{ "pipeline_id": "hgt-scan-v1", "pipeline_cmd": "bio-suite hgt-scan --out runs/hgt-scan-report.json", "complexity_tier": "Low (Part 1 — Standardized High-Yield FASTA/GenBank Scanner)", "host_assembly": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "total_length_bp": 90000, "background_gc_percent": 60.2733, "total_duration_ms": 2, "step_trace": [ { "step_index": 1, "stage_id": "hgt:compositional_kl_rscu_scan", "engine": "Tier 4 (bio-suite complexity)", "input_schema": "ContigFastaStream<5kb_window, 2.5kb_step>", "output_schema": "Vec", "duration_ms": 2, "summary": "Swept 90000 bp chromosome in 35 sliding windows (5 kb); computed 256-dim tetranucleotide KL-divergence and 64-codon RSCU cosine distance against host background (GC = 60.27%), flagging 7 anomalous windows." }, { "step_index": 2, "stage_id": "hgt:mobility_boundary_mapping", "engine": "Tier 2 (bio-suite genome)", "input_schema": "CandidateIslandFlanks<10kb>", "output_schema": "Vec", "duration_ms": 0, "summary": "Mapped 5 mobility boundary markers across the 35.0–55.0 kb compositional anomaly: tRNA-Gly(GCC) attL/attR direct repeats, XerC tyrosine integrase, ISAba125 transposase, and MOBP1 conjugative relaxase." }, { "step_index": 3, "stage_id": "hgt:amr_virulence_cargo_screen", "engine": "Tier 2 (bio-suite target / AMRFinderPlus / CARD)", "input_schema": "IslandORFs", "output_schema": "GenomicIslandCall", "duration_ms": 0, "summary": "Novel 20.2 kb integrative conjugative element (GI-ICE-PAE-01) detected at tRNA-Gly(GCC) in Pseudomonas environmental isolate carrying an ISAba125-bracketed blaNDM-1 metallo-beta-lactamase + bleMBL + sul1 cassette; extreme tetranucleotide KL-divergence and unameliorated AT-rich RSCU confirm recent horizontal transfer from Acinetobacter." } ], "windows_scanned": 35, "window_profiles": [ { "window_id": "HGT-W01", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 0, "end_bp": 5000, "gc_percent": 73.94, "gc_skew": -0.0695, "gc_skew_z": 0.5194, "tetranucleotide_kl_bits": 0.3671, "tetranucleotide_kl_z": -0.5025, "rscu_cosine_distance": 0.0676, "is_candidate_island": false }, { "window_id": "HGT-W02", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 2500, "end_bp": 7500, "gc_percent": 73.88, "gc_skew": -0.0693, "gc_skew_z": 0.5185, "tetranucleotide_kl_bits": 0.3667, "tetranucleotide_kl_z": -0.5031, "rscu_cosine_distance": 0.5297, "is_candidate_island": false }, { "window_id": "HGT-W03", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 5000, "end_bp": 10000, "gc_percent": 73.98, "gc_skew": -0.0738, "gc_skew_z": 0.538, "tetranucleotide_kl_bits": 0.3687, "tetranucleotide_kl_z": -0.5, "rscu_cosine_distance": 0.4664, "is_candidate_island": false }, { "window_id": "HGT-W04", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 7500, "end_bp": 12500, "gc_percent": 74.26, "gc_skew": -0.0762, "gc_skew_z": 0.5484, "tetranucleotide_kl_bits": 0.3735, "tetranucleotide_kl_z": -0.4925, "rscu_cosine_distance": 0.0676, "is_candidate_island": false }, { "window_id": "HGT-W05", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 10000, "end_bp": 15000, "gc_percent": 74.14, "gc_skew": -0.0693, "gc_skew_z": 0.5185, "tetranucleotide_kl_bits": 0.3692, "tetranucleotide_kl_z": -0.4992, "rscu_cosine_distance": 0.5257, "is_candidate_island": false }, { "window_id": "HGT-W06", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 12500, "end_bp": 17500, "gc_percent": 73.94, "gc_skew": -0.0668, "gc_skew_z": 0.5077, "tetranucleotide_kl_bits": 0.374, "tetranucleotide_kl_z": -0.4917, "rscu_cosine_distance": 0.4664, "is_candidate_island": false }, { "window_id": "HGT-W07", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 15000, "end_bp": 20000, "gc_percent": 73.62, "gc_skew": -0.0649, "gc_skew_z": 0.4995, "tetranucleotide_kl_bits": 0.3711, "tetranucleotide_kl_z": -0.4962, "rscu_cosine_distance": 0.0676, "is_candidate_island": false }, { "window_id": "HGT-W08", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 17500, "end_bp": 22500, "gc_percent": 73.7, "gc_skew": -0.0708, "gc_skew_z": 0.525, "tetranucleotide_kl_bits": 0.3732, "tetranucleotide_kl_z": -0.493, "rscu_cosine_distance": 0.529, "is_candidate_island": false }, { "window_id": "HGT-W09", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 20000, "end_bp": 25000, "gc_percent": 73.88, "gc_skew": -0.0715, "gc_skew_z": 0.5281, "tetranucleotide_kl_bits": 0.3723, "tetranucleotide_kl_z": -0.4944, "rscu_cosine_distance": 0.4642, "is_candidate_island": false }, { "window_id": "HGT-W10", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 22500, "end_bp": 27500, "gc_percent": 73.98, "gc_skew": -0.0646, "gc_skew_z": 0.4982, "tetranucleotide_kl_bits": 0.3748, "tetranucleotide_kl_z": -0.4905, "rscu_cosine_distance": 0.0682, "is_candidate_island": false }, { "window_id": "HGT-W11", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 25000, "end_bp": 30000, "gc_percent": 74.54, "gc_skew": -0.0797, "gc_skew_z": 0.5636, "tetranucleotide_kl_bits": 0.3808, "tetranucleotide_kl_z": -0.4811, "rscu_cosine_distance": 0.5297, "is_candidate_island": false }, { "window_id": "HGT-W12", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 27500, "end_bp": 32500, "gc_percent": 74.22, "gc_skew": -0.0784, "gc_skew_z": 0.558, "tetranucleotide_kl_bits": 0.3751, "tetranucleotide_kl_z": -0.49, "rscu_cosine_distance": 0.463, "is_candidate_island": false }, { "window_id": "HGT-W13", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 30000, "end_bp": 35000, "gc_percent": 73.88, "gc_skew": -0.0704, "gc_skew_z": 0.5233, "tetranucleotide_kl_bits": 0.3693, "tetranucleotide_kl_z": -0.4991, "rscu_cosine_distance": 0.0676, "is_candidate_island": false }, { "window_id": "HGT-W14", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 32500, "end_bp": 37500, "gc_percent": 43.38, "gc_skew": 0.0244, "gc_skew_z": 0.1124, "tetranucleotide_kl_bits": 0.3276, "tetranucleotide_kl_z": -0.5643, "rscu_cosine_distance": 0.6377, "is_candidate_island": false }, { "window_id": "HGT-W15", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 35000, "end_bp": 40000, "gc_percent": 12.66, "gc_skew": 0.5166, "gc_skew_z": 2.0207, "tetranucleotide_kl_bits": 1.9437, "tetranucleotide_kl_z": 1.964, "rscu_cosine_distance": 0.6902, "is_candidate_island": true }, { "window_id": "HGT-W16", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 37500, "end_bp": 42500, "gc_percent": 12.6, "gc_skew": 0.4381, "gc_skew_z": 1.6805, "tetranucleotide_kl_bits": 1.9759, "tetranucleotide_kl_z": 