agentsclimarketplace

Antibody design agent

Skill rbr7/MedClawMini/skills/antibody-design-agent

A focused, production-minded library of 197 clinical-AI and healthcare data-science skills for the OpenClaw agent platform featuring data quality, clinical NLP, big-data ML, explainable AI, drug safety, and regulatory.

Install
npx -y skills add rbr7/MedClawMini --skill antibody-design-agent

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

An advanced agent for de novo antibody design and optimization using state-of-the-art protein language models (MAGE, RFdiffusion).

SKILL.md

2.3 KB, as published. Nobody here has run it

Antibody Design Agent

This skill brings together cutting-edge tools for antibody engineering, including MAGE (Monoclonal Antibody Generator) and RFdiffusion for Antibodies. It enables the de novo design of antibodies against specific viral or tumoral targets.

When to Use This Skill

  • De Novo Design: Generating antibody sequences/structures that bind to a specific antigen.
  • Epitope Targeting: Designing VHH or binders for a specific epitope on a target protein.
  • Optimization: Improving the affinity or stability of an existing antibody candidate.
  • Viral Defense: Rapidly generating antibodies against novel viral strains.

Core Capabilities

  1. MAGE (Monoclonal Antibody Generator): Uses a protein language model to generate diverse antibody sequences against unseen viral strains.
  2. RFdiffusion for Antibodies: Generates 3D antibody structures that bind to a target structure with high precision.
  3. ProteinMPNN: Optimizes the sequence of the generated structures for solubility and expression.

Workflow

  1. Target Definition: Input the PDB structure or sequence of the antigen (target).
  2. Design Phase:
    • Use RFdiffusion to generate the backbone of the binder (CDR loops).
    • Use ProteinMPNN to design the sequence for the backbone.
    • Alternatively, use MAGE to generate sequences directly from viral strain data.
  3. Validation (In Silico): Use AlphaFold3 or ESMFold to predict the complex structure and assess binding confidence (pLDDT, PAE).
  4. Selection: Rank candidates for synthesis.

Example Usage

User: "Design a VHH nanobody that binds to the RBD of the SARS-CoV-2 KP.2 variant."

Agent Action:

  1. Retrieves RBD structure for KP.2.
  2. Runs RFdiffusion with "binder" constraints on the RBD surface.
  3. Generates 100 backbone candidates.
  4. Sequences them with ProteinMPNN.
  5. Folds the complexes with AlphaFold3 to verify binding interface.
  6. Returns top 5 sequences.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.