protein-design-qc

Files (6)

• README.md
• SKILL.md
• binding-qc.md · references/
• composite-scoring.md · references/
• expression-qc.md · references/
• structural-qc.md · references/

SKILL.md (first lines)

# Protein Design Quality Control And Ranking

**Plain-language role**: Use this skill to decide which designs pass QC and which ones should move forward.

## Critical Limitation

**Individual metrics have weak predictive power for binding**. Research shows:
- Individual metric ROC AUC: 0.64-0.66 (slightly better than random)
- Metrics are **pre-screening filters**, not affinity predictors
- **Composite scoring is essential** for meaningful ranking

These thresholds filter out poor designs but do NOT predict binding affinity.

## QC Organization

QC is organized by **purpose** and **level**:

| Purpose | What it assesses | Key metrics |
|---------|------------------|-------------|
| **Binding** | Interface quality, binding geometry | ipTM, PAE, SC, dG, dSASA |
| **Expression** | Manufacturability, solubility | Instability, GRAVY, pI, cysteines |
| **Structural** | Fold confidence, consistency | pLDDT, pTM, scRMSD |

Each category has two levels:
- **Metric-level**: Calculated values with thresholds (pLDDT > 0.85)
- **Design-level**: Pattern/motif detection (odd cysteines, NG sites)

---

## Quick Reference: All Thresholds

| Category | Metric | Standard | Stringent | Source |
|----------|--------|----------|-----------|--------|
| **Structural** | pLDDT | > 0.85 | > 0.90 | AF2/Chai/Boltz |
| | pTM | > 0.70 | > 0.80 | AF2/Chai/Boltz |
| | scRMSD | < 2.0 Å | < 1.5 Å | Design vs pred |
| **Binding** | ipTM | > 0.50 | > 0.60 | AF2/Chai/Boltz |
| | PAE_interaction | < 12 Å | < 10 Å | AF2/Chai/Boltz |
| | Shape Comp (SC) | > 0.50 | > 0.60 | PyRosetta |
| | interface_dG | < -10 | < -15 | PyRosetta |
| **Expression** | Instability | < 40 | < 30 | BioPython |
| | GRAVY | < 0.4 | < 0.2 | BioPython |
| | ESM2 PLL | > 0.0 | > 0.2 | ESM2 |

### Design-Level Checks (Expression)
| Pattern | Risk | Action |
|---------|------|--------|
| Odd cysteine count | Unpaired disulfides | Redesign |
| NG/NS/NT motifs | Deamidation | Flag/avoid |
| K/R >= 3 consecutive | Proteolysis | Flag |
| >= 6 hydrophobic run | Aggregation | Redesign |

See: references/binding-qc.md, references/expression-qc.md, references/structural-qc.md

---

## Sequential Filtering Pipeline

```python
import pandas as pd

designs = pd.read_csv('designs.csv')

# Stage 1: Structural confidence
designs = designs[designs['pLDDT'] > 0.85]

# Stage 2: Self-consistency
designs = designs[designs['scRMSD'] < 2.0]

# Stage 3: Binding quality
designs = designs[(designs['ipTM'] > 0.5) & (designs['PAE_interaction'] < 10)]

# Stage 4: Sequence plausibility
designs = designs[designs['esm2_pll_normalized'] > 0.0]

# Stage 5: Expression checks (design-level)
designs = designs[designs['cysteine_count'] % 2 == 0]  # Even cysteines
designs = designs[designs['instability_index'] < 40]
```

---

## Composite Scoring (Required for Ranking)

Individual metrics alone are too weak. Use composite scoring:

```python
def composite_score(row):
    return (
        0.30 * row['pLDDT'] +
        0.20 * row['ipTM'] +
        0.20 * (1 - row['PAE_interaction'] / 20) +
        0.15 * row['shape_complementarity'] +
        0.15 * row['esm2_pll_normalized']
    )

designs['score'] = designs.apply(composite_score, axis=1)
top_designs = designs.nlargest(100, 'score')
```

For advanced composite scoring, see references/composite-scoring.md.

---

## Tool-Specific Filtering

### BindCraft Filter Levels
| Level | Use Case | Stringency |
|-------|----------|------------|
| Default | Standard design | Most stringent |
| Relaxed | Need more designs | Higher failure rate |
| Peptide | Designs < 30 AA | ~5-10x lower success |

### BoltzGen Filtering
```bash
boltzgen run ... \
  --budget 60 \
  --alpha 0.01 \
  --filter_biased true \

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

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