pipeline_paths.yaml

# ─────────────────────────────────────────────────────────────────────────────
#  pipeline_paths.yaml  —  Static paths & permanent tool parameters
#  You should rarely need to edit this file.
#  All paths are relative to the workflow base directory unless absolute.
# ─────────────────────────────────────────────────────────────────────────────

# ── Shared script directory ──────────────────────────────────────────────────
scripts: "script_base"

# ── Synteny processing ───────────────────────────────────────────────────────
satsuma_alignments:       "inputs/synteny_processing/Satsuma_alignments"
sequence_lengths_file:    "inputs/synteny_processing/all_sequence_lengths.txt"
synteny_results:          "outputs/synteny_processing"

# ── Output folder name for pre-EBA synteny ──
out_final: "synteny_plots"

# ── De-novo Satsuma alignment (only used when run_satsuma_alignment: true) ───
# When active, the pipeline aligns FASTA files instead of reading
# pre-computed Satsuma output.  The alignment results are written to
# output_dir, which then replaces  satsuma_alignments  as the source
# of alignment files for downstream synteny processing.
satsuma_align:
  fasta_dir:    "inputs/fasta"        # folder containing all genome FASTA files
  # chr_fasta_dir is auto-populated at runtime; do not edit.
  # When run_satsuma_alignment, chainNet_generation, or Ancestor_seq_recunstruction
  # is active, FASTA files are copied here with filenames like sps1.fa (Genus_
  # prefix stripped) and headers rewritten from ">1" to ">chr1".
  chr_fasta_dir: "outputs/fasta_chr"   # auto-generated; chr-prefixed FASTA files
  output_dir:   "outputs/synteny_processing/Satsuma_alignments"  # where SatsumaSynteny2 writes results
  tool_path:    "tools/product/bin/SatsumaSynteny2"      # path to the SatsumaSynteny2 binary
  threads:      40                                        # CPU threads given to each SatsumaSynteny2 job
  max_parallel: 1                                         # how many alignments run at the same time
  # satsuma2_path: "tools/product/bin"                   # directory containing Satsuma binaries
  #   Set this only if SATSUMA2_PATH needs to differ from the directory
  #   that tool_path lives in.  By default it is derived automatically as
  #   dirname(tool_path), which is correct for a standard Satsuma install.

# ── EBA analysis — paths ─────────────────────────────────────────────────────
eba_format:
  pre_EBA_dir:        "outputs/eba_analysis/pre-EBA"
  scaffolds_file:     "ALL_CHROMOSOMES"   # use path"inputs/synteny_processing/Scaffolds.txt" or "ALL_CHROMOSOMES" to include everything
  eba_input_dir:      "inputs/eba_analysis/EBA-input"
  mshsbs_dir:         "outputs/eba_analysis/msHSBs"
  ebrs_dir:           "outputs/eba_analysis/EBRs"
  copy_destination_dir: "outputs/eba_analysis/EBA_results"
  chr_size_file:      "outputs/eba_analysis/chr_size.txt"
  reference_fasta:    "inputs/eba_analysis/reference.fasta"       # reference genome FASTA for msHSBs sequence extraction

# ── EBA tool paths ────────────────────────────────────────────────────────────
eba_tools:
  eba_script_path: "tools/EBA3.0/EBA.pl"

# ── EBA static parameters (paths + fixed run params) ─────────────────────
eba:
  d: "inputs/eba_analysis/EBA-input"
  t: 20
  c: "inputs/eba_analysis/classification.eba"
  k: true
  # n, r, p come from run_sybr_config.yaml and are deep-merged by config_handling.smk

# ── Enrichment analysis — paths ───────────────────────────────────────────────
enrichment:
  annotation_file: "inputs/enrichment_analysis/protein_annotation.tsv"
  kegg_file:       "inputs/enrichment_analysis/3kegg_annotationTOgenes.txt"
  msHSBs_dir:      "outputs/eba_analysis/msHSBs"

# ── Alignment processing / chainNet ──────────────────────────────────────────
chainNet:
  seq_dir:           "inputs/Ancestor_seq_recunstruction/seq"
  lastZ_alignments:  "inputs/Ancestor_seq_recunstruction/LastZ_alignments"  # pre-computed .axt files; overridden automatically when run_lastz_alignment: true
  output_dir:        "outputs/Ancestor_seq_recunstruction"

# ── De-novo LastZ alignment (only used when run_lastz_alignment: true) ────────
# When active, FASTA files are read from  satsuma_align.fasta_dir  (the same
# directory used by satsuma_alignment.smk).  The short species name for .axt
# output is derived automatically from  reference_name  by taking the last
# word after the underscore and lowercasing it:
#   e.g.  reference_name: "Adineta_vaga"  →  reference short name: "vaga"
# Output .axt files land in  chainNet.lastZ_alignments  so that
# alignment_processing.smk and deschrambler.smk pick them up normally.
lastz_align:
  tool_path:    "lastz"           # path to lastz binary, or just "lastz" if on PATH
  output_dir:   "outputs/Ancestor_seq_recunstruction/LastZ_alignments"  # where .axt files are written when run_lastz_alignment: true
  threads:      1                 # threads per LastZ job
  max_parallel: 10                 # how many LastZ jobs run at the same time
  params: "C=0 E=30 H=2000 K=2200 L=2200 O=400 Y=3400"  # lastz scoring parameters

# ── DESCHRAMBLER ─────────────────────────────────────────────────────────────
deschrambler:
  pipeline_tool_dir: "tools/DESCHRAMBLER"
  tree_file:         "inputs/Ancestor_seq_recunstruction/tree.txt"
  species_file:      "inputs/Ancestor_seq_recunstruction/species_info.txt"

# ── HGT overlap analysis ──────────────────────────────────────────────────────
# Compares inputs/HGTs/hgt.txt against msHSBs, EBRs, and DESCHRAMBLER ancestoral genes (block_list.txt).
# Results are written to outputs/hgt_overlap/ by default.
# Override either path here if needed.
hgt_overlap:
  hgt_dir:    "inputs/HGTs"            # directory containing hgt.txt
  output_dir: "outputs/hgt_overlap"    # where overlap results are written