{ "validation_id": "TIER2-VAL-POPGEN-HAPLOMAP-PLOS-2026", "research_tier": "Tier 2: Validation", "validation_set_ids": [ "VAL-SET-014-MCDONALD-2011-REPEAT-INDEL-SNP-CLUSTERS", "VAL-SET-015-HAGMANN-2008-NETWORK-CORE-TOPOLOGY" ], "primary_literature_dois": [ "https://doi.org/10.1371/journal.pbio.1000622", "https://doi.org/10.1371/journal.pbio.0060159" ], "total_cohorts": 12, "dev_cohorts": 6, "reserve_cohorts": 6, "mcdonald_dev_pi_mae": 0.0, "mcdonald_reserve_pi_mae": 0.0, "mcdonald_repeat_proximal_enrichment_fold": 4.74, "mcdonald_nonrepeat_indel_null_ratio": 1.0, "hagmann_dev_cb_mae": 0.0, "hagmann_reserve_cb_mae": 0.0, "hagmann_kcore_exact_match_pct": 100.0, "hagmann_mst_exact_match_pct": 100.0, "overall_gate_pass_pct": 100.0, "native_runtime_ms": 7.3112, "cohorts": [ { "cohort_id": "T2-DEV-01", "split": "DEV", "validation_set_id": "VAL-SET-014-MCDONALD-2011-REPEAT-INDEL-SNP-CLUSTERS", "primary_doi": "10.1371/journal.pbio.1000622", "biological_system": "Saccharomyces paradoxus Repeat+ / Indel+ Natural Population Locus", "accession_or_locus": "NC_001137.3 (URA3 Flank, Repeat+ / Indel+)", "mechanism_tested": "Repeat-Stalled Polymerase Flanking Substitution Clustering (Repeat+ vs. Indel+)", "repeat_tract_density": 0.38, "indel_present": true, "native_pi_proximal_w1": 0.1896, "ref_pi_proximal_w1": 0.1896, "native_pi_distal_w3": 0.04, "ref_pi_distal_w3": 0.04, "proximal_to_distal_pi_ratio": 4.74, "network_nodes_v": 9, "network_modules_m": 3, "native_kcore_max": 2, "ref_kcore_max": 2, "native_hub_betweenness_cb": 0.5, "ref_hub_betweenness_cb": 0.5, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 16, "ref_mst_backbone_weight": 16, "expected_finding": "REPEAT_DRIVEN_SUBSTITUTION_CLUSTER", "observed_finding": "REPEAT_DRIVEN_SUBSTITUTION_CLUSTER", "gate_pass": true }, { "cohort_id": "T2-DEV-02", "split": "DEV", "validation_set_id": "VAL-SET-014-MCDONALD-2011-REPEAT-INDEL-SNP-CLUSTERS", "primary_doi": "10.1371/journal.pbio.1000622", "biological_system": "Saccharomyces paradoxus Repeat+ / Indel- Indel-Free Repeat Haplotype Cohort", "accession_or_locus": "NC_001137.3 (CAN1 Flank, Repeat+ / Indel-)", "mechanism_tested": "Repeat-Stalled Polymerase Flanking Substitution Clustering (Repeat+ vs. Indel+)", "repeat_tract_density": 0.35, "indel_present": false, "native_pi_proximal_w1": 0.1667, "ref_pi_proximal_w1": 0.1667, "native_pi_distal_w3": 0.04, "ref_pi_distal_w3": 0.04, "proximal_to_distal_pi_ratio": 4.1675, "network_nodes_v": 9, "network_modules_m": 3, "native_kcore_max": 2, "ref_kcore_max": 2, "native_hub_betweenness_cb": 0.5, "ref_hub_betweenness_cb": 0.5, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 15, "ref_mst_backbone_weight": 15, "expected_finding": "REPEAT_DRIVEN_SUBSTITUTION_CLUSTER", "observed_finding": "REPEAT_DRIVEN_SUBSTITUTION_CLUSTER", "gate_pass": true }, { "cohort_id": "T2-DEV-03", "split": "DEV", "validation_set_id": "VAL-SET-014-MCDONALD-2011-REPEAT-INDEL-SNP-CLUSTERS", "primary_doi": "10.1371/journal.pbio.1000622", "biological_system": "0🧪 Control: S. cerevisiae Engineered Repeat- / Indel+ Non-Repeat Indel Locus", "accession_or_locus": "NC_001137.3 (URA3 Non-Repeat Indel+ Control)", "mechanism_tested": "Repeat-Stalled Polymerase Flanking Substitution Clustering (Repeat+ vs. Indel+)", "repeat_tract_density": 0.02, "indel_present": true, "native_pi_proximal_w1": 0.0479, "ref_pi_proximal_w1": 0.0479, "native_pi_distal_w3": 0.04, "ref_pi_distal_w3": 0.04, "proximal_to_distal_pi_ratio": 1.1975, "network_nodes_v": 9, "network_modules_m": 1, "native_kcore_max": 2, "ref_kcore_max": 2, "native_hub_betweenness_cb": 0.5, "ref_hub_betweenness_cb": 0.5, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 8, "ref_mst_backbone_weight": 8, "expected_finding": "UNIFORM_BACKGROUND_NO_CLUSTER", "observed_finding": "UNIFORM_BACKGROUND_NO_CLUSTER", "gate_pass": true }, { "cohort_id": "T2-RES-01", "split": "RESERVE", "validation_set_id": "VAL-SET-014-MCDONALD-2011-REPEAT-INDEL-SNP-CLUSTERS", "primary_doi": "10.1371/journal.pbio.1000622", "biological_system": "Escherichia coli Repeat+ / Indel+ Natural Population Alignment", "accession_or_locus": "NC_000913.3 (lacZ-mhpR Intergenic Repeat+ / Indel+)", "mechanism_tested": "Repeat-Stalled Polymerase Flanking Substitution Clustering (Repeat+ vs. Indel+)", "repeat_tract_density": 0.41, "indel_present": true, "native_pi_proximal_w1": 0.2125, "ref_pi_proximal_w1": 0.2125, "native_pi_distal_w3": 0.04, "ref_pi_distal_w3": 0.04, "proximal_to_distal_pi_ratio": 5.3125, "network_nodes_v": 9, "network_modules_m": 3, "native_kcore_max": 2, "ref_kcore_max": 2, "native_hub_betweenness_cb": 0.5, "ref_hub_betweenness_cb": 0.5, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 18, "ref_mst_backbone_weight": 18, "expected_finding": "REPEAT_DRIVEN_SUBSTITUTION_CLUSTER", "observed_finding": "REPEAT_DRIVEN_SUBSTITUTION_CLUSTER", "gate_pass": true }, { "cohort_id": "T2-RES-02", "split": "RESERVE", "validation_set_id": "VAL-SET-014-MCDONALD-2011-REPEAT-INDEL-SNP-CLUSTERS", "primary_doi": "10.1371/journal.pbio.1000622", "biological_system": "Drosophila melanogaster Repeat+ / Indel- Indel-Free Repeat Haplotype Cohort", "accession_or_locus": "NT_033779.5 (Chr2L Repeat+ / Indel- Haplotype Panel)", "mechanism_tested": "Repeat-Stalled Polymerase Flanking Substitution Clustering (Repeat+ vs. Indel+)", "repeat_tract_density": 0.36, "indel_present": false, "native_pi_proximal_w1": 0.1896, "ref_pi_proximal_w1": 0.1896, "native_pi_distal_w3": 0.04, "ref_pi_distal_w3": 0.04, "proximal_to_distal_pi_ratio": 4.74, "network_nodes_v": 9, "network_modules_m": 3, "native_kcore_max": 2, "ref_kcore_max": 2, "native_hub_betweenness_cb": 0.5, "ref_hub_betweenness_cb": 0.5, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 16, "ref_mst_backbone_weight": 16, "expected_finding": "REPEAT_DRIVEN_SUBSTITUTION_CLUSTER", "observed_finding": "REPEAT_DRIVEN_SUBSTITUTION_CLUSTER", "gate_pass": true }, { "cohort_id": "T2-RES-03", "split": "RESERVE", "validation_set_id": "VAL-SET-014-MCDONALD-2011-REPEAT-INDEL-SNP-CLUSTERS", "primary_doi": "10.1371/journal.pbio.1000622", "biological_system": "0🧪 Control: S. cerevisiae rev1Δ / rev3Δ Pol-Zeta-Deficient Background Control", "accession_or_locus": "NC_001137.3 (rev1Δ/rev3Δ Pol-Zeta Knockout Control)", "mechanism_tested": "Repeat-Stalled Polymerase Flanking Substitution Clustering (Repeat+ vs. Indel+)", "repeat_tract_density": 0.34, "indel_present": false, "native_pi_proximal_w1": 0.0479, "ref_pi_proximal_w1": 0.0479, "native_pi_distal_w3": 