skills.rest
polaires
polairesCOMMUNITY
Explore all skills by this author →
GitHub

ligandmpnn-reference

Reference LigandMPNN model types, parameters, and bias presets for protein sequence design.

Updated Aug 23, 2026
Search Tags:#bioinformatics#protein design#sequence optimization#ligandmpnn#mpnn#ligand binding
One-click install
npx skills add https://github.com/polaires/Banta_Lab_RFdiffusion --skill ligandmpnn-reference
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ligandmpnn-reference
Source: https://github.com/polaires/Banta_Lab_RFdiffusion/tree/main/.claude/skills/ligandmpnn-reference
Command: npx skills add https://github.com/polaires/Banta_Lab_RFdiffusion --skill ligandmpnn-reference

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides quick access to essential information and parameters for LigandMPNN, a powerful tool for protein sequence design, particularly when dealing with ligands, metals, or membrane proteins.

Core Features & Use Cases

  • Model Selection: Understand and choose between different MPNN model types (protein_mpnn, ligand_mpnn, etc.).
  • Parameter Configuration: Quickly reference key command-line arguments for biasing amino acids, fixing residues, controlling temperature, and packing side chains.
  • Use Case: When designing a protein to bind a specific metal ion, you can use this Skill to find the appropriate bias presets and parameters for ligand_mpnn to guide the sequence design.

Quick Start

Use the ligandmpnn-reference skill to find the correct bias_AA parameters for designing a protein that binds to a lanthanide.

Frequently Asked Questions about ligandmpnn-reference

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure LigandMPNN parameters for protein sequence design with ligand binding?▼

LigandMPNN model types include `protein_mpnn` and `ligand_mpnn`, which you choose based on whether your protein sequence design task involves general optimization or specific ligand binding interactions. Selecting the correct model ensures accurate sequence design results.

Can I use bias presets to design membrane proteins using LigandMPNN?▼

Fixed residue constraints in LigandMPNN are specified using residue formatting rules provided by the reference. This allows you to lock specific amino acid positions during sequence optimization, ensuring critical structural or functional residues remain unchanged during the design process.

What is the difference between ligand_mpnn and protein_mpnn model types?▼

The `ligand_mpnn` model type is designed for protein sequence optimization involving ligands, metals, or membrane proteins, while `protein_mpnn` handles general protein design. The distinction lies in the model's capability to account for ligand binding interactions during sequence generation.

How do I control temperature sampling and side chain packing in LigandMPNN?▼

Temperature sampling and side chain packing in LigandMPNN are controlled through specific command-line arguments detailed in the reference. These parameters let you adjust the stochasticity of sequence sampling and manage rotamer conformational space during protein design.

Related Skills

Explore More Software Engineering Skills→
junior1pjunior1p
11

solublempnn

Generate solubility-optimized protein sequences using SolubleMPNN workflows.

Community
Intermediate
yf8578yf8578
1

molecular-dynamics

Run molecular dynamics simulations with OpenMM and analyze trajectories using MDAnalysis.

Community
Advanced
silversteinsilverstein
21

diffdock

Predict ranked protein–ligand binding poses with confidence scores from PDB structures or sequences and SMILES inputs.

Community
Advanced
LeonChaoXLeonChaoX
783

diffdock

Predict ranked 3D protein–ligand binding poses with confidence scores.

Community
Advanced