Contemporary ProFOLD
PFOLD adopts the neural network architecture of AlphaFold2 with some local adjustments:
- The input consists only of amino acid or nucleic acid sequences, without MSA (Multiple Sequence Alignment) and templates.
- An Evolutionary Module has been added to recover MSA using the Potts model.
Diffusion (EDM) as a Structure Module
AlphaFold3 uses EDM as a structural module to unify biomolecular structure modeling.
Train ProFOLD with EDM
A clear and concise description of any alternative solutions or features you've considered.
Additional context
Add any other context or screenshots about the feature request here.
Contemporary ProFOLD
PFOLD adopts the neural network architecture of AlphaFold2 with some local adjustments:
Diffusion (EDM) as a Structure Module
AlphaFold3 uses EDM as a structural module to unify biomolecular structure modeling.
Train ProFOLD with EDM
A clear and concise description of any alternative solutions or features you've considered.
Additional context
Add any other context or screenshots about the feature request here.