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

You can trigger a rebase of this PR 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)

Note
Automatic rebases have been disabled on this pull request as it has been open for over 30 days.

[github-actions]

This PR is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.

[github-actions]

This PR was closed because it has been stalled for 5 days with no activity.

[dependabot]

OK, I won't notify you again about this release, but will get in touch when a new version is available. If you'd rather skip all updates until the next major or minor version, let me know by commenting @dependabot ignore this major version or @dependabot ignore this minor version. You can also ignore all major, minor, or patch releases for a dependency by adding an ignore condition with the desired update_types to your config file.

If you change your mind, just re-open this PR and I'll resolve any conflicts on it.