diff --git a/.planning/ROADMAP.md b/.planning/ROADMAP.md index 9434f57..d972efd 100644 --- a/.planning/ROADMAP.md +++ b/.planning/ROADMAP.md @@ -119,9 +119,12 @@ Plans: 2. Negative control validation shows housekeeping genes are deprioritized (low scores, excluded from high-confidence tier) 3. Sensitivity analysis across parameter sweeps demonstrates rank stability for top candidates 4. Final scoring weights are tuned based on validation metrics and documented with rationale -**Plans**: TBD +**Plans**: 3 plans -Plans: (to be created during plan-phase) +Plans: +- [ ] 06-01-PLAN.md -- Negative control validation (housekeeping genes) and enhanced positive control metrics (recall@k) +- [ ] 06-02-PLAN.md -- Sensitivity analysis (weight perturbation sweeps with Spearman rank correlation) +- [ ] 06-03-PLAN.md -- Comprehensive validation report, CLI validate command, and unit tests ## Progress @@ -135,4 +138,4 @@ Phases execute in numeric order: 1 -> 2 -> 3 -> 4 -> 5 -> 6 | 3. Core Evidence Layers | 6/6 | Complete | 2026-02-11 | | 4. Scoring & Integration | 3/3 | Complete | 2026-02-11 | | 5. Output & CLI | 3/3 | Complete | 2026-02-12 | -| 6. Validation | 0/TBD | Not started | - | +| 6. Validation | 0/3 | Not started | - | diff --git a/.planning/phases/06-validation/06-01-PLAN.md b/.planning/phases/06-validation/06-01-PLAN.md new file mode 100644 index 0000000..33ecbc0 --- /dev/null +++ b/.planning/phases/06-validation/06-01-PLAN.md @@ -0,0 +1,158 @@ +--- +phase: 06-validation +plan: 01 +type: execute +wave: 1 +depends_on: [] +files_modified: + - src/usher_pipeline/scoring/negative_controls.py + - src/usher_pipeline/scoring/validation.py + - src/usher_pipeline/scoring/__init__.py +autonomous: true + +must_haves: + truths: + - "Housekeeping genes are compiled as a curated negative control set with source provenance" + - "Negative control validation shows housekeeping genes rank below 50th percentile median" + - "Positive control validation reports recall@k metrics at k=10%, 20%, top-100" + - "Known genes achieve >70% recall in top 10% of scored candidates" + artifacts: + - path: "src/usher_pipeline/scoring/negative_controls.py" + provides: "Housekeeping gene compilation and negative control validation" + exports: ["HOUSEKEEPING_GENES_CORE", "compile_housekeeping_genes", "validate_negative_controls"] + - path: "src/usher_pipeline/scoring/validation.py" + provides: "Enhanced positive control validation with recall@k and per-source breakdown" + exports: ["validate_known_gene_ranking", "compute_recall_at_k", "generate_validation_report"] + - path: "src/usher_pipeline/scoring/__init__.py" + provides: "Updated exports including negative control functions" + contains: "validate_negative_controls" + key_links: + - from: "src/usher_pipeline/scoring/negative_controls.py" + to: "DuckDB scored_genes table" + via: "PERCENT_RANK window function query" + pattern: "PERCENT_RANK.*ORDER BY composite_score" + - from: "src/usher_pipeline/scoring/validation.py" + to: "src/usher_pipeline/scoring/known_genes.py" + via: "compile_known_genes import" + pattern: "from usher_pipeline.scoring.known_genes import" +--- + + +Implement negative control validation with housekeeping genes and enhance positive control validation with recall@k metrics. + +Purpose: Negative controls ensure the scoring system does not indiscriminately rank all genes high (complementing the existing positive control validation). Enhanced positive control metrics (recall@k) provide the specific ">70% in top 10%" measurement required by success criteria. + +Output: Two modules -- negative_controls.py (new) and enhanced validation.py (updated) -- ready for integration into the comprehensive validation report (Plan 03). + + + +@/Users/gbanyan/.claude/get-shit-done/workflows/execute-plan.md +@/Users/gbanyan/.claude/get-shit-done/templates/summary.md + + + +@.planning/PROJECT.md +@.planning/ROADMAP.md +@.planning/STATE.md +@.planning/phases/06-validation/06-RESEARCH.md + +@src/usher_pipeline/scoring/validation.py +@src/usher_pipeline/scoring/known_genes.py +@src/usher_pipeline/scoring/quality_control.py +@src/usher_pipeline/scoring/__init__.py +@src/usher_pipeline/persistence/duckdb_store.py + + + + + + Task 1: Create negative control validation module with housekeeping genes + src/usher_pipeline/scoring/negative_controls.py + +Create `src/usher_pipeline/scoring/negative_controls.py` with: + +1. **HOUSEKEEPING_GENES_CORE** frozenset constant containing 13 curated housekeeping genes: + RPL13A, RPL32, RPLP0, GAPDH, ACTB, B2M, HPRT1, TBP, SDHA, PGK1, PPIA, UBC, YWHAZ. + Include inline comments grouping by function (ribosomal, metabolic, transcription/reference). + +2. **compile_housekeeping_genes() -> pl.DataFrame** function returning DataFrame with columns: + - gene_symbol (str) + - source (str): "literature_validated" for all + - confidence (str): "HIGH" for all + Follow the exact same pattern as `compile_known_genes()` in known_genes.py. + +3. **validate_negative_controls(store: PipelineStore, percentile_threshold: float = 0.50) -> dict** function: + - Register housekeeping genes as temporary DuckDB table `_housekeeping_genes` + - Use the same PERCENT_RANK window function pattern as `validate_known_gene_ranking()` in validation.py + - Query: join ranked_genes CTE with _housekeeping_genes on gene_symbol + - INVERTED validation logic: `validation_passed = median_percentile < percentile_threshold` + - Return dict with keys: total_expected, total_in_dataset, median_percentile, top_quartile_count, in_high_tier_count, validation_passed, housekeeping_gene_details (top 20 by percentile ASC) + - Clean up temp table after query + - Use structlog logger with info/warning levels matching validation.py patterns + +4. **generate_negative_control_report(metrics: dict) -> str** function: + - Follow the exact formatting pattern from generate_validation_report() in validation.py + - Show gene table with Score, Percentile, headers + - Include interpretation text for pass/fail + +Use structlog, polars, duckdb imports matching existing scoring module patterns. Import PipelineStore from usher_pipeline.persistence.duckdb_store. + + +Run: `cd /Users/gbanyan/Project/usher-exploring && python -c "from usher_pipeline.scoring.negative_controls import HOUSEKEEPING_GENES_CORE, compile_housekeeping_genes, validate_negative_controls, generate_negative_control_report; df = compile_housekeeping_genes(); print(f'Housekeeping genes: {df.height}'); assert df.height == 13; assert set(df.columns) == {'gene_symbol', 'source', 'confidence'}; print('OK')"` exits 0 + + +negative_controls.py exists with 13 curated housekeeping genes, compile function returns correct DataFrame structure, validate function uses PERCENT_RANK with inverted threshold logic, report function generates human-readable output. + + + + + Task 2: Enhance positive control validation with recall@k metrics + src/usher_pipeline/scoring/validation.py, src/usher_pipeline/scoring/__init__.py + +**In validation.py**, add the following functions (do NOT modify existing functions, only ADD): + +1. **compute_recall_at_k(store: PipelineStore, k_values: list[int] | None = None) -> dict** function: + - Default k_values: [100, 500, 1000, 2000] (absolute counts) + - Also compute recall at percentage thresholds: top 5%, 10%, 20% of scored genes + - Query scored_genes ordered by composite_score DESC (WHERE NOT NULL) + - For each k: count how many known genes (from compile_known_genes, deduplicated on gene_symbol) appear in top-k + - Recall@k = found_in_top_k / total_known_unique + - Return dict with: recalls_absolute (dict mapping k -> recall float), recalls_percentage (dict mapping pct_string -> recall float), total_known_unique (int), total_scored (int) + - Use structlog for logging results + +2. **validate_positive_controls_extended(store: PipelineStore, percentile_threshold: float = 0.75) -> dict** function: + - Call existing validate_known_gene_ranking(store, percentile_threshold) to get base metrics + - Call compute_recall_at_k(store) to get recall metrics + - Add per-source breakdown: compute median percentile separately for "omim_usher" and "syscilia_scgs_v2" genes + - Per-source query: same PERCENT_RANK CTE but filter JOIN by source + - Return dict combining base metrics + recall_at_k + per_source_breakdown (dict mapping source -> {median_percentile, count, top_quartile_count}) + - This is the "full" positive control validation for Phase 6 + +**In __init__.py**, add exports for: compute_recall_at_k, validate_positive_controls_extended, and also add imports/exports for negative_controls module: HOUSEKEEPING_GENES_CORE, compile_housekeeping_genes, validate_negative_controls, generate_negative_control_report. + + +Run: `cd /Users/gbanyan/Project/usher-exploring && python -c "from usher_pipeline.scoring import compute_recall_at_k, validate_positive_controls_extended, HOUSEKEEPING_GENES_CORE, compile_housekeeping_genes, validate_negative_controls, generate_negative_control_report; print('All imports OK')"` exits 0 + + +validation.py has compute_recall_at_k and validate_positive_controls_extended functions. __init__.py exports all new functions from both negative_controls.py and updated validation.py. Recall@k computes at both absolute and percentage thresholds. Per-source breakdown separates OMIM from SYSCILIA metrics. + + + + + + +- `python -c "from usher_pipeline.scoring.negative_controls import HOUSEKEEPING_GENES_CORE; assert len(HOUSEKEEPING_GENES_CORE) == 13"` -- housekeeping genes compiled +- `python -c "from usher_pipeline.scoring import validate_negative_controls, compute_recall_at_k, validate_positive_controls_extended"` -- all functions importable +- `python -c "from usher_pipeline.scoring.negative_controls import compile_housekeeping_genes; df = compile_housekeeping_genes(); assert 'gene_symbol' in df.columns and 'source' in df.columns"` -- DataFrame structure correct + + + +- negative_controls.py creates housekeeping gene set and validates they rank low (inverted threshold) +- validation.py compute_recall_at_k measures recall at multiple k values including percentage-based thresholds +- validate_positive_controls_extended combines percentile + recall + per-source metrics +- All new functions exported from scoring.__init__ + + + +After completion, create `.planning/phases/06-validation/06-01-SUMMARY.md` + diff --git a/.planning/phases/06-validation/06-02-PLAN.md b/.planning/phases/06-validation/06-02-PLAN.md new file mode 100644 index 0000000..6eee874 --- /dev/null +++ b/.planning/phases/06-validation/06-02-PLAN.md @@ -0,0 +1,195 @@ +--- +phase: 06-validation +plan: 02 +type: execute +wave: 1 +depends_on: [] +files_modified: + - src/usher_pipeline/scoring/sensitivity.py +autonomous: true + +must_haves: + truths: + - "Sensitivity analysis perturbs each weight by +-5% and +-10% and measures rank stability" + - "Spearman rank correlation is computed for top-100 genes between baseline and perturbed configurations" + - "Weight perturbation renormalizes remaining weights to maintain sum=1.0 constraint" + - "Rank stability assessment classifies each perturbation as stable (rho>=0.85) or unstable" + artifacts: + - path: "src/usher_pipeline/scoring/sensitivity.py" + provides: "Parameter sweep sensitivity analysis with Spearman correlation" + exports: ["perturb_weight", "run_sensitivity_analysis", "summarize_sensitivity"] + key_links: + - from: "src/usher_pipeline/scoring/sensitivity.py" + to: "src/usher_pipeline/scoring/integration.py" + via: "compute_composite_scores import" + pattern: "from usher_pipeline.scoring.integration import compute_composite_scores" + - from: "src/usher_pipeline/scoring/sensitivity.py" + to: "scipy.stats" + via: "spearmanr import" + pattern: "from scipy.stats import spearmanr" + - from: "src/usher_pipeline/scoring/sensitivity.py" + to: "src/usher_pipeline/config/schema.py" + via: "ScoringWeights import" + pattern: "from usher_pipeline.config.schema import ScoringWeights" +--- + + +Implement sensitivity analysis module for