Adme Property Predictor

Predict ADME (Absorption, Distribution, Metabolism, Excretion) properties for drug candidates using cheminformatics models and molecular descriptors. Evaluates drug-likeness, bioavailability, and pharmacokinetic profile to guide lead optimization and candidate selection in drug discovery.

# ADME Property Predictor

## Overview

Comprehensive pharmacokinetic prediction tool that assesses drug-likeness and ADME properties of small molecules using validated cheminformatics models, molecular descriptors, and structure-property relationships.

**Key Capabilities:**
- **Multi-Property Prediction**: Absorption, Distribution, Metabolism, Excretion
- **Drug-Likeness Scoring**: Lipinski's Rule of 5, Veber rules, QED score
- **Batch Processing**: Analyze compound libraries efficiently
- **Structure-Based Insights**: Identify liability hotspots and optimization opportunities
- **Comparative Analysis**: Rank candidates by predicted PK profile

## When to Use

**✅ Use this skill when:**
- Screening compound libraries for drug-like properties in early discovery
- Prioritizing lead compounds for advancement based on predicted PK
- Identifying ADME liabilities requiring structural optimization
- Comparing analogs to select candidates with optimal ADME profiles
- Filtering virtual screening hits before synthesis
- Generating ADME data for regulatory pre-submission packages
- Teaching pharmacokinetics and drug design principles

**❌ Do NOT use when:**
- Exact PK parameters needed for dosing → Use experimental PK studies
- Biologics (antibodies, proteins) → Use `antibody-pk-predictor`
- Natural products with complex structures → Models trained on synthetic small molecules
- Prodrugs requiring metabolic activation → Use `prodrug-activation-predictor`
- Prediction for clinical dosing decisions → **CRITICAL**: Experimental validation required
- Assessing toxicity or safety → Use `toxicity-structure-alert` or `admetox-predictor`

**Related Skills:**
- **上游**: `chemical-structure-converter` (structure preparation), `lipinski-rule-filter` (rule-based filtering)
- **下游**: `drug-candidate-evaluator` (integrated scoring), `molecular-dynamics-sim` (detailed binding)

## Integration with Other Skills

**Upstream Skills:**
- `chemical-structure-converter`: Convert between SMILES, InChI, MOL formats
- `lipinski-rule-filter`: Initial rule-based drug-likeness screening
- `chemical-structure-converter`: Generate 3D conformers for structure-based predictions
- `smiles-de-salter`: Remove salt counterions before analysis

**Downstream Skills:**
- `drug-candidate-evaluator`: Multi-parameter optimization including ADME
- `toxicity-structure-alert`: Assess safety alongside ADME
- `target-novelty-scorer`: Evaluate target uniqueness for selected candidates
- `biotech-pitch-deck-narrative`: Create investor materials with PK data

**Complete Workflow:**
```
Chemical Structure Converter (prepare structures) → 
  Lipinski Rule Filter (initial filtering) → 
    ADME Property Predictor (this skill, detailed PK) → 
      Drug Candidate Evaluator (integrated scoring) → 
        Toxicity Structure Alert (safety check)
```

## Core Capabilities

### 1. Absorption (A) Prediction

Predict intestinal absorption, solubility, and permeability:

```python
from scripts.adme_predictor import ADMEPredictor

predictor = ADMEPredictor()

# Predict absorption properties
absorption = predictor.predict_absorption(
    smiles="CC(=O)Oc1ccccc1C(=O)O",  # Aspirin
    properties=["all"]  # or specific: ["hia", "caco2", "solubility"]
)

print(absorption.summary())
```

**Predicted Properties:**
| Property | Model | Units | Interpretation |
|----------|-------|-------|----------------|
| **HIA** | ML + physicochemical | % | Human intestinal absorption; >80% good |
| **Caco-2** | QSPR | 10⁻⁶ cm/s | Permeability; >70 high, <25 low |
| **Solubility** | QSPR | mg/mL | Aqueous solubility; >0.1 mg/mL acceptable |
| **LogS** | QSPR | unitless | Intrinsic solubility; >-4 acceptable |
| **Lipinski Pass** | Rule-based | boolean | Passes all 5 rules |
| **Veber Pass** | Rule-based | boolean | PSA <140, rotatable bonds <10 |

