Closed jiyanbio closed 3 years ago
Hi, yes in dmasif the matching labels between two points from two different proteins is based on the distance between their xyz coordinates. This is the same way it was done for masif. The distance between their descriptors gives you the prediction of whether the points are matching or not (both in masif and dmasif).
In masif, the label was defined based on descriptor vectors. But in dmasif, labels are defined based on xyz coordinates. Is it right?
`def generate_matchinglabels(args, P1, P2): if args.random_rotation: P1["xyz"] = torch.matmul(P1["rand_rot"].T, P1["xyz"].T).T + P1["atom_center"] P2["xyz"] = torch.matmul(P2["rand_rot"].T, P2["xyz"].T).T + P2["atom_center"] xyz1_i = LazyTensor(P1["xyz"][:, None, :].contiguous()) xyz2_j = LazyTensor(P2["xyz"][None, :, :].contiguous())