MGXlab / DNNGIOR

Scripts to build high-quality genome-scale metabolic model by using a deep neural network to guide gapfilling
MIT License
10 stars 3 forks source link

stoichiometry bug? #25

Open hariszaf opened 2 weeks ago

hariszaf commented 2 weeks ago

Hey @Biomerene , is there a chance in line 106 you wanted it to return the empyt list rxn_cpds_array of line 103? As is now, it fails.

https://github.com/MGXlab/DNNGIOR/blame/c2464362cce0f08230f22aa729224d5f5a692fe2/dnngior/MSEED_reactions.py#L106

you may have a look in this test too: https://github.com/MGXlab/DNNGIOR/actions/runs/11086814215/job/30804806478

Biomerene commented 2 weeks ago

This is not my code, but I think the problem is line 135, which should probably read return rxn_cpds_dict returning the empty dictionary if the stochiometry string is empty.

https://github.com/MGXlab/DNNGIOR/blame/c2464362cce0f08230f22aa729224d5f5a692fe2/dnngior/MSEED_reactions.py#L135

hariszaf commented 2 weeks ago

That's what I assumed too. @danielriosgarza it that correct? may I fix that as suggested?