vsomnath / holoprot

Multi-Scale Representation Learning on Proteins (NeurIPS 2021)
https://arxiv.org/abs/2204.02337
MIT License
47 stars 8 forks source link

Question on generation of patches #8

Open BJWiley233 opened 8 months ago

BJWiley233 commented 8 months ago

I tested pulling out one of the patches after running ers.computeSegmentation and then pulled out a submesh from for instance:

submesh = pymesh.submesh(mesh, np.where(patch_labels==2)[0], 0)

And I expected the the triangles to all be collected in a patch, however it looks like they are scattered all about from the pymol ply plugin from MaSIF. Is this intended? I cannot get much from the paper on what the indended behavior is.

image

BJWiley233 commented 8 months ago

If you use the output_patch_coords after and uncomment out the debug code in compute_polar_coordinates from MaSIF (you can also extract subpatch charges if you want) i get test patches that are grouped near eachother. This is done through simple run of dijkstra and then you can save some patches.

image