bionexuslab 0.1.0__tar.gz

bionexuslab-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,47 @@
+name: ci
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  core:  # P1: fast, dependency-light, no network
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with: { python-version: "3.12" }
+      - run: pip install pydantic pytest && pip install -e . --no-deps
+      - run: python -m pytest tests/ -q    # includes the anti-bloat import scan
+
+  example:  # P8: full round on the simulator
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with: { python-version: "3.12" }
+      - run: pip install pydantic pytest pyyaml && pip install -e . --no-deps
+      - run: python examples/iteration_loop.py
+      - run: python -m bionexus.cli prove branch-root --db bionexus.db
+
+  full-campaign:  # P8: entire pipeline flow on the virtual lab, then playback
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with: { python-version: "3.12" }
+      - run: pip install pydantic pytest && pip install -e . --no-deps
+      - run: python examples/full_campaign.py
+      - run: python -m bionexus.cli prove campaign-root --db campaign.db
+      - run: python -m pytest tests/ -q   # now includes recording-playback test
+
+  yaml-workflow:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with: { python-version: "3.12" }
+      - run: pip install pydantic pyyaml && pip install -e . --no-deps
+      - run: python -m bionexus.cli run examples/workflow.yml
+      - run: python -m bionexus.cli prove demo-run

bionexuslab-0.1.0/.github/workflows/release.yml

@@ -0,0 +1,41 @@
+name: release
+
+# Publishes to PyPI via Trusted Publishing (no token in repo).
+# One-time setup on pypi.org: add a pending publisher
+#   project: bionexuslab · owner: rbalachandar · repo: bionexus
+#   workflow: release.yml · environment: pypi
+on:
+  push:
+    tags: ["v*"]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with: { python-version: "3.12" }
+      - run: pip install build && python -m build
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write  # Trusted Publishing (OIDC)
+    steps:
+      - uses: actions/download-artifact@v4
+        with: { name: dist, path: dist/ }
+      - uses: pypa/gh-action-pypi-publish@release/v1
+
+  smoke:  # install the published wheel and run one command
+    needs: publish
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/setup-python@v5
+        with: { python-version: "3.12" }
+      - run: pip install bionexuslab==${GITHUB_REF_NAME#v} && bn new-adapter lab smoke --dir /tmp && ls /tmp/smoke_adapter

bionexuslab-0.1.0/.gitignore

@@ -0,0 +1,11 @@
+.DS_Store
+*.swp
+.venv/
+__pycache__/
+*.egg-info/
+.pytest_cache/
+campaign.db
+examples/_campaign_training.jsonl
+examples/_campaign_recording.json
+examples/report_example.html
+.data/

bionexuslab-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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.

