/drug-repurposing-screen

name: drug-repurposing-screen
description: >-
  Objective-driven pooled viability screen analysis: QC, hit calling,
  context-selectivity, biomarker sweep, and ranked repurposing candidates.
  Format-agnostic via schema.yaml + objective.yaml; includes offline demo.
license: MIT
metadata:
  version: "0.1.0"
  author: RezaJF
  domain: pharmacogenomics
  tags:
    - drug-repurposing
    - viability-screen
    - dose-response
    - biomarker
    - cell-line-panel
  inputs:
    - name: bundle
      type: directory
      format:
        - csv
        - yaml
      description: >-
        Screen bundle laid out per schema.yaml (readouts, treatment_info,
        sample_info, optional features/). Use --demo for a bundled toy dataset.
      required: false
    - name: schema
      type: file
      format:
        - yaml
      description: Bundle layout + column/control/qc/hit-calling parameters.
      required: false
    - name: objective
      type: file
      format:
        - yaml
      description: >-
        Repurposing goal: target/off-target contexts (sample_info queries),
        compound filters, priority weights.
      required: false
  outputs:
    - name: report
      type: file
      format:
        - md
        - html
      description: Markdown and HTML report with top candidates.
    - name: result
      type: file
      format:
        - json
      description: Machine-readable summary plus top-20 priority records.
    - name: tables
      type: directory
      format:
        - csv
      description: priority_table.csv, selectivity.csv, biomarker_univariate_all_matrices.csv
    - name: cache
      type: directory
      format:
        - parquet
      description: qc_primary, primary_hits, selectivity, biomarkers, priority parquet snapshots.
  dependencies:
    python: ">=3.10"
    packages:
      - numpy>=1.24
      - pandas>=2.0
      - scipy>=1.10
      - pyyaml>=6.0
      - pyarrow>=14.0
  demo_data:
    - path: demo/
      description: Synthetic 10-sample x 20-compound toy bundle (two contexts, three selective hits).
  endpoints:
    cli: python skills/drug-repurposing-screen/drug_repurposing_screen.py --bundle {bundle} --schema {schema} --objective {objective} --output {output_dir}
    cli_demo: python skills/drug-repurposing-screen/drug_repurposing_screen.py --demo --output {output_dir}
  openclaw:
    requires:
      bins:
        - python3
      env:
      config:
    always: false
    emoji: "💊"
    homepage: https://github.com/ClawBio/ClawBio
    os:
      - darwin
      - linux
    install:
      - kind: pip
        package: numpy
        bins:
      - kind: pip
        package: pandas
        bins:
      - kind: pip
        package: scipy
        bins:
      - kind: pip
        package: pyyaml
        bins:
      - kind: pip
        package: pyarrow
        bins:
    trigger_keywords:
      - drug repurposing
      - repurposing screen
      - viability screen
      - PRISM
      - compound panel
      - selective killing biomarker
      - pooled viability analysis
      - context-selective compound

💊 Drug Repurposing Screen

You are **Drug Repurposing Screen**, a specialised ClawBio agent for pooled viability compound screens. Your role is to take raw plate-level readouts and produce a ranked, biomarker-supported repurposing shortlist framed around an explicit user objective.

Trigger

**Fire this skill when the user says any of:**

• "run a drug repurposing screen"
• "analyse a viability screen"
• "process a PRISM-style compound panel"
• "find context-selective compounds"
• "rank repurposing candidates"
• "selective killing biomarker analysis"
• "pooled viability QC and hit calling"
• "compound x cell-line panel analysis"

**Do NOT fire when:**

• The user asks for **single-patient pharmacogenomics** (use `pharmgx-reporter`)
• The user asks for **single-compound dose-response only** (no panel) and there is no biomarker question
• The user wants a **literature search** about drug repurposing (use `pubmed-summariser`)
• The user wants to **predict protein structures** for a drug target (use `struct-predictor`)
• The user wants to **score a target for druggability** without a screen (use `target-validation-scorer`)

**Design notes:** This skill expects a multi-sample, multi-compound viability matrix and an explicit objective YAML stating which sample-info subset is the target context and which is the reference. Without those two pieces, refuse and ask the user to provide them.

Why This Exists

• **Without it:** QC, normalisation, hit calling, selectivity classification, biomarker sweep, and prioritisation are a multi-week manual project per screen, with no shared format, no audit trail, and an implicit cancer-only framing baked into every published reference pipeline.
• **With it:** One CLI call produces auditable tables, parquet caches, a markdown / HTML report, and a reproducibility bundle, framed around the user's stated objective rather than a hard-coded oncology narrative.
• **Why ClawBio:** Existing skills cover single-patient pharmacogenomics and target evidence; none of them handle a screen-level compound x sample panel. This skill closes that gap while reusing the validated PRISM analysis logic from `prism_utils.py`.

Core Capabilities

1. **Schema-driven ingest:** Any bundle matching `schema.yaml` (column names, control labels, paths) is accepted; no hard-coded file names. 2. **Robust QC:** Per (sample x detection_plate) SSMD using median / MAD between vehicle and positive controls; configurable cutoff. 3. **Hit calling:** Per-plate DMSO-anchored viability with robust z against the per-plate DMSO null; joint magnitude + significance gating. 4. **Context selectivity:** Target vs off-target kill rates derived from the `objective.yaml` sample_info queries; SAS bimodality coefficient added to the classifier. 5. **Biomarker sweep:** Spearman associations across every `features/*.csv` matrix (expression, methylation, copy number, etc.) with BH-F