search

Shen-Lab / TALE

Transformer-based protein function Annotation with joint feature-Label Embedding
https://doi.org/10.1093/bioinformatics/btab198
MIT License
32 stars 11 forks source link

Some data files are missing for CAFA3 dataset #3

Open coolmaksat opened 2 years ago

coolmaksat commented 2 years ago

Hi, Thank you for making your code publicly available. I would like to reproduce your results on CAFA3 challenge dataset, but I cannot run the predict.py script because some files are missing there. For example, bp_go_1.pickle, mf_go_1.pickle, cc_go_1.pickle and also some _ic files. Could you please kindly provide them or explain how to generate. Thanks.

coolmaksat commented 2 years ago

If I understand correctly {on}_go_1.pickle files store the prediction terms, right? Are you using the same files for both datasets? If I use the same files I don't get very good predictions.

Shen-Lab commented 2 years ago

Thank you for your interest in our work and our code. I don't think that the pickle files under data/ours are trained models for CAFA3. And I suspect that the readme and some files were not updated to be consistent with each other and matching the published version, given that some folders were updated 4 months ago while all others and readme were not. @YueCao2017 @YueCao94 Could you please address the issues?

coolmaksat commented 2 years ago

Dear @YueCao2017, @YueCao94, Could you please help? Thank you.

nicolasfredesfranco commented 2 years ago

@Shen-Lab @YueCao2017 @YueCao94 @coolmaksat Has there been any response to this? Thanks

altriasjy31 commented 10 months ago

still missing mf_go_1, bp_go_1, and cc_go_1 pickle files for CAFA3 dataset