{
  "pipeline_id": "chr1-section-a-complexity-v1",
  "pipeline_title": "Human Chromosome 1 Section A (1p36.33) Coding & Annotation-Agnostic Structural Complexity Scan",
  "accession": "NC_000001.11:1000001-1060000",
  "region_length_bp": 60000,
  "cached_from_disk": false,
  "total_duration_ms": 1364,
  "step_trace": [
    {
      "step_index": 1,
      "stage_id": "fetch:ncbi_grch38_chr1_sec_a",
      "engine": "Tier 1 (bio-suite fetch)",
      "input_schema": "GenomicCoordinate<NC_000001.11:1000001-1060000>",
      "output_schema": "(FastaRecord, Vec<GenomicAnnotation>)",
      "duration_ms": 635,
      "summary": "Loaded 60000 bp from Human GRCh38 Chr1p36.33 Section A (cached=false) with 5 annotated coding/repeat features."
    },
    {
      "step_index": 2,
      "stage_id": "task:complexity:cds_extraction_and_profile",
      "engine": "Tier 4 (bio-suite complexity)",
      "input_schema": "Vec<CodingRegionSlice>",
      "output_schema": "Vec<SequenceComplexityMetrics>",
      "duration_ms": 721,
      "summary": "Profiled 4 protein-coding sub-loci (HES4, ISG15, AGRN) for Shannon entropy, LZ76 compressibility, DFA Hurst scaling, and G4Hunter propensity."
    },
    {
      "step_index": 3,
      "stage_id": "task:genome:unbiased_window_scan_and_intersect",
      "engine": "Tier 2 & 4 (bio-suite genome + complexity)",
      "input_schema": "SlidingWindowStream<2000bp, step=1000bp>",
      "output_schema": "Vec<AnnotatedComplexityRegion>",
      "duration_ms": 7,
      "summary": "Scanned 59 annotation-agnostic sliding windows across Chr1 Section A and intersected 6 high-complexity anomaly regions (Z >= +1.15) with RefSeq & repeat annotations."
    }
  ],
  "locus_overall_complexity": {
    "id": "NC_000001.11:1000001-1060000",
    "taxon": "Homo sapiens",
    "length_bp": 60000,
    "gc_percent": 63.1633,
    "gc3_percent": 63.895,
    "cpg_obs_exp": 0.4672,
    "shannon_h1_bits": 1.946,
    "shannon_h2_bits": 3.8356,
    "shannon_h3_bits": 5.7054,
    "codon_pos1_entropy": 1.9439,
    "codon_pos2_entropy": 1.9535,
    "codon_pos3_entropy": 1.94,
    "lz76_phrases": 6450,
    "lz76_normalized": 0.8532,
    "dfa_alpha": 0.6026,
    "hurst_exponent": 0.6234,
    "g4hunter_max_score": 3.12,
    "g4_motif_count": 6721,
    "zdna_propensity": 2.4133,
    "composite_complexity_index": 76.2418
  },
  "cds_complexity_profiles": [
    {
      "id": "GENE_HES4",
      "taxon": "HES4",
      "length_bp": 1250,
      "gc_percent": 69.44,
      "gc3_percent": 65.8654,
      "cpg_obs_exp": 0.6529,
      "shannon_h1_bits": 1.8832,
      "shannon_h2_bits": 3.7084,
      "shannon_h3_bits": 5.5066,
      "codon_pos1_entropy": 1.8748,
      "codon_pos2_entropy": 1.8478,
      "codon_pos3_entropy": 1.9148,
      "lz76_phrases": 220,
      "lz76_normalized": 0.9053,
      "dfa_alpha": 0.6324,
      "hurst_exponent": 0.6344,
      "g4hunter_max_score": 2.36,
      "g4_motif_count": 237,
      "zdna_propensity": 0.72,
      "composite_complexity_index": 77.4993
    },
    {
      "id": "GENE_ISG15",
      "taxon": "ISG15",
      "length_bp": 1150,
      "gc_percent": 64.4348,
      "gc3_percent": 55.3525,
      "cpg_obs_exp": 0.4817,
      "shannon_h1_bits": 1.9337,
      "shannon_h2_bits": 3.7992,
      "shannon_h3_bits": 5.616,