bionexuslab-0.1.0/PKG-INFO

@@ -0,0 +1,202 @@
+Metadata-Version: 2.5
+Name: bionexuslab
+Version: 0.1.0
+Summary: Lean open-source framework for agentic drug discovery — pluggable models, bio tools, labs, and sandboxes behind five core interfaces.
+License: Apache-2.0
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: pydantic>=2.5
+Provides-Extra: bio-rdkit
+Requires-Dist: rdkit>=2023.9; extra == 'bio-rdkit'
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == 'dev'
+Provides-Extra: lab-imaging
+Requires-Dist: numpy>=1.24; extra == 'lab-imaging'
+Provides-Extra: models-openai
+Requires-Dist: httpx>=0.27; extra == 'models-openai'
+Provides-Extra: sandbox-agentenv
+Requires-Dist: httpx>=0.27; extra == 'sandbox-agentenv'
+Provides-Extra: store-postgres
+Requires-Dist: psycopg[binary]>=3; extra == 'store-postgres'
+Description-Content-Type: text/markdown
+
+# BioNexus
+
+A **lean open-source framework for agentic drug discovery** — pluggable models, bio
+tools, labs, and sandboxes behind five core interfaces.
+
+Core dependencies: `pydantic` only. Everything else (models, labs, sandboxes,
+stores) is an adapter you opt into.
+
+## Quickstart (simulator-first, no network needed)
+
+```sh
+python -m venv .venv && .venv/bin/pip install -e . dev-dependencies...  # see pyproject
+.venv/bin/pip install -e ".[dev]"
+.venv/bin/python examples/iteration_loop.py   # full design round on the virtual lab
+.venv/bin/python -m pytest                    # 11 tests, <1s, offline
+```
+
+The example runs: candidate generation → hypothesis tournament → human-approvable
+protocol → **safety engine** → virtual wet lab → fork branch → safety rejection demo →
+hash-chained provenance. See [`docs/PLAN.md`](docs/PLAN.md) for the full build plan.
+
+### Simulated lab devices with image readouts
+
+The virtual lab goes one level deeper: a simulated **imaging plate reader**. A
+protocol run captures raw fluorescence micrographs per well (96-well plate), an
+analysis pipeline fits dose–response IC50s **from the images**, and assay QC is a
+Z' factor computed from controls. Measured IC50s recover the seeded ground truth
+within realistic noise, and the raw well images are kept as evidence that agents
+(or vision-capable LLMs) can inspect:
+
+```sh
+.venv/bin/pip install numpy                       # [lab-imaging] extra
+.venv/bin/python examples/demo_imaging.py
+# run img-c2f0183b: Z'=0.938 (controls PASS)
+#   compound    measured IC50   ground truth
+#   C2              11.98 uM      10.85 uM
+# raw evidence: 14 well images in .data/images/
+```
+
+Failure modes are simulated too: well artifacts (pipetting spikes, bubbles, edge
+effects) are flagged, weak compounds are right-censored (no IC50 — test higher
+concentrations), and runs failing Z' QC are marked unusable. See
+[`docs/virtual-lab.md`](docs/virtual-lab.md).
+
+**CLI:**
+
+```sh
+bn run examples/workflow.yml       # tournament + assay on the configured lab
+bn sim                             # reference round on the virtual lab
+bn prove <branch> --html out.html  # tamper-evident provenance + shareable report
+bn mcp                             # MCP server: drive BioNexus from Claude/Cursor
+```
+
+**Works with Claude / Cursor / any MCP client** — add to your MCP config:
+
+```json
+{"bionexus": {"command": "bn", "args": ["mcp"]}}
+```
+
+Exposes `generate_candidates`, `run_assay` (dose-response + IC50),
+`propose_hypothesis`, and `list_lab_capabilities` as agent tools.
+
+**Tutorials:** [`notebooks/`](notebooks/) — run a campaign · write an adapter · bring your own model.
+
+**Extend it:**
+
+```sh
+bn new-adapter lab my_robot      # scaffold a tested LabAdapter in seconds
+bn new-adapter tool my_docking --cap e.sim.docking
+```
+
+See [`docs/ADAPTERS.md`](docs/ADAPTERS.md) and the
+[stability policy](docs/stability.md) — the five core interfaces are stable
+surfaces with additive-evolution guarantees.
+
+| Doc | Contents |
+|---|---|
+| [`docs/QUICKSTART.md`](docs/QUICKSTART.md) | install, run, workflows |
+| [`docs/ADAPTERS.md`](docs/ADAPTERS.md) | authoring adapters (labs, models, tools, stores) |
+| [`docs/SAFETY.md`](docs/SAFETY.md) | safety rules, LabGateway, audit trail |
+| [`docs/domain-review.md`](docs/domain-review.md) | flow fidelity review vs. the real drug-discovery cycle |
+| [`docs/benchmarks.md`](docs/benchmarks.md) | public datasets (MoleculeNet, TDC, DOCKSTRING, ProteinGym) + first benchmark results |
+| [`docs/virtual-lab.md`](docs/virtual-lab.md) | simulated devices, image-based readouts, QC and failure modes |
+| [`docs/security.md`](docs/security.md) | threat model, trust boundaries, agent capability matrix |
+| [`docs/stability.md`](docs/stability.md) | versioning, stability tiers, deprecation policy |
+| [`docs/PLAN.md`](docs/PLAN.md) | build plan, principles, guardrails |
+
+### Five core interfaces (everything is one of these)
+
+| Interface | Adapters (now → roadmap) |
+|---|---|
+| `ModelProvider` | openai_compat (OpenAI/ollama/vLLM/stub) → anthropic, gemini |
+| `LabAdapter` (+ `SafetyEngine`, `LabGateway`) | simulator, imaging-simulator (synthetic plate images + analysis + Z' QC) → opentrons, cloud labs |
+| `Sandbox` | local (copy-on-fork) → AgentENV (real fork/snapshot) |
+| `ProvenanceStore` | sqlite → postgres, s3-worm |
+| `BioTool` | rdkit descriptors → docking, ADMET, ESMFold |
+
+## Architecture Diagrams
