oncoref 1.6.0__tar.gz

oncoref-1.6.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

oncoref-1.6.0/MANIFEST.in

@@ -0,0 +1,10 @@
+# sdist content control. Mirror the wheel exclusions in pyproject.toml's
+# [tool.setuptools.exclude-package-data] — without this the sdist auto-includes
+# every git-tracked file and the heavy per-cohort expression data (added in a
+# later milestone) would balloon the .tar.gz past PyPI's 100 MiB limit.
+recursive-exclude oncoref/data/cancer-reference-expression *
+recursive-exclude oncoref/data/cancer-reference-expression-percentiles *
+recursive-exclude oncoref/data/cancer-reference-expression-representatives *
+recursive-exclude oncoref/data/cancer-reference-expression-within-sample-top5 *
+exclude oncoref/data/pan-cancer-expression.csv
+exclude oncoref/data/hpa-cell-type-expression.csv

oncoref-1.6.0/PKG-INFO

@@ -0,0 +1,169 @@
+Metadata-Version: 2.4
+Name: oncoref
+Version: 1.6.0
+Summary: Curated cancer reference data: ontology, TMB, incidence/mortality, and expression
+Author-email: Alex Rubinsteyn <alex.rubinsteyn@unc.edu>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/pirl-unc/oncoref
+Project-URL: Repository, https://github.com/pirl-unc/oncoref
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: pyarrow
+Requires-Dist: PyYAML
+Requires-Dist: pyensembl
+Provides-Extra: plots
+Requires-Dist: matplotlib; extra == "plots"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: matplotlib; extra == "dev"
+Dynamic: license-file
+
+# oncoref
+
+[![Tests](https://github.com/pirl-unc/oncoref/actions/workflows/tests.yml/badge.svg)](https://github.com/pirl-unc/oncoref/actions/workflows/tests.yml)
+[![PyPI](https://img.shields.io/pypi/v/oncoref.svg)](https://pypi.org/project/oncoref/)
+
+Curated cancer reference data — cancer-type ontology, tumor mutational burden
+(TMB), incidence/mortality, checkpoint-inhibitor (ICI) response, per-cohort RNA-seq expression,
+and cancer-testis antigens — behind one small Python API, a data fetch/cache
+CLI, and a set of reference plots.
+
+## oncoref is the base layer
+
+`oncoref` is **designed as the base layer** of the openvax/PIRL stack — the
+intended single upstream **source of truth** for cancer reference data, meant to
+become a shared dependency of
+[pirlygenes](https://github.com/pirl-unc/pirlygenes),
+[trufflepig](https://github.com/pirl-unc/trufflepig), and
+[tsarina](https://github.com/pirl-unc/tsarina). Adoption is still in progress —
+most of these don't depend on it yet. Architecturally it stays at the bottom: it
+depends only on pandas / numpy / pyarrow / PyYAML, it **never imports its
+consumers** (data and logic flow only downward), and it **owns** these
+definitions rather than mirroring them from elsewhere.
+
+Anything that needs to know about
+
+- **gene expression of cancer samples** — per-cohort RNA-seq in a normalized,
+  comparable space: summary stats, tail-weighted percentiles, and medoid/exemplar
+  samples per cancer type/subtype;
+- **HPA protein / RNA** normal-tissue expression;
+- the **definition of cancer-testis antigens** — the HPA tissue-restriction call
+  over the candidate list (HPA-only; no MS/peptide layer);
+- the **ontology of cancer types** — codes, the parent/child hierarchy, subtypes,
+  families, characteristic driver fusions, and the cross-cutting MSI/POLE/HPV
+  groupings; and
+- **checkpoint-inhibitor response rates** and **TMB** per cancer type
+
+depends on `oncoref` — including `pirlygenes` (gene-set curation/analysis),
+`tsarina` (personalized target selection), `hitlist` (panel selection),
+`trufflepig` (sample classification), and anything else downstream.
+
+Everything keys on the cancer-type registry. The small curated tables ship in the
+wheel; the heavy per-cohort expression bundle downloads on first use from
+oncoref's own GitHub Release.
+
+## Install
+
+```bash
+pip install oncoref
+```
+
+## Python API
+
+```python
+import oncoref as od
+
+od.resolve_cancer_type("prostate")        # -> "PRAD"