      "codon_pos1_entropy": 1.8333,
      "codon_pos2_entropy": 1.9249,
      "codon_pos3_entropy": 1.9846,
      "lz76_phrases": 206,
      "lz76_normalized": 0.9106,
      "dfa_alpha": 0.5059,
      "hurst_exponent": 0.515,
      "g4hunter_max_score": 1.64,
      "g4_motif_count": 53,
      "zdna_propensity": 0.7826,
      "composite_complexity_index": 74.4986
    },
    {
      "id": "GENE_AGRN_N",
      "taxon": "AGRN (5' exons 1-8)",
      "length_bp": 16400,
      "gc_percent": 65.7073,
      "gc3_percent": 65.258,
      "cpg_obs_exp": 0.3868,
      "shannon_h1_bits": 1.9232,
      "shannon_h2_bits": 3.7533,
      "shannon_h3_bits": 5.5635,
      "codon_pos1_entropy": 1.9145,
      "codon_pos2_entropy": 1.9263,
      "codon_pos3_entropy": 1.9279,
      "lz76_phrases": 1888,
      "lz76_normalized": 0.8059,
      "dfa_alpha": 0.5939,
      "hurst_exponent": 0.5961,
      "g4hunter_max_score": 3.12,
      "g4_motif_count": 2478,
      "zdna_propensity": 3.7195,
      "composite_complexity_index": 73.7757
    },
    {
      "id": "GENE_AGRN_C",
      "taxon": "AGRN (3' exons 9-36)",
      "length_bp": 19599,
      "gc_percent": 65.7483,
      "gc3_percent": 66.2636,
      "cpg_obs_exp": 0.482,
      "shannon_h1_bits": 1.9228,
      "shannon_h2_bits": 3.7841,
      "shannon_h3_bits": 5.6289,
      "codon_pos1_entropy": 1.9234,
      "codon_pos2_entropy": 1.9272,
      "codon_pos3_entropy": 1.9173,
      "lz76_phrases": 2436,
      "lz76_normalized": 0.8861,
      "dfa_alpha": 0.6053,
      "hurst_exponent": 0.649,
      "g4hunter_max_score": 3.04,
      "g4_motif_count": 2466,
      "zdna_propensity": 2.5665,
      "composite_complexity_index": 76.8405
    }
  ],
  "unbiased_window_count": 59,
  "high_complexity_anomalies": [
    {
      "region_id": "Region-X01",
      "window_id": "W030",
      "start": 29000,
      "end": 31000,
      "structural_complexity_z": 4.2392,
      "gc_percent": 56.7,
      "cpg_obs_exp": 0.2425,
      "g4hunter_score": 2.12,
      "zdna_score": 19.95,
      "lz76_normalized": 0.3893,
      "dfa_alpha": 0.3874,
      "overlapping_cds_count": 1,
      "overlapping_repeat_count": 0,
      "overlapping_features": [
        "AGRN (5' exons 1-8) [CDS +:20100..36500]"
      ],
      "narrative_summary": "Region-X01 (29000..31000 bp, Z = +4.24) overlaps 1 protein-coding locus/loci and 0 repeat element(s) (AGRN (5' exons 1-8) [CDS +:20100..36500]), exhibiting elevated GC (56.7%), G4Hunter propensity (2.12), and normalized Lempel-Ziv complexity (0.389)."
    },
    {
      "region_id": "Region-X02",
      "window_id": "W031",
      "start": 30000,
      "end": 32000,
      "structural_complexity_z": 3.6828,
      "gc_percent": 56.75,
      "cpg_obs_exp": 0.1877,
      "g4hunter_score": 1.8,
      "zdna_score": 17.8,
      "lz76_normalized": 0.4606,
      "dfa_alpha": 0.4067,
      "overlapping_cds_count": 1,
      "overlapping_repeat_count": 0,
      "overlapping_features": [
        "AGRN (5' exons 1-8) [CDS +:20100..36500]"
      ],
      "narrative_summary": "Region-X02 (30000..32000 bp, Z = +3.68) overlaps 1 protein-coding locus/loci and 0 repeat element(s) (AGRN (5' exons 1-8) [CDS +:20100..36500]), exhibiting elevated GC (56.8%), G4Hunter propensity (1.80), and normalized Lempel-Ziv complexity (0.461)."
