@bgicli/bgicli 2.1.1 → 2.2.0

package/data/skills/claims-appeals/SKILL.md

@@ -0,0 +1,35 @@
+<!--
+# 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: 'claims-appeals'
+description: 'Claims Appeals agent for healthcare workflows.'
+measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes.
+allowed-tools:
+  - read_file
+  - run_shell_command
+---
+
+
+# Claims Appeals
+
+This skill implements the Claims Appeals workflow using Anthropic's Claude.
+
+## Usage
+
+```bash
+python3 Skills/Anthropic_Health_Stack/Claims_Appeals/coworker.py
+```
+
+
+<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->

package/data/skills/claw-ancestry-pca/SKILL.md

@@ -0,0 +1,145 @@
+---
+name: claw-ancestry-pca
+version: 0.1.0
+description: Ancestry decomposition PCA against the Simons Genome Diversity Project
+author: Manuel Corpas
+license: MIT
+tags:
+  - population-genetics
+  - PCA
+  - ancestry
+  - SGDP
+  - global-diversity
+inputs:
+  - name: vcf
+    type: file
+    format: [vcf, vcf.gz]
+    description: VCF file with genotype data for your study cohort
+  - name: pop-map
+    type: file
+    format: [tsv, txt]
+    description: Tab-separated file mapping sample IDs to population labels
+outputs:
+  - name: figure
+    type: file
+    format: [png, pdf]
+    description: Multi-panel PCA composite figure showing ancestry decomposition
+  - name: report
+    type: file
+    format: markdown
+    description: Ancestry analysis report with population assignments and statistics
+metadata:
+  openclaw:
+    category: bioinformatics
+    homepage: https://github.com/ClawBio/ClawBio
+    min_python: "3.9"
+    dependencies:
+      - pandas
+      - numpy
+      - matplotlib
+      - scikit-learn
+      - adjustText
+    system_dependencies:
+      - plink
+      - bcftools
+---
+
+# 🦖 Ancestry Decomposition PCA
+
+Place your study cohort in global genetic context by computing a joint PCA against the Simons Genome Diversity Project (SGDP) — 345 samples from 164 populations spanning every inhabited continent.
+
+## What it does
+
+1. Takes your VCF + population map as input
+2. Finds common variants between your cohort and the SGDP reference panel (bundled)
+3. Runs PLINK PCA on the merged dataset
+4. Separates your cohort from SGDP reference samples
+5. Matches SGDP samples to their population labels (164 populations)
+6. Generates a publication-quality multi-panel figure:
+   - **Panel A**: PC1 vs PC2 — main population structure of your cohort
+   - **Panel B**: PC3 vs PC2 with regional groupings and confidence ellipses
+   - **Panel C**: PC3 vs PC1 with language/cultural groupings
+   - **Panel D**: Global context — your samples (circles) vs SGDP (triangles)
+7. Produces a markdown report with variance explained, population assignments, and reproducibility bundle
+
+## Why this exists
+
+If you ask ChatGPT to "run a PCA against a global reference panel," it will:
+- Not know which reference panel to use
+- Hallucinate PLINK flags for merging datasets with different variant sets
+- Skip IBD removal (related individuals distort PCA)
+- Not normalise contig names between your VCF and the reference
+- Produce a single scatter plot with no population labels
+
+This skill encodes the correct methodological decisions:
+- Uses SGDP (the gold-standard reference for global diversity)
+- Handles contig normalisation (chr1 vs 1)
+- Filters to common biallelic SNPs shared between datasets
+- Removes related individuals via IBD checks
+- Produces publication-quality multi-panel figures with confidence ellipses
+- Differentiates your samples (circles) from reference (triangles)
+
+## Reference Panel
+
+The skill bundles the SGDP v4 dataset (Mallick et al., 2016, Nature):
+- 345 samples from 164 populations
+- Whole-genome sequencing at high coverage
+- MAF > 0.1% filter applied
+- Populations span: Africa, Americas, Central/South Asia, East Asia, Europe, Middle East, Oceania
+
+## Usage
+
+```bash
+python ancestry_pca.py \
+    --vcf your_cohort.vcf.gz \
+    --pop-map your_populations.tsv \
+    --output ancestry_report
+```
+
+### Demo (works out of the box)
+
+```bash
+python ancestry_pca.py --demo --output demo_report
+```
+
+The demo uses pre-computed PCA results from the Peruvian Genome Project (736 samples, 28 populations) and generates the full 4-panel figure instantly.
+
+## Example Output
+
+```
+Ancestry Decomposition PCA
+==========================
+Cohort: 736 samples, 28 populations
+Reference: SGDP (345 samples, 164 populations)
+Common variants: 42,831 biallelic SNPs
+
+Variance explained:
+  PC1: 51.44%  PC2: 21.70%  PC3: 6.70%
+
+Panel D — Global Context:
+  Cohort samples cluster between European and East Asian
+  reference populations, with Amazonian groups showing
+  distinct positioning from Highland and Coastal groups.
+
+Figures saved to: ancestry_report/
+  Figure3_PCA_composite.png (300 dpi)
+  Figure3_PCA_composite.pdf (vector)
+
+Reproducibility:
+  commands.sh | environment.yml | checksums.sha256
+```
+
+## Interpretation Guide
+
+- **PC1** typically captures the largest axis of global differentiation (often Africa vs non-Africa)
+- **PC2** separates major continental groups (Europe, East Asia, Americas)
+- **PC3** often reveals finer substructure within continental groups
+- Confidence ellipses show 2.5 standard deviations around each population cluster
+- Your samples shown as **circles**, SGDP reference as **triangles**
+
+## Citation
+
+If you use this skill in a publication, please cite:
+
+- Mallick, S. et al. (2016). The Simons Genome Diversity Project. Nature, 538, 201-206.
+- Corpas, M. (2026). ClawBio. https://github.com/ClawBio/ClawBio

package/data/skills/claw-metagenomics/SKILL.md

@@ -0,0 +1,238 @@
+---
+name: claw-metagenomics
+version: 0.1.0
+description: Shotgun metagenomics profiling — taxonomy, resistome, and functional pathways
+author: Manuel Corpas
+license: MIT
+tags:
+  - metagenomics
+  - antimicrobial-resistance
+  - taxonomy
+  - functional-profiling
+  - environmental
+  - WHO-critical-ARGs
+inputs:
+  - name: r1
+    type: file
+    format: [fastq, fastq.gz, fq, fq.gz]
+    description: Forward reads (paired-end FASTQ R1)
+  - name: r2
+    type: file
+    format: [fastq, fastq.gz, fq, fq.gz]
+    description: Reverse reads (paired-end FASTQ R2)
+  - name: input
+    type: file
+    format: [fastq, fastq.gz, fq, fq.gz]
+    description: Single concatenated or interleaved FASTQ (alternative to R1+R2)
+outputs:
+  - name: taxonomy_report
+    type: file
+    format: tsv
+    description: Bracken-adjusted species-level taxonomy abundance table
+  - name: resistome_profile
+    type: file
+    format: tsv
+    description: RGI/CARD antimicrobial resistance gene hits with WHO priority classification
+  - name: functional_pathways
+    type: file
+    format: tsv
+    description: HUMAnN3 pathway abundance table (MetaCyc/UniRef)
+  - name: figures
+    type: directory
+    format: [png, pdf]
+    description: Publication-quality figures (taxonomy bar chart, resistome heatmap, WHO-critical ARG summary)
+  - name: reproducibility
+    type: directory
+    description: commands.sh, environment.yml, checksums.sha256
+metadata:
+  openclaw:
+    category: bioinformatics
+    homepage: https://github.com/ClawBio/ClawBio
+    min_python: "3.9"
+    dependencies:
+      - pandas
+      - numpy
+      - matplotlib
+      - seaborn
+      - scipy
+      - biopython
+    system_dependencies:
+      - kraken2
+      - bracken
+      - rgi
+      - humann
+---
+
+# Shotgun Metagenomics Profiler
+
+Comprehensive shotgun metagenomics analysis combining taxonomic classification, antimicrobial resistance gene detection, and functional pathway profiling from paired-end FASTQ files.
+
+## What it does
+
+1. Takes paired-end FASTQ files (R1, R2) or a single concatenated FASTQ as input
+2. Runs **Kraken2** taxonomic classification against a standard database (e.g., Standard-8, PlusPF)
+3. Refines abundances with **Bracken** at species level (read re-estimation)
+4. Detects antimicrobial resistance genes with **RGI** against the **CARD** database
+5. Classifies detected ARGs by **WHO critical priority pathogen** association
+6. Optionally runs **HUMAnN3** for functional pathway profiling (MetaCyc + UniRef)
+7. Generates three publication-quality figures:
+   - **Figure 1**: Taxonomy bar chart — top 20 species by relative abundance
+   - **Figure 2**: Resistome heatmap — ARG families by drug class with abundance
+   - **Figure 3**: WHO-critical ARG summary — priority-tier breakdown of detected resistance genes
+8. Produces a full reproducibility bundle (commands.sh, environment.yml, checksums.sha256)
+
+## Why this exists
+
+If you ask a general AI to "analyse a metagenome," it will:
+- Not know which Kraken2 database to use or how to set confidence thresholds
+- Hallucinate Bracken parameters for read-length and taxonomic level
+- Miss the connection between detected ARGs and WHO priority pathogen lists
+- Skip HUMAnN3 entirely (or misconfigure its database paths)
+- Produce a single bar chart with no resistance context
+- Not provide a reproducibility bundle
+
+This skill encodes the correct methodological decisions:
+- Kraken2 confidence threshold of 0.2 (reduces false positives in environmental samples)
+- Bracken re-estimation at species level with minimum 10 reads
+- RGI MAIN with "Perfect" and "Strict" hit criteria only (no "Loose" hits)
+- WHO Critical Priority Pathogen list mapped to detected ARG families
+- HUMAnN3 with MetaCyc stratification for pathway-level functional context
+- Thread count auto-detected from available CPUs
+- Full reproducibility bundle for every run
+
+## Validated On
+
+The skill works with any shotgun metagenome but has been validated on:
+- **Peru sewage metagenomics study** (6 samples, 3 collection sites: Lima, Cusco, Iquitos)
+- Environmental sewage samples with mixed microbial communities
+- Read depths ranging from 2M to 15M paired-end reads per sample
+
+## WHO-Critical ARG Detection
+
+A key feature is the classification of detected resistance genes by WHO priority tier:
+
+| Priority | Pathogen | Resistance |
+|----------|----------|------------|
+| Critical | *Acinetobacter baumannii* | Carbapenem-resistant |
+| Critical | *Pseudomonas aeruginosa* | Carbapenem-resistant |
+| Critical | *Enterobacteriaceae* | Carbapenem-resistant, 3rd-gen cephalosporin-resistant |
+| High | *Enterococcus faecium* | Vancomycin-resistant |
+| High | *Staphylococcus aureus* | Methicillin-resistant, vancomycin-resistant |
+| High | *Helicobacter pylori* | Clarithromycin-resistant |
+| High | *Campylobacter* | Fluoroquinolone-resistant |
+| High | *Salmonella* spp. | Fluoroquinolone-resistant |
+| High | *Neisseria gonorrhoeae* | 3rd-gen cephalosporin-resistant, fluoroquinolone-resistant |
+| Medium | *Streptococcus pneumoniae* | Penicillin-non-susceptible |
+| Medium | *Haemophilus influenzae* | Ampicillin-resistant |
+| Medium | *Shigella* spp. | Fluoroquinolone-resistant |
+
+## Usage
+
+```bash
+# Full pipeline (taxonomy + resistome + functional)
+python metagenomics_profiler.py \
+    --r1 sample_R1.fastq.gz \
+    --r2 sample_R2.fastq.gz \
+    --output metagenomics_report
+
+# Skip HUMAnN3 (faster — taxonomy + resistome only)
+python metagenomics_profiler.py \
+    --r1 sample_R1.fastq.gz \
+    --r2 sample_R2.fastq.gz \
+    --output metagenomics_report \
+    --skip-functional
+
+# Single concatenated FASTQ
+python metagenomics_profiler.py \
+    --input combined.fastq.gz \
+    --output metagenomics_report
+
+# Specify Kraken2 database path
+python metagenomics_profiler.py \
+    --r1 sample_R1.fastq.gz \
+    --r2 sample_R2.fastq.gz \
+    --output metagenomics_report \
+    --kraken2-db /path/to/kraken2_db \
+    --read-length 150
+```
+
+### Demo (works out of the box)
+
+```bash
+python metagenomics_profiler.py --demo --output demo_report
+```
+
+The demo uses pre-computed results from the Peru sewage metagenomics study (6 samples, 3 sites) and generates all figures and reports instantly without requiring external tools.
