SkillAgentSearch skills...

LigandMPNN

Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN).

Install / Use

npx skills add aipoch/open-science --skill ligandmpnn

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

89/100

Supported Platforms

Universal

Our assessment of LigandMPNN

LigandMPNN scores 89/100 on our quality scale, 1539th of 4,698 Development & Engineering skills we index (top 33%).

Its SKILL.md is 6.6 KB long, split into 7 sections with 1 code example: a thorough specification that gives an agent plenty to work with.

With 4,918 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
29/30
Structure
15/20
Description
15/15
Adoption
16/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so LigandMPNN is actively maintained.
  • Our last check on 2026-10-31 found the source still online.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-29. Automated pattern scan on 2026-09-29. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

LigandMPNN compared with similar skills

All 4 of these similar skills score higher than LigandMPNN; compare them before choosing.

SkillScoreStarsUpdatedFormat
LigandMPNN (this skill)by aipoch894.9k53d agoSKILL.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
ai-job-searchby ai-job-search-dev10072.1ktodayCLAUDE.md
claude-howtoby luongnv8910047.3k2d agoCLAUDE.md

Frequently asked questions

How do I install LigandMPNN?
Run npx skills add aipoch/open-science --skill LigandMPNN. The install tabs above show the steps for each supported agent.
Which AI agents does LigandMPNN work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is LigandMPNN safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is LigandMPNN still maintained?
The repository was last updated about 2 months ago, so LigandMPNN is actively maintained.

name: ligandmpnn description: > Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be respected, or to get threaded designed-sequence PDBs out of any MPNN run. license: Apache-2.0 category: biomodels metadata: display-name: LigandMPNN

github.com/dauparas/LigandMPNN/blob/main/LICENSE: MIT (© 2024 Justas

Dauparas). verified 2026-06-30

third_party: - kind: weights name: LigandMPNN license: MIT terms_url: https://github.com/dauparas/LigandMPNN/blob/main/LICENSE

LigandMPNN

LigandMPNN extends the ProteinMPNN graph with non-protein atoms — small molecules, nucleic acids, and metals are visible to the network — so it is the right inverse-folding tool whenever the design surface includes a bound ligand or cofactor that vanilla proteinmpnn would ignore. The same run.py is also the most convenient runner for the other MPNN families because, unlike the original ProteinMPNN script, it threads designs back onto the input structure and writes PDBs alongside the FASTA. Code and weights are MIT (github.com/dauparas/LigandMPNN). The model is small enough to run on CPU — for a handful of designs on one structure that is seconds and usually faster than dispatching, so the normal path is local with pip install torch numpy biopython ProDy ml_collections dm-tree; a GPU helps for batched campaigns.

Running it

pip install torch numpy biopython ProDy ml_collections dm-tree
git clone --depth 1 https://github.com/dauparas/LigandMPNN.git ligandmpnn
cd ligandmpnn
sed -i 's/np\.int\b/np.int64/g' openfold/np/residue_constants.py   # repo pins numpy 1.23; alias removed in >=1.24
bash get_model_params.sh ./model_params
python run.py \
  --model_type ligand_mpnn \
  --checkpoint_ligand_mpnn ./model_params/ligandmpnn_v_32_010_25.pt \
  --pdb_path complex.pdb \
  --out_folder out \
  --batch_size 8 --number_of_batches 4 \
  --temperature 0.1 \
  --fixed_residues "A45 A46 A47 A48"

Residue selections are space-separated {chain}{resnum} tokens inside one quoted string ("A45 A46 B10"; insertion codes append directly, "B82A"). That is the format for --fixed_residues and --redesigned_residues; --bias_AA_per_residue and --omit_AA_per_residue instead take a path to a JSON file whose keys use the same {chain}{resnum} form, and --chains_to_design is comma-separated ("A,B"). If you want to redesign only the pocket, naming the pocket residues in --redesigned_residues is usually shorter than fixing everything else.

Under --out_folder you get seqs/<stem>.fa (headers carry overall_confidence and ligand_confidence), backbones/<stem>_{1..N}.pdb with the designed sequence threaded onto the input coordinates, and — with --pack_side_chains 1 — full-atom packed models in packed/. The threaded PDBs are the reason to prefer this runner even for protein-only jobs.

Model types — which one to pick

| --model_type | sees | use | | ----------------- | -------------------------------- | ---------------------------------------------- | | ligand_mpnn | backbone + ligand/NA/metal atoms | binding-pocket or active-site design | | protein_mpnn | backbone only | protein–protein; same weights as proteinmpnn | | soluble_mpnn | backbone only, soluble-trained | expression-biased prior; see solublempnn | | *_membrane_mpnn | backbone + membrane label | transmembrane designs |

Each model type has its own --checkpoint_<type> flag; the wrong pairing is caught at load time, but the default checkpoint path is relative to the repo, so run from inside the clone or pass the absolute path.

ProDy compiles from source on py3.11 — pip install fails without a C compiler

run.py imports ProDy unconditionally for ligand atom parsing. On py3.11 the prebuilt wheel is missing on PyPI, so pip install ProDy compiles from source and needs a working C/C++ compiler. On Modal's add_python bases the default CXX=clang++ points at a missing binary — apt_install("build-essential") and export CC=gcc CXX=g++ before the install. On most CPU-local Python distributions the sdist builds in ~10 s if no wheel matches your Python.

Turning ligand context off changes the answer, not the model

--ligand_mpnn_use_atom_context 0 keeps the ligand-aware weights but masks the ligand atoms at inference. That is useful for an ablation — the difference between context-on and context-off tells you how much the ligand is shaping the design — but it is not equivalent to running protein_mpnn, which uses a different checkpoint trained without those features. For a fair protein-only baseline, switch --model_type.

Stripped HETATM or a chain filter silently drops the ligand — the design comes back pocket-blind

LigandMPNN does not warn when no ligand atoms are found; it just runs as if --model_type protein_mpnn had been picked. The two common ways this happens are an input PDB whose HETATM records were stripped by an upstream clean-up step, and --parse_these_chains_only naming the protein chains but not the ligand's. If ligand_confidence in the FASTA header is missing or zero across every design, the model never saw the ligand — fix the input, do not trust the sequences.

Errors worth recognizing

| You see | It means / do this | | --------------------------------------------------------- | -------------------------------------------------------------------------------------------------- | | ModuleNotFoundError: No module named 'tree' | pip install dm-tree — the vendored openfold imports it unconditionally. | | module 'numpy' has no attribute 'int' | Run the sed patch on openfold/np/residue_constants.py, or pin numpy<1.24 (py≤3.11 only). | | error: command 'clang' failed while pip install ProDy | See the ProDy gotcha above — apt_install("build-essential") and env({"CC":"gcc","CXX":"g++"}). | | FileNotFoundError for model_params/... | Checkpoints not fetched — run bash get_model_params.sh ./model_params from inside the clone. |


Next: fold the designs in complex with the ligand via boltz or chai1 (both accept SMILES/CCD) and filter on ipTM and ligand placement.

Related Skills

View on GitHub
GitHub Stars4.9k
CategoryDevelopment
Updated1mo ago
Forks294

Languages

TypeScript

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions