@bgicli/bgicli 2.1.1 → 2.2.0

package/data/skills/mesh-generation/SKILL.md

@@ -0,0 +1,149 @@
+---
+name: mesh-generation
+description: Plan and evaluate mesh generation for numerical simulations. Use when choosing grid resolution, checking aspect ratios/skewness, estimating mesh quality constraints, or planning adaptive mesh refinement for PDE discretization.
+allowed-tools: Read, Bash, Write, Grep, Glob
+---
+
+# Mesh Generation
+
+## Goal
+
+Provide a consistent workflow for selecting mesh resolution and checking mesh quality for PDE simulations.
+
+## Requirements
+
+- Python 3.8+
+- No external dependencies (uses stdlib)
+
+## Inputs to Gather
+
+| Input | Description | Example |
+|-------|-------------|---------|
+| Domain size | Physical dimensions | `1.0 × 1.0 m` |
+| Feature size | Smallest feature to resolve | `0.01 m` |
+| Points per feature | Resolution requirement | `10 points` |
+| Aspect ratio limit | Maximum dx/dy ratio | `5:1` |
+| Quality threshold | Skewness limit | `< 0.8` |
+
+## Decision Guidance
+
+### Resolution Selection
+
+```
+What is the smallest feature size?
+├── Interface width → dx ≤ width / 5
+├── Boundary layer → dx ≤ layer_thickness / 10
+├── Wave length → dx ≤ lambda / 20
+└── Diffusion length → dx ≤ sqrt(D × dt) / 2
+```
+
+### Mesh Type Selection
+
+| Problem | Recommended Mesh |
+|---------|------------------|
+| Simple geometry, uniform | Structured Cartesian |
+| Complex geometry | Unstructured triangular/tetrahedral |
+| Boundary layers | Hybrid (structured near walls) |
+| Adaptive refinement | Quadtree/Octree or AMR |
+
+## Script Outputs (JSON Fields)
+
+| Script | Key Outputs |
+|--------|-------------|
+| `scripts/grid_sizing.py` | `dx`, `nx`, `ny`, `nz`, `notes` |
+| `scripts/mesh_quality.py` | `aspect_ratio`, `skewness`, `quality_flags` |
+
+## Workflow
+
+1. **Estimate resolution** - From physics scales
+2. **Compute grid sizing** - Run `scripts/grid_sizing.py`
+3. **Check quality metrics** - Run `scripts/mesh_quality.py`
+4. **Adjust if needed** - Fix aspect ratios, reduce skewness
+5. **Validate** - Mesh convergence study
+
+## Conversational Workflow Example
+
+**User**: I need to mesh a 1mm × 1mm domain for a phase-field simulation with interface width of 10 μm.
+
+**Agent workflow**:
+1. Compute grid sizing:
+   ```bash
+   python3 scripts/grid_sizing.py --length 0.001 --resolution 200 --json
+   ```
+2. Verify interface is resolved: dx = 5 μm, interface width = 10 μm → 2 points per interface width.
+3. Recommend: Increase to 500 points (dx = 2 μm) for 5 points across interface.
+
+## Pre-Mesh Checklist
+
+- [ ] Define target resolution per feature/interface
+- [ ] Ensure dx meets stability constraints (see numerical-stability)
+- [ ] Check aspect ratio < limit (typically 5:1)
+- [ ] Check skewness < threshold (typically 0.8)
+- [ ] Validate mesh convergence with refinement study
+
+## CLI Examples
+
+```bash
+# Compute grid sizing for 1D domain
+python3 scripts/grid_sizing.py --length 1.0 --resolution 200 --json
+
+# Check mesh quality
+python3 scripts/mesh_quality.py --dx 1.0 --dy 0.5 --dz 0.5 --json
+
+# High aspect ratio check
+python3 scripts/mesh_quality.py --dx 1.0 --dy 0.1 --json
+```
+
+## Error Handling
+
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| `length must be positive` | Invalid domain size | Use positive value |
+| `resolution must be > 1` | Insufficient points | Use at least 2 |
+| `dx, dy must be positive` | Invalid spacing | Use positive values |
+
+## Interpretation Guidance
+
+### Aspect Ratio
+
+| Aspect Ratio | Quality | Impact |
+|--------------|---------|--------|
+| 1:1 | Excellent | Optimal accuracy |
+| 1:1 - 3:1 | Good | Acceptable |
+| 3:1 - 5:1 | Fair | May affect accuracy |
+| > 5:1 | Poor | Solver issues likely |
+
+### Skewness
+
+| Skewness | Quality | Impact |
+|----------|---------|--------|
+| 0 - 0.25 | Excellent | Optimal |
+| 0.25 - 0.50 | Good | Acceptable |
+| 0.50 - 0.80 | Fair | May affect accuracy |
