quark-tre-sdk 0.1.0__tar.gz

quark_tre_sdk-0.1.0/.claudeignore

@@ -0,0 +1,2 @@
+!/main.py
+!/local.py

quark_tre_sdk-0.1.0/.env.example

@@ -0,0 +1,21 @@
+# quark-tre-sdk configuration
+# Copy this file to .env and fill in your values.
+# The SDK will auto-load .env on startup if python-dotenv is installed.
+
+# Required: Athena data catalog name registered for the Quark connector
+TRE_CATALOG=your-catalog
+
+# Required: Athena workgroup to submit queries under (managed workgroup, no S3 staging dir needed)
+TRE_WORKGROUP=your-workgroup
+
+# Optional: AWS region. Auto-detected from EC2 IMDSv2 when running on a TRE workstation.
+# Set explicitly if running outside EC2 or IMDSv2 is not available.
+# AWS_DEFAULT_REGION=us-east-1
+
+# AWS credentials — resolved by boto3 in standard order:
+#   1. Env vars below
+#   2. ~/.aws/credentials
+#   3. EC2 instance profile (recommended on TRE workstations)
+# AWS_ACCESS_KEY_ID=
+# AWS_SECRET_ACCESS_KEY=
+# AWS_SESSION_TOKEN=

quark_tre_sdk-0.1.0/.github/workflows/publish-pypi.yaml

@@ -0,0 +1,36 @@
+name: Publish Python SDK to PyPI
+
+on:
+  push:
+    tags:
+      - "v*"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: astral-sh/setup-uv@v5
+
+      - name: Build
+        run: uv build
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - uses: pypa/gh-action-pypi-publish@release/v1

quark_tre_sdk-0.1.0/.gitignore

@@ -0,0 +1,53 @@
+# Python
+__pycache__/
+*.py[cod]
+*.pyo
+*.pyd
+*.so
+*.egg
+*.egg-info/
+dist/
+build/
+.eggs/
+.cache/
+
+# Virtual environments
+.venv/
+venv/
+env/
+
+# uv
+.uv/
+
+# Testing
+.pytest_cache/
+.coverage
+coverage.xml
+htmlcov/
+
+# Type checkers
+.mypy_cache/
+.ruff_cache/
+
+# Jupyter
+.ipynb_checkpoints/
+*.ipynb
+
+# Local dev / secrets
+.env
+
+# OS
+.DS_Store
+Thumbs.db
+
+# IDE
+.idea/
+.vscode/
+*.swp
+
+# Build
+*.whl
+*.tar.gz
+/main.py
+/local.py
+/tmp

quark_tre_sdk-0.1.0/LICENSE

@@ -0,0 +1,182 @@
+                                 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 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, as submitted to the 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 lists, discussion forums, and other communication systems 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 designated in writing by the copyright owner as "Not a
+      Contribution."
+
+      "Contributor" shall mean Licensor and any Legal Entity on behalf of
+      whom a Contribution has been received by the Licensor and included
+      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 the 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 any patent
+      claim embodied in 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, You must include a readable copy of the
+          attribution notices contained within such NOTICE file, 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 in addition 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 license statement for Your modifications and
+      may provide additional grant of rights to use, copy, modify, merge,
+      publish, distribute, sublicense, and/or sell copies of the Work
+      derivative works, 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 reproducing 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 exemplary 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 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 offer only
+      conditions consistent with this License.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2024 Invisibl Cloud
+
+   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.

quark_tre_sdk-0.1.0/Makefile

@@ -0,0 +1,25 @@
+.PHONY: install test check lint fmt build clean
+
+install:
+	uv sync --extra dev --extra dotenv
+
+test:
+	uv run pytest tests/ -v
+
+check:
+	uv run python -m py_compile quark_tre_sdk/tre.py quark_tre_sdk/__init__.py
+	@echo "syntax OK"
+
+lint: check
+	uv run ruff check quark_tre_sdk/
+	uv run ruff format --check quark_tre_sdk/
+
+fmt:
+	uv run ruff format quark_tre_sdk/
+	uv run ruff check --fix quark_tre_sdk/
+
+build:
+	uv build
+
+clean:
+	rm -rf dist/ .pytest_cache/ __pycache__ quark_tre_sdk/__pycache__

