Bump deeprank-gnn-esm from 1.1.0 to 2.0.0

[dependabot]

Bumps deeprank-gnn-esm from 1.1.0 to 2.0.0.

Release notes

Sourced from deeprank-gnn-esm's releases.

v2.0.0 — Embedding generation pipeline refactor

[!NOTE]
This release note was AI-generated

Refactors the prediction pipeline to support heterogeneous, multi-chain, multi-model input instead of a fixed 2-chain complex. This is a breaking release.

Breaking changes

• CLI signature changed. Chain IDs and core count are no longer positional arguments; chain pairing is now automatic.

  # before (1.x)
  deeprank-gnn-esm-predict 1B6C.pdb A B 1
  after (2.0)
  deeprank-gnn-esm-predict 1B6C.pdb --num_cores 1

  pdb_files now accepts one or more paths. Every chain pair in every input model is scored automatically — a 3-chain complex yields 3 pairwise predictions (A-B, A-C, B-C); an ensemble of N models yields predictions for every model.

• Console entry point moved. deeprank-gnn-esm-predict now resolves to deeprank_gnn.main:main (was deeprank_gnn.predict:main). Anything importing deeprank_gnn.predict.main directly will break.

• Output layout changed. Previously all intermediate files (renumbered PDB, fasta, embeddings, graph/prediction hdf5) were written to a permanent {pdb}-gnn_esm_pred_{chain_i}_{chain_j}/ directory in the CWD. Now they're written to a temporary directory that's deleted after the run; only the final GNN_esm_prediction.csv is copied back to the CWD. Pass --output-dir to keep intermediates around (new flag).

• CSV output schema changed. Output is now pdb_id,chain_i,chain_j,predicted_fnat with one row per chain pair per input (previously implied a single pair per run). A new sibling file, <output>_summary.csv (pdb_id,combined_fnat), sums predicted fnat across all pairs of each model.

• Library API changed — anyone importing deeprank_gnn.predict directly, not just the CLI:

  • Removed: renumber_pdb, three_to_one, pdb_to_fasta, process_batch, get_model_output, get_embedding, split_input_pdb (replaced by deeprank_gnn.input.PDBInput and deeprank_gnn.sequence.MultiFasta/Sequence).
  • setup_workspace(identificator: str) → setup_workspace(output_dir: Optional[Path] = None).
  • parse_output(csv_output, workspace_path, chain_ids) → parse_output(csv_output, pair_info: dict[str, tuple[str, str, str]]).

• Input constraint added. When scoring multiple PDB files in one invocation, each input file must have a unique filename stem — the CLI now errors out otherwise.

New

• --output-dir flag to persist intermediate files for inspection.
• Multi-PDB / multi-model ensemble scoring in a single invocation, with embeddings deduplicated and batched once across all inputs.
• <output>_summary.csv — combined predicted fnat per model, summed across its chain pairs.
• e2e pytest marker for full-pipeline tests (downloads/loads the ESM model).

Migration

• Drop the chain_id_1 chain_id_2 num_cores positional args; use --num_cores (optional, default 1) and pass PDB path(s) only — pairs are inferred.
• If you relied on the old output directory sticking around, pass --output-dir <dir>.
• If you parsed the CSV expecting exactly one row, update to handle one row per chain pair.
• If you imported helper functions from deeprank_gnn.predict, switch to deeprank_gnn.input/deeprank_gnn.sequence equivalents.

version bumped 1.1.0 → 2.0.0 (pyproject.toml) accordingly.

Commits

• 2058b7e Merge pull request #37 from haddocking/36-add-support-to-heterogenous-input
• a253f05 update parse output
• d46a228 review 2
• 29ed8b1 update README
• 4148ed9 review
• 9c574cd bump version
• 0f43c69 update test
• 9686d62 add optional output_dir
• 485438a update ci
• e673bd8 add e2e test
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)