phylogenetics

What this skill does

# Phylogenetics

## Overview

Phylogenetic analysis reconstructs the evolutionary history of biological sequences (genes, proteins, genomes) by inferring the branching pattern of descent. This skill covers the standard pipeline:

1. **MAFFT** — Multiple sequence alignment
2. **IQ-TREE 2** — Maximum likelihood tree inference with model selection
3. **FastTree** — Fast approximate maximum likelihood (for large datasets)
4. **ETE3** — Python library for tree manipulation and visualization

**Installation:**
```bash
# Conda (recommended for CLI tools)
conda install -c bioconda mafft iqtree fasttree
pip install ete3
```

## When to Use This Skill

Use phylogenetics when:

- **Evolutionary relationships**: Which organism/gene is most closely related to my sequence?
- **Viral phylodynamics**: Trace outbreak spread and estimate transmission dates
- **Protein family analysis**: Infer evolutionary relationships within a gene family
- **Horizontal gene transfer detection**: Identify genes with discordant species/gene trees
- **Ancestral sequence reconstruction**: Infer ancestral protein sequences
- **Molecular clock analysis**: Estimate divergence dates using temporal sampling
- **GWAS companion**: Place variants in evolutionary context (e.g., SARS-CoV-2 variants)
- **Microbiology**: Species phylogeny from 16S rRNA or core genome phylogeny

## Standard Workflow

### 1. Multiple Sequence Alignment with MAFFT

```python
import subprocess
import os

def run_mafft(input_fasta: str, output_fasta: str, method: str = "auto",
               n_threads: int = 4) -> str:
    """
    Align sequences with MAFFT.

    Args:
        input_fasta: Path to unaligned FASTA file
        output_fasta: Path for aligned output
        method: 'auto' (auto-select), 'einsi' (accurate), 'linsi' (accurate, slow),
                'fftnsi' (medium), 'fftns' (fast), 'retree2' (fast)
        n_threads: Number of CPU threads

    Returns:
        Path to aligned FASTA file
    """
    methods = {
        "auto": ["mafft", "--auto"],
        "einsi": ["mafft", "--genafpair", "--maxiterate", "1000"],
        "linsi": ["mafft", "--localpair", "--maxiterate", "1000"],
        "fftnsi": ["mafft", "--fftnsi"],
        "fftns": ["mafft", "--fftns"],
        "retree2": ["mafft", "--retree", "2"],
    }

    cmd = methods.get(method, methods["auto"])
    cmd += ["--thread", str(n_threads), "--inputorder", input_fasta]

    with open(output_fasta, 'w') as out:
        result = subprocess.run(cmd, stdout=out, stderr=subprocess.PIPE, text=True)

    if result.returncode != 0:
        raise RuntimeError(f"MAFFT failed:\n{result.stderr}")

    # Count aligned sequences
    with open(output_fasta) as f:
        n_seqs = sum(1 for line in f if line.startswith('>'))
    print(f"MAFFT: aligned {n_seqs} sequences → {output_fasta}")

    return output_fasta

# MAFFT method selection guide:
# Few sequences (<200), accurate: linsi or einsi
# Many sequences (<1000), moderate: fftnsi
# Large datasets (>1000): fftns or auto
# Ultra-fast (>10000): mafft --retree 1
```

### 2. Trim Alignment (Optional but Recommended)

```python
def trim_alignment_trimal(aligned_fasta: str, output_fasta: str,
                            method: str = "automated1") -> str:
    """
    Trim poorly aligned columns with TrimAl.

    Methods:
    - 'automated1': Automatic heuristic (recommended)
    - 'gappyout': Remove gappy columns
    - 'strict': Strict gap threshold
    """
    cmd = ["trimal", f"-{method}", "-in", aligned_fasta, "-out", output_fasta, "-fasta"]
    result = subprocess.run(cmd, capture_output=True, text=True)
    if result.returncode != 0:
        print(f"TrimAl warning: {result.stderr}")
        # Fall back to using the untrimmed alignment
        import shutil
        shutil.copy(aligned_fasta, output_fasta)
    return output_fasta
```