parameter sweep validation of scoring weights. + +Purpose: Demonstrates that top candidate rankings are robust to reasonable weight perturbations (+-5-10%), satisfying success criterion 3 (rank stability). This is the core of the "are our results defensible?" validation. + +Output: sensitivity.py module with weight perturbation, Spearman correlation analysis, and stability classification. + + + +@/Users/gbanyan/.claude/get-shit-done/workflows/execute-plan.md +@/Users/gbanyan/.claude/get-shit-done/templates/summary.md + + + +@.planning/PROJECT.md +@.planning/ROADMAP.md +@.planning/STATE.md +@.planning/phases/06-validation/06-RESEARCH.md + +@src/usher_pipeline/scoring/integration.py +@src/usher_pipeline/config/schema.py +@src/usher_pipeline/persistence/duckdb_store.py + + + + + + Task 1: Create sensitivity analysis module with weight perturbation and rank correlation + src/usher_pipeline/scoring/sensitivity.py + +Create `src/usher_pipeline/scoring/sensitivity.py` with: + +1. **EVIDENCE_LAYERS** list constant: ["gnomad", "expression", "annotation", "localization", "animal_model", "literature"] + +2. **DEFAULT_DELTAS** list constant: [-0.10, -0.05, 0.05, 0.10] + +3. **STABILITY_THRESHOLD** float constant: 0.85 (Spearman rho threshold for "stable") + +4. **perturb_weight(baseline: ScoringWeights, layer: str, delta: float) -> ScoringWeights** function: + - Get baseline weights as dict via baseline.model_dump() + - Apply perturbation: w_dict[layer] = max(0.0, min(1.0, w_dict[layer] + delta)) + - Renormalize ALL weights so they sum to 1.0: divide each by total + - Return new ScoringWeights instance + - Raise ValueError if layer not in EVIDENCE_LAYERS + +5. **run_sensitivity_analysis(store: PipelineStore, baseline_weights: ScoringWeights, deltas: list[float] | None = None, top_n: int = 100) -> dict** function: + - Default deltas to DEFAULT_DELTAS if None + - Compute baseline scores via compute_composite_scores(store, baseline_weights) + - Sort by composite_score DESC, take top_n genes as baseline ranking + - For each layer in EVIDENCE_LAYERS, for each delta in deltas: + - Create perturbed weights via perturb_weight() + - Compute perturbed scores via compute_composite_scores(store, perturbed_weights) + - Sort by composite_score DESC, take top_n genes + - Inner join baseline and perturbed on gene_symbol to get paired scores + - If fewer than 10 overlapping genes, log warning and record rho=None + - Otherwise compute spearmanr() on paired composite_score columns + - Record: layer, delta, perturbed_weights (as dict), spearman_rho, spearman_pval, overlap_count (how many of top_n genes appear in both), top_n + - Return dict with keys: baseline_weights (dict), results (list of per-perturbation dicts), top_n, total_perturbations + - Use structlog for progress logging (log each perturbation result) + + IMPORTANT: The compute_composite_scores function re-queries the DB each time. This is by design -- different weights produce different composite_score values from the same underlying evidence layer scores. + + For the Spearman correlation, join baseline_top_n and perturbed_top_n DataFrames on gene_symbol (inner join). Use the composite_score from each as the paired values. This measures whether the relative ordering of shared top genes is preserved. + +6. **summarize_sensitivity(analysis_result: dict) -> dict** function: + - From the results list, compute: + - min_rho, max_rho, mean_rho across all perturbations (excluding None values) + - count of stable perturbations (rho >= STABILITY_THRESHOLD) + - count of unstable perturbations (rho < STABILITY_THRESHOLD) + - most_sensitive_layer: layer with lowest mean rho across its perturbations + - most_robust_layer: layer with highest mean rho across its perturbations + - overall_stable: bool = all non-None rhos >= STABILITY_THRESHOLD + - Return dict with: min_rho, max_rho, mean_rho, stable_count, unstable_count, total_perturbations, overall_stable, most_sensitive_layer, most_robust_layer + +7. **generate_sensitivity_report(analysis_result: dict, summary: dict) -> str** function: + - Follow the formatting pattern from generate_validation_report() in validation.py + - Show table: Layer | Delta | Spearman rho | p-value | Stable? + - Show summary: overall stability verdict, most/least sensitive layers + - Include interpretation text + +Use structlog, polars, scipy.stats.spearmanr imports. Import compute_composite_scores from usher_pipeline.scoring.integration, ScoringWeights from usher_pipeline.config.schema, PipelineStore from usher_pipeline.persistence.duckdb_store. + + +Run: `cd /Users/gbanyan/Project/usher-exploring && python -c " +from usher_pipeline.scoring.sensitivity import perturb_weight, EVIDENCE_LAYERS, STABILITY_THRESHOLD, DEFAULT_DELTAS +from usher_pipeline.config.schema import ScoringWeights + +# Test weight perturbation +w = ScoringWeights() +p = perturb_weight(w, 'gnomad', 0.10) +p.validate_sum() # Must not raise +print(f'Original gnomad: {w.gnomad}, Perturbed: {p.gnomad:.4f}') +assert p.gnomad > w.gnomad, 'Perturbed weight should be higher' + +# Test renormalization +total = p.gnomad + p.expression + p.annotation + p.localization + p.animal_model + p.literature +assert abs(total - 1.0) < 1e-6, f'Weights must sum to 1.0, got {total}' + +# Test edge: perturb to near-zero +p_low = perturb_weight(w, 'gnomad', -0.25) +p_low.validate_sum() +assert p_low.gnomad >= 0.0, 'Weight must not go negative' + +print('All perturb_weight tests passed') +"` exits 0 + + +sensitivity.py exists with perturb_weight (renormalizing), run_sensitivity_analysis (computing Spearman rho for top-N genes across all layer/delta combinations), summarize_sensitivity (stability classification), and generate_sensitivity_report (formatted output). Weights always renormalize to sum=1.0 after perturbation. + + + + + Task 2: Export sensitivity module from scoring package + src/usher_pipeline/scoring/__init__.py + +Update `src/usher_pipeline/scoring/__init__.py` to add imports and exports for the sensitivity module: + +Add imports: +```python +from usher_pipeline.scoring.sensitivity import ( + perturb_weight, + run_sensitivity_analysis, + summarize_sensitivity, + generate_sensitivity_report, + EVIDENCE_LAYERS, + STABILITY_THRESHOLD, +) +``` + +Add to __all__ list: "perturb_weight", "run_sensitivity_analysis", "summarize_sensitivity", "generate_sensitivity_report", "EVIDENCE_LAYERS", "STABILITY_THRESHOLD" + +NOTE: Plan 01 may have already updated __init__.py to add negative_controls exports. If so, ADD the sensitivity imports alongside those -- do not remove them. Read the file first to check current state. + + +Run: `cd /Users/gbanyan/Project/usher-exploring && python -c "from usher_pipeline.scoring import perturb_weight, run_sensitivity_analysis, summarize_sensitivity, generate_sensitivity_report, EVIDENCE_LAYERS, STABILITY_THRESHOLD; print(f'EVIDENCE_LAYERS: {EVIDENCE_LAYERS}'); print(f'STABILITY_THRESHOLD: {STABILITY_THRESHOLD}'); print('All sensitivity exports OK')"` exits 0 + + +All sensitivity analysis functions and constants are importable from usher_pipeline.scoring. Existing exports from negative_controls (Plan 01) are preserved. + + + + + + +- `python -c "from usher_pipeline.scoring.sensitivity import perturb_weight; from usher_pipeline.config.schema import ScoringWeights; w = ScoringWeights(); p = perturb_weight(w, 'gnomad', 0.05); p.validate_sum(); print('OK')"` -- weight perturbation works and renormalizes +- `python -c "from usher_pipeline.scoring import run_sensitivity_analysis, summarize_sensitivity, generate_sensitivity_report"` -- all exports available +- `python -c "from usher_pipeline.scoring.sensitivity import STABILITY_THRESHOLD; assert STABILITY_THRESHOLD == 0.85"` -- threshold configured + + + +- perturb_weight correctly perturbs one layer and renormalizes to sum=1.0 +- run_sensitivity_analysis computes Spearman rho for all layer x delta combinations +- summarize_sensitivity classifies perturbations as stable/unstable +- generate_sensitivity_report