TYPHON/config_template.yaml at main · erenada/TYPHON · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
# TYPHON Pipeline Configuration Template
# Authors: Harry Kane, PhD; Eren Ada, PhD
#
# This configuration file controls all aspects of the TYPHON chimeric RNA detection pipeline.
# TYPHON integrates three complementary tools: LongGF, Genion, and JaffaL for comprehensive fusion detection.

# =============================================================================
# PROJECT SETTINGS
# =============================================================================
project:
  name: TYPHON_Test_Analysis                    # Analysis name for output labeling
  output_dir: ./test_output_pipeline            # Main output directory for all results
  threads: 20                                   # Default threads for parallel processing
  author: Your Name                     # Author names for documentation

# =============================================================================
# INPUT DATA PATHS
# =============================================================================
input:
  fastq_dir: ./test_data/FASTQ                  # Directory containing FASTQ files (.fastq, .fq, .gz supported)

# =============================================================================
# REFERENCE FILES
# =============================================================================
references:
  genome: ./test_data/REFERENCES/GRCm39.primary_assembly.genome.fa     # Reference genome FASTA
  gtf: ./test_data/REFERENCES/gencode.vM28.annotation.gtf              # Gene annotation GTF file
  transcriptome: ./test_data/REFERENCES/gencode.vM28.transcripts.fa    # Transcriptome FASTA for Genion

# =============================================================================
# PIPELINE MODULES
# =============================================================================
modules:
  # ---------------------------------------------------------------------------
  # LongGF MODULE: Direct RNA-seq fusion detection
  # ---------------------------------------------------------------------------
  longgf:
    enabled: true                              # Enable/disable LongGF analysis
    keep_intermediate: false                    # Keep intermediate BAM/SAM files

    # Core LongGF parameters (command: LongGF input.bam gtf.gtf 100 50 100 2 0 1 0)
    min_overlap_len: 100                        # Minimum overlap length for fusion detection
    bin_size: 50                                # Bin size for genomic interval processing
    min_map_len: 100                           # Minimum mapping length for valid alignments
    pseudogene: 2                              # Pseudogene filter level (0=off, 1=strict, 2=moderate)
    secondary_alignment: 0                      # Include secondary alignments (0=no, 1=yes)
    min_sup_read: 1                            # Minimum supporting reads per fusion
    output_flag: 0                             # Output format flag (0=standard, 1=verbose)

  # ---------------------------------------------------------------------------
  # GENION MODULE: Graph-based fusion detection with custom TYPHON enhancements
  # ---------------------------------------------------------------------------
  genion:
    enabled: true                             # Enable/disable Genion analysis
    min_support: 1                             # Minimum supporting reads (--min-support parameter)
    keep_debug: true                           # Keep .fail files with detailed debug information
    output_bin_dir: ./bin                      # Directory containing custom Genion binary
    debug_compilation: true                     # Compile Genion with debug flags for detailed output
    threads: 20                                 # Compilation threads (Genion itself is single-threaded)

    # Advanced Genion parameters (currently hardcoded, future expansion)
    # genomic_superdups_file: ""               # Path to genomic segmental duplications file (optional)
    # custom_gtf_modifications: true           # Apply TYPHON-specific GTF processing

  # ---------------------------------------------------------------------------
  # JAFFAL MODULE: JAFFA-Long pipeline for Nanopore/PacBio data
  # ---------------------------------------------------------------------------
  jaffal:
    enabled: true                             # Enable/disable JaffaL analysis
    jaffal_dir: ./jaffal/JAFFA-version-2.3     # JaffaL installation directory (absolute path)
    genome_build: mm39                         # Genome build identifier (mm39, hg38, etc.)
    annotation: gencode_M28                    # Annotation build identifier

    # Memory management
    max_memory: "20G"                         # Maximum memory for JaffaL processes (conservative)
    bpipe_memory: "20G"                       # Memory allocation for bpipe Java heap
    process_samples_sequentially: true        # Process one sample at a time to manage memory usage

    # Reference files for JaffaL (processed by setup_jaffal.py)
    reference_files:
      genome_fasta_gz: ./test_data/FILES_FOR_JAFFAL/mm39.fa.gz           # Genome FASTA (can be .gz)
      transcriptome_fasta: ./test_data/FILES_FOR_JAFFAL/mm39_gencode_M28.fasta    # Transcriptome FASTA
      annotation_bed: ./test_data/FILES_FOR_JAFFAL/mm39_gencode_M28.bed           # Gene annotations in BED format
      annotation_tab: ./test_data/FILES_FOR_JAFFAL/mm39_gencode_M28.tab           # Tab-delimited gene info

    # JaffaL execution parameters
    threads: 20                                # Number of threads for bpipe/JaffaL execution
    keep_intermediate: false                   # Keep intermediate bpipe files
    min_low_spanning_reads: 1                  # Minimum spanning reads for low-confidence fusions

    # Advanced JaffaL parameters (applied during setup)
    assembly_parameters:                     # Parameters for transcript assembly
      kmer_lengths: "19,36,4"                # K-mer lengths for assembly (Ks parameter)
      oases_merge_length: 27                 # Oases merge k-mer length (Kmerge parameter)
      transcript_min_length: 100             # Minimum contig length (transLength parameter)
    trimming_parameters:                     # Parameters for read trimming
      phred_scores: 33                       # PHRED quality score type
      min_read_length: 35                    # Minimum read length after trimming
      min_quality_score: 0                   # Quality trimming threshold (0=no trimming)
    alignment_parameters:                    # Parameters for read alignment
      map_params: "-k1 --no-mixed --no-discordant --mm"  # Bowtie2 mapping parameters
      blast_options: "-perc_identity 96"     # BLAST identity threshold
      blat_options: "-minIdentity=96 -minScore=30"  # BLAT alignment options

# =============================================================================
# GLOBAL OPTIONS
# =============================================================================
options:
  cleanup_intermediate: true                   # Remove intermediate files after successful completion
  debug: true                                 # Enable debug logging throughout pipeline
  keep_sam_files: true                        # Preserve SAM files for downstream analysis

  # Resource management
  max_memory_gb: 28                           # Maximum memory usage per process (GB)
  temp_dir: /tmp                              # Temporary directory for large file operations

  # Integration and overlap analysis
  enable_integration: true                    # Run integration analysis after all modules complete

  # Exon repair protocol settings
  exon_repair:
    enabled: true                             # Enable molecular-level sequence reconstruction
    bam_file: null                           # BAM file path (auto-detected from output_dir if null)
    keep_intermediate: true                  # Keep intermediate BLAST and BED files
    blast_threads: 20                        # Threads for BLAST operations