+
+## Example Output
+
+```
+Metagenomics Profiler — ClawBio
+================================
+Mode: demo (pre-computed Peru sewage data)
+Samples: 6 (3 sites: Lima, Cusco, Iquitos)
+
+Taxonomy (Kraken2 + Bracken):
+  Total classified: 94.2%
+  Top species: Escherichia coli (12.3%), Klebsiella pneumoniae (8.7%),
+               Pseudomonas aeruginosa (5.1%), Acinetobacter baumannii (3.9%)
+
+Resistome (RGI/CARD):
+  Total ARG hits: 247 (Perfect: 89, Strict: 158)
+  Drug classes: 14
+  WHO-Critical ARGs detected: 23
+    - Carbapenem resistance: NDM-1, OXA-48, KPC-3
+    - 3rd-gen cephalosporin resistance: CTX-M-15, CTX-M-27
+
+Functional Pathways (HUMAnN3):
+  Total pathways: 312
+  Top: PWY-7219 (adenosine ribonucleotides de novo biosynthesis)
+
+Figures saved to: demo_report/figures/
+  taxonomy_barplot.png (300 dpi)
+  resistome_heatmap.png (300 dpi)
+  who_critical_args.png (300 dpi)
+
+Reproducibility:
+  commands.sh | environment.yml | checksums.sha256
+```
+
+## Pipeline Architecture
+
+```
+FASTQ R1 + R2
+     |
+     v
+[Kraken2] --> kraken2_report.txt
+     |
+     v
+[Bracken] --> bracken_species.tsv   --> Figure 1: Taxonomy bar chart
+     |
+     v
+[RGI MAIN] --> rgi_results.txt      --> Figure 2: Resistome heatmap
+     |                                --> Figure 3: WHO-critical ARG summary
+     v
+[HUMAnN3] --> pathabundance.tsv     (optional, --skip-functional to omit)
+     |
+     v
+[Report] --> report.md + figures/ + reproducibility/
+```
+
+## Database Requirements
+
+| Tool | Database | Size | Notes |
+|------|----------|------|-------|
+| Kraken2 | Standard-8 or PlusPF | 8-70 GB | Set via `--kraken2-db` or `$KRAKEN2_DB` |
+| Bracken | (built from Kraken2 DB) | included | Read-length specific (default: 150 bp) |
+| RGI | CARD | ~500 MB | Auto-downloaded via `rgi auto_load` |
+| HUMAnN3 | ChocoPhlAn + UniRef90 | ~15 GB | Set via `--humann-db` or `$HUMANN_DB` |
+
+## Citations
+
+If you use this skill in a publication, please cite:
+
+- Wood, D.E., Lu, J. & Langmead, B. (2019). Improved metagenomic analysis with Kraken 2. Genome Biology, 20, 257.
+- Lu, J. et al. (2017). Bracken: estimating species abundance in metagenomics data. PeerJ Computer Science, 3, e104.
+- Alcock, B.P. et al. (2023). CARD 2023: expanded curation, support for machine learning, and resistome prediction at the Comprehensive Antibiotic Resistance Database. Nucleic Acids Research, 51(D1), D419-D430.
+- Beghini, F. et al. (2021). Integrating taxonomic, functional, and strain-level profiling of diverse microbial communities with bioBakery 3. eLife, 10, e65088.
+- Corpas, M. (2026). ClawBio. https://github.com/ClawBio/ClawBio

package/data/skills/claw-semantic-sim/SKILL.md

@@ -0,0 +1,151 @@
+---
+name: claw-semantic-sim
+version: 0.1.0
+description: Semantic Similarity Index for disease research literature using PubMedBERT embeddings
+author: Manuel Corpas
+license: MIT
+tags: [health-equity, semantic-analysis, NLP, PubMedBERT, disease-neglect]
+metadata:
+  openclaw:
+    requires:
+      bins:
+        - python3
+      env: []
+      config: []
+    always: false
+    emoji: "🔬"
+    homepage: https://github.com/ClawBio/ClawBio
+    os: [macos, linux]
+    install:
+      - kind: pip
+        package: torch
+        bins: []
+      - kind: pip
+        package: transformers
+        bins: []
+      - kind: pip
+        package: h5py
+        bins: []
+      - kind: pip
+        package: umap-learn
+        bins: []
+      - kind: pip
+        package: biopython
+        bins: []
+      - kind: pip
+        package: networkx
+        bins: []
+    trigger_keywords:
+      - semantic similarity
+      - disease neglect
+      - research gaps
+      - NTDs
+      - SII
+      - knowledge silo
+---
+
+# 🦖 Semantic Similarity Index
+
+Measure how isolated or connected disease research is across the global biomedical literature, using PubMedBERT embeddings on PubMed abstracts spanning 175 GBD diseases.
