LigandMPNN (ligand-aware sequence design)

SkillMedia

This skill lets your AI design protein sequences that fit around a ligand, metal, or nucleic acid already in place. It is built on LigandMPNN, a 2023 method that takes the surrounding molecule into account, so the amino acids it picks for binding pockets and metal sites are chosen to match the actual ligand. Use it when you want to design a small-molecule or metal binding pocket.

Available today. Use it from your connected AI after setup.

After adding the skill, give your AI the structure with the ligand, metal, or nucleic acid in place and ask it to design a protein sequence around it.

Then ask your AI: use the LigandMPNN (ligand-aware sequence design) skill

What your AI can do with it

  • Design protein sequences around a bound small-molecule ligand
  • Design sequences that hold metals at metal sites
  • Design sequences around nucleic acids
  • Choose binding-pocket amino acids that fit the actual ligand
  • Choose metal-site amino acids suited to the metal in place

What this skill tells your AI

The instructions your AI receives, as published by alterlab-ieu/alterlab-academic-skills in skills/bioinformatics/alterlab-ligandmpnn/SKILL.md and read by ahel’s review.

Overview

LigandMPNN (Dauparas et al. 2023; dauparas/LigandMPNN) extends ProteinMPNN's inverse folding to condition on non-protein context — small-molecule ligands, metal ions, and nucleic acids. Because the model sees the ligand/metal atoms, the residues it designs for a binding pocket or metal site are chosen to complement what is actually bound, which plain ProteinMPNN (protein-atoms-only) cannot do.

Use it whenever the design target is a site that contacts a ligand or ion. For sequence design of a backbone with no bound context, use alterlab-proteinmpnn.

When to Use This Skill

Use this skill when the user wants to:

  • Design a small-molecule binding pocket so the residues fit the ligand.
  • Design a metal-coordinating site (e.g. Zn/Fe) with the ion in context.
  • Redesign residues that contact a ligand, ion, or nucleic acid.
  • Do enzyme active-site design where the substrate/cofactor should guide the choice.

Does NOT Trigger

ScenarioUse instead
Sequence design for a backbone with no ligand/metal contextalterlab-proteinmpnn
Generate a backbone or scaffold a functional motifalterlab-rfdiffusion
Validate a design by refoldingalterlab-alphafold
Co-fold the protein WITH the ligand from scratchalterlab-boltz
Dock a ligand into a fixed pocket (pose, not sequence)alterlab-diffdock

Core Capabilities

1. Ligand-aware pocket design

# dauparas/LigandMPNN CLI — TODO(verify) flags/checkpoint names against your checkout
python run.py \
  --model_type ligand_mpnn \
  --pdb_path complex_with_ligand.pdb \
  --out_folder out/ \
  --number_of_batches 8

The input PDB must contain the ligand/metal atoms (HETATM). LigandMPNN designs pocket residues that fit that context; supply a fixed-positions/redesign spec to target only the site.

2. Metal-site and nucleic-acid context

Provide the coordinating ion or the nucleic-acid chain in the structure so the model conditions on it — critical for metalloenzyme and DNA/RNA-binding designs.

3. Site-focused redesign

Restrict design to the residues within a shell of the ligand (redesign the pocket, keep the scaffold), analogous to ProteinMPNN's fixed-positions workflow. Verify the exact argument names for your version (TODO(verify)).

4. In the design pipeline

LigandMPNN provides the sequence step when the functional site involves a ligand: scaffold or generate the site with alterlab-rfdiffusion, design the pocket sequence here, then validate by refolding (alterlab-alphafold) and — if you need a pose/affinity — co-fold with alterlab-boltz or dock with alterlab-diffdock.

Resources

  • references/ligandmpnn_usage.md — install/pinning, model types, HETATM/context input, site-restricted design, and pipeline integration. Loaded on demand.

Part of the AlterLab Academic Skills suite.

Signals

GitHub stars
66
Forks
13
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
alterlab-ligandmpnn
Source
github.com/alterlab-ieu/alterlab-academic-skills