Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Appropriate model_config arguments for initial training upon predicting with long sequence #17

Open
eunos-1128 opened this issue Apr 1, 2024 · 2 comments

Comments

@eunos-1128
Copy link
Contributor

eunos-1128 commented Apr 1, 2024

Hi,

I have some long sequences that can't be predicted using alphaflow default settings.

To deal with long ones I changed arguments to predict as below.

config = model_config(
    'initial_training',
    train=False, 
    low_prec=False
    long_sequence_inference=True
) 

For long sequence prediction initial training is not needed? I'm afraid it results in decrease in precision. I want conformer ensembles with wide ranges of conformations and high precision.

There seems no description about the best practice or settings to predict proteins with long sequences.

@jyaacoub
Copy link
Contributor

jyaacoub commented Apr 4, 2024

I think they set "inital_training" just for config sake since no training should be occurring if we are just making predictions and loading up pre-trained weights.

From the config.py script we can see that it just keeps the default args set by the config dict:

if name == "initial_training":

I see where the confusion comes from though since train is set to true in the predict.py file, I am not sure why this is.

train=True,

@eunos-1128
Copy link
Contributor Author

@jyaacoub

Thank you for your comment. As you say, training usually doesn't happen but I just harbored a thought of that possibility.

After reading code I noticed that thought is not correct.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants