encode-toolkit 0.3.0__tar.gz

encode_toolkit-0.3.0/.claude/settings.json

@@ -0,0 +1,11 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(.venv/bin/python -m pytest:*)",
+      "Bash(.venv/bin/python -c:*)",
+      "Bash(grep -c '@mcp.tool':*)",
+      "Bash(wc -l:*)",
+      "Bash(ls:*)"
+    ]
+  }
+}

encode_toolkit-0.3.0/.claude-plugin/marketplace.json

@@ -0,0 +1,18 @@
+{
+  "name": "ammawla",
+  "owner": {
+    "name": "Dr. Alex M. Mawla, PhD"
+  },
+  "metadata": {
+    "description": "ENCODE Project genomics research infrastructure for Claude Code",
+    "homepage": "https://github.com/ammawla/encode-toolkit"
+  },
+  "plugins": [
+    {
+      "name": "encode-toolkit",
+      "version": "0.3.0",
+      "source": "./plugin",
+      "description": "20 ENCODE API tools + 47 expert skills for genomics research. Search experiments, download files with MD5 verification, run pipelines, and cross-reference 14 databases."
+    }
+  ]
+}

encode_toolkit-0.3.0/.claude-plugin/plugin.json

@@ -0,0 +1,126 @@
+{
+  "name": "encode-toolkit",
+  "description": "20 ENCODE API tools + 47 expert skills for genomics research. Search experiments, download files with MD5 verification, run pipelines, and cross-reference 14 databases.",
+  "version": "0.3.0",
+  "author": {
+    "name": "Dr. Alex M. Mawla, PhD",
+    "email": "ammawla@ucdavis.edu"
+  },
+  "homepage": "https://github.com/ammawla/encode-toolkit",
+  "repository": "https://github.com/ammawla/encode-toolkit",
+  "icon": "docs/icon.svg",
+  "license": "AGPL-3.0-only",
+  "keywords": [
+    "genomics",
+    "encode",
+    "bioinformatics",
+    "epigenomics",
+    "chip-seq",
+    "atac-seq",
+    "rna-seq",
+    "wgbs",
+    "hi-c",
+    "cut-and-run",
+    "pipeline",
+    "nextflow",
+    "GTEx",
+    "ClinVar",
+    "GWAS",
+    "JASPAR",
+    "CellxGene",
+    "gnomAD",
+    "Ensembl",
+    "UCSC",
+    "provenance",
+    "biology",
+    "science"
+  ],
+  "mcpServers": {
+    "encode-toolkit": {
+      "command": "npx",
+      "args": ["-y", "encode-toolkit@latest"]
+    }
+  },
+  "tools": [
+    {
+      "name": "encode_search_experiments",
+      "description": "Search ENCODE experiments with 20+ filters including assay type, organism, organ, biosample, target, and more."
+    },
+    {
+      "name": "encode_get_experiment",
+      "description": "Get full details for a specific experiment including all files, quality metrics, and audit info."
+    },
+    {
+      "name": "encode_list_files",
+      "description": "List files for a specific experiment with format/type filters."
+    },
+    {
+      "name": "encode_search_files",
+      "description": "Search files across all experiments with combined experiment + file filters."
+    },
+    {
+      "name": "encode_download_files",
+      "description": "Download specific files by accession to a local directory with MD5 verification."
+    },
+    {
+      "name": "encode_get_metadata",
+      "description": "List valid filter values for any search parameter."
+    },
+    {
+      "name": "encode_batch_download",
+      "description": "Search + download files in one step with preview mode."
+    },
+    {
+      "name": "encode_manage_credentials",
+      "description": "Store, check, or clear ENCODE credentials for restricted data access."
+    },
+    {
+      "name": "encode_get_facets",
+      "description": "Get live counts from ENCODE showing what data exists for given filters."
+    },
+    {
+      "name": "encode_get_file_info",
+      "description": "Get detailed metadata for a single file."
+    },
+    {
+      "name": "encode_track_experiment",
+      "description": "Track an experiment locally with publications, methods, and pipeline info."
+    },
+    {
+      "name": "encode_list_tracked",
+      "description": "List all tracked experiments with metadata and publication counts."
+    },
+    {
+      "name": "encode_get_citations",
+      "description": "Get publications for tracked experiments. Export as BibTeX or RIS."
+    },
+    {
+      "name": "encode_compare_experiments",
+      "description": "Analyze whether two experiments are compatible for combined analysis."
+    },
+    {
+      "name": "encode_log_derived_file",
+      "description": "Log derived files for provenance tracking back to ENCODE source data."
+    },
+    {
+      "name": "encode_get_provenance",
+      "description": "View provenance chains from derived files to source ENCODE data."
+    },
+    {
+      "name": "encode_export_data",
+      "description": "Export tracked experiments as CSV, TSV, or JSON with PMIDs for cross-referencing."
+    },
+    {
+      "name": "encode_summarize_collection",
+      "description": "Get grouped statistics of your tracked experiment collection."
+    },
+    {
+      "name": "encode_link_reference",
+      "description": "Link external references (PubMed, bioRxiv, ClinicalTrials, GEO) to experiments."
+    },
+    {
+      "name": "encode_get_references",
+      "description": "Get external references linked to experiments for cross-server workflows."
+    }
+  ]
+}

