easy way to get features
rohanvarm opened this issue · comments
Is there an easy way to access the feature descriptor of the SAS points?
Hi and sorry for a late reply. Currently, there is no easy/straightforward way to do this.
If you are still interested, could you say something more about your use case?
In the future release I plan to add:
- easy way to export all feature vectors for all SAS points for individual proteins to a CSV file
- ability to visualize all individual features mapped to SAS points in PyMol
For now, you actually can export the feature vectors to an ARFF file (basically CSV with a header), but it is a hassle. It is only possible to do it in a training phase and only for the whole dataset at once. So, you can start a fake training run on a single-protein dataset with -delete_vectors 0
:
prank traineval -train test.ds -eval test.ds -delete_vectors 0 -extra_features xyz
# Notes:
# * test.ds should contain a path to only a single pdb/cif file
# * xyz feature adds (x,y,z) coordinates of the SAS point to the feature vector (optional)
# * vectorsTrain.arff.gz file will be produced in the output folder
Thanks! That is useful, I intended to use this for another downstream app