+od.cancer_type_info("SARC_RMS_ARMS")      # full registry record + burden + tmb
+od.cancer_tmb("LUAD_EGFR")                # 6.9  (inherited from LUAD)
+od.cancer_burden("pancreas", metric="us_mortality_pct")
+od.burden_category("SARC_OS")             # -> "bone_and_joint" (incidence/mortality bucket)
+od.cancer_ici_response("SKCM")            # 42  (anti-PD-1 ORR %; fallback aPD-1 → aPD-L1 → combo)
+od.cancer_ici_response("SKCM", regimen="PD-1+CTLA-4")   # 57.6  (pin a regimen)
+
+# Cancer-testis antigens (HPA-derived tissue-restriction):
+od.cta_gene_names()                       # expressed CTA symbols (MAGEA4, CT83, …)
+od.cta_evidence()                         # full HPA restriction table
+
+# Per-cohort expression percentiles (downloads the data bundle on first use):
+od.cohort_gene_percentiles("PRAD")        # per-gene p0…p100 vector (within-cohort)
+od.within_sample_top_fraction("PRAD")     # per-gene frac of samples top-5% (within-sample)
+```
+
+### Domains
+
+- **Ontology** — `cancer_type_registry`, `resolve_cancer_type`,
+  `cancer_type_info`, `cancer_types_in_family`, `viral_status`, `fusion_status`,
+  the cohort vocabulary (`cohort_registry`, `cohort_aggregates`).
+- **TMB** — `cancer_tmb`, `cancer_tmb_df` (parent-chain inheritance).
+- **Incidence / mortality** — `cancer_burden`, `burden_category` (ACS / GLOBOCAN).
+- **Checkpoint response** — `cancer_ici_response` (ORR per type/regimen: anti-PD-1,
+  anti-PD-L1, anti-PD-1+anti-CTLA-4), with `cancer_apd1_response` the PD-1 shortcut.
+- **Expression** — `cohort_gene_percentiles`, `within_sample_top_fraction`,
+  `representative_cohort_samples` over the lazy-downloaded per-cohort bundle.
+- **Cancer-testis antigens** — `cta_gene_names`/`cta_gene_ids`, `cta_evidence`,
+  `synthesize_restriction` (HPA-only tissue-restriction; MS evidence stays in the
+  target-selection layer).
+- **HPA normal tissue** — `hpa_rna_consensus`, `hpa_normal_tissue` (IHC),
+  `hpa_single_cell`, and per-gene lookups (`gene_tissue_ntpm`,
+  `gene_protein_tissues`, `gene_cell_type_ntpm`) over HPA v23, fetched on demand
+  (`oncoref hpa fetch`).
+- **Genome reference** — `canonical_gene_id_and_name`, `find_gene_id_by_name`,
+  `find_gene_name_from_ensembl_{gene,transcript}_id`, `aggregate_gene_expression`
+  (pyensembl-backed symbol ↔ Ensembl-ID resolution). pyensembl ships with the
+  package, but resolution needs a downloaded human release once:
+  `pyensembl install --release 111 --species homo_sapiens` (the accessors return
+  `None` until then).
+- **Peptides** — `cta_specific_9mer_counts`, `cta_specific_9mer_load` (per-cohort
+  mean per-patient CTA-specific 9-mer load): 9-mers found in a CTA protein but in no
+  non-CTA protein, enumerated from the reference proteome and cached per release.
+- **Plots** (`pip install oncoref[plots]`) — `oncoref.plots.apd1_vs_tmb`,
+  `apd1_orr_bars`, `incidence_vs_mortality`, and the CTA/coverage figures.
+
+## CLI
+
+```bash
+oncoref cancer-type prostate     # registry info as JSON
+oncoref tmb LUAD_EGFR            # 6.9
+oncoref ici SKCM                # 42  (--regimen to pin, --all-regimens to compare)
+oncoref burden pancreas --metric us_mortality_pct
+oncoref cta --count             # number of expressed CTAs
+oncoref plot apd1-vs-tmb --out apd1_vs_tmb.png
+
+# expression-bundle cache (per-cohort expression):
+oncoref cache fetch             # download the ~340 MB bundle
+oncoref cache status            # which bundle paths are cached (no download)
+oncoref cache dir               # where the data bundle is cached
+oncoref cache prune --yes       # delete stale version caches
+oncoref hpa fetch               # download HPA reference data (RNA / IHC / single-cell)
+oncoref version
+```
+
+## Development
+
+```bash
+./develop.sh   # editable install with dev extras
+./format.sh    # ruff format
+./lint.sh      # ruff check + format --check
+./test.sh      # lint + pytest with coverage
+```
+
+## License
+
+Apache 2.0.