+
+## What it does
+
+1. Takes a disease list (GBD taxonomy) as input
+2. Retrieves PubMed abstracts (2000-2025) for each disease with quality filtering
+3. Generates 768-dimensional PubMedBERT embeddings for every abstract
+4. Computes four semantic equity metrics per disease:
+   - **Semantic Isolation Index (SII)**: average cosine distance to k-nearest disease neighbours; higher = more isolated, less connected research
+   - **Knowledge Transfer Potential (KTP)**: cross-disease centroid similarity; higher = more potential for research spillover
+   - **Research Clustering Coefficient (RCC)**: within-disease embedding variance; higher = more diverse research approaches
+   - **Temporal Semantic Drift**: cosine distance between yearly centroids; measures how research focus evolves
+5. Generates publication-quality multi-panel figures:
+   - **Panel A**: Semantic isolation by disease category (boxplot)
+   - **Panel B**: Top 20 most semantically isolated diseases (bar chart, NTD/Global South colour-coded)
+   - **Panel C**: Semantic isolation vs research volume (scatter with regression)
+   - **Panel D**: NTD vs non-NTD significance test (Welch's t-test, Cohen's d)
+6. Produces a markdown report with all metrics, rankings, and reproducibility bundle
+
+## Why this exists
+
+If you ask ChatGPT to "measure research neglect for diseases," it will:
+- Not know which embedding model to use for biomedical text
+- Hallucinate metrics that sound plausible but have no methodological grounding
+- Skip quality filtering (year coverage, abstract coverage, minimum papers)
+- Not handle MPS acceleration or checkpointed batch processing
+- Produce a single scatter plot with no disease classification
+
+This skill encodes the correct methodological decisions:
+- Uses PubMedBERT (the gold-standard biomedical language model)
+- Fetches from PubMed with exponential backoff and NCBI rate limiting
+- Quality filters: year coverage >= 70%, abstract coverage >= 95%, minimum 50 papers
+- Batch embedding with Apple MPS acceleration and CPU fallback
+- Checkpointed processing (resume after interruption)
+- HDF5 storage with gzip compression and SHA-256 checksums
+- Classification against WHO NTD list and Global South priority diseases
+- Statistical significance testing (Welch's t-test, Cohen's d)
+
+## Key Finding
+
+Neglected tropical diseases (NTDs) are significantly more semantically isolated than other conditions (P < 0.001, Cohen's d = 0.8+). They exist in knowledge silos with limited cross-disciplinary research bridges. The 25 most isolated diseases are disproportionately Global South priority conditions.
+
+## Pipeline
+
+```
+05-00-heim-sem-setup.py     # Validate environment, create directories
+05-01-heim-sem-fetch.py     # Retrieve PubMed abstracts (checkpointed)
+05-02-heim-sem-embed.py     # Generate PubMedBERT embeddings (MPS/CPU)
+05-03-heim-sem-compute.py   # Compute SII, KTP, RCC, temporal drift
+05-04-heim-sem-figures.py   # Generate publication figures
+05-05-heim-sem-integrate.py # Merge with biobank + clinical trial dimensions
+```
+
+### Demo (works out of the box)
+
+```bash
+python semantic_sim.py --demo --output demo_report
+```
+
+The demo uses pre-computed embeddings and metrics for 175 GBD diseases and generates the full 4-panel figure instantly.
+
+## Example Output
+
+```
+Semantic Similarity Index
+=========================
+Diseases analysed: 175
+Total PubMed abstracts: 13,100,000
+Embedding model: PubMedBERT (768-dim)
+
+Metric Ranges:
+  SII: 0.0412 - 0.1893
+  KTP: 0.6234 - 0.9187
+  RCC: 0.0891 - 0.3421
+
+Key Finding:
+  NTDs show +38% higher semantic isolation
+  P < 0.0001, Cohen's d = 0.84
+  14/25 most isolated diseases are Global South priority
+
+Figures saved to: demo_report/
+  Fig5_Semantic_Structure.png (300 dpi)
+  Fig5_Semantic_Structure.pdf (vector)
+
+Reproducibility:
+  commands.sh | environment.yml | checksums.sha256
+```
+
+## Interpretation Guide
+
+- **High SII**: Disease research exists in a knowledge silo; limited cross-disciplinary bridges
+- **Low KTP**: Research on this disease has few methodological overlaps with others
+- **High RCC**: Diverse research approaches within the disease (many subtopics)
+- **High Temporal Drift**: Research focus has shifted significantly over time
+- NTDs shown in **red**, Global South diseases in **orange**, others in **grey**
+- The scatter plot (Panel C) reveals the inverse relationship between research volume and isolation
+
+## Citation
+
+If you use this skill in a publication, please cite:
+
+- Corpas, M. et al. (2026). HEIM: Health Equity Index for Measuring structural bias in biomedical research. Under review.
+- Corpas, M. (2026). ClawBio. https://github.com/ClawBio/ClawBio