encode_toolkit-0.3.0/.cursor-plugin/marketplace.json

@@ -0,0 +1,27 @@
+{
+  "name": "ammawla",
+  "owner": {
+    "name": "Dr. Alex M. Mawla, PhD",
+    "email": "ammawla@ucdavis.edu"
+  },
+  "metadata": {
+    "description": "ENCODE Project genomics research infrastructure for Cursor",
+    "version": "0.3.0",
+    "homepage": "https://github.com/ammawla/encode-toolkit"
+  },
+  "plugins": [
+    {
+      "name": "encode-toolkit",
+      "source": ".",
+      "description": "20 ENCODE API tools + 47 expert skills for genomics research. Search experiments, download files with MD5 verification, run pipelines, and cross-reference 14 databases.",
+      "category": "science",
+      "tags": [
+        "genomics",
+        "bioinformatics",
+        "encode",
+        "epigenomics",
+        "pipelines"
+      ]
+    }
+  ]
+}

encode_toolkit-0.3.0/.cursor-plugin/plugin.json

@@ -0,0 +1,48 @@
+{
+  "name": "encode-toolkit",
+  "description": "20 ENCODE API tools + 47 expert skills for genomics research. Search experiments, download files with MD5 verification, run pipelines, and cross-reference 14 databases.",
+  "version": "0.3.0",
+  "author": {
+    "name": "Dr. Alex M. Mawla, PhD",
+    "email": "ammawla@ucdavis.edu"
+  },
+  "homepage": "https://github.com/ammawla/encode-toolkit",
+  "repository": "https://github.com/ammawla/encode-toolkit",
+  "license": "AGPL-3.0-only",
+  "logo": "docs/icon.svg",
+  "keywords": [
+    "genomics",
+    "encode",
+    "bioinformatics",
+    "epigenomics",
+    "chip-seq",
+    "atac-seq",
+    "rna-seq",
+    "wgbs",
+    "hi-c",
+    "cut-and-run",
+    "pipeline",
+    "nextflow",
+    "gtex",
+    "clinvar",
+    "gwas",
+    "jaspar",
+    "cellxgene",
+    "gnomad",
+    "ensembl",
+    "ucsc",
+    "provenance",
+    "biology",
+    "science"
+  ],
+  "rules": "rules",
+  "skills": "plugin/skills",
+  "commands": "commands",
+  "agents": "agents",
+  "mcpServers": {
+    "encode-toolkit": {
+      "command": "npx",
+      "args": ["-y", "encode-toolkit@latest"]
+    }
+  }
+}

encode_toolkit-0.3.0/.env.example

@@ -0,0 +1,9 @@
+# Optional: ENCODE access credentials for restricted data
+# Get these from your ENCODE account profile at https://www.encodeproject.org/
+# These are only needed for unreleased/restricted datasets.
+# Public data (most of ENCODE) requires no authentication.
+#
+# On first use, credentials are moved to your OS keyring (macOS Keychain,
+# Linux Secret Service, Windows Credential Locker) and removed from env vars.
+ENCODE_ACCESS_KEY=
+ENCODE_SECRET_KEY=

encode_toolkit-0.3.0/.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,79 @@
+name: Bug Report
+description: Report a bug in ENCODE Toolkit
+title: "[Bug]: "
+labels: ["bug"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for reporting a bug! Please fill out the sections below.
+
+  - type: dropdown
+    id: component
+    attributes:
+      label: Component
+      description: Which part of ENCODE Toolkit is affected?
+      options:
+        - MCP Tools (search, download, track)
+        - Skills (analysis, pipelines, external DBs)
+        - File Downloads / MD5 verification
+        - Credential Management
+        - SQLite Tracker
+        - Installation / Setup
+        - Other
+    validations:
+      required: true
+
+  - type: textarea
+    id: description
+    attributes:
+      label: What happened?
+      description: Clear description of the bug.
+      placeholder: "When I run encode_search_experiments with..."
+    validations:
+      required: true
+
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected behavior
+      description: What should have happened instead?
+    validations:
+      required: true
+
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: Steps to reproduce
+      description: Minimal steps to reproduce the issue.
+      placeholder: |
+        1. Run `encode_search_experiments(assay_title="ChIP-seq", organ="liver")`
+        2. See error...
+
+  - type: input
+    id: version
+    attributes:
+      label: Version
+      description: Output of `pip show encode-toolkit | grep Version`
+      placeholder: "0.3.0b1"
+
+  - type: dropdown
+    id: python
+    attributes:
+      label: Python version
+      options:
+        - "3.13"
+        - "3.12"
+        - "3.11"
+        - "3.10"
+
+  - type: dropdown
+    id: client
+    attributes:
+      label: MCP Client
+      options:
+        - Claude Code
+        - Claude Desktop
+        - VS Code (Continue/Cline)
+        - Cursor
+        - Other

encode_toolkit-0.3.0/.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,49 @@
+name: Feature Request
+description: Suggest a new feature or improvement
+title: "[Feature]: "
+labels: ["enhancement"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for your suggestion! Help us understand what you need.
+
+  - type: dropdown
+    id: category
+    attributes:
+      label: Category
+      options:
+        - New MCP Tool
+        - New Skill
+        - New Pipeline
+        - New Database Integration
+        - Existing Tool Enhancement
+        - Existing Skill Enhancement
+        - Documentation
+        - Other
+    validations:
+      required: true
+
+  - type: textarea
+    id: problem
+    attributes:
+      label: Problem or use case
+      description: What research problem does this solve?
+      placeholder: "I'm trying to analyze ENCODE CRISPR screen data and need..."
+    validations:
+      required: true
+
+  - type: textarea
+    id: solution
+    attributes:
+      label: Proposed solution
+      description: How should this work? Include example tool calls if possible.
+      placeholder: |
+        A new tool `encode_analyze_screen` that takes an experiment accession
+        and returns guide-level scores...
+
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternatives considered
+      description: Other approaches you've thought about.

encode_toolkit-0.3.0/.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,36 @@
+## Summary
+
+<!-- Brief description of changes (1-3 sentences) -->
+
+## Changes
+
+<!-- Bulleted list of what was changed -->
+
+-
+
+## Type
+
+<!-- Check the relevant option -->
+
+- [ ] Bug fix
+- [ ] New feature (tool, skill, pipeline)
+- [ ] Enhancement to existing feature
+- [ ] Documentation
+- [ ] Infrastructure (CI, packaging, config)
+
+## Testing
+
+<!-- How was this tested? -->
+
+- [ ] All 540 existing tests pass (`pytest tests/ -v`)
+- [ ] New tests added for new functionality
+- [ ] Lint passes (`ruff check src/`)
+- [ ] Format passes (`ruff format --check src/`)
+- [ ] Plugin validation passes (plugin.json valid, skills load)
+
+## Checklist
+
+- [ ] CHANGELOG.md updated
+- [ ] CLAUDE.md updated (if architecture/tools changed)
+- [ ] No secrets or credentials in code
+- [ ] No breaking changes to existing tool signatures

encode_toolkit-0.3.0/.github/dependabot.yml

@@ -0,0 +1,25 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    labels:
+      - "dependencies"
+    open-pull-requests-limit: 5
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    labels:
+      - "ci"
+    open-pull-requests-limit: 3
+
+  - package-ecosystem: "npm"
+    directory: "/"
+    schedule:
+      interval: "monthly"
+    labels:
+      - "dependencies"
+    open-pull-requests-limit: 2

