bio-comparative-genomics-hgt-detection

name	bio-comparative-genomics-hgt-detection
description	Detect horizontal gene transfer events using HGTector, compositional analysis, and phylogenetic incongruence methods. Identify foreign genes in bacterial and archaeal genomes from anomalous composition or unexpected phylogenetic placement. Use when searching for horizontally transferred genes or analyzing genome evolution in prokaryotes.
tool_type	mixed
primary_tool	HGTector

Horizontal Gene Transfer Detection

HGTector Workflow

'''HGT detection with HGTector and compositional methods'''

import subprocess
import pandas as pd
import numpy as np
from Bio import SeqIO
from collections import Counter


def run_hgtector(proteome, taxonomy_db, output_dir, threads=4):
    '''Run HGTector for HGT detection

    HGTector uses BLAST-based phyletic distribution analysis:
    1. BLAST proteome against reference database
    2. Classify genes by taxonomic distribution
    3. Identify genes with unexpected phyletic patterns

    Requires:
    - NCBI taxonomy database
    - Reference protein database (e.g., RefSeq)
    '''
    # Search against database
    search_cmd = f'''hgtector search \\
        -i {proteome} \\
        -o {output_dir}/search \\
        -m diamond \\
        -t {threads} \\
        -d refseq'''

    subprocess.run(search_cmd, shell=True)

    # Analyze results
    analyze_cmd = f'''hgtector analyze \\
        -i {output_dir}/search \\
        -o {output_dir}/analyze \\
        -t {taxonomy_db}'''

    subprocess.run(analyze_cmd, shell=True)

    return f'{output_dir}/analyze'


def parse_hgtector_results(results_dir):
    '''Parse HGTector output for HGT candidates

    Output columns:
    - gene: Gene identifier
    - close: Score for close taxonomic matches
    - distal: Score for distal taxonomic matches
    - hgt: HGT prediction (1 = putative HGT)
    '''
    results_file = f'{results_dir}/scores.tsv'
    df = pd.read_csv(results_file, sep='\t')

    # Classify HGT candidates
    # distal > close suggests foreign origin
    df['hgt_score'] = df['distal'] - df['close']

    # Threshold: Higher positive score = stronger HGT signal
    # Score > 0.5: Moderate HGT evidence
    # Score > 1.0: Strong HGT evidence
    df['hgt_call'] = df['hgt_score'] > 0.5

    return df

Compositional Analysis

def calculate_gc_content(sequence):
    '''Calculate GC content of a sequence'''
    gc = sum(1 for nt in sequence.upper() if nt in 'GC')
    return gc / len(sequence) if sequence else 0


def calculate_codon_usage(cds_sequence):
    '''Calculate codon usage frequencies

    Foreign genes often have different codon usage
    reflecting their donor genome's bias
    '''
    if len(cds_sequence) % 3 != 0:
        return None

    codons = [cds_sequence[i:i+3] for i in range(0, len(cds_sequence) - 2, 3)]
    counts = Counter(codons)
    total = sum(counts.values())

    return {codon: count / total for codon, count in counts.items()}


def calculate_cai(gene_codons, reference_codons):
    '''Calculate Codon Adaptation Index

    CAI measures how well a gene matches the host codon usage
    Low CAI suggests foreign origin

    CAI < 0.5: Potentially foreign
    CAI 0.5-0.7: Intermediate
    CAI > 0.7: Native-like codon usage
    '''
    import math

    w_values = {}
    for aa_codons in group_synonymous_codons(reference_codons):
        max_freq = (reference_codons.get(c, )  c  aa_codons)
         max_freq > :
             c  aa_codons:
                w_values[c] = reference_codons.get(c, ) / max_freq

    cai_sum = 
    n = 
     codon, freq  gene_codons.items():
         codon  w_values  w_values[codon] > :
            cai_sum += math.log(w_values[codon]) * freq
            n += freq

     math.exp(cai_sum)  n >   


 ():
    
    genetic_code = {
        : [, ], : [, , , , , ],
        : [, , ], : [], : [, , , ],
        : [, , , , , ],
        : [, , , ], : [, , , ],
        : [, , , ], : [, ],
        : [, ], : [, ], : [, ],
        : [, ], : [, ], : [, ],
        : [, ], : [], : [, , , , , ],
        : [, , , ]
    }
     [codons  codons  genetic_code.values()]


