solublempnn — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited solublempnn (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
| Requirement | Minimum | Recommended |
|---|---|---|
| Python | 3.8+ | 3.10 |
| CUDA | 11.0+ | 11.7+ |
| GPU VRAM | 8GB | 16GB (T4) |
| RAM | 8GB | 16GB |
First time? See Getting started to set up Modal and biomodals.
SolubleMPNN is the soluble model type within the LigandMPNN wrapper:
cd biomodals
modal run modal_ligandmpnn.py \
--input-pdb backbone.pdb \
--params-str "--model_type soluble_mpnn --number_of_batches 16 --temperature 0.1"GPU: A10G default | Timeout: 900s default
git clone https://github.com/dauparas/ProteinMPNN.git
cd ProteinMPNN
# The soluble weights are selected with --use_soluble_model, not a model name
python protein_mpnn_run.py \
--pdb_path backbone.pdb \
--out_folder output/ \
--num_seq_per_target 16 \
--sampling_temp "0.1" \
--use_soluble_model| Parameter | Default | Description |
|---|---|---|
--pdb_path | required | Input structure |
--use_soluble_model | off | Use the solubility-trained weights |
--num_seq_per_target | 1 | Sequences per structure |
--sampling_temp | "0.1" | Temperature (string) |
--model_name | v_48_020 | Noise level (0.20 A); orthogonal to solubility |
--model_name sets the training-noise level (v_48_002 = 0.02 A, v_48_010 = 0.10 A, v_48_020 = 0.20 A), not a solubility tier. Solubility is a separate weight set chosen with --use_soluble_model, available for v_48_010 and v_48_020. Higher noise gives more sequence diversity.
output/
├── seqs/backbone.fa
└── backbone_pdb/backbone_0001.pdb$ python protein_mpnn_run.py --pdb_path backbone.pdb --use_soluble_model --num_seq_per_target 8
Loading soluble model weights (v_48_020)...
Designing sequences for backbone.pdb
Generated 8 sequences in 2.1 seconds
output/seqs/backbone.fa:
>backbone_0001, score=1.31, global_score=1.24, seq_recovery=0.78
MKTAYIAKQRQISFVKSHFSRQLE...
>backbone_0002, score=1.28, global_score=1.21, seq_recovery=0.81
MKTAYIAKQRQISFVKSQFSRQLD...What good output looks like:
Should I use SolubleMPNN?
│
├─ What expression system?
│ ├─ E. coli → SolubleMPNN ✓
│ ├─ Mammalian → ProteinMPNN (PTMs matter more)
│ └─ Yeast → Either
│
├─ History of expression problems?
│ ├─ Yes, aggregation → SolubleMPNN ✓
│ ├─ Yes, low yield → SolubleMPNN ✓
│ └─ No → ProteinMPNN is fine
│
├─ What's in the binding site?
│ ├─ Small molecule / ligand → Use LigandMPNN
│ └─ Nothing / protein only → SolubleMPNN ✓
│
└─ Optimizing for expression?
└─ Add --use_soluble_model to ProteinMPNN| Campaign Size | Time (T4) | Cost (Modal) | Notes |
|---|---|---|---|
| 100 backbones × 8 seq | 15-20 min | ~$2 | Standard |
| 500 backbones × 8 seq | 1-1.5h | ~$8 | Large campaign |
Expected improvement: +15-30% solubility score vs standard ProteinMPNN.
grep -c "^>" output/seqs/*.fa # Should match backbone_count × num_seq_per_targetStill insoluble: Confirm --use_soluble_model is set; redesign more positions or add explicit hydrophobic-residue bias Low diversity: Increase temperature to 0.2 Poor folding: Use standard ProteinMPNN and optimize later
| Error | Cause | Fix |
|---|---|---|
RuntimeError: CUDA out of memory | Long protein or large batch | Reduce batch_size |
FileNotFoundError: v_48_020 | Missing model weights | Download soluble weights |
Next: Structure prediction for validation → protein-qc for filtering.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.