pen-stack 6.4.3__tar.gz → 6.6.0__tar.gz

{pen_stack-6.4.3 → pen_stack-6.6.0}/CHANGELOG.md

@@ -3,6 +3,62 @@
 All notable changes to PEN-STACK are documented here. This file follows
 [Keep a Changelog](https://keepachangelog.com/) and the program's phase structure.
 
+## [6.6.0] - 2026-06-16 - License-clean provenance (COSMIC → CancerMine)
+
+**MINOR — provenance refactor, no new science, no capability lost.** The shipped artifact now sources the
+oncogene/TSG/driver list from **CancerMine (CC0)** instead of COSMIC Cancer Gene Census (free for academia but
+**no-redistribution**). Copyright protects the *compiled database*, not the *fact* that a gene is an oncogene — so
+sourcing the *list* from a CC0 compilation removes all licensing doubt while keeping the same capability. Prep for
+the BioFirewall release, whose open repo vendors PEN-STACK's hazard data. Workstream WS-LIC + WS-CM + WS-REGEN.
+
+### Changed
+- `pen_stack/data/ingest_safety_annot.py` — `load_cancermine()` (CC0) is the **default** oncogene/TSG source
+  (HUGO→coords via GENCODE, `--min-citations` precision knob); `load_cosmic()` stays available but **off by
+  default** (bring-your-own-license, local enrichment only).
+- `configs/genotoxicity_oracle.yaml` — regenerated from CancerMine; provenance + DOIs updated (CancerMine
+  10.1038/s41592-019-0422-y). `safety_{ct}.pkl` + the Writable-Genome atlas regenerated on CancerMine features
+  (re-deposited on Zenodo, superseding the COSMIC-derived deposit).
+
+### Added
+- **`DATA_LICENSES.md`** — every source × license × redistribution-status × where-used.
+- `tests/unit/test_data_licenses.py` — **CI license gate**: fails if a restricted source (COSMIC/OncoKB) is the
+  shipped derived-data source or a raw restricted gene-list is committed; CancerMine is the default.
+- `scripts/fetch_licensed_sources.py` — bring-your-own-license fetcher for COSMIC/OncoKB (local-only, validation).
+
+### Honesty
+- Metrics may shift (CancerMine has broader coverage than CGC) — reported, not hidden. The genotoxicity axis is a
+  **mechanism-grounded proxy (🟡, not outcome-validated)** before and after; the swap changes only the *source*.
+
+## [6.5.0] - 2026-06-15 - Comprehensive expression model + honest proxy-validation pass
+
+**MINOR feature release.** Two threads, one principle (no fabrication):
+
+### Added — comprehensive, literature-cited expression model (WS-EXPRESS)
+- `configs/expression/promoters.yaml` — the twin's promoter palette expands **5 → 31 promoters** (constitutive +
+  tissue-specific: liver TBG/LP1/hAAT, neuron hSyn/CaMKIIα, muscle MHCK7/MCK/CK8, astrocyte GfaABC1D, SFFV/MND/
+  MSCV/RSV, …). Each entry carries `strength` + **context** + assay + **citation** + confidence — because promoter
+  strength has **no universal scalar** (it depends on cell type × vector × readout), so a single number is encoded
+  *with* its context, never as a universal truth.
+- `configs/expression/modifiers.yaml` — a modifier layer (WPRE, intron, polyA, Kozak, codon-optimization/CAI,
+  CpG-silencing) as **literature priors/ranges**, applied as a bounded uplift RANGE (never a point multiplier —
+  the chimeric intron is ~20× for one transgene, ~3× for another). `twin/mechanistic.py` consumes both.
+
+### Added — proxy → outcome validation harness (WS-CALIB run)
+- `scripts/calibrate_immune_axes.py` + `configs/calibration/preexisting_nab_independent.yaml` — runs the existing
+  `calibrate_axis` gate (N≥6 AND bootstrap Spearman CI excludes 0) against **independent** measured data.
+
+### Honest result (the deliverable)
+- **No immune or expression axis flips to ✅.** Pre-existing NAb tested vs an independent cohort
+  (Navarro-Oliveros 2024, Basque): ρ=0.12, CI includes 0 — geography-dependent. Relative-expression tested vs an
+  independent promoter study (Damdindorj 2014): ρ=0.12, CI includes 0 — promoter strength is context-dependent
+  (Damdindorj found CMV strongest; Qin found the opposite). Genotoxicity (3 vectors), CD8 (5 capsids), anti-PEG
+  (1), innate (0 fixed) are structurally below the N≥6 gate. The labels stay 🟡 **with empirical backing** —
+  flipping them would require measured-outcome data at a statistical power the public literature does not provide.
+
+### Tests
+- `tests/unit/test_ws_express.py` — palette is comprehensive + cited; context is encoded; modifier profile is a
+  bounded range; the proxy does NOT falsely claim cross-study validation (the no-fabrication gate holds).
+
 ## [6.4.3] - 2026-06-12 - Chat vehicle-parse fix (AAVS1 no longer hijacks the vehicle)
 
 **PATCH.** `web/tools.py::parse_goal` matched the delivery vehicle by substring, so the safe-harbour nickname

{pen_stack-6.4.3 → pen_stack-6.6.0}/CITATION.cff

@@ -1,7 +1,7 @@
 cff-version: 1.2.0
 message: "If you use PEN-STACK, please cite it as below."
 title: "PEN-STACK: open infrastructure for genome writing"
-version: 6.4.3
+version: 6.6.0
 date-released: 2026-06-12
 authors:
   - family-names: "Mahaboob Ali"

{pen_stack-6.4.3 → pen_stack-6.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pen-stack
-Version: 6.4.3
+Version: 6.6.0
 Summary: Open infrastructure for genome writing: the Writable Genome atlas, the Writer Atlas, and the Write Planner.
 Author-email: Anees Ahmed Mahaboob Ali <ahmedaneesm@gmail.com>
 License: MIT
@@ -90,7 +90,7 @@ every design against rule-grounded mechanism, reports calibrated confidence, cit
 [![codecov](https://codecov.io/gh/ahmedanees-m/pen-stack/branch/main/graph/badge.svg)](https://codecov.io/gh/ahmedanees-m/pen-stack)
 [![License: MIT](https://img.shields.io/badge/License-MIT-informational.svg)](LICENSE)
 [![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org/)
-[![Version](https://img.shields.io/badge/version-6.4.3-blue.svg)](CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-6.6.0-blue.svg)](CHANGELOG.md)
 [![Status](https://img.shields.io/badge/status-1.0%20First%20Stable-success.svg)](docs/STABILITY.md)
 [![Tests](https://img.shields.io/badge/tests-378%20passing-success.svg)](tests/)
 [![Lint: ruff](https://img.shields.io/badge/lint-ruff-purple.svg)](https://github.com/astral-sh/ruff)

{pen_stack-6.4.3 → pen_stack-6.6.0}/README.md

@@ -15,7 +15,7 @@ every design against rule-grounded mechanism, reports calibrated confidence, cit
 [![codecov](https://codecov.io/gh/ahmedanees-m/pen-stack/branch/main/graph/badge.svg)](https://codecov.io/gh/ahmedanees-m/pen-stack)
 [![License: MIT](https://img.shields.io/badge/License-MIT-informational.svg)](LICENSE)
 [![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org/)
-[![Version](https://img.shields.io/badge/version-6.4.3-blue.svg)](CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-6.6.0-blue.svg)](CHANGELOG.md)
 [![Status](https://img.shields.io/badge/status-1.0%20First%20Stable-success.svg)](docs/STABILITY.md)
 [![Tests](https://img.shields.io/badge/tests-378%20passing-success.svg)](tests/)
 [![Lint: ruff](https://img.shields.io/badge/lint-ruff-purple.svg)](https://github.com/astral-sh/ruff)

pen_stack-6.6.0/configs/calibration/preexisting_nab_independent.yaml

@@ -0,0 +1,25 @@
+# PEN-STACK — INDEPENDENT calibration data for the pre-existing-NAb axis (proxy → outcome validation).
+#
+# The preexisting_nab PROXY (configs/seroprevalence.yaml) is curated from Calcedo 2009 (10.1086/595830) and
+# Boutin 2010 (10.1089/hum.2009.182). To test it WITHOUT circularity, the "observed" column below is from an
+# INDEPENDENT serosurvey that did not feed the proxy:
+#
+#   Navarro-Oliveros M, et al. "Seroprevalence of adeno-associated virus types 1, 2, 3, 4, 5, 6, 8, and 9 in a
+#   Basque cohort of healthy donors." Scientific Reports 2024;14:15941.  doi:10.1038/s41598-024-66546-4  (N=100)
+#
+# Per-serotype NEUTRALIZING-antibody seroprevalence (%) as reported. eligibility = 1 − prevalence/100, to match
+# the proxy's direction (higher score = fewer patients excluded). Fed to validate.immune_calibration.calibrate_axis.
+source:
+  citation: "Navarro-Oliveros et al., Sci Rep 2024;14:15941"
+  doi: "10.1038/s41598-024-66546-4"
+  cohort: "100 healthy Basque-Country donors"
+  measure: "neutralizing-antibody seroprevalence (%)"
+  independence: "does NOT feed the proxy (proxy = Calcedo 2009 + Boutin 2010); a genuine out-of-sample test"
+observed_nab_prevalence_pct:
+  AAV1: 42
+  AAV2: 54
+  AAV5: 42
+  AAV6: 39
+  AAV8: 52
+  AAV9: 17
+# (AAV3 64%, AAV4 21% also reported but not scored by PEN-STACK → excluded from the paired test.)

