search

prokia / drugVQA

Predicting Drug Protein Interaction using Quasi-Visual Question Answering System
MIT License
111 stars 39 forks source link

The histogram comparison and DUDE dataset #3

Open SakuraRiven opened 4 years ago

SakuraRiven commented 4 years ago

Thanks for sharing such great work! I have some questions and would appreciate your kind help:

(1) The original metrics[1] of different methods on BIndingDB dataset are fuzzy histogram. How can we get the precise values to draw new comparison as your paper?

(2) I am confused about the DUDE dataset and can not find reference about the datasets. Could you kindly explain how to get the detailed DTI records "drug(smiles) protein(amino_acid) label(0,1)" from original dataset?

Thanks for your help!

[1] Gao, K. Y., Fokoue, A., Luo, H., Iyengar, A., Dey, S. & Zhang, P. Interpretable drug target prediction using deep neural representation. In Int. Joint Conf. on Artificial Intelligence 3371–3377 (IJCAI, 2018).

prokia commented 4 years ago

Thank you for your interest.

For the histogram, we have checked with the original authors. For the DUD-E dataset, you can find more details in http://dude.docking.org/. The active files are labeled as 1 and decoy files as 0.

SakuraRiven commented 4 years ago

Thanks for you reply. Actually, I have sent emails to original authors almost 1 month ago, but did not any response. I just wonder is it possible to share the detailed metrics? Your kind help would be cited in our future work.

Thanks again for your help!

SakuraRiven commented 4 years ago

Hi, in fact, we are planning to submit our own paper for peer review. In the experiment comparison, however, the original metrics in your paper are fuzzy histograms. So could you kindly share the detailed metric values if it is convenient?

prokia commented 4 years ago

Sorry for the late reply. Because of the COVID-19, we cannot go back to school to retrieve the final results recently. Attached is the old accuracy results. I hope that will be helpful.

SakuraRiven notifications@github.com 于2020年7月22日周三 下午3:32写道：

Hi, in fact, we are planning to submit our own paper for peer review. In the experiment comparison, however, the original metrics in your paper are fuzzy histograms. So could you kindly share the detailed metric values if it is convenient?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/prokia/drugVQA/issues/3#issuecomment-662293279, or unsubscribe https://github.com/notifications/unsubscribe-auth/AHGHEVONZZHGAXPQGWZ2LHDR42IXXANCNFSM4NCZZMVQ .

SakuraRiven commented 4 years ago

Thanks for your help~ I have received the results ~