+| > 0.80 | Poor | Likely problems |
+
+### Resolution Guidelines
+
+| Application | Points per Feature |
+|-------------|-------------------|
+| Phase-field interface | 5-10 |
+| Boundary layer | 10-20 |
+| Shock | 3-5 (with capturing) |
+| Wave propagation | 10-20 per wavelength |
+| Smooth gradients | 5-10 |
+
+## Limitations
+
+- **2D/3D only**: No unstructured mesh generation
+- **Quality metrics**: Basic aspect ratio and skewness only
+- **No mesh generation**: Sizing recommendations only
+
+## References
+
+- `references/mesh_types.md` - Structured vs unstructured
+- `references/quality_metrics.md` - Aspect ratio/skewness thresholds
+
+## Version History
+
+- **v1.1.0** (2024-12-24): Enhanced documentation, decision guidance, examples
+- **v1.0.0**: Initial release with 2 mesh quality scripts

package/data/skills/metabolomics-workbench-database/SKILL.md

@@ -0,0 +1,253 @@
+---
+name: metabolomics-workbench-database
+description: "Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery."
+---
+
+# Metabolomics Workbench Database
+
+## Overview
+
+The Metabolomics Workbench is a comprehensive NIH Common Fund-sponsored platform hosted at UCSD that serves as the primary repository for metabolomics research data. It provides programmatic access to over 4,200 processed studies (3,790+ publicly available), standardized metabolite nomenclature through RefMet, and powerful search capabilities across multiple analytical platforms (GC-MS, LC-MS, NMR).
+
+## When to Use This Skill
+
+This skill should be used when querying metabolite structures, accessing study data, standardizing nomenclature, performing mass spectrometry searches, or retrieving gene/protein-metabolite associations through the Metabolomics Workbench REST API.
+
+## Core Capabilities
+
+### 1. Querying Metabolite Structures and Data
+
+Access comprehensive metabolite information including structures, identifiers, and cross-references to external databases.
+
+**Key operations:**
+- Retrieve compound data by various identifiers (PubChem CID, InChI Key, KEGG ID, HMDB ID, etc.)
+- Download molecular structures as MOL files or PNG images
+- Access standardized compound classifications
+- Cross-reference between different metabolite databases
+
+**Example queries:**
+```python
+import requests
+
+# Get compound information by PubChem CID
+response = requests.get('https://www.metabolomicsworkbench.org/rest/compound/pubchem_cid/5281365/all/json')
+
+# Download molecular structure as PNG
+response = requests.get('https://www.metabolomicsworkbench.org/rest/compound/regno/11/png')
+
+# Get compound name by registry number
+response = requests.get('https://www.metabolomicsworkbench.org/rest/compound/regno/11/name/json')
+```
+
+### 2. Accessing Study Metadata and Experimental Results
+
+Query metabolomics studies by various criteria and retrieve complete experimental datasets.
+
+**Key operations:**
+- Search studies by metabolite, institute, investigator, or title
+- Access study summaries, experimental factors, and analysis details
+- Retrieve complete experimental data in various formats
+- Download mwTab format files for complete study information
+- Query untargeted metabolomics data
+
+**Example queries:**
+```python
+# List all available public studies
+response = requests.get('https://www.metabolomicsworkbench.org/rest/study/study_id/ST/available/json')
+
+# Get study summary
+response = requests.get('https://www.metabolomicsworkbench.org/rest/study/study_id/ST000001/summary/json')
+
+# Retrieve experimental data
+response = requests.get('https://www.metabolomicsworkbench.org/rest/study/study_id/ST000001/data/json')
+
+# Find studies containing a specific metabolite
+response = requests.get('https://www.metabolomicsworkbench.org/rest/study/refmet_name/Tyrosine/summary/json')
+```
+
+### 3. Standardizing Metabolite Nomenclature with RefMet
+
+Use the RefMet database to standardize metabolite names and access systematic classification across four structural resolution levels.