+
+Hand-drawn blueprint-style diagrams (SVG — rendered directly on GitHub):
+
+**1 · Layered View** — L0 governance → L3 infrastructure, with the five architectural blocks between.
+
+![Layered View](diagrams/svg/01-layered-view.svg)
+
+**2 · Design Iteration Loop** — one active-learning round, from dossier to next-round proposals.
+
+![Design Iteration Loop](diagrams/svg/02-iteration-loop.svg)
+
+**3 · Hypothesis Tournament** — Generate → Reflect → Rank → Evolve, plus the fine-tuning flywheel.
+
+![Hypothesis Tournament](diagrams/svg/03-tournament.svg)
+
+**4 · Wet-Lab Round Trip** — protocol through the safety boundary, instruments, and back as provenance.
+
+![Wet-Lab Round Trip](diagrams/svg/04-wetlab-roundtrip.svg)
+
+**5 · Fork / Snapshot Branching** — sandbox lifecycle as experiment tree.
+
+![Fork / Snapshot Branching](diagrams/svg/05-branching.svg)
+
+**6 · Campaign Pipeline** — target ID through trial design with human gates and failure loops.
+
+![Campaign Pipeline](diagrams/svg/06-campaign.svg)
+
+Styled HTML versions (dark blueprint pages with legends/captions) live in
+[`diagrams/artifacts/`](diagrams/artifacts/) — open locally in a browser.
+
+## Repository Layout
+
+| Path | Contents |
+|---|---|
+| [`docs/architecture.md`](docs/architecture.md) | Architectural blocks A–F, components, responsibilities, interfaces |
+| [`docs/flows.md`](docs/flows.md) | End-to-end flows: design iteration loop, fork/branch, review gates, wet-lab round trip |
+| [`docs/blocks/`](docs/blocks/) | One deep-dive doc per block (A–F) |
+| [`docs/research-landscape.md`](docs/research-landscape.md) | Review vs. Google AI co-scientist, Anthropic, Isomorphic, Cradle, Lila, FutureHouse, Coscientist, OpenAI Rosalind |
+| [`contracts/`](contracts/README.md) | The five shared integration contracts (StageTask, ToolInvocation, ProtocolSubmission, AssayResult, ProvenanceRecord) |
+| [`diagrams/`](diagrams/) | SVG diagrams + styled HTML artifact pages |
+
+## Architectural Blocks at a Glance
+
+| Block | Name | Layer | Can start with |
+|---|---|---|---|
+| [A](docs/blocks/A-orchestration.md) | Workflow & Orchestration | L1 | stub tool endpoints |
+| [B](docs/blocks/B-agents.md) | Agent Workforce | L2 | virtual lab + mocked models |
+| [C](docs/blocks/C-models-knowledge.md) | Model & Knowledge Services | L2 | open-source FMs on a GPU box |
+| [D](docs/blocks/D-lab-execution.md) | Lab Execution | L2/L3 | full virtual lab simulator |
+| [E](docs/blocks/E-simulation-data.md) | Simulation & Data Services | L2 | existing MD/docking tools |
+| [F](docs/blocks/F-infrastructure.md) | Infrastructure (AgentENV) | L3 | exists — integrate |
+
+## Design Principles
+
+1. **Contract-first integration** — blocks communicate only through five versioned
+   schemas; nothing else couples them.
+2. **Hardware behind an abstraction** — agents see the Instrument Abstraction Layer
+   (IAL) only; a Virtual Lab Simulator is a drop-in stand-in for real robots.
+3. **State is snapshot-able** — every experiment branch runs in a sandbox that can be
+   forked, paused at review gates, and replayed for audits.
+4. **Provenance is immutable** — every artifact carries full lineage (inputs, model
+   versions, prompts, instrument run IDs) in WORM storage.
+5. **Safety is non-bypassable** — a policy engine sits in the physical-action path,
+   outside any agent's trust boundary.
+
+## References & Sources
+
+The architecture draws on published work from teams operating in this space. The
+full review — what each system does, how it compares, and which learnings were
+folded into this design — is in [`docs/research-landscape.md`](docs/research-landscape.md).
+
+**Key sources:**
+
+- Google — [AI co-scientist](https://research.google/blog/accelerating-scientific-breakthroughs-with-an-ai-co-scientist/) ([paper](https://arxiv.org/abs/2502.18864)) · [AlphaFold 3](https://www.nature.com/articles/s41586-024-07487-w) · [Isomorphic Labs Drug Design Engine](https://www.isomorphiclabs.com/articles/the-isomorphic-labs-drug-design-engine-unlocks-a-new-frontier) · [Bioresilience approach](https://www.isomorphiclabs.com/articles/our-approach-to-bioresilience)
+- Anthropic — [Claude for Life Sciences](https://www.anthropic.com/news/claude-for-life-sciences) · [Model Hardware Standard](https://www.anthropic.com/news/model-hardware-standard-research-preview)
+- Cradle Bio — [Platform](https://www.cradle.bio/platform) · [Series B / wet-lab expansion](https://techcrunch.com/2024/11/26/cradle-builds-out-its-protein-design-ai-platform-and-wet-lab-with-73m-in-new-funding/)
+- FutureHouse — [Robin multi-agent system](https://www.futurehouse.org/research-announcements)
+- Lila Sciences — [Agent-driven science on NVIDIA BioNeMo](https://www.lilasciences.com/news/building-the-agent-driven-era-of-science-with-nvidia-bionemo-agent-toolkit)
+- Helical — [Virtual AI lab / Helix-mRNA FM](https://www.helical.bio/)
+- Coscientist (CMU) — [Autonomous chemical research with LLMs + robotics, Nature 2023](https://www.nature.com/articles/s41586-023-06792-0)
+- OpenAI + Retro Biosciences — [GPT-4b micro protein engineering, MIT Tech Review](https://www.technologyreview.com/2024/12/09/1108188/openai-model-for-protein-engineering-gpt-4b-micro-retro-biosciences/)
+- Chai Discovery — [chai-1/chai-2 structure & antibody models](https://www.chaidiscovery.com/)