oncoref-1.6.0/README.md

@@ -0,0 +1,133 @@
+# oncoref
+
+[![Tests](https://github.com/pirl-unc/oncoref/actions/workflows/tests.yml/badge.svg)](https://github.com/pirl-unc/oncoref/actions/workflows/tests.yml)
+[![PyPI](https://img.shields.io/pypi/v/oncoref.svg)](https://pypi.org/project/oncoref/)
+
+Curated cancer reference data — cancer-type ontology, tumor mutational burden
+(TMB), incidence/mortality, checkpoint-inhibitor (ICI) response, per-cohort RNA-seq expression,
+and cancer-testis antigens — behind one small Python API, a data fetch/cache
+CLI, and a set of reference plots.
+
+## oncoref is the base layer
+
+`oncoref` is **designed as the base layer** of the openvax/PIRL stack — the
+intended single upstream **source of truth** for cancer reference data, meant to
+become a shared dependency of
+[pirlygenes](https://github.com/pirl-unc/pirlygenes),
+[trufflepig](https://github.com/pirl-unc/trufflepig), and
+[tsarina](https://github.com/pirl-unc/tsarina). Adoption is still in progress —
+most of these don't depend on it yet. Architecturally it stays at the bottom: it
+depends only on pandas / numpy / pyarrow / PyYAML, it **never imports its
+consumers** (data and logic flow only downward), and it **owns** these
+definitions rather than mirroring them from elsewhere.
+
+Anything that needs to know about
+
+- **gene expression of cancer samples** — per-cohort RNA-seq in a normalized,
+  comparable space: summary stats, tail-weighted percentiles, and medoid/exemplar
+  samples per cancer type/subtype;
+- **HPA protein / RNA** normal-tissue expression;
+- the **definition of cancer-testis antigens** — the HPA tissue-restriction call
+  over the candidate list (HPA-only; no MS/peptide layer);
+- the **ontology of cancer types** — codes, the parent/child hierarchy, subtypes,
+  families, characteristic driver fusions, and the cross-cutting MSI/POLE/HPV
+  groupings; and
+- **checkpoint-inhibitor response rates** and **TMB** per cancer type
+
+depends on `oncoref` — including `pirlygenes` (gene-set curation/analysis),
+`tsarina` (personalized target selection), `hitlist` (panel selection),
+`trufflepig` (sample classification), and anything else downstream.
+
+Everything keys on the cancer-type registry. The small curated tables ship in the
+wheel; the heavy per-cohort expression bundle downloads on first use from
+oncoref's own GitHub Release.
+
+## Install
+
+```bash
+pip install oncoref
+```
+
+## Python API
+
+```python
+import oncoref as od
+
+od.resolve_cancer_type("prostate")        # -> "PRAD"
+od.cancer_type_info("SARC_RMS_ARMS")      # full registry record + burden + tmb
+od.cancer_tmb("LUAD_EGFR")                # 6.9  (inherited from LUAD)
+od.cancer_burden("pancreas", metric="us_mortality_pct")
+od.burden_category("SARC_OS")             # -> "bone_and_joint" (incidence/mortality bucket)
+od.cancer_ici_response("SKCM")            # 42  (anti-PD-1 ORR %; fallback aPD-1 → aPD-L1 → combo)
+od.cancer_ici_response("SKCM", regimen="PD-1+CTLA-4")   # 57.6  (pin a regimen)
+
+# Cancer-testis antigens (HPA-derived tissue-restriction):
+od.cta_gene_names()                       # expressed CTA symbols (MAGEA4, CT83, …)
+od.cta_evidence()                         # full HPA restriction table
+
