Arian Jamasb

It looks like tests are failing due to metadata changes in the local AF2 pdb/mmcif files. I'll fix this up.

It looks like it was just metadata. They just changed the date in the PDB file. In the mmCIF there were more changes but coords are unaffected. I added another...

Hey @wjs20 I’m pretty certain this will be caused by altlocs/insertions ([read more](https://www.umass.edu/microbio/chime/pe_beta/pe/protexpl/badpdbs.htm)) You’ll likely have to filter them out.

> @a-r-j any changes you want me to make? Hey, sorry - busy period. A few minor comments but otherwise LGTM. Thanks for the contributions!

Hi @cimranm great suggestion! To address your immediate problem, I think you can try just passing the filenames (no extension) as the `pdb_code` arg in `ProteinGraphDataset`. The download is only...

Hi @cimranm will check this out for you on the weekend. Could you true using `filter_dataframe=True` and maybe `update_coords=True` too?

Figured it out, typo here: https://github.com/a-r-j/graphein/blob/0a2d5e39787cf002c06b03615d9dd3fe62e0171d/graphein/protein/subgraphs.py#L70 should be `"dist_mat"`, not `"distmat"`. Have pushed a fix to master.

Good spot. Seems like the start of a solution, but I think your solution breaks down with multichain proteins, no?

Yep, go ahead with a PR. Happy to review & support :) That's an interesting use case you've described. I think it would be a good addition. The plot functions...

Hi Eric, thanks for writing this up. It's super comprehensive! You definitely took better notes than I did. I'm going to start refactorising the protein graph component this week into...