chai1-structure-prediction

Files (3)

• README.md
• SKILL.md
• api-reference.md · references/

SKILL.md (first lines)

# Chai-1 Structure Prediction

**Plain-language role**: Use Chai when you want a modern structure-prediction model for validating designed binders or complexes.

## Prerequisites

| Requirement | Minimum | Recommended |
|-------------|---------|-------------|
| Python | 3.10+ | 3.11 |
| CUDA | 12.0+ | 12.1+ |
| GPU VRAM | 24GB | 40GB (A100) |
| RAM | 32GB | 64GB |

## How to run

> **First time?** See [Installation Guide](../../docs/installation.md) to set up Modal and biomodals.

### Option 1: Modal
```bash
cd biomodals
modal run modal_chai1.py \
  --input-faa complex.fasta \
  --out-dir predictions/
```

**GPU**: A100 (40GB) | **Timeout**: 30min default

### Option 2: Chai API (recommended)
```bash
pip install chai_lab

python -c "
import chai_lab
from chai_lab.chai1 import run_inference

# Run prediction
run_inference(
    fasta_file='complex.fasta',
    output_dir='predictions/',
    num_trunk_recycles=3
)
"
```

### Option 3: Local installation
```bash
git clone https://github.com/chaidiscovery/chai1-structure-prediction-lab.git
cd chai1-structure-prediction-lab
pip install -e .

chai1-structure-prediction-lab predict \
  --fasta complex.fasta \
  --output predictions/
```

## FASTA Format

### Protein complex
```
>binder
MKTAYIAKQRQISFVKSHFSRQLE...
>target
MVLSPADKTNVKAAWGKVGAHAGE...
```

### Protein + ligand
```
>protein
MKTAYIAKQRQISFVKSHFSRQLE...
>ligand|smiles
CCO
```

### Protein + DNA/RNA
```
>protein
MKTAYIAKQRQISFVKSHFSRQLE...
>dna
ATCGATCGATCG
```

## Key parameters

| Parameter | Default | Range | Description |
|-----------|---------|-------|-------------|
| `num_trunk_recycles` | 3 | 1-10 | Recycles (more = better) |
| `num_diffn_timesteps` | 200 | 50-500 | Diffusion steps |
| `seed` | 0 | int | Random seed |

## Output format

```
predictions/
├── pred.model_idx_0.cif    # Best model (CIF format)
├── pred.model_idx_1.cif    # Second model
├── scores.json             # Confidence scores
├── pae.npy                 # PAE matrix
└── plddt.npy               # pLDDT values
```

**Note**: Chai-1 outputs CIF format. Convert to PDB if needed:
```python
from Bio.PDB import MMCIFParser, PDBIO
parser = MMCIFParser()
structure = parser.get_structure("pred", "pred.model_idx_0.cif")
io = PDBIO()
io.set_structure(structure)
io.save("pred.model_idx_0.pdb")
```

### Extracting metrics
```python
import numpy as np
import json

# Load scores
with open('predictions/scores.json') as f:
    scores = json.load(f)

From BioTender-max/awesome-bio-agent-skills, MIT.

More from BioTender-max/awesome-bio-agent-skills