encode_toolkit-0.3.0/.github/workflows/clone-count.yml

@@ -0,0 +1,102 @@
+name: Track Clone Count
+
+on:
+  push:
+    branches: [main]
+  schedule:
+    - cron: "0 0 * * *"  # Daily at midnight UTC
+  workflow_dispatch:
+
+env:
+  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
+
+jobs:
+  clone-count:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Fetch clone data from GitHub API
+        env:
+          GH_ACTOR: ${{ github.actor }}
+          GH_REPO: ${{ github.repository }}
+          SECRET_TOKEN: ${{ secrets.SECRET_TOKEN }}
+        run: |
+          curl --user "$GH_ACTOR:$SECRET_TOKEN" \
+            -H "Accept: application/vnd.github.v3+json" \
+            "https://api.github.com/repos/$GH_REPO/traffic/clones" \
+            > clone.json
+
+      - name: Create or retrieve gist for persistent storage
+        id: set_id
+        env:
+          GH_TOKEN: ${{ secrets.SECRET_TOKEN }}
+          GIST_SECRET: ${{ secrets.GIST_ID }}
+          GH_ACTOR: ${{ github.actor }}
+        run: |
+          if [ -n "$GIST_SECRET" ]; then
+              echo "GIST_ID found"
+              echo "GIST=$GIST_SECRET" >> "$GITHUB_OUTPUT"
+              curl "https://gist.githubusercontent.com/$GH_ACTOR/$GIST_SECRET/raw/clone.json" > clone_before.json
+              if grep -q '404: Not Found' clone_before.json; then
+                echo "GIST_ID not valid anymore. Creating another gist..."
+                gist_id=$(gh gist create clone.json | awk -F / '{print $NF}')
+                echo "$gist_id" | gh secret set GIST_ID
+                echo "GIST=$gist_id" >> "$GITHUB_OUTPUT"
+                cp clone.json clone_before.json
+                git rm --ignore-unmatch CLONE.md
+              fi
+          else
+              echo "GIST_ID not found. Creating a gist..."
+              gist_id=$(gh gist create clone.json | awk -F / '{print $NF}')
+              echo "$gist_id" | gh secret set GIST_ID
+              echo "GIST=$gist_id" >> "$GITHUB_OUTPUT"
+              cp clone.json clone_before.json
+          fi
+
+      - name: Accumulate clone statistics
+        run: |
+          curl https://raw.githubusercontent.com/MShawon/github-clone-count-badge/master/main.py > main.py
+          python3 main.py
+
+      - name: Update gist with accumulated data
+        env:
+          SECRET_TOKEN: ${{ secrets.SECRET_TOKEN }}
+          GH_ACTOR: ${{ github.actor }}
+          GH_REPO: ${{ github.repository }}
+          GIST: ${{ steps.set_id.outputs.GIST }}
+        run: |
+          content=$(sed -e 's/\\/\\\\/g' -e 's/\t/\\t/g' -e 's/"/\\"/g' -e 's/\r//g' "clone.json" | sed -E ':a;N;$!ba;s/\r{0,1}\n/\\n/g')
+          echo "{\"description\": \"$GH_REPO clone statistics\", \"files\": {\"clone.json\": {\"content\": \"$content\"}}}" > post_clone.json
+          curl -s -X PATCH \
+            --user "$GH_ACTOR:$SECRET_TOKEN" \
+            -H "Content-Type: application/json" \
+            -d @post_clone.json "https://api.github.com/gists/$GIST" > /dev/null 2>&1
+
+          if [ ! -f CLONE.md ]; then
+            shields="https://img.shields.io/badge/dynamic/json?color=success&label=Clone&query=count&url="
+            url="https://gist.githubusercontent.com/$GH_ACTOR/$GIST/raw/clone.json"
+            repo="https://github.com/$GH_REPO"
+            {
+              echo ''
+              echo '**Badge Markdown**'
+              echo ''
+              echo '```markdown'
+              echo "[![GitHub Clones]($shields$url&logo=github)]($repo)"
+              echo '```'
+            } > CLONE.md
+
+            git add CLONE.md
+            git config --global user.name "GitHub Action"
+            git config --global user.email "action@github.com"
+            git commit -m "Create clone count badge"
+          fi
+
+      - name: Push changes
+        env:
+          SECRET_TOKEN: ${{ secrets.SECRET_TOKEN }}
+          GH_REPO: ${{ github.repository }}
+        run: |
+          git remote set-url origin "https://x-access-token:$SECRET_TOKEN@github.com/$GH_REPO.git"
+          git push origin HEAD:main || echo "Nothing to push"

encode_toolkit-0.3.0/.github/workflows/lint.yml

@@ -0,0 +1,27 @@
+name: Lint
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+
+      - name: Install ruff
+        run: pip install ruff
+
+      - name: Check formatting
+        run: ruff format --check src/ tests/
+
+      - name: Check linting
+        run: ruff check src/ tests/