**Best Practices:**
- ✅ Consider HIA and solubility together (high HIA but low solubility = dissolution-limited)
- ✅ Caco-2 good for oral absorption prediction; poor for BBB penetration
- ✅ Use both rule-based (Lipinski) and ML-based predictions for consensus
- ✅ Check solubility at physiological pH (not just intrinsic)

**Common Issues and Solutions:**

**Issue: Lipinski pass but poor solubility**
- Symptom: "Passes Rule of 5 but LogS = -5"
- Solution: Lipinski checks MW and LogP, not solubility directly; use explicit solubility prediction

**Issue: Caco-2 predicts high absorption but HIA low**
- Symptom: "Caco-2 = 85 (high) but HIA = 60%"
- Solution: Models have different training sets; Caco-2 is in vitro, HIA in vivo; HIA generally more reliable

### 2. Distribution (D) Prediction

Predict tissue distribution, protein binding, and brain penetration:

```python
# Predict distribution properties
distribution = predictor.predict_distribution(
    smiles="CC(=O)Oc1ccccc1C(=O)O",
    properties=["vd", "ppb", "bbb"]
)

# Access specific predictions
vd = distribution.volume_of_distribution
bbb = distribution.blood_brain_barrier
ppb = distribution.plasma_protein_binding
```

**Predicted Properties:**
| Property | Model | Units | Interpretation |
|----------|-------|-------|----------------|
| **Vd** | QSPR | L/kg | Volume of distribution; 0.1-10 typical |
| **PPB** | ML | % | Plasma protein binding; >90% high, <50% low |
| **BBB** | LogBB | unitless | Brain penetration; >0.3 penetrant |
| **fu** | Calculated | fraction | Free (unbound) fraction; 1 - PPB/100 |

**Best Practices:**
- ✅ High PPB (>90%) may require higher doses but longer half-life
- ✅ Low Vd (<0.3) = mainly in plasma; high Vd (>3) = extensive tissue distribution
- ✅ BBB penetration critical for CNS drugs; avoid for peripherally-acting drugs
- ✅ fu (free fraction) drives pharmacological activity, not total concentration

**Common Issues and Solutions:**

**Issue: BBB predictions unreliable for certain chemotypes**
- Symptom: "BBB model gives conflicting predictions for peptides"
- Solution: Models trained on small molecules; use specialized BBB predictors for peptides, macrocycles

**Issue: PPB overestimated for acidic drugs**
- Symptom: "PPB predicted 95% but experimental is 70%"
- Solution: Some models biased toward neutral/basic compounds; check model training set overlap

### 3. Metabolism (M) Prediction

Predict metabolic stability, CYP interactions, and liability sites:

```python
# Predict metabolism properties
metabolism = predictor.predict_metabolism(
    smiles="CC(=O)Oc1ccccc1C(=O)O",
    include_site_prediction=True
)

# Check CYP interactions
cyp_profile = metabolism.cyp_profile
stability = metabolism.metabolic_stability
```

**Predicted Properties:**
| Property | Model | Output | Interpretation |
|----------|-------|--------|----------------|
| **CYP Inhibition** | ML | IC50 or class | Potential DDI; <1 μM high risk |
| **CYP Substrate** | Classification | Boolean/Probability | Metabolized by specific CYP |
| **Stability** | ML | T1/2 or class | Microsomal/ hepatocyte stability |
| **Liability Sites** | Reactivity models | Atom indices | Soft spots for metabolism |
| **MAO Substrate** | Classification | Boolean | Monoamine oxidase substrate |

**Best Practices:**
- ✅ Screen for CYP3A4 inhibition early (most common DDI)
- ✅ Check if compound is CYP substrate (for polymorphism concerns)
- ✅ Identify metabolic hotspots for structural blocking
- ✅ Consider species differences (human vs rodent metabolism)

**Common Issues and Solutions:**

**Issue: False negatives for time-dependent inhibition (TDI)**
- Symptom: "No CYP inhibition predicted but TDI observed experimentally"
- Solution: Standard models predict reversible inhibition; use specialized TDI predictors

**Issue: Metabolic site prediction shows multiple hotspots**
- Symptom: "5 different atoms flagged as metabolic liabilities"
- Solution: Prioritize by reactivity score; consider blocking highest-risk site first

### 4. Excretion (E) Prediction

Predict clearance routes and elimination kinetics:

```python
# Predict excretion properties
excretion = predictor.predict_excre