A specialized research architect that generates end-to-end bioinformatic study designs for identifying shared molecular mechanisms between two diseases using public GEO data.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install dual-disease-transcriptomic-ml-planner
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install dual-disease-transcriptomic-ml-planner using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Dual-Disease Transcriptomic ML Planner?
The Dual-Disease Transcriptomic ML Planner is a high-level research architect designed for bioinformaticians and medical researchers. By leveraging Openclaw Skills, this tool automates the complex logic required to design cross-disease transcriptomic studies, moving from raw GEO dataset selection to machine learning-based biomarker validation. It specifically targets the identification of shared Differentially Expressed Genes (DEGs), common hub genes, and shared molecular pathways.
This skill ensures scientific rigor by enforcing strict validation protocols, including ROC/AUC analysis and immune infiltration deconvolution. It bridges the gap between raw data and a publishable manuscript by providing structured workflows, figure plans, and specific R code frameworks tailored for dual-disease comparison.
Dual-Disease Transcriptomic ML Planner Use Cases
- Identifying shared biomarkers and hub genes between two distinct but related phenotypes
- Designing a publication-ready bioinformatic pipeline for cross-disease mechanism discovery
- Generating pilot study designs for shared DEG and PPI network analysis
- Validating diagnostic gene signatures across multiple GEO discovery and validation cohorts
- Investigating common immune infiltration patterns between comorbid conditions
How Dual-Disease Transcriptomic ML Planner Works
- Inference & Theme Identification: The skill analyzes the disease pair to determine the biological theme (e.g., autoimmune, neurodegenerative) and identifies the appropriate research goal.
- Multi-Config Generation: It automatically generates four distinct workload tiers: Lite, Standard, Advanced, and Publication+.
- Primary Plan Recommendation: Based on data availability in the GEO database and user goals, it justifies a specific recommended approach.
- Workflow Orchestration: It details the technical steps including tissue-specific filtering, limma-based DEG analysis, and STRING PPI construction.
- Machine Learning Validation: The skill plans ROC analysis and hub gene prioritization using multi-algorithm consensus (e.g., CytoHubba).
- Risk & Robustness Assessment: It performs a self-critical review to flag potential false positives, small cohort inflation, and overinterpretation risks.
Dual-Disease Transcriptomic ML Planner Setup
To utilize this skill within your AI agent environment, ensure you have the standard bioinformatics R stack installed. Use the following commands to set up the necessary environment:
# Install BiocManager if not already present
R -e "install.packages('BiocManager')"
# Install core bioinformatic dependencies
R -e "BiocManager::install(c('GEOquery', 'limma', 'clusterProfiler', 'org.Hs.eg.db', 'pROC', 'WGCNA'))"
Configure your agent to access the Openclaw Skills repository and point it toward the dual-disease-transcriptomic-ml-planner markdown definition.
Dual-Disease Transcriptomic ML Planner Data Schema & Taxonomy
The skill organizes research data and outputs according to a structured taxonomy to ensure reproducibility:
| Data Category | Component | Metadata/Format |
|---|---|---|
| Input Data | GEO Accessions | GSE IDs, Platform (GPL) IDs, Tissue Source |
| Signatures | Shared DEGs | logFC thresholds, adj.p-values, Venn intersections |
| Networks | PPI Metadata | STRING confidence scores, MCODE clusters, Hub rankings |
| Validation | ROC Metrics | AUC values, 95% CI (Bootstrap), Sensitivity/Specificity |
| Immune | Deconvolution | Cell-type proportions (CIBERSORT/alternative), Spearman correlation |
Dual-Disease Transcriptomic ML Planner Advanced Features
- Multi-Algorithm Hub Consensus: Requires at least 5 algorithms (Degree, MCC, Betweenness, Closeness, EPC) for ranking hub genes.
- Fault-Tolerant DEG Recovery: Automated logic to relax thresholds or switch to WGCNA co-expression if initial intersections yield zero results.
- Tissue-Tool Decision Matrix: Specialized logic to select the best immune deconvolution tool based on the specific tissue type being analyzed.
- Publication Upgrade Path: Detailed impact analysis for adding validation cohorts or single-gene GSEA to increase manuscript competitiveness using Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
AI Cinema Director
A specialized tool that translates high-level creative intent into professional technical directives for state-of-the-art AI video models.
Forguncy Web Operator
A specialized tool for programmatically interacting with and extracting data from SpreadJS tables within Forguncy web applications.
Word
A macOS-specific skill for AI agents to control live Microsoft Word applications, handling selections, comments, and review states via osascript.
Maps
A sophisticated tool for cross-provider map workflows including geocoding, routing, and spatial data normalization.
Creator Payment Terms Template
A specialized template generator for drafting clear, milestone-based payment terms for creator and influencer campaigns.
Chanai Search Workflow
A sophisticated dual-route search engine for AI agents that intelligently navigates Chinese and international web landscapes.
Featured*