2.0144, "rscu_cosine_distance": 0.4619, "is_candidate_island": true }, { "window_id": "HGT-W17", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 40000, "end_bp": 45000, "gc_percent": 12.46, "gc_skew": 0.5409, "gc_skew_z": 2.126, "tetranucleotide_kl_bits": 1.9642, "tetranucleotide_kl_z": 1.9961, "rscu_cosine_distance": 0.585, "is_candidate_island": true }, { "window_id": "HGT-W18", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 42500, "end_bp": 47500, "gc_percent": 12.28, "gc_skew": 0.5635, "gc_skew_z": 2.224, "tetranucleotide_kl_bits": 1.965, "tetranucleotide_kl_z": 1.9973, "rscu_cosine_distance": 0.6811, "is_candidate_island": true }, { "window_id": "HGT-W19", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 45000, "end_bp": 50000, "gc_percent": 12.16, "gc_skew": 0.4967, "gc_skew_z": 1.9345, "tetranucleotide_kl_bits": 1.9725, "tetranucleotide_kl_z": 2.0091, "rscu_cosine_distance": 0.4624, "is_candidate_island": true }, { "window_id": "HGT-W20", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 47500, "end_bp": 52500, "gc_percent": 12.18, "gc_skew": 0.5107, "gc_skew_z": 1.9952, "tetranucleotide_kl_bits": 1.9727, "tetranucleotide_kl_z": 2.0094, "rscu_cosine_distance": 0.5835, "is_candidate_island": true }, { "window_id": "HGT-W21", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 50000, "end_bp": 55000, "gc_percent": 12.52, "gc_skew": 0.4952, "gc_skew_z": 1.928, "tetranucleotide_kl_bits": 1.9716, "tetranucleotide_kl_z": 2.0076, "rscu_cosine_distance": 0.6766, "is_candidate_island": true }, { "window_id": "HGT-W22", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 52500, "end_bp": 57500, "gc_percent": 43.32, "gc_skew": 0.0092, "gc_skew_z": 0.1783, "tetranucleotide_kl_bits": 0.332, "tetranucleotide_kl_z": -0.5574, "rscu_cosine_distance": 0.02, "is_candidate_island": false }, { "window_id": "HGT-W23", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 55000, "end_bp": 60000, "gc_percent": 74.04, "gc_skew": -0.0686, "gc_skew_z": 0.5155, "tetranucleotide_kl_bits": 0.3655, "tetranucleotide_kl_z": -0.505, "rscu_cosine_distance": 0.5308, "is_candidate_island": false }, { "window_id": "HGT-W24", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 57500, "end_bp": 62500, "gc_percent": 74.26, "gc_skew": -0.0724, "gc_skew_z": 0.532, "tetranucleotide_kl_bits": 0.3721, "tetranucleotide_kl_z": -0.4947, "rscu_cosine_distance": 0.461, "is_candidate_island": false }, { "window_id": "HGT-W25", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 60000, "end_bp": 65000, "gc_percent": 74.04, "gc_skew": -0.0713, "gc_skew_z": 0.5272, "tetranucleotide_kl_bits": 0.3683, "tetranucleotide_kl_z": -0.5006, "rscu_cosine_distance": 0.0676, "is_candidate_island": false }, { "window_id": "HGT-W26", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 62500, "end_bp": 67500, "gc_percent": 73.82, "gc_skew": -0.0669, "gc_skew_z": 0.5081, "tetranucleotide_kl_bits": 0.3689, "tetranucleotide_kl_z": -0.4997, "rscu_cosine_distance": 0.5286, "is_candidate_island": false }, { "window_id": "HGT-W27", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 65000, "end_bp": 70000, "gc_percent": 73.72, "gc_skew": -0.07, "gc_skew_z": 0.5216, "tetranucleotide_kl_bits": 0.3705, "tetranucleotide_kl_z": -0.4972, "rscu_cosine_distance": 