+
+**Key operations:**
+- Match common metabolite names to standardized RefMet names
+- Query by chemical formula, exact mass, or InChI Key
+- Access hierarchical classification (super class, main class, sub class)
+- Retrieve all RefMet entries or filter by classification
+
+**Example queries:**
+```python
+# Standardize a metabolite name
+response = requests.get('https://www.metabolomicsworkbench.org/rest/refmet/match/citrate/name/json')
+
+# Query by molecular formula
+response = requests.get('https://www.metabolomicsworkbench.org/rest/refmet/formula/C12H24O2/all/json')
+
+# Get all metabolites in a specific class
+response = requests.get('https://www.metabolomicsworkbench.org/rest/refmet/main_class/Fatty%20Acids/all/json')
+
+# Retrieve complete RefMet database
+response = requests.get('https://www.metabolomicsworkbench.org/rest/refmet/all/json')
+```
+
+### 4. Performing Mass Spectrometry Searches
+
+Search for compounds by mass-to-charge ratio (m/z) with specified ion adducts and tolerance levels.
+
+**Key operations:**
+- Search precursor ion masses across multiple databases (Metabolomics Workbench, LIPIDS, RefMet)
+- Specify ion adduct types (M+H, M-H, M+Na, M+NH4, M+2H, etc.)
+- Calculate exact masses for known metabolites with specific adducts
+- Set mass tolerance for flexible matching
+
+**Example queries:**
+```python
+# Search by m/z value with M+H adduct
+response = requests.get('https://www.metabolomicsworkbench.org/rest/moverz/MB/635.52/M+H/0.5/json')
+
+# Calculate exact mass for a metabolite with specific adduct
+response = requests.get('https://www.metabolomicsworkbench.org/rest/moverz/exactmass/PC(34:1)/M+H/json')
+
+# Search across RefMet database
+response = requests.get('https://www.metabolomicsworkbench.org/rest/moverz/REFMET/200.15/M-H/0.3/json')
+```
+
+### 5. Filtering Studies by Analytical and Biological Parameters
+
+Use the MetStat context to find studies matching specific experimental conditions.
+
+**Key operations:**
+- Filter by analytical method (LCMS, GCMS, NMR)
+- Specify ionization polarity (POSITIVE, NEGATIVE)
+- Filter by chromatography type (HILIC, RP, GC)
+- Target specific species, sample sources, or diseases
+- Combine multiple filters using semicolon-delimited format
+
+**Example queries:**
+```python
+# Find human blood studies on diabetes using LC-MS
+response = requests.get('https://www.metabolomicsworkbench.org/rest/metstat/LCMS;POSITIVE;HILIC;Human;Blood;Diabetes/json')
+
+# Find all human blood studies containing tyrosine
+response = requests.get('https://www.metabolomicsworkbench.org/rest/metstat/;;;Human;Blood;;;Tyrosine/json')
+
+# Filter by analytical method only
+response = requests.get('https://www.metabolomicsworkbench.org/rest/metstat/GCMS;;;;;;/json')
+```
+
+### 6. Accessing Gene and Protein Information
+
+Retrieve gene and protein data associated with metabolic pathways and metabolite metabolism.
+
+**Key operations:**
+- Query genes by symbol, name, or ID
+- Access protein sequences and annotations
+- Cross-reference between gene IDs, RefSeq IDs, and UniProt IDs
+- Retrieve gene-metabolite associations
+
+**Example queries:**
+```python
+# Get gene information by symbol
+response = requests.get('https://www.metabolomicsworkbench.org/rest/gene/gene_symbol/ACACA/all/json')
+
+# Retrieve protein data by UniProt ID
+response = requests.get('https://www.metabolomicsworkbench.org/rest/protein/uniprot_id/Q13085/all/json')
+```
+
+## Common Workflows
+
+### Workflow 1: Finding Studies for a Specific Metabolite
+
+To find all studies containing measurements of a specific metabolite:
+
+1. First standardize the metabolite name using RefMet:
+   ```python
+   response = requests.get('https://www.metabolomicsworkbench.org/rest/refmet/match/glucose/name/json')
+   ```
+
+2. Use the standardized name to search for studies:
+   ```python
+   response = requests.get('https://www.metabolomicsworkbench.org/rest/study/refmet_name/Glucose/summary/json')
+   ```
+
+3. Retrieve experimental data from specific studies:
+   ```python
+   response = requests.get('https://www.metabolomicsworkbench.org/rest/study/study_id/ST000001/data/json')
+   ```
+
+### Workflow 2: Identifying Compounds from MS Data
+
+To identify potential compounds from mass spectrometry m/z values:
+
+1. Perform m/z search with appropriate adduct and tolerance:
+   ```python
+   response = requests.get('https://www.metabolomicsworkbench.org/rest/moverz/MB/180.06/M+H/0.5/json')
