lucidrains / alphafold2

To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released
MIT License
1.57k stars 258 forks source link

pairwise_repr should be used in rowAttention #89

Closed CiaoHe closed 3 years ago

CiaoHe commented 3 years ago

Hi, Phil

https://github.com/lucidrains/alphafold2/blob/a78352805204d47851f3b972e3d5c142ec7a3b49/alphafold2_pytorch/alphafold2.py#L400-L401

according to the original paper, (Algorithm 6, line2-4), the pairwise_repr(bias) used in MSARowAttentionWithPairBias instead of MSAColumnAttention. plz have a check

Best,

lucidrains commented 3 years ago

https://github.com/lucidrains/alphafold2/commit/2c574801bab437b25018c2591fbc06fe17dee06c :+1: