Repository navigation
Conversation
generate_features() now returns a dict of raw predictions keyed by generator name. When keepIntermediate is true (default), the pipeline assembles them into BA.parquet under <output_dir>/intermediate/. - Add _build_ba_parquet() to feature_generation.py to handle per-tool normalization (NetMHCpan/II rank-based best-allele, MHCflurry presentation percentile) and outer-join merge - Fix generator memory release: del before gc.collect() so the object is freed immediately rather than at next iteration - Add keepIntermediate: True to DEFAULT_CONFIG - Broaden .gitignore to cover data/, examples/, and playground/
* standardize netmhcpan and netmhciipan on BA mode * align feature names with mhcflurry (remove _best_) * clean up dead code
- Updated README to clarify the use of allele names for MHC binding and PWM features. - Expanded examples in tutorial documentation to include allele naming conventions for Class I and Class II. - Added details on PWM matrix requirements and how allele names map to PWM directory formats.
Standardize feature generator docstrings for flanking amino acid and modification removal options, and align DeepLC/SpectralSimilarity docs with their actual parameters.
5h4ng
changed the title
5h4ng
marked this pull request as ready for review
July 16, 2026 20:30
Owner
Author
|
@codex review |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 786d1ed6a8
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
keepIntermediate(default:true).<outputDir>/<experimentName>/intermediate/BA.parquet.BA.parquetThe Parquet table is indexed by
peptide. Depending on the configured predictors, it contains:netmhcpan_allele,netmhcpan_affinity,netmhcpan_ba_ranknetmhciipan_allele,netmhciipan_affinity,netmhciipan_ba_rankmhcflurry_allele,mhcflurry_affinity,mhcflurry_el_rankNetMHCpan and NetMHCIIpan retain the allele with the lowest valid percentile rank for each peptide. MHCflurry contributes its best-allele prediction.
User impact
Validation
uv run mkdocs build --strictuv run ruff check .git diff --checkPYTEST_DISABLE_PLUGIN_AUTOLOAD=1 uv run pytest tests/test_utils.py tests/parser— 11 passedThe complete pytest suite was not collected successfully because importing
optimhc.coreeagerly loads the TensorFlow-backed feature stack and deadlocks during the native TensorFlow import in this environment. This behavior predates the documentation-only final review changes.Follow-up work
BA.parquetschema and round-trip regression tests.overlap.parquetsupport in separate changes.