Alex

I was hoping to access a list of residue numbers, and assumed that this was what was meant to be returned in record.annotations["residues"] (although on closer look the docs only...

Exactly, yes. In general L could vary, but fixing L is a good starting point.

Thanks, my question wasn't actually about the search space construction, but about the 'distribution' parameter that is passed to optimisers. I haven't completely understood how this works in the case...

Right, so the behaviour I'd like to see is something like this: Suppose I'm at a position in the search space and I want the next candidate position to evaluate...

I had the same problem, and fixed it by adding a trailing slash to data_dir, i.e. `--data_dir data/QM9/qm9/`

Hi, I'm also interested in replicating the results on the Zhou and Troyanskaya dataset - but haven't been able to figure out either from the paper or the code (which...

This also (somewhat surprisingly) affects iterable datasets, making map very challenging to use for data with large arrays, unless there is some workaround?

Thanks! this works for me However, it raises an error if batched=False and map batch_size isn't explicitly set to 1 due to map's default batch_size affecting the batch size of...

opened a new issue for the numpy slowdown #7206

I believe these may be sequences containing stop codons, which are sometimes represented with '\*' (and is implied by these sequences having the value 'stop' in the category column). There...