agentleFS
PharMolixPharMolix/OpenBioMed/skills/protein-mutation-analysis/SKILL.md

protein-mutation-analysis

Skill1.1k starsChanged 8 months agoMITView on GitHub

Analyze protein mutations by retrieving protein data, explaining mutation effects, predicting protein structure, and visualizing results. Use this skill when the user asks about protein mutations, wants to understand mutation effects, or needs to analyze genetic variants. Triggers on phrases like "analyze mutation", "explain mutation", "what does this mutation do", "protein variant analysis".

Trending

Quiet this year.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 0 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the PharMolix/OpenBioMed repository that our weekly crawl found: only 1 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Who's talking about PharMolix/OpenBioMed

The biggest 1 of 1 mention linking to the repository that our crawl found. Each line is their own headline.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Solution: Check checkpoints exist:

    line 86
  2. Distinctive:

    Fallback: Use web search for mutation literature.

    line 91

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Protein Mutation Analysis

Analyze the functional impact of protein mutations using MutaPLM and visualize protein structures.

When to Use

  • User provides a UniProt ID and mutation (e.g., "P04637 R248Q")
  • User wants to understand the effect of a specific mutation
  • User needs to visualize a mutated protein structure
  • Research on disease-associated genetic variants

Workflow

Step 1: Retrieve Protein from UniProt

from open_biomed.tools.tool_registry import TOOLS

tool = TOOLS["protein_uniprot_request"]
result, message = tool.run(accession="P04637")
protein = result.get("protein")

Step 2: Explain Mutation with MutaPLM

mutation_tool = TOOLS["mutation_explanation"]
mutation_result, _ = mutation_tool.run(
    protein=protein,
    mutation="R248Q"  # Format: OriginalAA + Position + MutantAA
)

Step 3: Predict Structure with ESMFold

folding_tool = TOOLS["protein_folding"]
fold_result, _ = folding_tool.run(protein=protein)
predicted_protein = fold_result.get("protein")

Step 4: Visualize Protein Structure

viz_tool = TOOLS["visualize_protein"]
viz_result, _ = viz_tool.run(protein=predicted_protein, style="cartoon")

See examples/basic_analysis.py for the complete implementation.

Expected Outputs

StepOutputDescription
Retrieve ProteinProtein objectName, sequence from UniProt
Explain MutationTextFunctional impact from MutaPLM
Predict StructureProtein with 3D coordsStructure from ESMFold
VisualizePNG fileRendered protein structure

Mutation Format

Single amino acid mutation: OriginalAA + Position + MutantAA

ValidInvalidReason
R248QR248Missing mutant AA
V600E248QMissing original AA
L858RARG248GLNUse single-letter codes

Error Handling

Missing Model Checkpoints

Symptom: FileNotFoundError or AttributeError

Solution: Check checkpoints exist:

  • ./checkpoints/server/mutaplm.pth
  • ./checkpoints/esm2/650m/
  • ./checkpoints/biomedgpt-lm/

Fallback: Use web search for mutation literature.

Position Out of Range

position = int(mutation[1:-1])
if position > len(protein.sequence):
    print(f"Error: Position exceeds sequence length")

See references/troubleshooting.md for detailed error handling.

Interpretation

MutaPLM Output

  • Disease association: "In [cancer type]..." indicates known disease link
  • Functional change: Describes altered protein function
  • Structural impact: May mention stability effects

ESMFold Confidence

pLDDT ScoreConfidence
> 90High
70-90Moderate
< 70Low (disordered)

Example

Input: P04637 R248Q

Step 1: Retrieved TP53 (393 aa)
Step 2: "In lung cancer, mutation R248Q..."
Step 3: Structure predicted (~8s)
Step 4: Visualization saved

Output: Mutation analysis + structure + visualization

Prerequisites

Model checkpoints required (see references/troubleshooting.md):

  • MutaPLM, ESM2, BioMedGPT-LM, ESMFold

Related Tools

  • protein_pdb_request - Get existing PDB structures
  • protein_question_answering - Ask about protein function
  • export_protein - Save structure to PDB format

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.