search

aaayushg / generative_IDPs

Autoencoder based model to mine new conformations of IDPs
2 stars 4 forks source link

Quenstion about the use of distance_train_generate.py and dihedral_train_generate.py #4

Open Martialnb opened 8 months ago

Martialnb commented 8 months ago

Hello!I'm doing research with the code you uploaded, but I have question about the use of distance_train_generate.py and dihedral_train_generate.py in your code, and I noticed that README.md don't mention their use. My question is: do I need to use distance_train_generate.py and dihedral_train_generate.py for training after using autoencoder_train_generate.py and generate_new_IDPs.py to train?

Thanks!

aaayushg commented 8 months ago

Hi, thanks for trying out our code. The distance_train_generate.py and dihedral_train_generate.py are for the codes for training with distance/dihedrals instead of cartesian coordinates. There is no need to run these codes. You can replicate results in the paper by just running autoencoder_train_generate.py

Martialnb commented 8 months ago

Hi, thanks for trying out our code. The distance_train_generate.py and dihedral_train_generate.py are for the codes for training with distance/dihedrals instead of cartesian coordinates. There is no need to run these codes. You can replicate results in the paper by just running autoencoder_train_generate.py

OK，thank you so much！

Martialnb commented 8 months ago

Hi, thanks for trying out our code. The distance_train_generate.py and dihedral_train_generate.py are for the codes for training with distance/dihedrals instead of cartesian coordinates. There is no need to run these codes. You can replicate results in the paper by just running autoencoder_train_generate.py

Also, I want to know whether generate_new_IDPs.py is need to run? Thanks a lot!