pen_stack-6.6.0/configs/expression/modifiers.yaml

@@ -0,0 +1,59 @@
+# PEN-STACK — expression-MODIFIER priors (v6.5, WS-EXPRESS). Multiplicative cis-elements that shift relative
+# cassette expression. CRITICAL HONESTY: every fold-effect below is STRONGLY transgene-, cell-, and construct-
+# dependent (the canonical warning: the chimeric intron is ~20× for CAT but ~3× for luciferase in the SAME assay).
+# These are PRIORS/RANGES with citations — NOT deterministic multipliers. The model applies them with WIDE
+# uncertainty and NEVER asserts an absolute fold; the in-vivo expression MAGNITUDE stays a known-unknown.
+version: "1.0"
+
+modifiers:
+  wpre:
+    present_fold: [2.0, 5.0]        # AAV8 in vivo: ~5× mRNA liver, ~4× brain, ~2× muscle; lenti ~2–5×
+    default: 2.5
+    direction: increase
+    confidence: high
+    note: "woodchuck post-transcriptional regulatory element; most effective 3' of transgene, proximal to polyA"
+    citation: ["10.7150/ijms.14152", "Zufferey 1999 J Virol 73:2886"]
+  intron:
+    present_fold: [1.5, 5.0]        # SV40 intron ~4.39× eGFP (CHO); chimeric 3–20× (transgene-dependent)
+    default: 2.0
+    direction: increase
+    confidence: medium
+    note: "chimeric/SV40/MVM intron; STRONGLY transgene-dependent (20× CAT vs 3× luciferase); some transgenes none"
+    citation: ["10.1111/jcmm.13504", "Promega pCI bulletin"]
+  polya_strength:                   # relative, bGH as the strong reference (≈3× SV40 early polyA)
+    bgh: 1.0
+    synthetic_spa: 0.85
+    sv40: 0.6
+    default: 0.8
+    confidence: high
+    note: "bGH ≈ 3× SV40 early polyA; synthetic/SV40 give lower variance + better nuclease resistance"
+    citation: ["10.1089/dna.1986.5.115", "PMC8819543"]
+  kozak_strength:                   # translation-initiation context (GCCRCCaugG optimal)
+    optimal: 1.0
+    moderate: 0.7
+    weak: 0.4
+    default: 0.85
+    confidence: medium
+    note: "-3 purine + +4G dominant; weak context can cut expression up to ~95%; restoring optimal ~3× (RUNX3)"
+    citation: ["10.1038/s41598-018-22330-9"]
+  codon_optimization:               # CAI-driven; NON-MONOTONIC — higher CAI usually but not always higher
+    optimized_fold: [1.0, 10.0]     # typical 2–10×; documented 6–9× and ~10×; can also fail/backfire
+    default: 2.0
+    direction: increase_usually
+    confidence: medium
+    note: "CAI correlates with expression IMPERFECTLY (GC%, mRNA structure, hidden motifs also matter); not guaranteed"
+    citation: ["10.3389/fbioe.2024.1371596", "Sharp & Li 1987 NAR 15:1281"]
+  cpg_silencing:                    # high CpG density in the transcribed region -> repression/silencing
+    direction: decrease
+    magnitude: "context/locus-dependent — NO single sourced fold"
+    confidence: high_direction_low_magnitude
+    note: "high CpG promotes transcriptional repression + de-novo methylation + immunogenicity; CpG-depletion can escape silencing"
+    citation: ["10.1186/gb-2003-4-9-r53"]
+
+# composition policy (honesty): modifiers are applied as a BOUNDED relative shift with WIDE uncertainty, NOT a
+# naive product of independent folds (no source supports multiplicativity). The output stays a relative,
+# dimensionless estimate; absolute titer / % of normal remains a known-unknown.
+composition:
+  policy: "bounded_relative_shift"
+  max_total_uplift: 4.0            # cap the combined modifier uplift (avoid runaway products)
+  uncertainty: "wide — modifier effects are transgene/context-dependent priors, not measured for this construct"

