@bgicli/bgicli 2.1.1 → 2.2.0

package/data/skills/biomaster-workflows/SKILL.md

@@ -0,0 +1,55 @@
+<!--
+# COPYRIGHT NOTICE
+# This file is part of the "Universal Biomedical Skills" project.
+# Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>
+# All Rights Reserved.
+#
+# This code is proprietary and confidential.
+# Unauthorized copying of this file, via any medium is strictly prohibited.
+#
+# Provenance: Authenticated by MD BABU MIA
+
+-->
+
+---
+name: biomaster-workflows
+description: Pipeline maestro
+keywords:
+  - workflows
+  - RNAseq
+  - ChIPseq
+  - automation
+  - YAML
+measurable_outcome: Execute a configured pipeline end-to-end (including QC report + summary) within 24 hours of receiving inputs, logging every tool/parameter.
+license: MIT
+metadata:
+  author: BioMaster Team
+  version: "1.0.0"
+compatibility:
+  - system: Python 3.9+
+allowed-tools:
+  - run_shell_command
+  - read_file
+---
+
+# BioMaster Workflows
+
+Orchestrate BioMaster’s multi-agent pipelines (RNA-seq, ChIP-seq, single-cell, Hi-C) using the provided configs and repos to deliver reproducible outputs.
+
+## Workflow
+1. **Config prep:** Populate YAML with tool paths, reference genomes, and workflow selection (`rnaseq`, `chipseq`, `singlecell`, `hic`).
+2. **Environment:** `cd repo && pip install -r requirements.txt` (or container) prior to running.
+3. **Launch:** `python repo/run.py --config repo/config.yaml` (or chosen config) and monitor progress.
+4. **Error recovery:** Let BioMaster agents retry failing stages; review logs for missing reference/index files.
+5. **Output packaging:** Collect BAMs/counts/peaks + QC + narrative summary of parameters and runtimes.
+
+## Guardrails
+- Fail fast when reference files or indices are absent to avoid wasted compute.
+- Record tool versions for every stage (alignment, quantification, etc.).
+- Require confirmation before deleting intermediates or rerunning destructive steps.
+
+## References
+- Full workflow descriptions, supported modalities, and repo links reside in `README.md`.
+
+
+<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->

package/data/skills/biomcp-server/SKILL.md

@@ -0,0 +1,65 @@
+<!--
+# COPYRIGHT NOTICE
+# This file is part of the "Universal Biomedical Skills" project.
+# Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>
+# All Rights Reserved.
+#
+# This code is proprietary and confidential.
+# Unauthorized copying of this file, via any medium is strictly prohibited.
+#
+# Provenance: Authenticated by MD BABU MIA
+
+-->
+
+---
+name: biomcp-server
+description: MCP bio bridge
+keywords:
+  - MCP
+  - PubMed
+  - ClinicalTrials
+  - server
+  - uv
+measurable_outcome: Stand up a working BioMCP endpoint (pip or uv) and return ≥1 PubMed + ≥1 ClinicalTrials.gov response to the client within 10 minutes.
+license: MIT
+metadata:
+  author: BioMCP Team
+  version: "1.0.0"
+compatibility:
+  - system: MCP-compliant clients
+allowed-tools:
+  - web_fetch
+---
+
+# BioMCP Server
+
+Deploy and operate the BioMCP server so MCP-compatible clients (Claude Desktop, LobeChat, etc.) can query biomedical databases via a single standardized interface.
+
+## When to Use
+- Unified literature search (PubMed/PMC) inside MCP clients.
+- Entity normalization via PubTator3 or genomic variant lookups.
+- ClinicalTrials.gov queries without bespoke API wrappers.
+
+## Core Capabilities
+1. **PubMed/PMC search:** Execute complex literature queries.
+2. **PubTator3 annotations:** Map text to genes, diseases, chemicals, species.
+3. **ClinicalTrials.gov:** Retrieve trial metadata/protocols.
+4. **Genomic variant lookups:** Fetch variant/gene summaries from connected sources.
+
+## Deployment Workflow
+1. **Install deps:** `cd repo && uv sync` (preferred) or `pip install .`.
+2. **Run server:** `python -m biomcp.server` or `make run`; Docker Compose provided.
+3. **Configure client:** Add command/args snippet from `README.md` into MCP client config (Claude Desktop, BioKernel, etc.).
+4. **Test tools:** Invoke PubMed + ClinicalTrials + variant endpoints to ensure connectivity.
+5. **Monitor:** Capture logs, rate-limit statuses, and data-source versions for audit.
+
+## Guardrails
+- Keep API keys/env secrets outside the repo.
+- Respect upstream rate limits to avoid throttling or bans.
+- Document which data sources are enabled per deployment and update when they change.
+
+## References
+- Source repo + configuration examples in `README.md`, `repo/docker-compose.yml`, and `repo/Makefile`.
+
+
+<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->

package/data/skills/biomedical-data-analysis/SKILL.md

@@ -0,0 +1,56 @@
+<!--
+# COPYRIGHT NOTICE
+# This file is part of the "Universal Biomedical Skills" project.
+# Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>
+# All Rights Reserved.
+#
+# This code is proprietary and confidential.
+# Unauthorized copying of this file, via any medium is strictly prohibited.
+#
+# Provenance: Authenticated by MD BABU MIA
+
+-->
+
+---
+name: biomedical-data-analysis
+description: Omics data forge
+keywords:
+  - pandas
+  - R-tidyverse
+  - SQL
+  - visualization
+  - reproducible
+measurable_outcome: Deliver a cleaned dataset + statistical summary + at least one visualization or dashboard spec for each request within 1 working session (≤30 minutes).
+license: MIT
+metadata:
+  author: BioSkills Team
+  version: "1.0.0"
+compatibility:
+  - system: Python 3.9+ / R 4.0+
+allowed-tools:
+  - run_shell_command
+  - read_file
+  - python_repl
+---
+
+# Biomedical Data Analysis
+
+Run the cross-language data analysis workflows (Python, R, SQL, Tableau/Power BI) described in this module to clean, analyze, and visualize biomedical datasets end-to-end.
+
+## Workflow
+1. **Scope request:** Identify analysis_type (`exploratory`, `statistical`, `predictive`, `visualization`) and required language/tooling.
+2. **Acquire data:** Load from CSV/Parquet/SQL using pandas, tidyverse, or connectors described in `README.md`.
+3. **Process:** Apply wrangling, descriptive stats, modeling, or SQL aggregations as listed in the capability tables.
+4. **Visualize:** Choose Matplotlib/Seaborn/Plotly for inline plots or emit Tableau/Power BI specs per need.
+5. **Document:** Provide code snippets + outputs, noting package versions and any assumptions.
+
+## Guardrails
+- Use reproducible scripts or notebooks—avoid manual spreadsheet edits.
+- Keep PHI secure; when touching EHR-level SQL list filters minimizing data exposure.
+- Clearly separate exploratory findings from validated statistical conclusions.
+
+## References
+- Capability tables, code samples, and parameter definitions live in `README.md` (plus `tutorials/README.md` for step-by-step lessons).
+
+
+<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->

package/data/skills/biomedical-search/SKILL.md

@@ -0,0 +1,214 @@
+---
+name: biomedical-search
+description: Complete biomedical information search combining PubMed, preprints, clinical trials, and FDA drug labels. Powered by Valyu semantic search.
+keywords:
+  - biomedical-search
+  - clinical-research
+  - evidence-based-medicine
+  - medical-research
+  - comprehensive-search
+  - semantic-search
+license: MIT
+---
+
+
+# Biomedical Search
+
+Search across all major biomedical databases (PubMed, bioRxiv, medRxiv, ClinicalTrials.gov, FDA drug labels) simultaneously using natural language queries powered by Valyu's semantic search API.
+
+## Why This Skill is Powerful
+
+- **No API Parameter Parsing**: Just pass natural language queries directly - no need to construct complex search parameters
+- **Semantic Search**: Understands the meaning of your query, not just keyword matching
+- **Full-Text Access**: Returns complete content from literature, trials, and drug labels
+- **Image Links**: Includes figures and images when available
+- **Comprehensive Coverage**: Search across PubMed, bioRxiv, medRxiv, clinical trials, and drug labels simultaneously
+- **Unified Results**: Get results from all biomedical sources in a single query
+
+## Requirements
+
+1. Node.js 18+ (uses built-in fetch)
+2. Valyu API key from https://platform.valyu.ai ($10 free credits)
+
+## CRITICAL: Script Path Resolution
+
+The `scripts/search` commands in this documentation are relative to this skill's installation directory.
+
+Before running any command, locate the script using:
+
+```bash
+BIOMEDICAL_SCRIPT=$(find ~/.claude/plugins/cache -name "search" -path "*/biomedical-search/*/scripts/*" -type f 2>/dev/null | head -1)
+```
+
+Then use the full path for all commands:
+```bash
+$BIOMEDICAL_SCRIPT "CAR-T cell therapy" 20
+```
+
+## API Key Setup Flow
+
+When you run a search and receive `"setup_required": true`, follow this flow:
+
+1. **Ask the user for their API key:**
+   "To search biomedical databases, I need your Valyu API key. Get one free ($10 credits) at https://platform.valyu.ai"
+
+2. **Once the user provides the key, run:**
+   ```bash
+   scripts/search setup <api-key>
+   ```
+
+3. **Retry the original search.**
+
+## When to Use This Skill
+
+- Complete biomedical information gathering
+- Clinical research combined with basic science
+- Finding trials, literature, and official drug info together
+- Evidence-based medicine research
+- Disease understanding from multiple angles
+## Output Format
+
+```json
+{
+  "success": true,
+  "type": "biomedical_search",
+  "query": "CAR-T cell therapy",
+  "result_count": 20,
+  "results": [
+    {
+      "title": "Title",
+      "url": "https://...",
+      "content": "Full content...",
+      "source": "pubmed|biorxiv|medrxiv|clinical-trials|drug-labels",
+      "relevance_score": 0.95,
+      "images": ["https://example.com/figure1.jpg"]
+    }
+  ],
+  "cost": 0.035
+}
+```
+
+## Processing Results
+
+### With jq
+
+```bash
+# Get titles
+scripts/search "query" 20 | jq -r '.results[].title'
+
+# Get URLs
+scripts/search "query" 20 | jq -r '.results[].url'
+
+# Extract full content
+scripts/search "query" 20 | jq -r '.results[].content'
+
+# Filter by source type
+scripts/search "query" 20 | jq -r '.results[] | select(.source == "clinical-trials") | .title'
+```
+
+## Common Use Cases
+
+### Clinical Research Planning
+
+```bash
+# Gather evidence for clinical study design
+scripts/search "phase 2 trials checkpoint inhibitors melanoma" 50
+```
+
+### Drug Safety Assessment
+
+```bash
+# Search literature, labels, and trials for safety data
+scripts/search "SGLT2 inhibitors cardiovascular safety" 40
+```
+
+### Treatment Protocol Development
+
+```bash
+# Find current practice and emerging approaches
+scripts/search "pembrolizumab dosing regimens NSCLC" 30
+```
+
+### Medical Writing
+
+```bash
+# Comprehensive research for medical communications
+scripts/search "JAK inhibitors rheumatoid arthritis efficacy" 60
+```
+
+
+## Error Handling
+
+All commands return JSON with `success` field:
+
+```json
+{
+  "success": false,
+  "error": "Error message"
+}
+```
+
+Exit codes:
+- `0` - Success
+- `1` - Error (check JSON for details)
+
+## API Endpoint
+
+- Base URL: `https://api.valyu.ai/v1`
+- Endpoint: `/search`
+- Authentication: X-API-Key header
+
+## Architecture
+
+```
+scripts/
+├── search          # Bash wrapper
+└── search.mjs      # Node.js CLI
+```
+
+Direct API calls using Node.js built-in `fetch()`, zero external dependencies.
+
+## Adding to Your Project
+
+If you're building an AI project and want to integrate Biomedical Search directly into your application, use the Valyu SDK:
+
+### Python Integration
+
+```python
+from valyu import Valyu
+
+client = Valyu(api_key="your-api-key")
+
+response = client.search(
+    query="your search query here",
+    included_sources=["valyu/valyu-pubmed", "valyu/valyu-biorxiv", "valyu/valyu-medrxiv", "valyu/valyu-clinical-trials", "valyu/valyu-drug-labels"],
+    max_results=20
+)
+
+for result in response["results"]:
+    print(f"Title: {result['title']}")
+    print(f"URL: {result['url']}")
+    print(f"Content: {result['content'][:500]}...")
+```
+
+### TypeScript Integration
+
+```typescript
+import { Valyu } from "valyu-js";
+
+const client = new Valyu("your-api-key");
+
+const response = await client.search({
+  query: "your search query here",
+  includedSources: ["valyu/valyu-pubmed", "valyu/valyu-biorxiv", "valyu/valyu-medrxiv", "valyu/valyu-clinical-trials", "valyu/valyu-drug-labels"],
+  maxResults: 20
+});
+
+response.results.forEach((result) => {
+  console.log(`Title: ${result.title}`);
+  console.log(`URL: ${result.url}`);
+  console.log(`Content: ${result.content.substring(0, 500)}...`);
+});
+```
+
+See the [Valyu docs](https://docs.valyu.ai) for full integration examples and SDK reference.

package/data/skills/biomni/SKILL.md

@@ -0,0 +1,309 @@
+---
+name: biomni
+description: Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.
+---
+
+# Biomni
+
+## Overview
+
+Biomni is an open-source biomedical AI agent framework from Stanford's SNAP lab that autonomously executes complex research tasks across biomedical domains. Use this skill when working on multi-step biological reasoning tasks, analyzing biomedical data, or conducting research spanning genomics, drug discovery, molecular biology, and clinical analysis.
+
+## Core Capabilities
+
+Biomni excels at:
+
+1. **Multi-step biological reasoning** - Autonomous task decomposition and planning for complex biomedical queries
+2. **Code generation and execution** - Dynamic analysis pipeline creation for data processing
+3. **Knowledge retrieval** - Access to ~11GB of integrated biomedical databases and literature
+4. **Cross-domain problem solving** - Unified interface for genomics, proteomics, drug discovery, and clinical tasks
+
+## When to Use This Skill
+
+Use biomni for:
+- **CRISPR screening** - Design screens, prioritize genes, analyze knockout effects
+- **Single-cell RNA-seq** - Cell type annotation, differential expression, trajectory analysis
+- **Drug discovery** - ADMET prediction, target identification, compound optimization
+- **GWAS analysis** - Variant interpretation, causal gene identification, pathway enrichment
+- **Clinical genomics** - Rare disease diagnosis, variant pathogenicity, phenotype-genotype mapping
+- **Lab protocols** - Protocol optimization, literature synthesis, experimental design
+
+## Quick Start
+
+### Installation and Setup
+
+Install Biomni and configure API keys for LLM providers:
+
+```bash
+uv pip install biomni --upgrade
+```
+
+Configure API keys (store in `.env` file or environment variables):
+```bash
+export ANTHROPIC_API_KEY="your-key-here"
+# Optional: OpenAI, Azure, Google, Groq, AWS Bedrock keys
+```
+
+Use `scripts/setup_environment.py` for interactive setup assistance.
+
+### Basic Usage Pattern
+
+```python
+from biomni.agent import A1
+
+# Initialize agent with data path and LLM choice
+agent = A1(path='./data', llm='claude-sonnet-4-20250514')
+
+# Execute biomedical task autonomously
+agent.go("Your biomedical research question or task")
+
+# Save conversation history and results
+agent.save_conversation_history("report.pdf")
+```
+
+## Working with Biomni
+
+### 1. Agent Initialization
+
+The A1 class is the primary interface for biomni:
+
+```python
+from biomni.agent import A1
+from biomni.config import default_config
+
+# Basic initialization
+agent = A1(
+    path='./data',  # Path to data lake (~11GB downloaded on first use)
+    llm='claude-sonnet-4-20250514'  # LLM model selection
+)
+
+# Advanced configuration
+default_config.llm = "gpt-4"
+default_config.timeout_seconds = 1200
+default_config.max_iterations = 50
+```
+
+**Supported LLM Providers:**
+- Anthropic Claude (recommended): `claude-sonnet-4-20250514`, `claude-opus-4-20250514`
+- OpenAI: `gpt-4`, `gpt-4-turbo`
+- Azure OpenAI: via Azure configuration
+- Google Gemini: `gemini-2.0-flash-exp`
+- Groq: `llama-3.3-70b-versatile`
+- AWS Bedrock: Various models via Bedrock API
+
+See `references/llm_providers.md` for detailed LLM configuration instructions.
+
+### 2. Task Execution Workflow
+
+Biomni follows an autonomous agent workflow:
+
+```python
+# Step 1: Initialize agent
+agent = A1(path='./data', llm='claude-sonnet-4-20250514')
+
+# Step 2: Execute task with natural language query
+result = agent.go("""
+Design a CRISPR screen to identify genes regulating autophagy in
+HEK293 cells. Prioritize genes based on essentiality and pathway
+relevance.
+""")
+
+# Step 3: Review generated code and analysis
+# Agent autonomously:
+# - Decomposes task into sub-steps
+# - Retrieves relevant biological knowledge
+# - Generates and executes analysis code
+# - Interprets results and provides insights
+
+# Step 4: Save results
+agent.save_conversation_history("autophagy_screen_report.pdf")
+```
+
+### 3. Common Task Patterns
+
+#### CRISPR Screening Design
+```python
+agent.go("""
+Design a genome-wide CRISPR knockout screen for identifying genes
+affecting [phenotype] in [cell type]. Include:
+1. sgRNA library design
+2. Gene prioritization criteria
+3. Expected hit genes based on pathway analysis
+""")
+```
+
+#### Single-Cell RNA-seq Analysis
+```python
+agent.go("""
+Analyze this single-cell RNA-seq dataset:
+- Perform quality control and filtering
+- Identify cell populations via clustering
+- Annotate cell types using marker genes
+- Conduct differential expression between conditions
+File path: [path/to/data.h5ad]
+""")
+```
+
+#### Drug ADMET Prediction
+```python
+agent.go("""
+Predict ADMET properties for these drug candidates:
+[SMILES strings or compound IDs]
+Focus on:
+- Absorption (Caco-2 permeability, HIA)
+- Distribution (plasma protein binding, BBB penetration)
+- Metabolism (CYP450 interaction)
+- Excretion (clearance)
+- Toxicity (hERG liability, hepatotoxicity)
+""")
+```
+
+#### GWAS Variant Interpretation
+```python
+agent.go("""
+Interpret GWAS results for [trait/disease]:
+- Identify genome-wide significant variants
+- Map variants to causal genes
+- Perform pathway enrichment analysis
+- Predict functional consequences
+Summary statistics file: [path/to/gwas_summary.txt]
+""")
+```
+
+See `references/use_cases.md` for comprehensive task examples across all biomedical domains.
+
+### 4. Data Integration
+
+Biomni integrates ~11GB of biomedical knowledge sources:
+- **Gene databases** - Ensembl, NCBI Gene, UniProt
+- **Protein structures** - PDB, AlphaFold
+- **Clinical datasets** - ClinVar, OMIM, HPO
+- **Literature indices** - PubMed abstracts, biomedical ontologies
+- **Pathway databases** - KEGG, Reactome, GO
+
+Data is automatically downloaded to the specified `path` on first use.
