amorehead alphafold3-pytorch-lightning-hydra issues

amorehead / alphafold3-pytorch-lightning-hydra

Implementation of AlphaFold 3 in PyTorch Lightning + Hydra

MIT License

19 stars 6 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Add templates and ligand frames for confidence head outputs

#10 amorehead closed 1 week ago
0
initial commit msa loading

#9 sj900 closed 2 weeks ago
5
initial commit load msa

#8 sj900 closed 3 weeks ago
0
WeightedPDBSampler Integration

#7 sj900 closed 1 month ago
0
Weightedpdbsampler integration

#6 sj900 closed 1 month ago
0
Add the new `test_pdbinput_input` unit test

#5 amorehead closed 1 month ago
0
Force mmseqs2 database types, so nucl seq are not mistaken as proteins, disable peptide e-value

#4 milot-mirdita closed 1 month ago
0
Draft: Optimized MMseqs2 parameters

#3 milot-mirdita closed 1 month ago
0
Fix author chain ID-author residue ID issue causing `parse()`d `Biomolecules` to have missing residues (e.g., residues `1-10`) filled in (e.g., within chain `B` of `100d.cif`) by dummy residues upon exporting an mmCIF file from a `Biomolecule` object. This specifically happens because sometimes authors of mmCIF files specify that residue indices should be monotonically increasing from the first chain to the last chain (e.g., residue indices 1-10 in chain A and residue indices 11-20 in chain B), and when this happens the standard AlphaFold 2-borrowed logic we have in place currently will treat residues 1-10 in chain B as "missing" and will add padding residues consequently. This will break future re-parsing of these (filtered) mmCIF files since the residue sequences e.g., in chain B will be incorrect from then on.

#2 amorehead closed 2 months ago
0
TODOs

#1 amorehead opened 2 months ago
3