### 3. IQ-TREE 2 — Maximum Likelihood Tree

```python
def run_iqtree(aligned_fasta: str, output_prefix: str,
                model: str = "TEST", bootstrap: int = 1000,
                n_threads: int = 4, extra_args: list = None) -> dict:
    """
    Build a maximum likelihood tree with IQ-TREE 2.

    Args:
        aligned_fasta: Aligned FASTA file
        output_prefix: Prefix for output files
        model: 'TEST' for automatic model selection, or specify (e.g., 'GTR+G' for DNA,
               'LG+G4' for proteins, 'JTT+G' for proteins)
        bootstrap: Number of ultrafast bootstrap replicates (1000 recommended)
        n_threads: Number of threads ('AUTO' to auto-detect)
        extra_args: Additional IQ-TREE arguments

    Returns:
        Dict with paths to output files
    """
    cmd = [
        "iqtree2",
        "-s", aligned_fasta,
        "--prefix", output_prefix,
        "-m", model,
        "-B", str(bootstrap),   # Ultrafast bootstrap
        "-T", str(n_threads),
        "--redo"                # Overwrite existing results
    ]

    if extra_args:
        cmd.extend(extra_args)

    result = subprocess.run(cmd, capture_output=True, text=True)

    if result.returncode != 0:
        raise RuntimeError(f"IQ-TREE failed:\n{result.stderr}")

    # Print model selection result
    log_file = f"{output_prefix}.log"
    if os.path.exists(log_file):
        with open(log_file) as f:
            for line in f:
                if "Best-fit model" in line:
                    print(f"IQ-TREE: {line.strip()}")

    output_files = {
        "tree": f"{output_prefix}.treefile",
        "log": f"{output_prefix}.log",
        "iqtree": f"{output_prefix}.iqtree",  # Full report
        "model": f"{output_prefix}.model.gz",
    }

    print(f"IQ-TREE: Tree saved to {output_files['tree']}")
    return output_files

# IQ-TREE model selection guide:
# DNA:     TEST → GTR+G, HKY+G, TrN+G
# Protein: TEST → LG+G4, WAG+G, JTT+G, Q.pfam+G
# Codon:   TEST → MG+F3X4

# For temporal (molecular clock) analysis, add:
# extra_args = ["--date", "dates.txt", "--clock-test", "--date-CI", "95"]
```

### 4. FastTree — Fast Approximate ML

For large datasets (>1000 sequences) where IQ-TREE is too slow:

```python
def run_fasttree(aligned_fasta: str, output_tree: str,
                  sequence_type: str = "nt", model: str = "gtr",
                  n_threads: int = 4) -> str:
    """
    Build a fast approximate ML tree with FastTree.

    Args:
        sequence_type: 'nt' for nucleotide or 'aa' for amino acid
        model: For nt: 'gtr' (recommended) or 'jc'; for aa: 'lg', 'wag', 'jtt'
    """
    if sequence_type == "nt":
        cmd = ["FastTree", "-nt", "-gtr"]
    else:
        cmd = ["FastTree", f"-{model}"]

    cmd += [aligned_fasta]

    with open(output_tree, 'w') as out:
        result = subprocess.run(cmd, stdout=out, stderr=subprocess.PIPE, text=True)

    if result.returncode != 0:
        raise RuntimeError(f"FastTree failed:\n{result.stderr}")

    print(f"FastTree: Tree saved to {output_tree}")
    return output_tree
```

### 5. Tree Analysis and Visualization with ETE3

```python
from ete3 import Tree, TreeStyle, NodeStyle, TextFace, PhyloTree
import matplotlib.pyplot as plt

def load_tree(tree_file: str) -> Tree:
    """Load a Newick tree file."""
    t = Tree(tree_file)
    print(f"Tree: {len(t)} leaves, {len(list(t.traverse()))} nodes")
    return t

def basic_tree_stats(t: Tree) -> dict:
    """Compute basic tree statistics."""
    leaves = t.get_leaves()
    distances = [t.get_distance(l1, l2) for l1 in leaves[:min(50, len(leaves))]
                 for l2 in leaves[:min(50, len(leaves))] if l1 != l2]

    stats = {
        "n_leaves": len(leaves),
        "n_internal_nodes": len(t) - len(leaves),
        "total_branch_length": sum(n.dist for n in t.traverse()),
        "max_leaf_distance": max(distances) if distances else 0,
        "mean_leaf_distance": sum(distances)/len(distances) if distances else 0,
    }
    return stats

def find_mrca(t: Tree, leaf_names: list) -> Tree:
    """Find the most recent common ancestor of a set of leaves."""
    return t.get_common_ancestor(*