+
+### 5. MCP Server Integration
+
+Extend biomni with external tools via Model Context Protocol:
+
+```python
+# MCP servers can provide:
+# - FDA drug databases
+# - Web search for literature
+# - Custom biomedical APIs
+# - Laboratory equipment interfaces
+
+# Configure MCP servers in .biomni/mcp_config.json
+```
+
+### 6. Evaluation Framework
+
+Benchmark agent performance on biomedical tasks:
+
+```python
+from biomni.eval import BiomniEval1
+
+evaluator = BiomniEval1()
+
+# Evaluate on specific task types
+score = evaluator.evaluate(
+    task_type='crispr_design',
+    instance_id='test_001',
+    answer=agent_output
+)
+
+# Access evaluation dataset
+dataset = evaluator.load_dataset()
+```
+
+## Best Practices
+
+### Task Formulation
+- **Be specific** - Include biological context, organism, cell type, conditions
+- **Specify outputs** - Clearly state desired analysis outputs and formats
+- **Provide data paths** - Include file paths for datasets to analyze
+- **Set constraints** - Mention time/computational limits if relevant
+
+### Security Considerations
+⚠️ **Important**: Biomni executes LLM-generated code with full system privileges. For production use:
+- Run in isolated environments (Docker, VMs)
+- Avoid exposing sensitive credentials
+- Review generated code before execution in sensitive contexts
+- Use sandboxed execution environments when possible
+
+### Performance Optimization
+- **Choose appropriate LLMs** - Claude Sonnet 4 recommended for balance of speed/quality
+- **Set reasonable timeouts** - Adjust `default_config.timeout_seconds` for complex tasks
+- **Monitor iterations** - Track `max_iterations` to prevent runaway loops
+- **Cache data** - Reuse downloaded data lake across sessions
+
+### Result Documentation
+```python
+# Always save conversation history for reproducibility
+agent.save_conversation_history("results/project_name_YYYYMMDD.pdf")
+
+# Include in reports:
+# - Original task description
+# - Generated analysis code
+# - Results and interpretations
+# - Data sources used
+```
+
+## Resources
+
+### References
+Detailed documentation available in the `references/` directory:
+
+- **`api_reference.md`** - Complete API documentation for A1 class, configuration, and evaluation
+- **`llm_providers.md`** - LLM provider setup (Anthropic, OpenAI, Azure, Google, Groq, AWS)
+- **`use_cases.md`** - Comprehensive task examples for all biomedical domains
+
+### Scripts
+Helper scripts in the `scripts/` directory:
+
+- **`setup_environment.py`** - Interactive environment and API key configuration
+- **`generate_report.py`** - Enhanced PDF report generation with custom formatting
+
+### External Resources
+- **GitHub**: https://github.com/snap-stanford/biomni
+- **Web Platform**: https://biomni.stanford.edu
+- **Paper**: https://www.biorxiv.org/content/10.1101/2025.05.30.656746v1
+- **Model**: https://huggingface.co/biomni/Biomni-R0-32B-Preview
+- **Evaluation Dataset**: https://huggingface.co/datasets/biomni/Eval1
+
+## Troubleshooting
+
+### Common Issues
+
+**Data download fails**
+```python
+# Manually trigger data lake download
+agent = A1(path='./data', llm='your-llm')
+# First .go() call will download data
+```
+
+**API key errors**
+```bash
+# Verify environment variables
+echo $ANTHROPIC_API_KEY
+# Or check .env file in working directory
+```
+
+**Timeout on complex tasks**
+```python
+from biomni.config import default_config
+default_config.timeout_seconds = 3600  # 1 hour
+```
+
+**Memory issues with large datasets**
+- Use streaming for large files
+- Process data in chunks
+- Increase system memory allocation
+
+### Getting Help
+
+For issues or questions:
+- GitHub Issues: https://github.com/snap-stanford/biomni/issues
+- Documentation: Check `references/` files for detailed guidance
+- Community: Stanford SNAP lab and biomni contributors