+# Per-cohort expression percentiles (downloads the data bundle on first use):
+od.cohort_gene_percentiles("PRAD")        # per-gene p0…p100 vector (within-cohort)
+od.within_sample_top_fraction("PRAD")     # per-gene frac of samples top-5% (within-sample)
+```
+
+### Domains
+
+- **Ontology** — `cancer_type_registry`, `resolve_cancer_type`,
+  `cancer_type_info`, `cancer_types_in_family`, `viral_status`, `fusion_status`,
+  the cohort vocabulary (`cohort_registry`, `cohort_aggregates`).
+- **TMB** — `cancer_tmb`, `cancer_tmb_df` (parent-chain inheritance).
+- **Incidence / mortality** — `cancer_burden`, `burden_category` (ACS / GLOBOCAN).
+- **Checkpoint response** — `cancer_ici_response` (ORR per type/regimen: anti-PD-1,
+  anti-PD-L1, anti-PD-1+anti-CTLA-4), with `cancer_apd1_response` the PD-1 shortcut.
+- **Expression** — `cohort_gene_percentiles`, `within_sample_top_fraction`,
+  `representative_cohort_samples` over the lazy-downloaded per-cohort bundle.
+- **Cancer-testis antigens** — `cta_gene_names`/`cta_gene_ids`, `cta_evidence`,
+  `synthesize_restriction` (HPA-only tissue-restriction; MS evidence stays in the
+  target-selection layer).
+- **HPA normal tissue** — `hpa_rna_consensus`, `hpa_normal_tissue` (IHC),
+  `hpa_single_cell`, and per-gene lookups (`gene_tissue_ntpm`,
+  `gene_protein_tissues`, `gene_cell_type_ntpm`) over HPA v23, fetched on demand
+  (`oncoref hpa fetch`).
+- **Genome reference** — `canonical_gene_id_and_name`, `find_gene_id_by_name`,
+  `find_gene_name_from_ensembl_{gene,transcript}_id`, `aggregate_gene_expression`
+  (pyensembl-backed symbol ↔ Ensembl-ID resolution). pyensembl ships with the
+  package, but resolution needs a downloaded human release once:
+  `pyensembl install --release 111 --species homo_sapiens` (the accessors return
+  `None` until then).
+- **Peptides** — `cta_specific_9mer_counts`, `cta_specific_9mer_load` (per-cohort
+  mean per-patient CTA-specific 9-mer load): 9-mers found in a CTA protein but in no
+  non-CTA protein, enumerated from the reference proteome and cached per release.
+- **Plots** (`pip install oncoref[plots]`) — `oncoref.plots.apd1_vs_tmb`,
+  `apd1_orr_bars`, `incidence_vs_mortality`, and the CTA/coverage figures.
+
+## CLI
+
+```bash
+oncoref cancer-type prostate     # registry info as JSON
+oncoref tmb LUAD_EGFR            # 6.9
+oncoref ici SKCM                # 42  (--regimen to pin, --all-regimens to compare)
+oncoref burden pancreas --metric us_mortality_pct
+oncoref cta --count             # number of expressed CTAs
+oncoref plot apd1-vs-tmb --out apd1_vs_tmb.png
+
+# expression-bundle cache (per-cohort expression):
+oncoref cache fetch             # download the ~340 MB bundle
+oncoref cache status            # which bundle paths are cached (no download)
+oncoref cache dir               # where the data bundle is cached
+oncoref cache prune --yes       # delete stale version caches
+oncoref hpa fetch               # download HPA reference data (RNA / IHC / single-cell)
+oncoref version
+```
+
+## Development
+
+```bash
+./develop.sh   # editable install with dev extras
+./format.sh    # ruff format
+./lint.sh      # ruff check + format --check
+./test.sh      # lint + pytest with coverage
+```
+
+## License
+
+Apache 2.0.