+   ```
+
+2. Review candidate compounds from results
+
+3. Retrieve detailed information for candidate compounds:
+   ```python
+   response = requests.get('https://www.metabolomicsworkbench.org/rest/compound/regno/{regno}/all/json')
+   ```
+
+4. Download structures for confirmation:
+   ```python
+   response = requests.get('https://www.metabolomicsworkbench.org/rest/compound/regno/{regno}/png')
+   ```
+
+### Workflow 3: Exploring Disease-Specific Metabolomics
+
+To find metabolomics studies for a specific disease and analytical platform:
+
+1. Use MetStat to filter studies:
+   ```python
+   response = requests.get('https://www.metabolomicsworkbench.org/rest/metstat/LCMS;POSITIVE;;Human;;Cancer/json')
+   ```
+
+2. Review study IDs from results
+
+3. Access detailed study information:
+   ```python
+   response = requests.get('https://www.metabolomicsworkbench.org/rest/study/study_id/ST{ID}/summary/json')
+   ```
+
+4. Retrieve complete experimental data:
+   ```python
+   response = requests.get('https://www.metabolomicsworkbench.org/rest/study/study_id/ST{ID}/data/json')
+   ```
+
+## Output Formats
+
+The API supports two primary output formats:
+- **JSON** (default): Machine-readable format, ideal for programmatic access
+- **TXT**: Human-readable tab-delimited text format
+
+Specify format by appending `/json` or `/txt` to API URLs. When format is omitted, JSON is returned by default.
+
+## Best Practices
+
+1. **Use RefMet for standardization**: Always standardize metabolite names through RefMet before searching studies to ensure consistent nomenclature
+
+2. **Specify appropriate adducts**: When performing m/z searches, use the correct ion adduct type for your analytical method (e.g., M+H for positive mode ESI)
+
+3. **Set reasonable tolerances**: Use appropriate mass tolerance values (typically 0.5 Da for low-resolution, 0.01 Da for high-resolution MS)
+
+4. **Cache reference data**: Consider caching frequently used reference data (RefMet database, compound information) to minimize API calls
+
+5. **Handle pagination**: For large result sets, be prepared to handle multiple data structures in responses
+
+6. **Validate identifiers**: Cross-reference metabolite identifiers across multiple databases when possible to ensure correct compound identification
+
+## Resources
+
+### references/
+
+Detailed API reference documentation is available in `references/api_reference.md`, including:
+- Complete REST API endpoint specifications
+- All available contexts (compound, study, refmet, metstat, gene, protein, moverz)
+- Input/output parameter details
+- Ion adduct types for mass spectrometry
+- Additional query examples
+
+Load this reference file when detailed API specifications are needed or when working with less common endpoints.

package/data/skills/microbiome-cancer-agent/SKILL.md

@@ -0,0 +1,180 @@
+<!--
+# 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: 'microbiome-cancer-agent'
+description: 'AI-powered analysis of microbiome-cancer interactions including tumor microbiome profiling, immunotherapy response prediction, and microbiome-targeted therapeutic opportunities.'
+measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes.
+allowed-tools:
+  - read_file
+  - run_shell_command
+---
+
+
+# Microbiome-Cancer Interaction Agent
+
+The **Microbiome-Cancer Interaction Agent** analyzes relationships between the microbiome and cancer, including tumor-associated bacteria, gut microbiome effects on immunotherapy, and microbiome-targeted therapeutic strategies.
+
+## When to Use This Skill
+
+* When analyzing tumor microbiome composition from sequencing data.
+* To predict immunotherapy response based on gut microbiome profiles.
+* For identifying microbiome-based biomarkers in cancer.
+* When assessing antibiotic impact on cancer treatment efficacy.
+* To design microbiome-modulating therapeutic interventions.
+
+## Core Capabilities
+
+1. **Tumor Microbiome Analysis**: Profile intratumoral bacteria from tumor sequencing data.
+
+2. **Gut-Cancer Axis**: Analyze fecal microbiome associations with cancer outcomes.
+
+3. **ICI Response Prediction**: Predict checkpoint inhibitor response from microbiome.
+
+4. **Metabolite Profiling**: Link microbial metabolites to cancer phenotypes.
+
+5. **Antibiotic Impact**: Model antibiotic effects on treatment efficacy.
+
+6. **FMT/Probiotic Design**: Support microbiome-modulating interventions.