 ():
    
    
    genome = SeqIO.read(genome_fasta, )
    genome_gc = calculate_gc_content((genome.seq))

    
    windows = []
    seq = (genome.seq)
     i  (, (seq) - window_size, window_size // ):
        window_seq = seq[i:i + window_size]
        gc = calculate_gc_content(window_seq)
        windows.append({
            : i,
            : i + window_size,
            : gc
        })

    df = pd.DataFrame(windows)

    
    mean_gc = df[].mean()
    std_gc = df[].std()

    
    df[] = (df[] - mean_gc) / std_gc
    df[] = (df[]) > 

     df, genome_gc

Phylogenetic Incongruence

def detect_phylogenetic_incongruence(gene_tree, species_tree):
    '''Detect HGT via phylogenetic incongruence

    Compare gene tree topology to species tree
    Genes with conflicting placement may be HGT

    Methods:
    - AU test: Approximately Unbiased test
    - SH test: Shimodaira-Hasegawa test
    - Bootstrap: Compare bootstrap support
    '''
    from Bio import Phylo
    from io import StringIO

    # Load trees
    g_tree = Phylo.read(StringIO(gene_tree), 'newick')
    s_tree = Phylo.read(StringIO(species_tree), 'newick')

    # Get taxa
    g_taxa = set(t.name for t in g_tree.get_terminals())
    s_taxa = set(t.name for t in s_tree.get_terminals())

    # Basic topological comparison
    # For full analysis, use IQ-TREE topology tests
    common_taxa = g_taxa & s_taxa

    return {
        'gene_taxa': g_taxa,
        'species_taxa': s_taxa,
        'common_taxa': common_taxa,
        'unique_to_gene': g_taxa - s_taxa
    }


def run_topology_test(alignment, tree1, tree2, output_prefix):
    '''Run AU/SH tests for tree comparison

    Tests if gene significantly favors unexpected topology
    p < 0.05 suggests trees are significantly different
    '''
    cmd = f'''iqtree2 -s {alignment} \\
        -z trees.nwk \\
        -n 0 \\
        -zb 10000 \\
        -au \\
        -pre {output_prefix}'''

    # Prepare tree file
    with open('trees.nwk', 'w')  f:
        f.write()

    subprocess.run(cmd, shell=)

     

Genomic Island Detection

def identify_genomic_islands(genome_gc, gene_annotations, gc_threshold=2):
    '''Identify putative genomic islands (HGT clusters)

    Genomic islands characteristics:
    - Anomalous GC content
    - Different codon usage
    - Flanked by mobile elements (IS, integrases)
    - Near tRNA genes (common integration sites)

    Islands often contain:
    - Pathogenicity factors
    - Antibiotic resistance genes
    - Metabolic capabilities
    '''
    # Group consecutive anomalous genes
    islands = []
    current_island = []

    sorted_genes = sorted(gene_annotations, key=lambda x: x['start'])

    for gene in sorted_genes:
        if abs(gene.get('gc_zscore', 0)) > gc_threshold:
            if not current_island:
                current_island = [gene]
            elif gene['start'] - current_island[-1]['end'] < 10000:
                current_island.append(gene)
            else:
                if len(current_island) >= 3:  # Minimum 3 genes for island
                    islands.append(current_island)
                current_island = [gene]
        else:
            if current_island and len(current_island) >= 3:
                islands.append(current_island)
            current_island = []

    if current_island and len(current_island) >= 3:
        islands.append(current_island)

    return islands


def ():
    
    features = {
        : ,
        : ,
        : ,
        : 
    }

     gene  island_genes:
        product = gene.get(, ).lower()
           product:
            features[] = 
           product:
            features[] = 
           product    product:
            features[] = 

     features

Related Skills

• comparative-genomics/ortholog-inference - Identify orthologs for phylogenetic tests
• phylogenetics/modern-tree-inference - Build gene trees for incongruence analysis
• metagenomics/amr-detection - AMR genes often on mobile elements