biomarker-pathway-analysis
Skill277 starsChanged 6 months agoMIT-0View on GitHub
Use when a researcher needs to analyze biological pathways for biomarker discovery, map disease mechanisms to druggable targets using Reactome/KEGG, identify pathway enrichment from gene sets, or understand mechanism-of-action for candidate biomarkers.
In this repository9 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 32
Use the biomni-research server with natural language queries:
- Distinctive: line 119
Always report pathway evidence level (curated vs.
- Distinctive: line 122
When multiple pathways match, rank by: disease relevance > gene count > evidence level
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Biomarker Pathway Analysis
When to use this skill
- Researcher asks which pathways a gene/biomarker belongs to
- Identify druggable targets within a disease pathway
- Map metagene clusters to biological mechanisms
- Understand mechanism-of-action for candidate biomarkers
- Perform pathway enrichment analysis on a gene set
MCP Server: biomni-research
Pathway analysis uses the biomni-research MCP server. Tools are discovered automatically — ask your question naturally and Claude will find the right tool.
Workflow: Pathway-Based Biomarker Discovery
Step 1: Identify the gene set of interest
Sources for gene sets:
- Output from
biomarker-database-analysis(top genes by p-value) - Known cancer driver genes (e.g., EGFR, KRAS, TP53, BRCA1/2)
- Metagene clusters from expression analysis
- Differentially expressed genes from cohort comparison
Step 2: Query pathway databases
Use the biomni-research server with natural language queries:
| Goal | Query approach |
| Find pathways for a gene | "EGFR signaling pathways in Reactome" |
| Find disease pathways | "pathways involved in non-small cell lung cancer" |
| Get pathway interactions | "protein interaction network for CDK4" via STRING |
| Validate drug targets | "CDK4 drug target tractability" via Open Targets |
| Cross-reference function | "CDK4 molecular function and biological process" via UniProt |
Step 3: Map pathway hierarchy
Reactome organizes pathways hierarchically. Navigate from broad to specific:
Top-level: Signal Transduction
-> RAS signaling
-> KRAS activation
-> Downstream effectors (RAF, MEK, ERK)Decision tree for pathway depth:
- Broad overview needed -> Query top-level pathways only
- Mechanism-of-action -> Drill into sub-pathways with specific reactions
- Drug target identification -> Find terminal nodes with known inhibitors
Step 4: Identify druggable targets in pathway
For each pathway hit, assess druggability:
- Query Open Targets for tractability assessment:
- Small molecule tractable
- Antibody tractable
- Other modalities (PROTAC, gene therapy)
- Check existing drugs:
- Approved drugs targeting this pathway node
- Clinical trial compounds (Phase I-III)
- Tool compounds for validation
- Prioritize by:
- Distance from disease-associated node (closer = better)
- Number of approved drugs (validated target)
- Safety profile of existing modulators
Step 5: Build pathway-to-biomarker rationale
Connect pathway findings back to biomarker candidates:
Gene (biomarker candidate)
-> Pathway membership (Reactome)
-> Disease relevance (pathway implicated in condition)
-> Mechanistic explanation (how gene contributes to disease)
-> Clinical utility (can measure this to stratify patients)Pathway Analysis Patterns
EGFR pathway in NSCLC:
- Query: EGFR, KRAS, ALK, ROS1, BRAF, MET, HER2, RET
- Pathways: RTK signaling, RAS-MAPK, PI3K-AKT-mTOR
- Biomarker implication: Mutation status predicts TKI response
Metagene cluster interpretation:
- Cluster of co-expressed genes -> query each for pathway membership
- Identify shared pathways -> that pathway drives the co-expression
- Example: GDF15, POSTN, VCAN cluster -> TGF-beta / extracellular matrix remodeling
Survival-associated pathway enrichment:
- Take top 10 genes by Cox regression p-value
- Query Reactome for each gene
- Count pathway overlaps (enrichment)
- Pathways with 3+ genes = significantly enriched
Decision Framework: When to Use Pathway Analysis
| Scenario | Recommended approach |
| Single gene of interest | Query Reactome + UniProt for function context |
| Gene panel (5-20 genes) | Pathway enrichment: find shared pathways |
| Drug target validation | Open Targets tractability + existing drugs |
| Mechanism explanation | Full pathway walk: gene -> pathway -> disease |
| Novel biomarker discovery | Combine pathway + expression + survival data |
Conventions
- Always report pathway evidence level (curated vs. inferred)
- Include Reactome stable IDs (R-HSA-xxxxx) for reproducibility
- For STRING interactions, use confidence threshold >= 0.7 (high confidence)
- When multiple pathways match, rank by: disease relevance > gene count > evidence level
- Cross-reference pathway findings with literature (PubMed) for validation
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