quark_tre_sdk-0.1.0/PKG-INFO

@@ -0,0 +1,15 @@
+Metadata-Version: 2.4
+Name: quark-tre-sdk
+Version: 0.1.0
+Summary: Python SDK for the Quark TRE Platform
+License-File: LICENSE
+Requires-Python: >=3.9
+Requires-Dist: pandas>=1.5
+Requires-Dist: pyathena[pandas]>=3.0
+Provides-Extra: dev
+Requires-Dist: pytest-mock>=3.0; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Requires-Dist: python-dotenv>=1.0; extra == 'dev'
+Requires-Dist: ruff>=0.4; extra == 'dev'
+Provides-Extra: dotenv
+Requires-Dist: python-dotenv>=1.0; extra == 'dotenv'

quark_tre_sdk-0.1.0/README.md

@@ -0,0 +1,174 @@
+# quark-tre-sdk
+
+Python SDK for the Quark TRE Platform.
+
+## Install
+
+```bash
+pip install quark-tre-sdk
+
+# With .env file support
+pip install 'quark-tre-sdk[dotenv]'
+```
+
+Requires Python 3.9+. Dependencies: `pyathena[pandas]`, `pandas`.
+
+```bash
+# Optional: CloudWatch log streaming (for .logs())
+pip install boto3
+
+# Optional: Parquet export (for .export(..., format="parquet"))
+pip install pyarrow
+```
+
+The package ships a `py.typed` marker, so mypy and Pyright pick up type hints automatically with no extra configuration.
+
+## Quickstart
+
+```python
+from quark_tre_sdk import TRE, parse_filter
+
+# Config from TRE_CATALOG / TRE_WORKGROUP env vars; region auto-detected via EC2 IMDSv2
+# Auto-loads .env if python-dotenv is installed
+tre = TRE()
+
+# -- Discover accessible cohorts --
+df = tre.cohorts()   # cohort_id, cohort_name, create_date, dataset_names
+
+# -- Cohort analytics --
+ctx = tre.cohort("my-cohort")
+
+df = ctx.demographics()               # gender / race / ethnicity / yearOfBirth / personsCount
+df = ctx.conditions()                 # top conditions + unique condition list
+df = ctx.drugs()                      # top drugs + unique drug list
+df = ctx.age_plot()                   # age at first drug exposure
+df = ctx.age_plot(plot="condition")   # age at first condition occurrence
+df = ctx.km_survival()                # Kaplan-Meier survival (single-arm)
+df = ctx.km_survival_multi_arm(1125315, 1127078)  # KM two-arm with log-rank test
+df = ctx.person_count()              # total persons in cohort
+df = ctx.persons(limit=1000)         # cohort members — limit required, max 10000
+df = ctx.persons(limit=1000, offset=1000)  # paginate
+df = ctx.datasets()                  # datasets the cohort spans
+
+# -- Per-person --
+p = ctx.person("P00123456")
+
+df = p.drug_timeline()            # one row per drug exposure
+df = p.drug_table()               # full drug table with dosing
+df = p.condition_timeline()       # one row per condition occurrence
+df = p.condition_table()          # full condition table
+df = p.variant_frequency()        # variant mutation frequency by specimen
+df = p.person_profile()           # demographic profile
+df = p.person_sankey()            # condition status for Sankey diagram
+df = p.specimen_procedure_table() # specimens + linked procedures
+
+# -- Per-specimen --
+s = ctx.specimen("SP-2024-0042")
+
+df = s.specimen_detail()                        # specimen metadata
+df = s.specimen_variants()                      # full variant annotation table (28 columns)
+df = s.specimen_variants(limit=100)             # paginated
+df = s.specimen_variants(limit=100, offset=100) # next page
+
+# -- Specimen summary (cohort-level) --
+df = ctx.specimen_summary()         # aggregate specimen counts, types, days range
+
+# -- Cache management --
+info = ctx.cache_info()             # L1/L2 cache status for this cohort's agg queries
+ctx.invalidate_cache()              # flush cached results (force re-run on next query)
+
+# -- Preflight validation --
+result = ctx.validate()             # dict: ok, cohort, table_count, tables, missing, errors
+if not result["ok"]:
+    print(result["errors"])
+
+# -- Export to file (Parquet / CSV / JSON) --