pen_stack-6.6.0/configs/expression/promoters.yaml

@@ -0,0 +1,52 @@
+# PEN-STACK — comprehensive relative-promoter-strength palette (v6.5, WS-EXPRESS).
+#
+# A RELATIVE, ordinal, dimensionless strength per named promoter (0–1, EF1a/CAG ≈ 1.0 as the reference top tier).
+# CRITICAL HONESTY: promoter strength has NO universal scalar — it depends on cell type, vector backbone, and
+# readout (peak intensity vs long-term durability give DIFFERENT orderings; Qin 2010 vs Norrman 2010). So each
+# entry carries its `context`, `assay`, a `citation`, and a `confidence`. The `strength` is an ordinal PRIOR
+# anchored to the cited head-to-head studies — it is a proxy, not a measured absolute. Values marked
+# `confidence: low` had no directly-sourced number (qualitative tier only). NEVER treat these as exact.
+#
+# Anchors: Qin 2010 PLoS ONE 5(5):e10611 (SV40/CMV/UBC/EF1A/PGK/CAGG × 8 cell types, peak GFP);
+# Norrman 2010 PLoS ONE 5(8):e12413 (durability in hESC); Damdindorj 2014 PLoS ONE 9(8):e106472 (AAV context);
+# plus the per-tissue citations below.
+version: "1.0"
+reference: "EF1a (full) / CAG ≈ 1.0 (top constitutive tier, Qin 2010)"
+
+constitutive:
+  ef1a:        { strength: 1.00, context: ubiquitous,   assay: "peak GFP, 8 cell types", confidence: high,   note: "full ~1.2 kb with intron 1; top tier (Qin 2010); durable", citation: "10.1371/journal.pone.0010611" }
+  cag:         { strength: 1.00, context: ubiquitous,   assay: "peak GFP, 8 cell types", confidence: high,   note: "CMVe+chicken β-actin+rabbit β-globin; co-strongest (Qin 2010)", citation: "10.1371/journal.pone.0010611" }
+  cba:         { strength: 0.95, context: ubiquitous,   assay: "AAV/brain",              confidence: medium, note: "CAG-class, ~1.6 kb (large for AAV)", citation: "10.1089/hum.2010.245" }
+  cbh:         { strength: 0.90, context: ubiquitous,   assay: "neurons/AAV",            confidence: medium, note: "~0.8 kb hybrid; ≈CBA at half size; serotype-dependent", citation: "10.1089/hum.2010.245" }
+  cmv:         { strength: 0.90, context: "variable!",  assay: "peak GFP",               confidence: high,   note: "very strong transiently (293T) but SILENCES over time + in stem cells (6.7% eGFP+ d50 hESC)", citation: "10.1371/journal.pone.0012413" }
+  rsv:         { strength: 0.85, context: ubiquitous,   assay: "muscle/various",         confidence: medium, note: "≈CMV-class historically", citation: "10.1038/sj.mt.6300027" }
+  sffv:        { strength: 0.95, context: hematopoietic,assay: "human HSPC/blood",       confidence: medium, note: "much stronger than CAG/EF1/PGK in blood lineage; silences in stem cells", citation: "10.1089/10430340252898984" }
+  mnd:         { strength: 0.90, context: "t_cell/lenti",assay: "lentiviral CAR-T",      confidence: medium, note: "≈EF1a in T cells (MND U3 / MoMuLV)", citation: "10.1016/j.omtm.2022.05.005" }
+  mscv:        { strength: 0.80, context: "hsc/retro",  assay: "gammaretro backbone",    confidence: medium, note: "strong in gammaretro; underperforms in lentiviral backbone", citation: "PMC7380635" }
+  sv40:        { strength: 0.70, context: ubiquitous,   assay: "peak GFP",               confidence: high,   note: "mid tier; generally weaker than EF1a/CAG (Qin 2010)", citation: "10.1371/journal.pone.0010611" }
+  efs:         { strength: 0.70, context: ubiquitous,   assay: "lenti/size-limited",     confidence: low,    note: "EF1a core (intronless ~0.2 kb); weaker than full EF1a — fold not directly sourced", citation: null }
+  jet:         { strength: 0.55, context: ubiquitous,   assay: synthetic,                confidence: low,    note: "compact synthetic minimal; relative number not sourced", citation: "10.1016/S0378-1119(02)00878-8" }
+  casi:        { strength: 0.90, context: hematopoietic,assay: synthetic,                confidence: low,    note: "CAG-derived synthetic (CMVe+β-actin+UBC enh); head-to-head fold not sourced", citation: null }
+  actb:        { strength: 0.80, context: ubiquitous,   assay: "durability hESC",        confidence: high,   note: "human β-actin promoter; top long-term durability (74% eGFP+ d50 hESC, Norrman 2010)", citation: "10.1371/journal.pone.0012413" }
+  hsv_tk:      { strength: 0.30, context: ubiquitous,   assay: "AAV",                    confidence: medium, note: "HSV thymidine-kinase promoter; weak constitutive reference (Damdindorj 2014)", citation: "10.1371/journal.pone.0106472" }
+  pgk:         { strength: 0.50, context: ubiquitous,   assay: "peak GFP",               confidence: high,   note: "weak peak but DURABLE/low-silencing (74% eGFP+ d50 hESC)", citation: "10.1371/journal.pone.0010611" }
+  ubc:         { strength: 0.40, context: ubiquitous,   assay: "peak GFP",               confidence: high,   note: "weakest of the common constitutive set (Qin 2010)", citation: "10.1371/journal.pone.0010611" }
+
+tissue_specific:
+  tbg:         { strength: 1.00, context: liver,   confidence: medium, note: "top liver promoter (> LP1 > HLP); clean liver restriction; compact", citation: "10.1016/j.gene.2012.07.009" }
+  apoe_haat:   { strength: 0.85, context: liver,   confidence: medium, note: "ApoE-HCR enhancer + hAAT; first hemophilia-B FIX trials", citation: "10.1182/blood-2005-10-4035" }
+  lp1:         { strength: 0.85, context: liver,   confidence: medium, note: "HCR1 enhancer + hAAT core; clinical FIX from single AAV (2nd after TBG)", citation: "10.1182/blood-2005-10-4035" }
+  haat:        { strength: 0.80, context: liver,   confidence: medium, note: "human α1-antitrypsin; base of ApoE-hAAT/LP1 hybrids", citation: "10.1182/blood-2005-10-4035" }
+  hlp:         { strength: 0.70, context: liver,   confidence: medium, note: "HCR+hAAT+ApoE ~800 bp; below TBG/LP1; therapeutic at compact size", citation: "10.1016/j.gene.2012.07.009" }
+  camkiia:     { strength: 0.90, context: neuron,  confidence: medium, note: "excitatory neurons; greater overall expression than hSyn1", citation: "10.1016/j.neulet.2021.135889" }
+  hsyn:        { strength: 0.70, context: neuron,  confidence: medium, note: "pan-neuronal ~460 bp; robust but slower kinetics (CAG-level only by ~3 mo)", citation: "10.1016/j.neulet.2021.135889" }
+  mecp2:       { strength: 0.50, context: neuron,  confidence: low,    note: "neuron-restricted compact; weaker — relative fold not sourced", citation: null }
+  gfaabc1d:    { strength: 0.80, context: astrocyte,confidence: high,  note: "~681 bp; ~2× stronger than full gfa2; astrocyte-restricted", citation: "10.1002/glia.20622" }
+  gfap:        { strength: 0.60, context: astrocyte,confidence: medium,note: "gfa2 ~2.2 kb astrocyte-selective", citation: "10.1002/glia.20622" }
+  mhck7:       { strength: 1.00, context: muscle,  confidence: medium, note: "MCK enh + α-MHC ~770 bp; highest of muscle panel; DMD clinical", citation: "10.1038/sj.mt.6300027" }
+  mck:         { strength: 0.90, context: muscle,  confidence: medium, note: "truncated MCK; more active than CMV in muscle", citation: "10.1038/gt.2008.104" }
+  ck8:         { strength: 0.85, context: muscle,  confidence: low,    note: "compact muscle promoter; DMD clinical vectors", citation: "10.32607/actanaturae.11063" }
+  desmin:      { strength: 0.70, context: muscle,  confidence: medium, note: "mid muscle tier; ≈CMV in myotubes", citation: "10.1038/sj.mt.6300027" }
+
+# default for an unrecognised / unspecified promoter (the prior mean; honest abstention to mid-strength).
+default_strength: 0.5

