Looking forward for your help and Question

[LLMforScience]

Hi Shengchao,

Thank you very much for your great work!

In your paper, you mentioned that "Yet, after confirming with the authors, certain mismatches exist between the 2D topologies and 3D conformations in Molecule3D."

Could you please explain this more? Do you mean that 2D topologies and 3D conformations can not match for every sample in Molecule3D?

Since I am using Molecule3D, I am really looking forward for your help!

Best,

[chao1224]

Hi @AGTSAAA,

Thank you for your question.

Your understanding is correct, that few of the molecular graphs are not correct in Molecule3D, while PCQM4Mv2 does not have this issue.

[LLMforScience]

Thank you for your reply! Do you rember how many molecular graphs (precentage) are not correct in Molecule3D?

[chao1224]

I don't remember the exact details. Maybe you can ask the authors of Molecule3D.