+n = ctx.export_parquet("demographics_all", "/tmp/demo.parquet")   # Parquet (requires pyarrow)
+n = ctx.export_csv("persons", "persons.csv")                      # CSV
+n = ctx.export_json("conditions_all", "conditions.json")          # JSON
+# Or use the generic form with format= argument:
+n = ctx.export("demographics_all", "/tmp/demo.parquet", format="parquet")
+
+# -- Async queries (non-blocking, for slow 10-30s queries) --
+future = ctx.age_plot_async(plot="condition")   # starts immediately, returns QueryFuture
+future2 = ctx.km_survival_async()              # fire a second query in parallel
+df1 = future.result()                          # block until done, raises on error
+df2 = future2.result()
+future.done()                                  # True / False — non-blocking poll
+future.cancel()                                # cancel if not yet started
+
+# Generic async variant — works for any CohortContext method:
+future = ctx.async_query("km_survival_multi_arm", concept_id_1=1125315, concept_id_2=1127078)
+df = future.result()
+
+# -- Debugging: CloudWatch Lambda logs --
+# Requires boto3 and logs:FilterLogEvents IAM permission on /aws/lambda/{workgroup}
+df = ctx.age_plot(plot="condition") # or any query that triggers the connector
+ctx.logs()                          # stream Lambda logs for the last query
+ctx.logs(minutes=10)                # look back further (default 5 min)
+ctx.logs(show_sql=True)             # include full SQL in log output (truncated by default)
+tre.logs()                          # same, at TRE level
+
+# -- Global analytics (cross-cohort, no restriction) --
+# tre.cohort() with no args is equivalent to tre.global_()
+g = tre.cohort()
+
+df = g.demographics()
+df = g.conditions()
+df = g.drugs()
+df = g.age_plot(plot="condition")
+df = g.km_survival()
+df = g.person_count()
+
+# -- Filtering global analytics --
+# Pass a SQL-like expression string or a StructuredQuery dict
+df = g.demographics(filter="drug = 1125315")
+df = g.person_count(filter="drug = 1125315 AND gene IN ('EGFR', 'KRAS')")
+df = g.demographics(filter="(drug = 1125315 OR drug = 1127078) AND gender = 8507")
+
+# Field shortcuts: drug, condition, gender, race, ethnicity, dataset
+# Operators: =  !=  <  >  <=  >=  IN  NOT IN
+# Logical:   AND  OR  ( )
+
+# Inspect the produced StructuredQuery dict before sending
+print(parse_filter("drug = 1125315 AND gene = 'EGFR'"))
+
+# -- Schema / table / column discovery --
+df = tre.schemas()                              # all connector schemas
+df = tre.cohort("my-cohort").tables()         # virtual tables in cohort's _agg schema
+df = tre.cohort("my-cohort").columns("demographics_all")  # columns for a table
+df = tre.global_().tables()                    # virtual tables in global_agg
+df = tre.global_().columns("conditions_all")
+
+# -- Raw SQL via schema properties --
+conn = tre._connect()
+import pandas as pd
+df = pd.read_sql(f'SELECT * FROM {ctx.agg_schema}."demographics_all"', conn)
+df = pd.read_sql(f'SELECT * FROM {ctx.omop_schema}."drug_exposure" LIMIT 10', conn)
+```
+
+## Configuration
+
+| Priority | Source | Variables |
+|---|---|---|
+| 1 | Constructor args | `catalog=`, `workgroup=`, `region=` |
+| 2 | Environment vars | `TRE_CATALOG`, `TRE_WORKGROUP`, `AWS_DEFAULT_REGION` |
+| 3 | EC2 IMDSv2 | region only |
+
+Copy `.env.example` → `.env` and fill in your values. With `pip install 'quark-tre-sdk[dotenv]'` the SDK loads `.env` automatically.
+
+The Athena connection is lazy — created on the first query call. Managed workgroups are supported (no S3 staging dir required).
+
+## Development
+
+```bash
+make install   # install dev dependencies
+make check     # syntax check (py_compile)
+make test      # run tests
+make lint      # ruff check + format check
+make fmt       # auto-format
+```
+
+## Documentation
+
+Full API reference: [`docs/sdk-reference.md`](docs/sdk-reference.md)