Vizfold Foundations

This repository has two main components:

Model inference & feature extraction: Run protein structure prediction models and extract intermediate activations (hidden representations) and attention maps from any chosen layer.
Visualization & analysis: Explore, visualize, and analyze the extracted activations and attention maps.

Link to Openfold implimentation - README_vizfold_openfold.md

License

This project is licensed under the Apache License 2.0.
See the LICENSE file for details.

Name		Name	Last commit message	Last commit date
Latest commit History 76 Commits
.github		.github
archive		archive
docs		docs
examples/monomer		examples/monomer
experiments		experiments
imgs		imgs
notebooks		notebooks
openfold		openfold
outputs/attention_images_6KWC_demo_tri_18		outputs/attention_images_6KWC_demo_tri_18
scripts		scripts
tests		tests
.gitignore		.gitignore
.readthedocs.yaml		.readthedocs.yaml
CITATION.cff		CITATION.cff
Dockerfile		Dockerfile
LICENSE		LICENSE
NOTICE		NOTICE
README.md		README.md
README_original.md		README_original.md
README_vizfold_openfold.md		README_vizfold_openfold.md
cybershuttle.yml		cybershuttle.yml
deepspeed_config.json		deepspeed_config.json
environment.yml		environment.yml
run_pretrained_openfold.py		run_pretrained_openfold.py
setup.py		setup.py
thread_sequence.py		thread_sequence.py
train_openfold.py		train_openfold.py
visualize_attention_3d_demo_utils.py		visualize_attention_3d_demo_utils.py
visualize_attention_arc_diagram_demo_utils.py		visualize_attention_arc_diagram_demo_utils.py
visualize_attention_general_utils.py		visualize_attention_general_utils.py
viz_attention_demo.ipynb		viz_attention_demo.ipynb
viz_attention_demo_base.ipynb		viz_attention_demo_base.ipynb