assume it will return some kind of `Image` data structure to hold all of...

That seems to have fixed it 👍

I have seen a similar issue when using a bonito-trained model with guppy. I lose a HUGE amount of reads to the dreaded "unclassified" bin. Have you managed to find...

I'm getting multi-GPU training failure also (v0.4.0 cuda 11.1), with the following error message ``` [loading data] [validation set not found: splitting training set] [loading model] Traceback (most recent call...