Camera ready analysis2 migration#7
Merged
Merged
Conversation
Resamples rejection-sampling and best-of-16 baselines at the sweep-optimal temperature per model (Base 1.0, SFT 1.0, GRPO 1.15) and re-runs strict QC through the actual analysis2 pipeline (BLAST against curated oriDB + AMRFinder + repeats2 + two-stage filter). Replaces the earlier in-process plasmidkit Scorer numbers, which over-counted ORIs by treating overlapping ColE1/pBR322/f1 motifs as separate features. Outputs land in new bucket prefixes (rejection_sampling_v2/, best_of_16_v2/, diversity_probe/) — existing v1 paths are untouched. Each cell records SHA-256 of outputs.csv + the full-column SHA, with cross-cell and cross- version distinctness checks in manifest.json.
Untrack private and cluster-specific paths (anyscale/, scripts/, experiments/, sweeps/, AGENTS.md, ICML_REVISION_LOG.md, rebuttal.md, reviews.md). They stay on disk and remain gitignored going forward. Add MIT LICENSE (placeholder copyright holder until decided) and CITATION.cff for ICML 2026. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Rename src/ to plasmidrl/ and update every `from src.*` to `from plasmidrl.*`
- Remove plasmidrl/main.py (Click CLI was unused)
- Bring the analysis2 QC pipeline into the package:
plasmidrl/qc/blast_ori.py (was analysis2/src/qc/qc_oriv_arg2.py)
plasmidrl/qc/repeats.py (was analysis2/src/qc/repeats2.py)
plasmidrl/qc/filter.py (was analysis2/src/qc/filter_qc_two_stage2.py)
plasmidrl/qc/__init__.py public run_strict_qc orchestrator
- Move reference assets:
analysis2/assets/oriV_refs.fasta → data/canonical_oris.fasta
analysis2/assets/annotations/ → data/annotations/
- Drop the old Jupyter notebooks, the figures script, and the on-disk
training parquets (now distributed via the public bucket)
- Move legacy paper figures into paper/figures/
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- plasmidrl.data: read-only loader for UCL-CSSB/PlasmidRL-ICML. load() / load_csv() / load_json() / load_fasta() / list_tree(). Cached under ~/.cache/plasmidrl/ (override via PLASMIDRL_CACHE_DIR). - plasmidrl.models: canonical Hugging Face paths (BASE / SFT / RL), the per-cell optimal temperatures used in every headline result, and a lazy load() that imports transformers on demand. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
1 participant
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.
No description provided.