Skip to content

Conversation

@Ninjani
Copy link
Contributor

@Ninjani Ninjani commented Apr 8, 2025

  • Allows parsing any cif files with Entry.from_custom_cif_file
  • Bump BindingDB version
  • Fix BindingDB to PDB mapping (based on 100% pocket sequence coverage and identity)
  • Better handling of counts for pocket residues, interactions etc only considering proper ligands
  • Release date fix (needs data regen)
  • Use proper_ligand-based counts for scoring
  • PDB conversion fix, rename residues with >3 characters
  • Residue export, add auth_number
  • Fallible rdkit parsing
  • crystal contact detection within asymmetric units

Closes #102

ligand_views[chain] = io.LoadEntity(
self.ligand_sdfs[chain], format="sdf"
).Select("ele != H")
lig_v2000 = make_v2000_from_v3000_sdf(Path(self.ligand_sdfs[chain]))
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@Ninjani I thought the new Openstructure update should handle this. I remember you mentioned that at some point

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Still a problem to get it into conda ?

@github-actions
Copy link

github-actions bot commented Apr 8, 2025

Coverage report

Click to see where and how coverage changed

FileStatementsMissingCoverageCoverage
(new stmts)
Lines missing
  src/plinder/core/index
  system.py 364-367
  src/plinder/core/structure
  atoms.py 247-251
  src/plinder/core/utils
  io.py 80
  src/plinder/data/pipeline
  io.py
  transform.py
  src/plinder/data/utils/annotations
  aggregate_annotations.py 287, 547, 1070-1137
  get_similarity_scores.py 431-443, 773-775
  interaction_utils.py 222
  ligand_utils.py
  rdkit_utils.py 41, 144-146
  save_utils.py 39
Project Total  

This report was generated by python-coverage-comment-action

@weitse-hsu
Copy link

Hi @Ninjani, thanks so much for working on this PR to address #102—really appreciate the progress so far. I noticed most of the checklist is complete and just wanted to check in on any updates.

Also, is there a plan for supporting custom PDB files in the codebase? Thanks a lot!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Possibility of using plinder codebase to perform splitting for other datasets

5 participants