JiaruiFeng / TAGLAS

An atlas of text-attributed graph datasets in the era of large graph and language model.
MIT License
15 stars 3 forks source link

code #10

Open ALLISWELL8 opened 2 weeks ago

ALLISWELL8 commented 2 weeks ago

Hello, how can I obtain text information for nodes such as BBBP and Bace datasets

JiaruiFeng commented 2 weeks ago

Hi,

There is a bug in getting data samples for molecule datasets. We just fix it. Would you mind updating your version and using the following code to obtain text information for nodes in the molecule dataset:

bbbp = get_dataset("bbbp")
# node text
bbbp[0].x
# edge text
bbbp[0].edge_attr

Sorry for the inconvenience and please let me know if you still face any issues.

Best.

ALLISWELL8 commented 1 week ago

Thank you very much for your reply. I have another question, which is that when I obtained a dataset of Bace or other chemical types, I checked all the contents of the dataset and couldn't find the corresponding smiles format for the chemical molecules. Can you provide this? Thank you,

JiaruiFeng commented 6 days ago

Sorry for the late reply. Currently, we don't provide smiles for molecule datasets. We will add it in the near future. Here I provide pointers to where we convert smiles to graph format: for molproperties, for other datasets.

Hope this could help!

Best.