{pen_stack-6.4.3 → pen_stack-6.6.0}/configs/genotoxicity_oracle.yaml

@@ -1,17 +1,17 @@
 version: '1.0'
-built: '2026-06-10'
+built: '2026-06-16'
 description: 'computed integration-site genotoxicity oracle: per vector class, the
-  observed enrichment of integration sites within window_bp of a COSMIC oncogene vs
-  genome background. genotox_score = min(1, 1/enrichment). In-vivo clonal outcome
-  is NOT modelled (stays a known-unknown).'
+  observed enrichment of integration sites within window_bp of a CancerMine (CC0)
+  oncogene vs genome background. genotox_score = min(1, 1/enrichment). In-vivo clonal
+  outcome is NOT modelled (stays a known-unknown).'
 window_bp: 50000
-genome_background_frac_oncogene_50kb: 0.02211
+genome_background_frac_oncogene_50kb: 0.11538
 inputs:
   visdb: VISDB per-virus hg38 catalogues
-  oncogenes: COSMIC CGC v104 (safety_annot)
+  oncogenes: CancerMine (CC0) via safety_annot
 provenance_dois:
 - 10.1093/nar/gkz867
-- 10.1038/s41568-018-0060-1
+- 10.1038/s41592-019-0422-y
 - 10.1016/S0092-8674(02)00864-4
 - 10.1126/science.1083413
 robust_min_n: 1000
@@ -19,29 +19,29 @@ classes:
   lentiviral:
     virus: HIV
     n_sites: 88743
-    frac_oncogene_50kb: 0.04602
-    ci95: 0.00138
-    enrichment: 2.081
+    frac_oncogene_50kb: 0.2244
+    ci95: 0.00274
+    enrichment: 1.945
     frac_genotoxic_cis: 0.000293
-    median_dist_oncogene: 2339098
+    median_dist_oncogene: 256384
     robust: true
   deltaretroviral:
     virus: HTLV
     n_sites: 51508
-    frac_oncogene_50kb: 0.02648
-    ci95: 0.00139
-    enrichment: 1.198
+    frac_oncogene_50kb: 0.14472
+    ci95: 0.00304
+    enrichment: 1.254
     frac_genotoxic_cis: 0.000369
-    median_dist_oncogene: 3766674
+    median_dist_oncogene: 547160
     robust: true
   gammaretroviral:
     virus: MLV
     n_sites: 32
-    frac_oncogene_50kb: 0.125
-    ci95: 0.11459
-    enrichment: 5.653
+    frac_oncogene_50kb: 0.21875
+    ci95: 0.14324
+    enrichment: 1.896
     frac_genotoxic_cis: 0.0
-    median_dist_oncogene: 2871705
+    median_dist_oncogene: 145675
     robust: false
 vehicle_class:
   lentiviral:

{pen_stack-6.4.3 → pen_stack-6.6.0}/configs/metric_guide.yaml

@@ -14,7 +14,7 @@ metrics:
     means: "relative insertional-oncogenesis safety of the delivery/integration strategy. 1.0 = episomal/
       non-integrating (no integration → no insertional mutagenesis); lower = an integrating vector whose insertion
       sites fall nearer known proto-oncogenes."
-    computed: "for integrating vectors, from VISDB integration-site maps × COSMIC Cancer-Gene-Census oncogene
+    computed: "for integrating vectors, from VISDB integration-site maps × CancerMine (CC0) oncogene
       proximity (per-vector enrichment of integrations within 50 kb of an oncogene vs background)."
     validation: "mechanistic proxy — NOT outcome-validated (the actual clonal-transformation rate is measured, not predicted)."
     reference: "e.g. lentiviral ~0.48 (2.08× oncogene-proximity enrichment) vs episomal AAV 1.0."
@@ -82,11 +82,18 @@ metrics:
     scale: "0–1 (relative, dimensionless), with an interval"
     direction: "higher = stronger relative cassette expression — NOT an absolute titer"
     bands: { strong: ">=0.6", moderate: "0.3–0.6", weak: "<0.3" }
-    means: "a RELATIVE, dimensionless expression estimate (promoter × copy number × accessibility). It is NOT a
-      phenotype, NOT a functional titer, and NOT a percent-of-normal — those are measured clinical endpoints."
-    computed: "closed-form mechanistic twin (steady-state; no silencing modeled; linear copy scaling), fused with
-      the immune context; interval is a heuristic band that WIDENS ~1.6× under out-of-distribution context."
-    validation: "honest heuristic band — NOT a trained conformal interval (no public perturbation-outcome calibration set)."
+    means: "a RELATIVE, dimensionless expression estimate (promoter × copy number × accessibility, + a bounded
+      modifier uplift range). It is NOT a phenotype, NOT a functional titer, and NOT a percent-of-normal — those
+      are measured clinical endpoints."
+    computed: "closed-form mechanistic twin over a COMPREHENSIVE literature-cited palette (v6.5: 31 promoters,
+      constitutive + tissue-specific, each with its context/assay/citation — configs/expression/promoters.yaml)
+      plus modifier PRIORS (WPRE, intron, polyA, Kozak, codon-opt, CpG-silencing — configs/expression/modifiers.yaml,
+      reported as a bounded uplift RANGE, never a point multiplier). Interval widens ~1.6× under OOD context."
+    validation: "richly literature-anchored PROXY, NOT outcome-validated: an INDEPENDENT promoter study
+      (Damdindorj 2014) disagrees with the anchor (Qin 2010) on CMV/CAG/EF1a ordering — promoter strength is
+      genuinely CONTEXT-dependent (cell × vector × readout), so a single context-free ordinal does not validate
+      cross-study (Spearman ~0.12 vs Damdindorj, CI includes 0). The palette now ENCODES that context rather than
+      asserting a universal number. Modifier folds are transgene-dependent priors."
     reference: "absolute titer / % of normal is explicitly out of scope (known-unknown in_vivo_expression_magnitude)."
 
 # how to read the safety decision (categorical, not a number)

{pen_stack-6.4.3 → pen_stack-6.6.0}/configs/oracles/scope_cards.yaml

@@ -115,16 +115,16 @@ oracles:
 
   delivery_genotoxicity:        # v5.2 WS-GENOTOX: computed integration-site oncogene-proximity
     family: genome
-    version: "visdb+cgc_v104-2026"
+    version: "visdb+cancermine-2026"
     output_kind: baseline       # an observed-data comparator (integration catalogues), not generative
     valid_for: "RELATIVE genotoxicity ordering of INTEGRATING vector classes via the observed enrichment of
-      integration sites near COSMIC oncogenes (lentiviral vs gammaretroviral, from VISDB x CGC); reproduces the
-      lentivirus-safer-than-gammaretrovirus ordering from data"
+      integration sites near CancerMine (CC0) oncogenes (lentiviral vs gammaretroviral, from VISDB x CancerMine);
+      reproduces the integrating-vector-enriched-near-oncogenes signal from data"
     not_valid_for: "the IN-VIVO clonal-expansion / leukemogenesis OUTCOME in a patient (a known-unknown); an
       absolute per-insertion oncogenesis probability; non-integrating vectors (no insertional mechanism);
       classes with too few catalogued sites (flagged extrapolating)"
     generalizes_to_unseen_loci: false
-    license: "open (this work; VISDB 10.1093/nar/gkz867, COSMIC CGC 10.1038/s41568-018-0060-1)"
+    license: "open / CC0 (this work; VISDB 10.1093/nar/gkz867, CancerMine 10.1038/s41592-019-0422-y)"
 
   capsid_epitope:               # v5.3 WS-EPITOPE: computed capsid/envelope CD8 T-cell epitope load
     family: protein_design

{pen_stack-6.4.3 → pen_stack-6.6.0}/pen_stack/__init__.py

@@ -1,2 +1,2 @@
 """PEN-STACK v3.0 - open infrastructure for genome writing."""
-__version__ = "6.4.3"
+__version__ = "6.6.0"

{pen_stack-6.4.3 → pen_stack-6.6.0}/pen_stack/data/ingest_safety_annot.py

@@ -1,7 +1,7 @@
-"""Safety annotations per 1 kb bin (Phase 1, Step 1.4).
+"""Safety annotations per 1 kb bin (Phase 1, Step 1.4; v6.6 license-clean source).
 
