Files
rdk c6ee163ece Audit cleanup: remove dead param, dead commented code, stale docs
- Drop dead mask_unknown_residues=true from default(_rescore).groovy
  (param removed from Params.groovy in 1b7809a6, 2019; configs missed)
- Rewrite distro/models/readme.md to match models on disk (add rescore_2024,
  rescore_conservation; remove nonexistent conservation.model)
- Remove broken documentation/rescoring.md link from distro/README.md
- distro/config/readme.md: drop nonexistent working.groovy reference,
  fix github link master->develop
- Delete dead commented-out method bodies in PdbUtils, RPlotter,
  PredictionVisualizer
- Fix typo in Main.groovy javadoc
2026-05-15 09:34:28 +02:00
..
2024-09-27 22:15:21 +02:00
2024-09-27 22:15:21 +02:00

Directory with pre-trained models

Prank looks here for the model specified by the -model / -m parameter.

The model should always be used only in combination with the parameters or config file that was used to train it. I.e.: the feature extraction has to be executed with the same parameters.

List of models

P2Rank (pocket prediction)

  • default ... config default.groovy
  • conservation_hmm ... config conservation_hmm.groovy (uses HMMER-based sequence conservation)
  • alphafold ... config alphafold.groovy (tuned for AlphaFold / NMR / cryo-EM structures, no b-factor)
  • alphafold_conservation_hmm ... config alphafold_conservation_hmm.groovy

PRANK (pocket rescoring)

  • default_rescore ... config default_rescore.groovy
  • rescore_2024 ... config rescore_2024.groovy (newer model, recommended for AlphaFold / NMR / cryo-EM)
  • rescore_conservation ... config rescore_conservation.groovy (rescoring with conservation features)

Auxiliary

  • _score_transform/ — score-transformer JSON files (probability calibration, z-score) loaded by the models above.