search

DeepRank / iScore

iScore: an MPI supported software for ranking protein-protein docking models based on a random walk graph kernel and support vector machines
Apache License 2.0
26 stars 11 forks source link

need pssm mapping code to be more flexible #18

Closed LilySnow closed 4 years ago

LilySnow commented 4 years ago

Many times, we just need to calculate pssm once (time-consuming) and map it to all the pdb files (fast). The current code does not seem to allow it.

CunliangGeng commented 4 years ago

Really? The PSSM class has map_pssm function.

NicoRenaud commented 4 years ago

I thought it was the case as well. It's maybe that we need better documentation :)

LilySnow commented 4 years ago

Yes, that function is there. But it is built in the class and that class requires a pdb file as input. See issue #15.

CunliangGeng commented 4 years ago

The function can actually do that by ignoring the PSSM.get_fasta() step, instead you create a ./fasta folder and put the customed fasta file to this folder, other steps are same as previous (https://iscoredoc.readthedocs.io/en/latest/pssm.html).

I will close this issue and update the doc then.

LilySnow commented 4 years ago

Thanks. One example in the doc should be enough.

CunliangGeng commented 4 years ago

Independent PSSMGen will be used (https://github.com/DeepRank/PSSMGen), clear examples are shown in README.