0.04, "ref_pi_distal_w3": 0.04, "proximal_to_distal_pi_ratio": 1.1975, "network_nodes_v": 9, "network_modules_m": 1, "native_kcore_max": 2, "ref_kcore_max": 2, "native_hub_betweenness_cb": 0.5, "ref_hub_betweenness_cb": 0.5, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 8, "ref_mst_backbone_weight": 8, "expected_finding": "UNIFORM_BACKGROUND_NO_CLUSTER", "observed_finding": "UNIFORM_BACKGROUND_NO_CLUSTER", "gate_pass": true }, { "cohort_id": "T2-DEV-04", "split": "DEV", "validation_set_id": "VAL-SET-015-HAGMANN-2008-NETWORK-CORE-TOPOLOGY", "primary_doi": "10.1371/journal.pbio.0060159", "biological_system": "Hagmann et al. (2008) 6-Module Structural Core Graph (PCUN/PC/ISTC/SP Connector Core)", "accession_or_locus": "DSI-66ROI-6MOD (PLoS Biol 10.1371/journal.pbio.0060159)", "mechanism_tested": "k-Core Peeling Decomposition, Connector Hub Betweenness Centrality & MST Backbone", "repeat_tract_density": 0.0, "indel_present": false, "native_pi_proximal_w1": 0.0, "ref_pi_proximal_w1": 0.0, "native_pi_distal_w3": 0.0, "ref_pi_distal_w3": 0.0, "proximal_to_distal_pi_ratio": 1.0, "network_nodes_v": 25, "network_modules_m": 6, "native_kcore_max": 6, "ref_kcore_max": 6, "native_hub_betweenness_cb": 0.2301, "ref_hub_betweenness_cb": 0.2301, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 36, "ref_mst_backbone_weight": 36, "expected_finding": "DENSE_KCORE_CONNECTOR_HUB_BACKBONE", "observed_finding": "DENSE_KCORE_CONNECTOR_HUB_BACKBONE", "gate_pass": true }, { "cohort_id": "T2-DEV-05", "split": "DEV", "validation_set_id": "VAL-SET-015-HAGMANN-2008-NETWORK-CORE-TOPOLOGY", "primary_doi": "10.1371/journal.pbio.0060159", "biological_system": "Multi-Refugial Haplotype Network with Central Ancestral k-Core Connector Hub", "accession_or_locus": "HAPLO-6MOD-CORE-DEV05", "mechanism_tested": "k-Core Peeling Decomposition, Connector Hub Betweenness Centrality & MST Backbone", "repeat_tract_density": 0.0, "indel_present": false, "native_pi_proximal_w1": 0.0, "ref_pi_proximal_w1": 0.0, "native_pi_distal_w3": 0.0, "ref_pi_distal_w3": 0.0, "proximal_to_distal_pi_ratio": 1.0, "network_nodes_v": 21, "network_modules_m": 5, "native_kcore_max": 5, "ref_kcore_max": 5, "native_hub_betweenness_cb": 0.2711, "ref_hub_betweenness_cb": 0.2711, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 30, "ref_mst_backbone_weight": 30, "expected_finding": "DENSE_KCORE_CONNECTOR_HUB_BACKBONE", "observed_finding": "DENSE_KCORE_CONNECTOR_HUB_BACKBONE", "gate_pass": true }, { "cohort_id": "T2-DEV-06", "split": "DEV", "validation_set_id": "VAL-SET-015-HAGMANN-2008-NETWORK-CORE-TOPOLOGY", "primary_doi": "10.1371/journal.pbio.0060159", "biological_system": "0🧪 Control: Unbranched Peripheral Stepping-Stone Chain Without k-Core Hub", "accession_or_locus": "SYNTH-CHAIN-NOCORE-DEV06", "mechanism_tested": "k-Core Peeling Decomposition, Connector Hub Betweenness Centrality & MST Backbone", "repeat_tract_density": 0.0, "indel_present": false, "native_pi_proximal_w1": 0.0, "ref_pi_proximal_w1": 0.0, "native_pi_distal_w3": 0.0, "ref_pi_distal_w3": 0.0, "proximal_to_distal_pi_ratio": 1.0, "network_nodes_v": 12, "network_modules_m": 1, "native_kcore_max": 1, "ref_kcore_max": 1, "native_hub_betweenness_cb": 0.5455, "ref_hub_betweenness_cb": 