    },
    {
      "region_id": "Region-X03",
      "window_id": "W053",
      "start": 52000,
      "end": 54000,
      "structural_complexity_z": 2.881,
      "gc_percent": 58.65,
      "cpg_obs_exp": 0.4272,
      "g4hunter_score": 2.0,
      "zdna_score": 14.6,
      "lz76_normalized": 0.7868,
      "dfa_alpha": 0.5899,
      "overlapping_cds_count": 1,
      "overlapping_repeat_count": 0,
      "overlapping_features": [
        "AGRN (3' exons 9-36) [CDS +:36501..56100]"
      ],
      "narrative_summary": "Region-X03 (52000..54000 bp, Z = +2.88) overlaps 1 protein-coding locus/loci and 0 repeat element(s) (AGRN (3' exons 9-36) [CDS +:36501..56100]), exhibiting elevated GC (58.6%), G4Hunter propensity (2.00), and normalized Lempel-Ziv complexity (0.787)."
    },
    {
      "region_id": "Region-X04",
      "window_id": "W052",
      "start": 51000,
      "end": 53000,
      "structural_complexity_z": 2.2648,
      "gc_percent": 61.0,
      "cpg_obs_exp": 0.5274,
      "g4hunter_score": 2.16,
      "zdna_score": 11.95,
      "lz76_normalized": 0.8115,
      "dfa_alpha": 0.6109,
      "overlapping_cds_count": 1,
      "overlapping_repeat_count": 0,
      "overlapping_features": [
        "AGRN (3' exons 9-36) [CDS +:36501..56100]"
      ],
      "narrative_summary": "Region-X04 (51000..53000 bp, Z = +2.26) overlaps 1 protein-coding locus/loci and 0 repeat element(s) (AGRN (3' exons 9-36) [CDS +:36501..56100]), exhibiting elevated GC (61.0%), G4Hunter propensity (2.16), and normalized Lempel-Ziv complexity (0.811)."
    },
    {
      "region_id": "Region-X05",
      "window_id": "W056",
      "start": 55000,
      "end": 57000,
      "structural_complexity_z": 1.5306,
      "gc_percent": 62.1,
      "cpg_obs_exp": 0.4607,
      "g4hunter_score": 2.92,
      "zdna_score": 8.65,
      "lz76_normalized": 0.8279,
      "dfa_alpha": 0.624,
      "overlapping_cds_count": 1,
      "overlapping_repeat_count": 0,
      "overlapping_features": [
        "AGRN (3' exons 9-36) [CDS +:36501..56100]"
      ],
      "narrative_summary": "Region-X05 (55000..57000 bp, Z = +1.53) overlaps 1 protein-coding locus/loci and 0 repeat element(s) (AGRN (3' exons 9-36) [CDS +:36501..56100]), exhibiting elevated GC (62.1%), G4Hunter propensity (2.92), and normalized Lempel-Ziv complexity (0.828)."
    },
    {
      "region_id": "Region-X06",
      "window_id": "W057",
      "start": 56000,
      "end": 58000,
      "structural_complexity_z": 1.4743,
      "gc_percent": 56.95,
      "cpg_obs_exp": 0.4614,
      "g4hunter_score": 2.0,
      "zdna_score": 8.7,
      "lz76_normalized": 0.8005,
      "dfa_alpha": 0.5673,
      "overlapping_cds_count": 1,
      "overlapping_repeat_count": 0,
      "overlapping_features": [
        "AGRN (3' exons 9-36) [CDS +:36501..56100]"
      ],
      "narrative_summary": "Region-X06 (56000..58000 bp, Z = +1.47) overlaps 1 protein-coding locus/loci and 0 repeat element(s) (AGRN (3' exons 9-36) [CDS +:36501..56100]), exhibiting elevated GC (57.0%), G4Hunter propensity (2.00), and normalized Lempel-Ziv complexity (0.800)."
    }
  ],
  "emergent_findings": [
    {
      "finding_id": "EMERGENT-CHR1-01",
      "title": "Subtelomeric VNTR–Coding Boundary Generates Peak Structural & Non-B DNA Complexity",
      "engines_bridged": [
        "bio-suite genome",
        "bio-suite complexity"
      ],
      "statistic_name": "Peak Structural Complexity Z-Score",
      "statistic_value": 4.2392,
      "biological_interpretation": "Region-X01 (29000..31000 bp, Z = +4.24) overlaps 1 protein-coding locus/loci and 0 repeat element(s) (AGRN (5' exons 1-8) [CDS +:20100..36500]), exhibiting elevated GC (56.7%), G4Hunter propensity (2.12), and normalized Lempel-Ziv complexity (0.389)."
    }
  ]
}