+
+## Microbiome-Cancer Associations
+
+| Cancer Type | Key Bacteria | Association |
+|-------------|--------------|-------------|
+| Colorectal | Fusobacterium nucleatum | Promotion, poor prognosis |
+| Colorectal | Bacteroides fragilis (ETBF) | Carcinogenesis |
+| Gastric | Helicobacter pylori | Established carcinogen |
+| Pancreatic | Gammaproteobacteria | Drug metabolism |
+| Breast | Fusobacterium | Metastasis |
+| Oral | Porphyromonas gingivalis | Oral SCC |
+
+## Workflow
+
+1. **Input**: 16S/shotgun metagenomics, tumor sequencing, clinical data.
+
+2. **Taxonomy Profiling**: Identify bacterial composition at genus/species level.
+
+3. **Diversity Analysis**: Calculate alpha and beta diversity metrics.
+
+4. **Association Testing**: Correlate microbiome with outcomes.
+
+5. **Functional Prediction**: Infer metabolic potential (PICRUSt2, HUMAnN).
+
+6. **Prediction Modeling**: Build response prediction models.
+
+7. **Output**: Microbiome profile, associations, predictions, interventions.
+
+## Example Usage
+
+**User**: "Analyze gut microbiome from melanoma patients and predict anti-PD-1 response."
+
+**Agent Action**:
+```bash
+python3 Skills/Microbiome/Microbiome_Cancer_Agent/microbiome_cancer.py \
+    --metagenomics fecal_shotgun.fastq.gz \
+    --tumor_data melanoma_rnaseq.tsv \
+    --clinical treatment_outcomes.csv \
+    --analysis ici_response \
+    --reference metaphlan_db \
+    --output microbiome_report/
+```
+
+## ICI Response and Microbiome
+
+**Favorable Microbiome**:
+- Akkermansia muciniphila
+- Faecalibacterium prausnitzii
+- Bifidobacterium spp.
+- Ruminococcaceae family
+- High diversity
+
+**Unfavorable Microbiome**:
+- Bacteroidales (in some studies)
+- Low diversity
+- Post-antibiotic dysbiosis
+
+## Microbial Metabolites in Cancer
+
+| Metabolite | Source | Effect |
+|------------|--------|--------|
+| Butyrate | Clostridia | Anti-inflammatory, anti-tumor |
+| Inosine | Akkermansia | Enhanced ICI response |
+| TMAO | Various | Pro-tumorigenic |
+| Secondary bile acids | Various | Variable, context-dependent |
+| LPS | Gram-negative | Inflammation, mixed effects |
+
+## AI/ML Components
+
+**Response Prediction**:
+- Random forest on microbiome features
+- Neural networks for metagenomic profiles
+- Integration with host factors
+
+**Microbiome-Metabolite Linking**:
+- Genome-scale metabolic models
+- Correlation networks
+- Causal inference methods
+
+**Intervention Design**:
+- FMT donor selection
+- Probiotic consortium optimization
+- Antibiotic avoidance recommendations
+
+## Tumor Microbiome Analysis
+
+**Challenges**:
+- Low bacterial biomass in tumors
+- Contamination from reagents/environment
+- Batch effects
+- Need for stringent controls
+
+**Best Practices**:
+- Negative controls (extraction, PCR)
+- Decontamination algorithms (decontam, SCRuB)
+- Multiple validation methods
+- Orthogonal confirmation (FISH, culture)
+
+## Clinical Implications
+
+1. **Biomarker Development**: Microbiome-based response prediction
+2. **Intervention Timing**: Avoid antibiotics pre-ICI
+3. **FMT Trials**: Responder microbiome transfer
+4. **Probiotics**: Rationally designed consortia
+5. **Prebiotics**: Fiber to support beneficial bacteria
+
+## Prerequisites
+
+* Python 3.10+
+* QIIME2, Metaphlan, HUMAnN
+* R (phyloseq, vegan)
+* ML frameworks
+
+## Related Skills
+
+* Metagenomics - For general microbiome analysis
+* Immune_Checkpoint_Combination_Agent - For ICI optimization
+* Metabolomics - For metabolite analysis
+
+## Research Frontiers
+
+1. **Intratumoral bacteria**: Direct tumor effects
+2. **Phage therapy**: Targeting pathobionts
+3. **Engineered probiotics**: Drug-producing bacteria
+4. **Diet interventions**: Modulating microbiome for therapy
+
+## Author
+
+AI Group - Biomedical AI Platform
+
+
+<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->