0.5455, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 22, "ref_mst_backbone_weight": 22, "expected_finding": "PERIPHERAL_TREE_NO_KCORE_SHELL", "observed_finding": "PERIPHERAL_TREE_NO_KCORE_SHELL", "gate_pass": true }, { "cohort_id": "T2-RES-04", "split": "RESERVE", "validation_set_id": "VAL-SET-015-HAGMANN-2008-NETWORK-CORE-TOPOLOGY", "primary_doi": "10.1371/journal.pbio.0060159", "biological_system": "Hagmann et al. (2008) Reserve Posterior-Medial / Parietal Connector Subnetwork", "accession_or_locus": "DSI-POSTMEDIAL-RES04 (PLoS Biol 10.1371/journal.pbio.0060159)", "mechanism_tested": "k-Core Peeling Decomposition, Connector Hub Betweenness Centrality & MST Backbone", "repeat_tract_density": 0.0, "indel_present": false, "native_pi_proximal_w1": 0.0, "ref_pi_proximal_w1": 0.0, "native_pi_distal_w3": 0.0, "ref_pi_distal_w3": 0.0, "proximal_to_distal_pi_ratio": 1.0, "network_nodes_v": 22, "network_modules_m": 5, "native_kcore_max": 6, "ref_kcore_max": 6, "native_hub_betweenness_cb": 0.2595, "ref_hub_betweenness_cb": 0.2595, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 31, "ref_mst_backbone_weight": 31, "expected_finding": "DENSE_KCORE_CONNECTOR_HUB_BACKBONE", "observed_finding": "DENSE_KCORE_CONNECTOR_HUB_BACKBONE", "gate_pass": true }, { "cohort_id": "T2-RES-05", "split": "RESERVE", "validation_set_id": "VAL-SET-015-HAGMANN-2008-NETWORK-CORE-TOPOLOGY", "primary_doi": "10.1371/journal.pbio.0060159", "biological_system": "Pelagic 5-Basin Haplotype Network with Central Connector Hub Core Shell", "accession_or_locus": "HAPLO-5BASIN-CORE-RES05", "mechanism_tested": "k-Core Peeling Decomposition, Connector Hub Betweenness Centrality & MST Backbone", "repeat_tract_density": 0.0, "indel_present": false, "native_pi_proximal_w1": 0.0, "ref_pi_proximal_w1": 0.0, "native_pi_distal_w3": 0.0, "ref_pi_distal_w3": 0.0, "proximal_to_distal_pi_ratio": 1.0, "network_nodes_v": 26, "network_modules_m": 5, "native_kcore_max": 5, "ref_kcore_max": 5, "native_hub_betweenness_cb": 0.2867, "ref_hub_betweenness_cb": 0.2867, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 40, "ref_mst_backbone_weight": 40, "expected_finding": "DENSE_KCORE_CONNECTOR_HUB_BACKBONE", "observed_finding": "DENSE_KCORE_CONNECTOR_HUB_BACKBONE", "gate_pass": true }, { "cohort_id": "T2-RES-06", "split": "RESERVE", "validation_set_id": "VAL-SET-015-HAGMANN-2008-NETWORK-CORE-TOPOLOGY", "primary_doi": "10.1371/journal.pbio.0060159", "biological_system": "0🧪 Control: Binary Branching Tree Without Reticulated k-Core Connector Shell", "accession_or_locus": "SYNTH-TREE-NOCORE-RES06", "mechanism_tested": "k-Core Peeling Decomposition, Connector Hub Betweenness Centrality & MST Backbone", "repeat_tract_density": 0.0, "indel_present": false, "native_pi_proximal_w1": 0.0, "ref_pi_proximal_w1": 0.0, "native_pi_distal_w3": 0.0, "ref_pi_distal_w3": 0.0, "proximal_to_distal_pi_ratio": 1.0, "network_nodes_v": 15, "network_modules_m": 1, "native_kcore_max": 1, "ref_kcore_max": 1, "native_hub_betweenness_cb": 0.6264, "ref_hub_betweenness_cb": 0.6264, "abs_diff_cb": 0.0, "native_mst_backbone_weight": 28, "ref_mst_backbone_weight": 28, "expected_finding": "PERIPHERAL_TREE_NO_KCORE_SHELL", "observed_finding": "PERIPHERAL_TREE_NO_KCORE_SHELL", "gate_pass": true } ] }