-Builds per-bin safety features from COSMIC Cancer Gene Census (oncogene/TSG loci),
-DepMap CRISPRGeneEffect (essential genes), and GENCODE (gene/TSS distances):
+Builds per-bin safety features from CancerMine (CC0; oncogene/TSG loci — the default, shipped) or COSMIC CGC
+(local-only, bring-your-own-license), DepMap CRISPRGeneEffect (essential genes), and GENCODE (gene/TSS distances):
   - dist_oncogene, dist_tsg, dist_essential, dist_tss  (bp to nearest, via bedtools closest)
   - genotoxic_cis flag (bins within a window of LMO2/MECOM/CCND2/PRDM16/HMGA2)
 
@@ -48,6 +48,30 @@ def load_cosmic(tsv: str) -> pd.DataFrame:
     return df[["chrom", "start", "end", "GENE_SYMBOL", "role"]]
 
 
+# v6.6: CancerMine (CC0) is the license-clean oncogene/TSG/driver source that REPLACES COSMIC CGC in the shipped
+# artifact. Lever et al., Nat Methods 16:505-507 (2019), doi:10.1038/s41592-019-0422-y, CC0; Zenodo record 7689627.
+# COSMIC stays available (load_cosmic) but OFF by default, for local enrichment under the user's own license (BYO).
+CANCERMINE_URL = "https://zenodo.org/records/7689627/files/cancermine_collated.tsv?download=1"
+_ROLE_MAP = {"Oncogene": "oncogene", "Tumor_Suppressor": "TSG", "Driver": "driver"}
+
+
+def load_cancermine(tsv: str, genes: pd.DataFrame, min_citations: int = 3) -> pd.DataFrame:
+    """CC0 oncogene/TSG/driver list. The collated file has one row per (gene, cancer, role) with a citation_count;
+    we aggregate per gene-role across cancers (sum citations), keep roles with >= min_citations, and map the HUGO
+    symbol -> genomic coordinates via GENCODE. Returns the SAME schema as load_cosmic (chrom,start,end,GENE_SYMBOL,
+    role) with the role string containing 'oncogene'/'TSG'/'driver' so the downstream filters are unchanged."""
+    cm = pd.read_csv(tsv, sep="\t", dtype=str)
+    cm["cites"] = pd.to_numeric(cm.get("citation_count"), errors="coerce").fillna(0)
+    agg = cm.groupby(["gene_normalized", "role"], as_index=False)["cites"].sum()
+    agg = agg[agg["cites"] >= float(min_citations)]
+    agg["rn"] = agg["role"].map(_ROLE_MAP).fillna(agg["role"])
+    roles = (agg.groupby("gene_normalized")["rn"]
+             .apply(lambda s: ",".join(sorted(set(s)))).reset_index(name="role"))
+    g = genes[["gene_name", "chrom", "start", "end"]].drop_duplicates("gene_name")
+    m = roles.merge(g, left_on="gene_normalized", right_on="gene_name", how="inner")
+    return m.rename(columns={"gene_normalized": "GENE_SYMBOL"})[["chrom", "start", "end", "GENE_SYMBOL", "role"]]
+
+
 def load_depmap_essential(csv: str, thresh: float = -0.5) -> set[str]:
     """Common-essential genes: mean Chronos effect across cell lines < thresh."""
     df = pd.read_csv(csv, index_col=0)
@@ -112,17 +136,24 @@ def nearest_dist(bins_bed: pybedtools.BedTool, feat_df: pd.DataFrame, name: str)
     return out.groupby(["chrom", "start"], as_index=False)[name].min()
 
 
-def build(bin_grid: str, cosmic_tsv: str, depmap_csv: str, gencode_dest: str,
-          sizes_tsv: str, out_parquet: str) -> pd.DataFrame:
+def build(bin_grid: str, depmap_csv: str, gencode_dest: str, sizes_tsv: str, out_parquet: str, *,
+          source: str = "cancermine", cancermine_tsv: str | None = None, cosmic_tsv: str | None = None,
+          min_citations: int = 3) -> pd.DataFrame:
+    """Build per-bin safety features. `source` selects the LICENSE-CLEAN oncogene/TSG list: 'cancermine' (CC0,
+    default, shipped) or 'cosmic' (local-only, under the user's own license — bring-your-own-license enrichment)."""
     grid = pd.read_parquet(bin_grid)[["chrom", "start", "bin"]]
     bins_bed = _bed(grid.assign(end=grid["start"] + BIN_BP)).sort()
 
-    cosmic = load_cosmic(cosmic_tsv)
-    onco = cosmic[cosmic["role"].str.contains("oncogene", case=False, na=False)]
-    tsg = cosmic[cosmic["role"].str.contains("TSG", case=False, na=False)]
-
     gtf = download_gencode(gencode_dest)
     genes = parse_gencode_genes(gtf)
+
+    if source == "cosmic":
+        cg = load_cosmic(cosmic_tsv)
+    else:  # default: CancerMine (CC0)
+        cg = load_cancermine(cancermine_tsv, genes, min_citations=min_citations)
+    onco = cg[cg["role"].str.contains("oncogene", case=False, na=False)]
+    tsg = cg[cg["role"].str.contains("TSG", case=False, na=False)]
+
     ess_syms = load_depmap_essential(depmap_csv)
     ess = genes[genes["gene_name"].isin(ess_syms)]
 