produces human-readable output +- All functions exported from scoring package + + + +After completion, create `.planning/phases/06-validation/06-02-SUMMARY.md` + diff --git a/.planning/phases/06-validation/06-03-PLAN.md b/.planning/phases/06-validation/06-03-PLAN.md new file mode 100644 index 0000000..d39db2a --- /dev/null +++ b/.planning/phases/06-validation/06-03-PLAN.md @@ -0,0 +1,211 @@ +--- +phase: 06-validation +plan: 03 +type: execute +wave: 2 +depends_on: ["06-01", "06-02"] +files_modified: + - src/usher_pipeline/scoring/validation_report.py + - src/usher_pipeline/cli/validate_cmd.py + - src/usher_pipeline/cli/main.py + - tests/test_validation.py +autonomous: true + +must_haves: + truths: + - "CLI validate command runs positive controls, negative controls, and sensitivity analysis in sequence" + - "Comprehensive validation report documents all three validation prongs with pass/fail verdicts" + - "Weight tuning recommendations are generated based on validation results with documented rationale" + - "Tests verify negative control logic, recall@k computation, weight perturbation, and report generation" + artifacts: + - path: "src/usher_pipeline/scoring/validation_report.py" + provides: "Comprehensive validation report combining all three validation prongs" + exports: ["generate_comprehensive_validation_report", "recommend_weight_tuning"] + - path: "src/usher_pipeline/cli/validate_cmd.py" + provides: "CLI validate command orchestrating full validation pipeline" + exports: ["validate"] + - path: "tests/test_validation.py" + provides: "Unit tests for negative controls, recall@k, sensitivity, and validation report" + key_links: + - from: "src/usher_pipeline/cli/validate_cmd.py" + to: "src/usher_pipeline/scoring/negative_controls.py" + via: "validate_negative_controls import" + pattern: "from usher_pipeline.scoring import validate_negative_controls" + - from: "src/usher_pipeline/cli/validate_cmd.py" + to: "src/usher_pipeline/scoring/sensitivity.py" + via: "run_sensitivity_analysis import" + pattern: "from usher_pipeline.scoring import run_sensitivity_analysis" + - from: "src/usher_pipeline/cli/validate_cmd.py" + to: "src/usher_pipeline/scoring/validation.py" + via: "validate_positive_controls_extended import" + pattern: "from usher_pipeline.scoring import validate_positive_controls_extended" + - from: "src/usher_pipeline/cli/main.py" + to: "src/usher_pipeline/cli/validate_cmd.py" + via: "Click group add_command" + pattern: "cli.add_command.*validate" +--- + + +Create comprehensive validation report generator, CLI validate command, and unit tests for all Phase 6 validation modules. + +Purpose: This plan wires together the positive control, negative control, and sensitivity analysis modules (from Plans 01 and 02) into a single CLI command and comprehensive report. Tests ensure correctness with synthetic data. This completes Phase 6 by providing the user-facing validation workflow. + +Output: validation_report.py, validate_cmd.py (CLI), updated main.py, and test_validation.py. + + + +@/Users/gbanyan/.claude/get-shit-done/workflows/execute-plan.md +@/Users/gbanyan/.claude/get-shit-done/templates/summary.md + + + +@.planning/PROJECT.md +@.planning/ROADMAP.md +@.planning/STATE.md +@.planning/phases/06-validation/06-RESEARCH.md + +# Need SUMMARYs from Plans 01 and 02 for what was actually built +@.planning/phases/06-validation/06-01-SUMMARY.md +@.planning/phases/06-validation/06-02-SUMMARY.md + +@src/usher_pipeline/scoring/__init__.py +@src/usher_pipeline/scoring/negative_controls.py +@src/usher_pipeline/scoring/sensitivity.py +@src/usher_pipeline/scoring/validation.py +@src/usher_pipeline/cli/score_cmd.py +@src/usher_pipeline/cli/main.py +@tests/test_scoring.py + + + + + + Task 1: Create comprehensive validation report and CLI validate command + src/usher_pipeline/scoring/validation_report.py, src/usher_pipeline/cli/validate_cmd.py, src/usher_pipeline/cli/main.py + +**Create `src/usher_pipeline/scoring/validation_report.py`:** + +1. **generate_comprehensive_validation_report(positive_metrics: dict, negative_metrics: dict, sensitivity_result: dict, sensitivity_summary: dict) -> str** function: + - Generate a multi-section Markdown report combining all three validation prongs + - Section 1: "Positive Control Validation" -- median percentile, recall@k table, per-source breakdown, pass/fail + - Section 2: "Negative Control Validation" -- median percentile, top quartile count, in-HIGH-tier count, pass/fail + - Section 3: "Sensitivity Analysis" -- Spearman rho table (layer x delta), overall stability verdict, most/least sensitive layers + - Section 4: "Overall Validation Summary" -- all-pass/partial-fail/fail verdict + - Section 5: "Weight Tuning Recommendations" -- call recommend_weight_tuning() + - Return the full Markdown string + +2. **recommend_weight_tuning(positive_metrics: dict, negative_metrics: dict, sensitivity_summary: dict) -> str** function: + - Analyze validation results and suggest weight adjustments + - If positive controls pass AND negative controls pass AND sensitivity stable: "Current weights are validated. No tuning recommended." + - If positive controls fail: suggest increasing weights for layers where known genes score highly + - If negative controls fail (housekeeping genes ranking too high): suggest examining which layers boost housekeeping genes + - If sensitivity unstable: identify most sensitive layer and suggest reducing its weight + - Document rationale for each recommendation + - CRITICAL: Note that any tuning is "post-validation" and flag circular validation risk per research pitfall + - Return formatted recommendation text + +3. **save_validation_report(report_text: str, output_path: Path) -> None**: Write report to file + +**Create `src/usher_pipeline/cli/validate_cmd.py`:** + +Follow the established CLI pattern from score_cmd.py (config load, store init, checkpoint, steps, summary, cleanup): + +1. Click command `validate` with options: + - `--force`: Re-run even if validation checkpoint exists + - `--skip-sensitivity`: Skip sensitivity analysis (faster iteration) + - `--output-dir`: Output directory for validation report (default: {data_dir}/validation) + - `--top-n`: Top N genes for sensitivity analysis (default: 100) + +2. Pipeline steps: + - Step 1: Load configuration and initialize store + - Step 2: Check scored_genes checkpoint exists (error if not -- must run `score` first) + - Step 3: Run positive control validation (validate_positive_controls_extended) + - Step 4: Run negative control validation (validate_negative_controls) + - Step 5: Run sensitivity analysis (unless --skip-sensitivity) -- run_sensitivity_analysis + summarize_sensitivity + - Step 6: Generate comprehensive validation report (generate_comprehensive_validation_report) + - Step 7: Save report to output_dir/validation_report.md and provenance sidecar + +3. Use click.echo with styled output matching score_cmd.py patterns (green for success, yellow for warnings, red for errors, bold for step headers) + +4. Provenance tracking: record_step for each validation phase with metrics + +5. Final summary: display overall pass/fail, recall@top-10%, housekeeping median percentile, sensitivity stability + +**Update `src/usher_pipeline/cli/main.py`:** +- Import validate from validate_cmd +- Add: `cli.add_command(validate)` +- Follow the existing pattern used for score and report commands + + +Run: `cd /Users/gbanyan/Project/usher-exploring && python -c "from usher_pipeline.cli.validate_cmd import validate; print(f'Command name: {validate.name}'); print('OK')"` exits 0 AND `cd /Users/gbanyan/Project/usher-exploring && python -c "from usher_pipeline.cli.main import cli; commands = list(cli.commands.keys()); print(f'CLI commands: {commands}'); assert 'validate' in commands; print('OK')"` exits 0 + + +validation_report.py generates comprehensive multi-section Markdown report with weight tuning recommendations. validate_cmd.py provides CLI command running all three validation prongs. main.py