example2.config.yaml

# PanHOG Configuration File
# This file contains default settings for the PanHOG pangenome analysis toolkit
# Command-line arguments will override these settings

# Input files (required)
hog: "path/to/your/N0.tsv"
fasta: "path/to/your/fasta_directory"

# Output settings
output: "./results"
prefix: "my_analysis_"

# Analysis options
pan: true
# clade: "species1,species2,species3"  # Uncomment for clade-specific analysis

# Optional analyses
proteome: "ALL"  # Set to "ALL" or specify comma-separated species list
genevar: "ALL"   # Set to "ALL" or specify comma-separated species list
saturation: true
saturation_cladepair: false
pav: true
matrix: true
summary: true
random_hog_matrix: 1000

# Bootstrap settings
bootstrap: 100

# Visualization settings for global saturation analysis
marker_core: "o"
marker_pan: "s"

# Clade-specific saturation analysis settings
clade1: "sample1,sample2,sample3"
clade2: "sample4,sample5,sample6"

# Markers for cladepair saturation analysis
marker_core_clade1: "^"
marker_pan_clade1: "^"
marker_core_clade2: "s"
marker_pan_clade2: "s"

# Colors for cladepair saturation analysis
color_core_clade1: "#c0392b"
color_pan_clade1: "#f1c40f"
color_core_clade2: "#c0392b"
color_pan_clade2: "#3498db"

# Gene variation heatmap transformation
zscore: false
log: true

# Ka/Ks analysis (requires CDS FASTA files)
# kaks: true
# cds: "path/to/cds_directory"
# kaks_type: "core"         # core, shell, private, all
# kaks_method: "biopython"  # biopython or kakscalculator
# aligner: "mafft"          # mafft or muscle
# backtrans: "naive"        # naive or pal2nal

# Phylogeny LCA analysis
# species_tree: "path/to/species_tree.nwk"

# Supermatrix from single-copy orthologs
# supermatrix: true