@@ -148,15 +179,21 @@ def build(bin_grid: str, cosmic_tsv: str, depmap_csv: str, gencode_dest: str,
 def main() -> None:
     ap = argparse.ArgumentParser()
     ap.add_argument("--bin-grid", default="/data/features/bin_grid_1kb.parquet")
+    ap.add_argument("--source", choices=["cancermine", "cosmic"], default="cancermine",
+                    help="oncogene/TSG source: cancermine (CC0, shipped default) or cosmic (local-only BYO-license)")
+    ap.add_argument("--cancermine", default="/data/external/cancermine_collated.tsv")
+    ap.add_argument("--min-citations", type=int, default=3,
+                    help="CancerMine per-gene-role citation threshold (3 = validated precision: safety AUROC 0.74)")
     ap.add_argument("--cosmic", default="/data/external/Cosmic_CancerGeneCensus_v104_GRCh38.tsv")
     ap.add_argument("--depmap", default="/data/external/CRISPRGeneEffect.csv")
     ap.add_argument("--gencode", default="/data/raw/gencode.v46.basic.gtf.gz")
     ap.add_argument("--sizes", default="/data/raw/hg38.chrom.sizes")
     ap.add_argument("--out", default="/data/features/safety_annot.parquet")
     a = ap.parse_args()
-    df = build(a.bin_grid, a.cosmic, a.depmap, a.gencode, a.sizes, a.out)
+    df = build(a.bin_grid, a.depmap, a.gencode, a.sizes, a.out, source=a.source,
+               cancermine_tsv=a.cancermine, cosmic_tsv=a.cosmic, min_citations=a.min_citations)
     n_onco = (df["dist_oncogene"] == 0).sum()
-    print(f"safety_annot bins={len(df)} cols={[c for c in df.columns if c.startswith('dist') or c=='genotoxic_cis']}")
+    print(f"safety_annot[{a.source}] bins={len(df)} cols={[c for c in df.columns if c.startswith('dist') or c=='genotoxic_cis']}")
     print(f"bins in an oncogene={n_onco} genotoxic_cis bins={int(df['genotoxic_cis'].sum())}")
 
 

{pen_stack-6.4.3 → pen_stack-6.6.0}/pen_stack/planner/genotoxicity_oracle.py

@@ -1,9 +1,9 @@
 """Computed genotoxicity oracle for integrating delivery vectors (v5.2, WS-GENOTOX).
 
 Replaces the hard-coded `genotoxicity` ordinal tier (v5.1, documented prior) with a DATA-COMPUTED signal for
-INTEGRATING vehicles: the observed enrichment of a vector class's integration sites near COSMIC Cancer-Gene-
-Census oncogenes, from VISDB integration catalogues x the Phase-1 oncogene annotation (configs/
-genotoxicity_oracle.yaml, built by scripts/p52_build_genotox_oracle.py on the VM where the data lives).
+INTEGRATING vehicles: the observed enrichment of a vector class's integration sites near CancerMine (CC0)
+oncogenes, from VISDB integration catalogues x the Phase-1 oncogene annotation (configs/genotoxicity_oracle.yaml,
+built by scripts/p52_build_genotox_oracle.py on the VM where the data lives). v6.6: oncogene source COSMIC->CancerMine.
 
     genotox_score = min(1, 1 / enrichment)      # 1 = safest; episomal/non-targeting ~ 1.0
 
@@ -46,7 +46,7 @@ def _vehicle_to_class() -> dict:
 
 def _prov(source: str, **extra) -> Provenance:
     art = _artifact()
-    return Provenance(model="visdb_integration_x_cosmic_cgc", version=str(art.get("version", "1.0")),
+    return Provenance(model="visdb_integration_x_cancermine", version=str(art.get("version", "1.0")),
                       source=source, extra={"built": art.get("built"),
                                             "provenance_dois": art.get("provenance_dois", []), **extra})
 
@@ -55,7 +55,7 @@ def genotoxicity_oracle(vehicle_name: str) -> OracleResult:
     """Computed genotoxicity for a delivery vehicle, as an OracleResult (v4.0 contract).
 
     - non-integrating vehicle  -> genotox_score 1.0 by mechanism (episomal/transient; no insertional risk).
-    - integrating + computed class -> data-derived score from VISDB x COSMIC; small-n class -> extrapolating.
+    - integrating + computed class -> data-derived score from VISDB x CancerMine; small-n class -> extrapolating.
     - integrating but no computed class / unknown vehicle -> available=False (caller falls back to the
       documented `immune_safety.genotoxicity` tier; no number is fabricated)."""
     rec = vehicle(vehicle_name)
@@ -97,7 +97,7 @@ def genotoxicity_oracle(vehicle_name: str) -> OracleResult:
         native_uncertainty=nu, scope_card=_SCOPE_CARD, in_scope=True,
         extrapolating=not robust, output_kind="baseline", available=True,
         note=(f"{cls} integration is {enrich}x enriched within "
-              f"{_artifact().get('window_bp')} bp of a COSMIC oncogene vs background "
+              f"{_artifact().get('window_bp')} bp of a CancerMine oncogene vs background "
               f"({frac:.3%}, n={n}); genotox_score=min(1,1/enrichment)."
               + ("" if robust else " SMALL-N class: directional only (extrapolating).")
               + " In-vivo clonal outcome is a known-unknown (not modelled).")