registers validate as a CLI subcommand. All follow established patterns from score_cmd.py. + + + + + Task 2: Create unit tests for all validation modules + tests/test_validation.py + +Create `tests/test_validation.py` with comprehensive tests using synthetic DuckDB data. Follow the test pattern from tests/test_scoring.py (use tmp_path fixtures, create in-memory DuckDB with synthetic data). + +**Test helper: create_synthetic_scored_db(tmp_path)** function: +- Create DuckDB with gene_universe (20 genes: GENE001-GENE020) +- Create scored_genes table with composite_score and all 6 layer scores +- Design scores so that: + - MYO7A, IFT88, BBS1 (known cilia genes) get high scores (0.8-0.95) + - GAPDH, ACTB, RPL13A (housekeeping genes) get low scores (0.1-0.3) + - Other genes get mid-range scores (0.3-0.6) +- This ensures positive controls rank high and negative controls rank low in tests + +**Tests to include:** + +1. **test_compile_housekeeping_genes_structure**: Verify compile_housekeeping_genes() returns DataFrame with 13 genes, correct columns (gene_symbol, source, confidence), all confidence=HIGH, all source=literature_validated + +2. **test_compile_housekeeping_genes_known_genes_present**: Assert GAPDH, ACTB, RPL13A, TBP are in the gene_symbol column + +3. **test_validate_negative_controls_with_synthetic_data**: Use synthetic DB where housekeeping genes score low. Assert validation_passed=True, median_percentile < 0.5 + +4. **test_validate_negative_controls_inverted_logic**: Create a DB where housekeeping genes score HIGH (artificial scenario). Assert validation_passed=False + +5. **test_compute_recall_at_k**: Use synthetic DB. Assert recall@k returns dict with recalls_absolute and recalls_percentage keys. With 3 known genes in top 5 of 20, recall@5 should be high (>0.5) + +6. **test_perturb_weight_renormalizes**: Perturb gnomad by +0.10, assert weights still sum to 1.0. Perturb by -0.25 (more than weight value), assert weight >= 0.0 and sum = 1.0 + +7. **test_perturb_weight_invalid_layer**: perturb_weight with layer="nonexistent" should raise ValueError + +8. **test_generate_comprehensive_validation_report_format**: Pass mock metrics dicts, assert report contains expected sections ("Positive Control", "Negative Control", "Sensitivity Analysis", "Weight Tuning") + +9. **test_recommend_weight_tuning_all_pass**: Pass metrics indicating all validations pass. Assert response contains "No tuning recommended" or similar + +All tests should use tmp_path for DuckDB isolation. Import from usher_pipeline.scoring (not internal modules directly where possible). Use PipelineStore with direct conn assignment pattern from test_scoring.py. + + +Run: `cd /Users/gbanyan/Project/usher-exploring && python -m pytest tests/test_validation.py -v --tb=short` -- all tests pass + + +test_validation.py contains 9+ tests covering negative controls, recall@k, weight perturbation, sensitivity analysis, and report generation. All tests pass using synthetic DuckDB data with designed score patterns ensuring known genes rank high and housekeeping genes rank low. + + + + + + +- `python -m pytest tests/test_validation.py -v` -- all validation tests pass +- `python -c "from usher_pipeline.cli.main import cli; assert 'validate' in cli.commands"` -- CLI command registered +- `python -c "from usher_pipeline.scoring.validation_report import generate_comprehensive_validation_report, recommend_weight_tuning"` -- report functions importable +- `usher-pipeline validate --help` displays usage information with all options + + + +- CLI `validate` command runs positive + negative + sensitivity validations and generates comprehensive report +- Validation report includes all three prongs with pass/fail verdicts and weight tuning recommendations +- Unit tests cover negative controls, recall@k, perturbation, and report generation +- All tests pass with synthetic data +- validate command registered in main CLI + + + +After completion, create `.planning/phases/06-validation/06-03-SUMMARY.md` +