AGENT SKILL

openfold3

Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill when predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation.

License 许可
Apache-2.0
最近更新
2026-11-14
Stars
★ 3
Forks
0

01 前言 Front Matter

name
openfold3
license
Apache-2.0
category
biomodels
metadata
{ "third_party": [ { "kind": "weights", "name": "OpenFold3", "license": "Apache-2.0", "provider": "OpenFold Consortium", "terms_url": "https://github.com/aqlaboratory/openfold-3/blob/main/LICENSE" }, { "kind": "service", "name": "ColabFold MSA server (api.colabfold.com)", "info_url": "https://github.com/sokrypton/ColabFold/wiki", "provider": "Steinegger Lab" } ], "display-name": "OpenFold3" }
description
Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill when predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation.
requirements
[ "gpu" ]

03 SKILL.md 正文

OpenFold3 Structure Prediction

Prerequisites

Requirement Minimum Recommended
Python 3.10+ 3.11
CUDA 12.1+ 12.4+
GPU VRAM 24GB 80GB (H100)
RAM 32GB 64GB
Disk (weights) 3GB -

How to run

Installation

pip install 'openfold3[cuequivariance]==0.4.1'

The default attention kernel is DeepSpeed DS4Sci_EvoformerAttention. If DeepSpeed is unavailable, switch to the cuEquivariance triangle kernels (no build-from-source) by overriding the eval memory settings in model_config.py (use_deepspeed_evo_attention: False, use_cueq_triangle_kernels: True). Some pre-built environments already ship this override; check before re-patching.

Weights

Apache-2.0, ~2.3 GB from HF OpenFold/OpenFold3. The repo is gated (auto-approval) — accept the access form on the HF model page and authenticate (huggingface-cli login or HF_TOKEN) before downloading:

export OPENFOLD_CACHE=~/.openfold3
huggingface-cli download OpenFold/OpenFold3 checkpoints/of3-p2-155k.pt \
  --local-dir "$OPENFOLD_CACHE"

run_openfold will also auto-download to $OPENFOLD_CACHE on first run if egress is open and HF credentials are available (either HF_TOKEN or a prior huggingface-cli login) with repo access granted. The interactive setup_openfold helper exists but prompts on stdin; prefer the explicit download above for non-interactive runs.

Running

export OPENFOLD_CACHE=/path/to/cache
run_openfold predict \
  --query_json=queries.json \
  --output-dir out/ \
  --use-msa-server false \
  --use-templates false

run_openfold discovers the checkpoint under $OPENFOLD_CACHE automatically. Only pass --inference-ckpt-path <file.pt> if you have a non-standard layout or multiple checkpoints and need to pin one explicitly.

For MSA + templates (slower, higher accuracy), drop the two false flags. The MSA server is api.colabfold.com; template chain-ID remap hits data.rcsb.org (GraphQL) — both must be reachable.

Query JSON format

OpenFold3 does not read FASTA. Queries are a JSON object validated by InferenceQuerySet (pydantic, extra: forbid — unknown keys reject):

{
  "queries": {
    "my_complex": {
      "chains": [
        {"molecule_type": "protein", "chain_ids": ["A"], "sequence": "MQIFVK…"},
        {"molecule_type": "protein", "chain_ids": ["B", "C"], "sequence": "MVLSPA…"},
        {"molecule_type": "ligand",  "chain_ids": ["L"], "smiles": "CC(=O)Oc1ccccc1C(=O)O"}
      ],
      "use_msas": true
    }
  },
  "seeds": [42]
}
molecule_type required field
protein / dna / rna sequence
ligand smiles or ccd_codes: ["HEM"]

chain_ids is a list — repeat the same sequence across multiple chain IDs for homo-oligomers. Per-chain paired_msa_file_paths / main_msa_file_paths let you supply your own a3m instead of the server.

Key parameters

Flag Default Description
--num-diffusion-samples 5 Structures per (query, seed)
--num-model-seeds 1 Number of model seeds per query (multiplies output count alongside JSON seeds and diffusion samples)
--use-msa-server true ColabFold MMseqs2 server for MSA
--use-templates true ColabFold template search + RCSB remap
--inference-ckpt-path auto-discovered under $OPENFOLD_CACHE Override only — for non-standard layouts or to pin a specific checkpoint file

Output format

out/
├── summary.txt
├── model_config.json / experiment_config.json
├── inference_query_set.json
└── <query_name>/seed_<N>/
    ├── <query>_seed_<N>_sample_<k>_model.cif
    ├── <query>_seed_<N>_sample_<k>_confidences.json           # full PAE/pLDDT
    ├── <query>_seed_<N>_sample_<k>_confidences_aggregated.json
    └── timing.json

*_confidences_aggregated.json is the small one to read first:

{
  "avg_plddt": 78.96, "ptm": 0.667, "iptm": 0.0, "gpde": 0.73,
  "has_clash": 0.0, "sample_ranking_score": 0.133,
  "chain_ptm": {"A": 0.667}, "chain_pair_iptm": {}
}

What good output looks like

  • summary.txt shows Successful Queries: N matching your input count
  • avg_plddt > 70 (single-seq) / > 80 (with MSA)
  • ptm > 0.6; for complexes, iptm > 0.5
  • has_clash: 0.0
  • .cif ~50-150 KB per sample for a small protein

Verify

grep -E 'Successful|Failed' out/summary.txt
find out -name '*_model.cif' | wc -l   # = queries x json_seeds x num-model-seeds x num-diffusion-samples

Troubleshooting

Error Cause Fix
_deepspeed_evo_attn requires that DeepSpeed be installed default eval kernel is DS4Sci on CUDA install deepspeed (needs nvcc + CUTLASS), or in model_config.py eval block set use_deepspeed_evo_attention: False + use_cueq_triangle_kernels: True (cuEq path; no build)
CUTLASS_PATH ... not set ... cutlass_library is not installed cuEq path still needs the python cutlass_library shim pip install nvidia-cutlass
libXrender.so.1: cannot open shared object file rdkit (via pdbeccdutils) needs X11 render libs apt-get install libxrender1 libxext6 libsm6
ModuleNotFoundError: boto3 (or awscrt) openfold3.core.data.io.s3 is eager-imported even when weights are local pip install boto3 awscrt
ValidationError: queries / Field required or Input should be an object wrong JSON shape top-level is {"queries": {"<name>": {...}}} (a dict, not a list)
ValidationError ... settings / Extra inputs are not permitted tried to override model config via --runner-yaml --runner-yaml is InferenceExperimentConfig only; kernel/memory settings live in model_config.py
Failed to fetch chain ID mappings from RCSB for N entries data.rcsb.org unreachable (allowlist/offline) run with --use-templates false, or open egress to data.rcsb.org
CUDA out of memory large complex / many samples reduce --num-diffusion-samples; the low_mem preset (model_setting_presets.yml) offloads more aggressively

04 同仓库更多 Skills

pengqianhan
pengqianhan/AI-Human-Research-OS

workflow-skill-creator

Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say "make this a skill", "create a skill from what we just did", "package this workflow" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).

★ 3
pengqianhan
pengqianhan/AI-Human-Research-OS

uv

Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.

★ 3
pengqianhan
pengqianhan/AI-Human-Research-OS

uniprot-database

Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).

★ 3
pengqianhan
pengqianhan/AI-Human-Research-OS

unibind-database

Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED/FASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.

★ 3
pengqianhan
pengqianhan/AI-Human-Research-OS

ucsc-conservation-and-tfbs

Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).

★ 3
pengqianhan
pengqianhan/AI-Human-Research-OS

string-database

Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.

★ 3