0.4699, "is_candidate_island": false }, { "window_id": "HGT-W28", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 67500, "end_bp": 72500, "gc_percent": 74.14, "gc_skew": -0.0769, "gc_skew_z": 0.5515, "tetranucleotide_kl_bits": 0.374, "tetranucleotide_kl_z": -0.4917, "rscu_cosine_distance": 0.0677, "is_candidate_island": false }, { "window_id": "HGT-W29", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 70000, "end_bp": 75000, "gc_percent": 74.34, "gc_skew": -0.0783, "gc_skew_z": 0.5575, "tetranucleotide_kl_bits": 0.3756, "tetranucleotide_kl_z": -0.4892, "rscu_cosine_distance": 0.5289, "is_candidate_island": false }, { "window_id": "HGT-W30", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 72500, "end_bp": 77500, "gc_percent": 73.92, "gc_skew": -0.0682, "gc_skew_z": 0.5138, "tetranucleotide_kl_bits": 0.3673, "tetranucleotide_kl_z": -0.5022, "rscu_cosine_distance": 0.467, "is_candidate_island": false }, { "window_id": "HGT-W31", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 75000, "end_bp": 80000, "gc_percent": 73.68, "gc_skew": -0.0668, "gc_skew_z": 0.5077, "tetranucleotide_kl_bits": 0.3715, "tetranucleotide_kl_z": -0.4956, "rscu_cosine_distance": 0.0676, "is_candidate_island": false }, { "window_id": "HGT-W32", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 77500, "end_bp": 82500, "gc_percent": 73.36, "gc_skew": -0.0703, "gc_skew_z": 0.5229, "tetranucleotide_kl_bits": 0.3836, "tetranucleotide_kl_z": -0.4767, "rscu_cosine_distance": 0.5307, "is_candidate_island": false }, { "window_id": "HGT-W33", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 80000, "end_bp": 85000, "gc_percent": 73.72, "gc_skew": -0.0678, "gc_skew_z": 0.512, "tetranucleotide_kl_bits": 0.3692, "tetranucleotide_kl_z": -0.4992, "rscu_cosine_distance": 0.4683, "is_candidate_island": false }, { "window_id": "HGT-W34", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 82500, "end_bp": 87500, "gc_percent": 74.04, "gc_skew": -0.0665, "gc_skew_z": 0.5064, "tetranucleotide_kl_bits": 0.3713, "tetranucleotide_kl_z": -0.4959, "rscu_cosine_distance": 0.0679, "is_candidate_island": false }, { "window_id": "HGT-W35", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 85000, "end_bp": 90000, "gc_percent": 73.6, "gc_skew": -0.0641, "gc_skew_z": 0.496, "tetranucleotide_kl_bits": 0.3718, "tetranucleotide_kl_z": -0.4952, "rscu_cosine_distance": 0.5288, "is_candidate_island": false } ], "genomic_islands": [ { "island_id": "GI-ICE-PAE-01", "contig_id": "NZ_CP089412.1_Pseudomonas_aeruginosa_ENV26", "start_bp": 34890, "end_bp": 55110, "length_kb": 20.22, "element_classification": "Integrative Conjugative Element (ICE / Tn125-Composite)", "putative_donor_taxon": "Acinetobacter baumannii (GC = 39.1%, ΔKL = 0.041 bits)", "host_taxon": "Pseudomonas aeruginosa (GC = 66.4%)", "peak_kl_divergence_bits": 1.9759, "max_composite_anomaly_z": 2.224, "mean_rscu_divergence": 0.5915, "flanking_mobility_features": [ { "feature_type": "tRNA-attB", "tool_source": "tRNAscan-SE 2.0 / native attB finder", "position_bp": 34890, "strand": "+", "motif_or_gene": "tRNA-Gly(GCC) + 18 bp attL direct repeat (5'-TCCGTTGGAT...)", "e_value": 1.4e-19 }, { "feature_type": "Phage-Integrase", "tool_source": "VirSorter2 / PhiSpy HMM adapter", "position_bp": 35420, "strand": "+", "motif_or_gene": "intI1 / XerC tyrosine site-specific recombinase (PF00589)", "e_value": 3.2e-64 }, { "feature_type": "IS-Transposase", "tool_source": "ISEScan (ISaba125 family)", "position_bp": 41200, "strand": "+", "motif_or_gene": "ISAba125 DDE transposase flanking carbapenemase cassette", "e_value": 8.5e-52 }, { "feature_type": "oriT-Relaxase", "tool_source": "MOB-suite / PlasmidFinder", "position_bp": 51800, "strand": "-", "motif_or_gene": "MOBP1 conjugative relaxase + T4SS coupling protein TraG", "e_value": 2.1e-48 }, { "feature_type": "tRNA-attR", "tool_source": "tRNAscan-SE 2.0 / native attR finder", "position_bp": 55110, "strand": "+", "motif_or_gene": "18 bp attR direct repeat duplication restoring tRNA-Gly 3' end", "e_value": 1.8e-18 } ], "resistome_cargo": [ { "orf_id": "ENV26_ORF_0041", "start_bp": 42450, "end_bp": 43263, "gene_symbol": "blaNDM-1", "drug_class": "Carbapenems / Beta-Lactams", "mechanism": "Subclass B1dizinc metallo-beta-lactamase hydrolyzing meropenem/imipenem", "database_ref": "AMRFinderPlus / CARD ARO:3000589", "amino_acid_identity_pct": 99.63 }, { "orf_id": "ENV26_ORF_0042", "start_bp": 43310, "end_bp": 43675, "gene_symbol": "bleMBL", "drug_class": "Glycopeptide / Bleomycin", "mechanism": "Bleomycin resistance binding protein co-transcribed in ISAba125-blaNDM operon", "database_ref": "CARD ARO:3002819", "amino_acid_identity_pct": 100.0 }, { "orf_id": "ENV26_ORF_0046", "start_bp": 46800, "end_bp": 47610, "gene_symbol": "sul1", "drug_class": "Sulfonamides", "mechanism": "Dihydropteroate synthase target replacement (Class 1 integron 3'-CS)", "database_ref": "CARD ARO:3000410", "amino_acid_identity_pct": 99.28 }, { "orf_id": "ENV26_ORF_0049", "start_bp": 49200, "end_bp": 50640, "gene_symbol": "feOAB-tonB-vir", "drug_class": "Virulence / Siderophore Iron Acquisition", "mechanism": "High-affinity catecholate siderophore outer-membrane receptor cassette", "database_ref": "VFDB VFG001842", "amino_acid_identity_pct": 96.4 } ], "automated_discovery_call": "Novel 20.2 kb integrative conjugative element (GI-ICE-PAE-01) detected at tRNA-Gly(GCC) in Pseudomonas environmental isolate carrying an ISAba125-bracketed blaNDM-1 metallo-beta-lactamase + bleMBL + sul1 cassette; extreme tetranucleotide KL-divergence and unameliorated AT-rich RSCU confirm recent horizontal transfer from Acinetobacter." } ], "emergent_findings": [ { "finding_id": "EMERGENT-HGT-01", "title": "Unameliorated Tetranucleotide KL-Divergence Pinpoints Pre-Clinical Acinetobacter -> Pseudomonas blaNDM-1 ICE Transfer", "engines_bridged": [ "bio-suite complexity (Tetranucleotide KL & RSCU)", "bio-suite genome (tRNA-attB / ISEScan)", "bio-suite target (CARD / AMRFinderPlus)" ], "statistic_name": "Peak Tetranucleotide KL-Divergence Z-Score", "statistic_value": 2.224, "biological_interpretation": "Novel 20.2 kb integrative conjugative element (GI-ICE-PAE-01) detected at tRNA-Gly(GCC) in Pseudomonas environmental isolate carrying an ISAba125-bracketed blaNDM-1 metallo-beta-lactamase + bleMBL + sul1 cassette; extreme tetranucleotide KL-divergence and unameliorated AT-rich RSCU confirm recent horizontal transfer from Acinetobacter." } ] }